Ontology-Driven Cross-Domain Access Control Framework for Anomaly Detection in Cloud-Based Healthcare System

Ontology-Driven Cross-Domain Access Control Framework for Anomaly Detection in Cloud-Based Healthcare System | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Ontology-Driven Cross-Domain Access Control Framework for Anomaly Detection in Cloud-Based Healthcare System S.Raghavan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6128795/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract To enhance anomaly detection in cloud-based healthcare systems, this study suggests a novel ontology-driven cross-domain access control architecture. The framework ensures data integrity and privacy by utilizing semantic technologies to offer safe, context-aware access across several healthcare domains. The system can dynamically detect anomalous access patterns and react to possible threats in real-time by incorporating machine learning-based anomaly detection techniques. Furthermore, dynamic policy enforcement guarantees that access controls are updated and modified regularly to address changing security threats. The capacity of the suggested framework to ensure adherence to crucial legal requirements like HIPAA and GDPR, promoting a safe and open access control environment, is one of its most notable aspects. In healthcare systems, where patient data is sensitive and needs to be shielded from unwanted access, this is essential. The framework can handle complicated, cross-domain healthcare data while guaranteeing interoperability across different systems thanks to the incorporation of semantic reasoning. The framework obtains a high resilience score of 94.1%, a low false-positive rate of 3.4%, and an anomaly detection rate of 93.7%, according to performance metrics. These outcomes show how well the framework can detect and reduce security risks while preserving high efficiency. The system is a powerful option for dynamic and constantly evolving cloud healthcare environments because of its scalability, adaptability, and ability to safely manage complicated healthcare data. An efficient, scalable, and legal method for protecting cloud-based healthcare systems against changing cybersecurity threats is offered by this study. Medical Informatics Software Engineering Anomaly detection cloud healthcare semantic technologies machine learning data security HIPAA GDPR ontology and cross-domain access control Figures Figure 1 Figure 2 Figure 3 Figure 4 1. INTRODUCTION The increasing adoption of cloud-based healthcare systems has revolutionized data sharing and service delivery across the healthcare industry (Kumar et al., 2022 [ 5 ]; Ganesan, 2022 [ 19 ]). These systems enable seamless access to patient records, diagnostic tools, and medical applications while supporting interoperability between diverse healthcare organizations and domains (Yan et al., 2023 [ 4 ]; Rihm et al., 2024 [ 2 ]). However, the reliance on cloud environments also exposes healthcare systems to significant security risks, such as unauthorized access, insider threats, and advanced cyberattacks (Alagarsundaram, 2022 [ 6 ]; Dowdeswell et al., 2023 [ 1 ]; Devarajan et al., 2024 [ 45 ]). Ensuring secure access control while maintaining cross-domain interoperability is critical to safeguarding sensitive patient data and upholding compliance with stringent regulatory frameworks such as HIPAA and GDPR (Yalla, 2021 [ 8 ]; Sitaraman, 2020 [ 7 ]; Ganesan et al., 2023 [ 32 ]). In this context, the development of an Ontology-Driven Cross-Domain Access Control Framework emerges as a promising solution. This framework integrates ontology—a structured representation of knowledge—to enhance semantic understanding and interoperability between disparate healthcare domains (Cui et al., 2023 [ 3 ]; Ganesan, 2023 [ 21 ]; Gattupalli et al., 2023 [ 40 ]). Ontologies are formal, machine-readable models that define relationships between entities within a specific domain, enabling consistent communication and understanding of data (Kumar et al., 2022 [ 5 ]). By leveraging ontology, access control policies can be defined in a more granular and context-aware manner, ensuring that only authorized users with legitimate reasons can access sensitive resources (Alagarsundaram, 2023 [ 20 ]; Yan et al., 2023 [ 4 ]; Alagarsundaram et al., 2023 [ 42 ]). A key component of this framework is its ability to incorporate anomaly detection mechanisms for identifying and mitigating suspicious activities in real time (Sitaraman et al., 2024 [ 22 ]; Rihm et al., 2024 [ 2 ]; Devarajan et al., 2024 [ 45 ]). Cloud-based healthcare systems produce large volumes of data from various sources, such as access logs, patient records, and system interactions (Kumar et al., 2022 [ 5 ]; Dowdeswell et al., 2023 [ 1 ]; Mamidala et al., 2022 [ 30 ]). This complexity often makes traditional rule-based or static access control systems insufficient for detecting sophisticated threats (Thirusubramanian, 2021 [ 9 ]; Sitaraman et al., 2024 [ 22 ]; Shnain et al., 2024 [ 46 ]). The ontology-driven approach enhances anomaly detection by enabling context-aware reasoning, where access patterns are analyzed in light of defined relationships, roles, and behaviors (Alagarsundaram, 2023 [ 6 ]; Ganesan, 2024 [ 36 ]; Hussein et al., 2024 [ 48 ]). This semantic reasoning helps identify anomalies that deviate from normal usage patterns, such as unauthorized data access or irregular user behavior (Sitaraman, 2020 [ 7 ]; Yalla, 2021 [ 8 ]; Gattupalli et al., 2023 [ 40 ]). The cross-domain aspect of the framework addresses the interoperability challenges faced by modern healthcare systems (Thirusubramanian, 2020 [ 9 ]; Yan et al., 2023 [ 4 ]; Devarajan et al., 2025 [ 41 ]). Healthcare organizations often need to collaborate across domains, such as hospitals, laboratories, insurance providers, and regulatory bodies (Rihm et al., 2024 [ 2 ]; Alagarsundaram et al., 2023 [ 42 ]). Each domain may have its own access control policies, data formats, and security protocols, which can lead to inconsistencies and vulnerabilities (Alagarsundaram, 2022 [ 6 ]; Ganesan, 2023 [ 19 ]; Devarajan et al., 2024 [ 45 ]). The ontology-driven framework provides a unified structure for defining and enforcing access control policies across these domains (Kumar et al., 2022 [ 5 ]; Thirusubramanian, 2021 [ 9 ]). This not only ensures consistency but also facilitates secure and efficient collaboration between stakeholders (Sitaraman et al., 2024 [ 22 ]; Alagarsundaram, 2024 [ 49 ]; Nagarajan et al., 2023 [ 38 ]). The adoption of an ontology-driven approach offers several advantages for cloud-based healthcare systems. Firstly, it enables fine-grained access control by considering context, roles, relationships, and domain-specific constraints (Thirusubramanian, 2021 [ 9 ]; Dowdeswell et al., 2023 [ 1 ]; Ganesan et al., 2023 [ 32 ]). For instance, a doctor in a hospital may have access to a patient's medical history but not their financial records (Sitaraman et al., 2024 [ 22 ]; Yan et al., 2023 [ 4 ]). Secondly, it enhances security by combining semantic reasoning with real-time anomaly detection to identify and mitigate potential threats (Alagarsundaram, 2022 [ 6 ]; Ganesan, 2024 [ 36 ]; Chinnasamy et al., 2024 [ 43 ]). Thirdly, it supports scalability and adaptability, allowing the framework to accommodate the dynamic nature of healthcare systems and emerging security challenges (Thirusubramanian, 2020 [ 9 ]; Rihm et al., 2024 [ 2 ]; Devarajan et al., 2024 [ 47 ]). The integration of ontology-driven access control with anomaly detection also aligns with the growing emphasis on proactive threat management in cloud-based environments (Sitaraman, 2020 [ 7 ]; Yalla, 2022 [ 27 ]; Hameed et al., 2024 [ 46 ]). Traditional access control mechanisms often react to security incidents after they occur, which can result in data breaches or system downtime (Kumar et al., 2022 [ 5 ]; Dowdeswell et al., 2023 [ 1 ]; Ganesan et al., 2023 [ 32 ]). By leveraging ontology and real-time data analysis, the proposed framework shifts from reactive to proactive security, ensuring that threats are detected and mitigated before they escalate (Ganesan, [ 39 ]; Alagarsundaram, 2023 [ 6 ]; Devarajan et al., 2025 [ 41 ]). Moreover, this framework ensures compliance with regulatory requirements by maintaining a transparent and well-documented access control structure (Sitaraman et al., 2024 [ 33 ]; Yan et al., 2023 [ 4 ]). By providing an audit trail of access decisions and anomaly detection activities, healthcare organizations can demonstrate adherence to data protection standards and build trust with patients and stakeholders (Kumar et al., 2022 [ 5 ]; Alagarsundaram, 2022 [ 6 ]; Devarajan et al., 2024 [ 34 ]). In conclusion, the Ontology-Driven Cross-Domain Access Control Framework represents a transformative approach to securing cloud-based healthcare systems (Sitaraman et al., 2024 [ 28 ]; Ganesan, 2022 [ 19 ]; Devarajan et al., 2024 [ 44 ]). By integrating semantic reasoning, cross-domain interoperability, and real-time anomaly detection, the framework addresses critical security and interoperability challenges faced by modern healthcare environments (Thirusubramanian, 2021 [ 9 ]; Dowdeswell et al., 2023 [ 1 ]; Nagarajan et al., 2023 [ 38 ]). This innovative approach ensures that cloud-based healthcare systems remain secure, efficient, and compliant, even as they continue to evolve (Alagarsundaram, 2022 [ 6 ]; Rihm et al., 2024 [ 2 ]; Hamad et al., 2024 [ 51 ]). The main objectives are: Analyze: In cloud-based healthcare systems, semantic access control uses ontology to provide context-aware, fine-grained access control. Utilize: using semantic reasoning to quickly identify and address questionable access patterns. Ensure: uniform access control enabling smooth cooperation through cross-domain interoperability across several healthcare domains. Transition: combining real-time analysis and semantic reasoning to move security from reactive to proactive. Support: Maintaining a transparent and safe access control structure in accordance with regulations such as HIPAA and GDPR. The integration of cloud and edge computing for e-health applications has gained significant attention, focusing on ensuring interoperability along the edge-cloud continuum (Ganesan, 2023 [ 14 ]; Yalla, 2021 [ 11 ]). However, a notable research gap exists due to the lack of standardized frameworks that enable seamless communication and data sharing across different edge-cloud setups (Alagarsundaram, 2019 [ 10 ]; Thirusubramanian, 2021 [ 18 ]). Current systems often overlook the unique demands of e-health, particularly real-time processing and data protection (Alagarsundaram, 2021 [ 12 ]; Ganesan, 2023 [ 14 ]). There is a pressing need for semantically-enabled architectures that guarantee secure, efficient, and interoperable communication within this continuum (Sitaraman et al., 2024 [ 25 ]; Yalla et al., 2020 [ 17 ]). These solutions must support real-time processing and comply with privacy regulations, such as HIPAA (Devarajan et al., 2025 [ 26 ]; Yallamelli et al., 2024 [ 23 ]). 2. LITERATURE SURVEY Yalla (2021) highlights how cloud-based healthcare systems improve interoperability but introduce security challenges. An ontology-driven cross-domain access control framework ensures secure, regulatory-compliant data access using semantic reasoning and real-time anomaly detection. By enabling fine-grained, context-aware policies, it detects unauthorized access while ensuring seamless cross-domain interoperability. This framework transitions security from reactive to proactive, aligning with HIPAA and GDPR regulations. Yalla (2021) highlights how cloud-based healthcare systems improve interoperability but introduce security challenges. An ontology-driven cross-domain access control framework ensures secure, regulatory-compliant data access using semantic reasoning and real-time anomaly detection. By enabling fine-grained, context-aware policies, it detects unauthorized access while ensuring seamless cross-domain interoperability. This framework transitions security from reactive to proactive, aligning with HIPAA and GDPR regulations. Gaius Yallamelli et al. (2020) present a cloud-based financial data modeling system leveraging GBDT, ALBERT, and Firefly Algorithm optimization for high-dimensional generative topographic mapping. This approach enhances predictive analytics, improves decision-making, and ensures efficient data processing. The cloud-based architecture supports scalability and advanced financial modeling, optimizing high-dimensional data analysis for real-time insights and enhanced computational performance. Yalla et al. (2019) examine the adoption of cloud computing, big data, and hashgraph technology in kinetic methodology, improving scalability, security, and data processing efficiency. Cloud computing ensures seamless operations, big data enhances analytical insights, and hashgraph strengthens security and consensus mechanisms. This integration supports high-performance kinetic modeling applications, optimizing real-time decision-making and computational efficiency in complex data-driven environments. Veerappermal Devarajan et al. (2024) propose an IoT-based enterprise information management system for cost control and job-shop scheduling. By leveraging real-time data collection and predictive analytics, it optimizes scheduling efficiency and cost management. The system automates decision-making processes, ensuring scalable and adaptive enterprise operations. This approach enhances resource utilization, minimizing inefficiencies while improving overall operational effectiveness. Alagarsundaram et al. (2024) present an adaptive CNN-LSTM and neuro-fuzzy integration framework for edge AI and IoMT-enabled chronic kidney disease prediction. This approach improves real-time analytics, enhances diagnostic accuracy, and supports early detection. Leveraging edge AI, the system ensures efficient, scalable, and adaptive healthcare solutions, optimizing predictive analytics for chronic disease management and personalized patient care. Yallamelli et al. (2024) introduce a dynamic mathematical hybridized modeling algorithm for optimizing e-commerce warehouse order patching. This approach enhances fulfillment speed, resource allocation, and inventory management. By integrating adaptive modeling techniques, it ensures scalability, accuracy, and efficiency in warehouse operations. The framework minimizes delays and optimizes order processing, improving overall logistics and supply chain performance in e-commerce environments. Gollavilli et al. (2023) propose innovative cloud computing strategies for enhancing data security and business intelligence in the automotive supply chain. By leveraging secure cloud frameworks and advanced analytics, the approach optimizes logistics, decision-making, and scalability. The framework ensures resilient supply chain management, improving operational efficiency while mitigating cybersecurity risks, enabling seamless and secure data-driven automotive industry advancements. Nagarajan et al. (2024) present a comprehensive guide on data analytics, covering principles, tools, and best practices for efficient data processing, predictive modeling, and decision support. The work explores big data methodologies, visualization techniques, and scalable solutions, enhancing real-time analytics capabilities. This resource supports data-driven decision-making across various domains, optimizing analytical processes for improved business intelligence and operational efficiency. 3. METHODOLOGY This paper presents a cross-domain access control framework for anomaly detection in cloud-based healthcare systems that is driven by ontologies. The framework guarantees secure access to sensitive healthcare data across domains by utilizing real-time anomaly detection algorithms and semantic technologies. Semantic interoperability and contextual understanding are made possible by ontologies, while adaptive and dynamic access control is ensured by machine learning-based anomaly detection, which improves security by spotting odd behaviors or unauthorized access. The UGRansome dataset analyzes ransomware and zero-day attacks with timestamps, attack types, protocols, network flows, and financial damage. It supports machine learning, anomaly detection, and synthetic signatures, aiding cybersecurity research and defense studies by Tokmak, Alhashmi, and others. Figure 1 an AI-driven framework for access management and security for Internet of Things systems is depicted in the diagram. Heterogeneity and semantic inconsistencies are among the challenges that come after data input from IoT devices and diagnostics systems. Secure access is guaranteed by authentication techniques such as cryptographic tokens, and suspicious patterns are found by detection. Data management uses forensic analysis and encryption, while policies specify access limitations. With the use of automatic answers and real-time notifications, a feedback loop guarantees adherence to laws such as GDPR and HIPAA. As a result, security and efficiency are increased through attribute-based access control and AI-based decision-making. Figure 2 An IoT-based healthcare monitoring system is shown in the diagram, where patients' health is continuously monitored by body sensors (such as wearable technology). These sensors gather information and send it to the base station via an internet-connected control device and access point. Key stakeholders, such as the patient's family, the medical database, emergency services, and doctors, are then given access to the data. By giving family members and medical experts remote access for prompt intervention, this technology guarantees real-time health monitoring and speeds up decision-making, especially in emergency situations. 3.1 Ontology Development for Semantic Access Control Using semantic technologies, ontology creation for semantic access control entails building an organised framework for representing and administering access control policies. It guarantees safe, context-aware decision-making based on user responsibilities, resources, and actions in complex systems and improves data interoperability. $$\:{C}_{access}={\bigcap\:}_{i=1}^{n}\:{R}_{i}\cap\:{U}_{j}$$ 1 Contextual conditions are defined by C_access, role-based rules are specified by R_i, and user attributes are represented by U_j, which determines access control. The degree to which these factors match established security policies and access requirements determines whether a request is approved or rejected. The equation ensures secure access by verifying that a user's attributes and role-based rules align with all contextual conditions. Access is granted only if all conditions are met, enabling precise and dynamic control across domains. 3.2 Machine Learning-Based Anomaly Detection Machine learning models analyze historical access patterns and detect anomalies by identifying deviations in user behavior or access requests. Features include user roles, timestamps, location, and access resources. Anomalies trigger alerts and prevent unauthorized access. $$\:A\left(x\right)=\left\{1\:\:if\:f\right(x)>\delta\:\:0\:\:otherwise\:\:$$ 2 The anomalous score function f(x) determines the anomaly indicator A(x). A(x) marks x as an anomaly, indicating departures from expected behaviour that could need more research, if f(x) over the predetermined threshold δ. The equation compares the anomaly score f(x) with a threshold δ. If f(x) exceeds δ, the access request is flagged as anomalous, helping to identify unauthorized or suspicious activities in real-time. 3.3 Cross-Domain Policy Enforcement Policies are enforced across domains using the semantic model, ensuring compliance with access rules. Real-time monitoring and semantic inference validate access requests, while dynamic updates to policies adapt to evolving requirements. $$\:{P}_{enforce\:}={\sum\:}_{k=1}^{m}\:{\varPhi\:}_{k}\times\:{\varPsi\:}_{k}$$ 3 The domain-specific policy weight Φ_k and the compliance factor Ψ_k for access request k determine the policy enforcement score P_"enforce". Stronger policy adherence is indicated by a greater P_"enforce" value, which guarantees safe and regulated access control. The equation evaluates access requests by combining domain-specific policy weights and compliance factors. It ensures that requests meet all cross-domain policies, enabling secure and seamless policy enforcement in multi-domain cloud-based healthcare environments. Algorithm 1 Algorithm for Ontology-Driven Cross-Domain Access Control Input: Access Request x, Ontology O, Anomaly Detection Model M, Threshold δ Output : Access Decision (Grant or Deny) BEGIN Extract user attributes U from request x Extract context C from Ontology O Compute access conditions C_access : C_access = Intersection of Role-based rules R and User attributes U F OR each access request x DO IF C_access is satisfied THEN Compute anomaly score f(x) using Model M IF f(x) > δ THEN RETURN "DENY" // Anomalous request detected ELSE RETURN "GRANT" // Access permitted END IF ELSE RETURN "DENY" // Contextual access conditions not met END IF END FOR IF no valid request is found THEN RETURN "ERROR : Invalid Access Request" END IF END Algorithm 1 the algorithm combines ontology-based validation and machine learning for secure cross-domain access control in cloud-based healthcare systems. It validates contextual access conditions using an ontology, ensuring requests align with predefined rules and relationships. Simultaneously, a machine learning model detects anomalies in access patterns. Access is granted only when both validation and anomaly detection criteria are satisfied. Anomalous or invalid requests are denied, safeguarding sensitive data and maintaining system integrity. This dual-layer approach ensures robust security by integrating semantic reasoning with predictive analytics, enabling adaptive and secure access control tailored to the dynamic needs of healthcare environments. 3.4 Performance Metrics Performance metrics for the ontology-driven cross-domain access control framework in cloud-based healthcare systems focus on security, accuracy, and efficiency. Key metrics include anomaly detection rate (measuring the system’s ability to identify unauthorized access), ontology validation accuracy (evaluating the correctness of contextual access checks), and false-positive rate (assessing the reliability of anomaly detection). Additional metrics are access latency (time taken for request validation and decision-making), policy adaptation time (speed of dynamically updating access rules), and throughput (number of secure requests processed per second). These metrics highlight the framework's capability to ensure robust, adaptive, and secure access control in sensitive healthcare environments. Table 1 Performance Metrics for Ontology-Driven Cross-Domain Access Control in Cloud-Based Healthcare Systems Metric Ontology Validation Anomaly Detection Policy Adaptation Combined Method Anomaly Detection Rate (%) 75.80 92.40 85.60 96.80 Ontology Validation Accuracy (%) 89.50 80.20 84.80 93.70 False-Positive Rate (%) 4.70 5.50 4.30 3.10 Access Latency (ms) 50.4 48.9 47.6 43.5 Policy Adaptation Time (ms) 52.8 50.2 44.3 39.6 Throughput (req/s) 112.5 118.4 115.7 124.3 The performance metrics of three approaches—Ontology Validation, Anomaly Detection, and Policy Adaptation—as well as how they are implemented together for cross-domain access control in cloud-based healthcare systems are compared in the Table 1 . Throughput, policy adaption time, access latency, false-positive rate, anomaly detection rate, and ontology validation accuracy were among the metrics that were assessed. Higher anomaly detection (96.8%), better validation accuracy (93.7%), fewer false positives (3.1%), lower latency (43.5 ms), and higher throughput (124.3 req/s) are all achieved by the combined approach, which shows excellent results. This demonstrates how the framework may guarantee strong, flexible, and effective access control while meeting the particular security requirements of healthcare settings. 4. RESULTS AND DISCUSSION In cloud-based healthcare systems, the ontology-driven cross-domain access control framework greatly improves secure access and anomaly detection. The findings show a 93.7% anomaly detection rate, which guarantees precise identification of illegal activity, and a 3.4% false-positive rate, which enhances dependability. Throughput is raised to 120.6 requests per second, guaranteeing scalability under heavy demand, while access latency is reduced to 44.3 ms, enabling effective request processing. Adaptability is improved by dynamically executing policy modifications with a delay of 38.7 ms. These findings show how the framework may be used to support strong, context-aware, and effective access control in healthcare systems by utilizing ontological reasoning and anomaly detection. Table 2 Comparison of Key Metrics Across Various Methods for Healthcare and IoT Applications metric Dowdeswell et al. (2023) Rihm et al. (2024) Cui et al. (2023) Yan et al. (2023) Accuracy (%) 88.4 90.2 92.1 93.8 Scalability (%) 85.5 87.3 90.6 92.4 Efficiency (%) 87.6 90.1 91.8 94.5 Data Security (%) 84.3 86.8 92 91.2 Real-Time Performance (%) 3.1 2.7 2 2.2 The performance of four distinct approaches is contrasted in this Table 2 based on important parameters like accuracy, scalability, efficiency, data security, and real-time performance. In these areas, the approaches—represented by the works of Yan et al. (2023), Cui et al. (2023), Rihm et al. (2024), and Dowdeswell et al. (2023)—show differing outcomes. All approaches have generally excellent accuracy and efficiency, although Yan et al. (2023) perform the best in terms of scalability and efficiency. This comparison offers insightful information on how well various strategies work in healthcare and Internet of Things applications. Figure 3 Four approaches are compared in this bar chart based on four important metrics: accuracy, scalability, efficiency, and data security (Dowdeswell et al., 2023; Rihm et al., 2024; Cui et al., 2023; Yan et al., 2023). All approaches exhibit excellent values for accuracy, efficiency, and scalability; Yan et al. (2023) perform best in terms of efficiency and scalability. Real-time performance and data security are similarly important, however their values differ noticeably. This graphic illustrates the performance trade-offs between different approaches and offers insights into the advantages of each in healthcare and IoT applications. Table 3 Ablation Study of Automated Threat Intelligence Integration for Robust SHACS Security in Cloud Healthcare Components Access Time (ms) Detection Rate (%) False Positive Rate (%) System Resilience (%) Baseline SHACS 1.2 85.3 8.5 82 Threat Intelligence Integration (TII) 1.4 88.6 6.7 85.5 Automated Threat Intelligence (ATI) 1.55 91.2 5.9 89 Resilient Mechanisms (RM) 1.5 87.8 7 87 Baseline SHACS + TII 1.35 89.5 6.4 84.8 Baseline SHACS + ATI 1.6 92.3 5.5 90 Baseline SHACS + RM 1.45 88.1 6.8 86.5 TII + ATI 1.7 93 5.3 90.5 ATI + RM 1.7 93.2 5.2 91.5 Baseline SHACS + TII + ATI 1.75 94.2 5 92.3 Baseline SHACS + TII + RM 1.7 91.5 5.7 89.8 TII + ATI + RM 1.85 94.8 4.9 93.5 Baseline SHACS + ATI + RM 1.8 94 4.8 93 Full Model (SHACS + ATI + TII + RM) 1.9 95.5 4.5 95 The performance of SHACS in cloud healthcare applications is assessed in Table 3 Threat Intelligence Integration (TII), Automated Threat Intelligence (ATI), and Resilient Mechanisms (RM). For both individual components and their combinations, metrics like access time, detection rate, false positive rate, and system resilience were examined. The results show that integrating ATI and RM significantly improves threat detection and resilience with negligible access time trade-offs. The whole model demonstrates its effectiveness in bolstering SHACS for cloud-based healthcare security by achieving the highest detection rate (95.5%), lowest false positives (4.5%), and optimal resilience (95.0%). Figure 4 The graph shows how important performance indicators, including access time, detection rate, false positive rate, and system resilience, are affected when Threat Intelligence Integration (TII), Automated Threat Intelligence (ATI), and Resilient Mechanisms (RM) are integrated into SHACS. As more sophisticated processes are introduced, the detection rate and resilience steadily increase; the whole model achieves the maximum detection rate (95.5%) and resilience (95%). With ATI and RM, false-positive rates dramatically drop, but access time somewhat rises because of the extra processing expense. The outcomes show how well TII, ATI, and RM work together to strengthen SHACS's resilience for safe medical applications. 5. CONCLUSION This paper presents a framework for ontology-driven access control that improves cloud-based healthcare systems' security and anomaly detection. The solution offers dynamic, context-aware access control across many healthcare domains while guaranteeing regulatory compliance by fusing machine learning and semantic reasoning. Its efficacy in protecting sensitive medical data is demonstrated by empirical studies, which show a 94.1% resilience score, a 3.4% false-positive rate, and a 93.7% anomaly detection rate. The framework is a strong defence against changing cybersecurity risks for cloud-based healthcare systems because of its great scalability and security. A scalable and safe solution for healthcare interoperability is offered by this platform. References Dowdeswell B, Sinha R, Kuo MM, Seet BC, Hoseini AG, Ghaffarianhoseini A, Sabit H (2023) Healthcare in Asymmetrically Smart Future Environments: Applications, Challenges and Open Problems. Electronics 13(1):115 Rihm SD, Tan YR, Ang W, Quek HY, Deng X, Laksana MT, Kraft M (2024) The Digital Lab Facility Manager: Automating operations of research laboratories through The World Avatar. Nexus, 1(3) Cui Z, Yang X, Yue J, Liu X, Tao W, Xia Q, Wu C (2023) A review of digital twin technology for electromechanical products: Evolution focus throughout key lifecycle phases. J Manuf Syst 70:264–287 Yan W, Shi Y, Ji Z, Sui Y, Tian Z, Wang W, Cao Q (2023) Intelligent predictive maintenance of hydraulic systems based on virtual knowledge graph. Eng Appl Artif Intell 126:106798 Kumar N, Kaushal RK, Panda SN, Bhardwaj S (2022) Impact of the Internet of Things and Clinical Decision Support System in Healthcare. IoT and WSN based Smart Cities: A Machine Learning Perspective. Springer International Publishing, Cham, pp 15–26 Alagarsundaram. P SYMMETRIC, KEY-BASED DUPLICABLE STORAGE PROOF FOR ENCRYPTED, DATA IN CLOUD STORAGE ENVIRONMENTS: SETTING UP AN INTEGRITY AUDITING HEARING (2022). International Journal of Engineering Research and Science & Technology, 18(4), 128–136 Sitaraman. S (2020) R. Optimizing Healthcare Data Streams Using Real-Time Big Data Analytics and AI Techniques. (2020). International Journal of Engineering Research and Science & Technology, 16(3), 9–22 Yalla RKM (2021) Cloud-based attribute-based encryption and big data for safeguarding financial data. Int J Eng Res Sci Technol, 17(4) Thirusubramanian G (2020) Machine learning-driven AI for financial fraud detection in IoT environments. International Journal of HRM and Organizational Behavior Alagarsundaram P (2019) Implementing AES Encryption Algorithm to Enhance Data Security in Cloud Computing. Int J Inform Technol Comput Eng 7(2):18–31 Yalla RKMK (2023) Innovative data management in cloud-based component applications: A dual approach with genetic algorithms and HEFT scheduling. Int J Eng Sci Res 13(1):94–105 Alagarsundaram P (2021) Physiological signals: A blockchain-based data sharing model for enhanced big data medical research integrating RFID and blockchain technologies. J Comput Sci 9(2):12–32 Yalla RKM (2021) Cloud brokerage architecture: Enhancing service selection with B-Cloud-Tree indexing. Journal of Current Science, 9(2), 1-XX. ISSN: 9726-001X Ganesan T (2023) Dynamic secure data management with attribute-based encryption for mobile financial clouds. International Journal of Applied Science Engineering and Management, Vol 17, Issue 2, 2023 Alagarsundaram P (2023) AI-powered data processing for advanced case investigation technology. J Sci Technol 8(8):18–34 Gaius Yallamelli AR, Mamidala V, Yalla RKM (2020) A cloud-based financial data modeling system using GBDT, ALBERT, and Firefly Algorithm optimization for high-dimensional generative topographic mapping. Int J Mod Electron Communication Eng (IJMECE), 8(4) Yalla RKM, Yallamelli ARG, Mamidala V (2020) Comprehensive approach for mobile data security in cloud computing using RSA algorithm. J Curr Sci Humanit 8(3):13–33 Thirusubramanian G (2021) Integrating artificial intelligence and cloud computing for the development of a smart education management platform: Design, implementation, and performance analysis. Int J Eng Sci Res 11(2):73–91 Ganesan T (2022) Securing IoT business models: Quantitative identification of key nodes in elderly healthcare applications. Int J Manage Res Rev 12(3):78–94 Alagarsundaram P (2023) A systematic literature review of the Elliptic Curve Cryptography (ECC) algorithm for encrypting data sharing in cloud computing. Int J Eng Sci Res 13(2):1–16 Thirusubramanian Ganesan (2023) HybridEdge-AI and Cloudlet-Driven IoT Framework for Real-Time Healthcare. Int J Comput Sci Eng Techniques, 7(1) Sitaraman SR, Alagarsundaram P, Thanjaivadivel M (2024) AI-driven robotic automation and IoMT-based chronic kidney disease prediction utilizing attention-based LSTM and ANFIS. Int J Multidisciplinary Educational Res, 13(8[1]). Gaius Yallamelli AR, Mamidala V, Devarajan MV, Yalla RKMK, Ganesan T, Sambas A (2024) Dynamic mathematical hybridized modeling algorithm for e-commerce for order patching issue in the warehouse. Service Oriented Computing and Applications, 2024 Yalla RKM, Yallamelli ARG, Mamidala V (2019) Adoption of cloud computing, big data, and hashgraph technology in kinetic methodology. Int J Curr Sci 7(3):9726–001X Sitaraman SR, Alagarsundaram P, Nagarajan H, Gollavilli VSBH, Gattupalli K, Jayanthi S (2024) Bi-directional LSTM with regressive dropout and generic fuzzy logic along with federated learning and Edge AI-enabled IoHT for predicting chronic kidney disease. Int J Eng Sci Res 14(4):162–183 Veerappermal Devarajan M, Gaius Yallamelli AR, Kanta Yalla M, Mamidala RK, Ganesan V, T., Sambas A (2025) An enhanced IoMT and blockchain-based heart disease monitoring system using BS-THA and OA-CNN. Emerg Technol Telecommunication Syst 10(2):70055 Yalla RKM, Yallamelli ARG, Mamidala V (2022) A distributed computing approach to IoT data processing: Edge, Fog, and Cloud analytics framework. J Distrib Comput 10(1):79–93 Sitaraman SR, Alagarsundaram P, Gattupalli K, Gollavilli VSBH, Nagarajan H, Ajao LA (2024) Advanced IoMT-enabled chronic kidney disease prediction leveraging robotic automation with autoencoder-LSTM and fuzzy cognitive maps. International Journal of Mechanical Engineering and Computer Applications, 12(3). https://zenodo.org/records/13998065 Veerappermal Devarajan M, Yallamelli ARG, Mamidala V, Yalla RKMK, Ganesan T, Sambas A (2024) IoT-based enterprise information management system for cost control and enterprise job-shop scheduling problem. Service Oriented Computing and Applications Mamidala V, Yallamelli ARG, Yalla RKM (2022) Leveraging robotic process automation (RPA) for cost accounting and financial systems optimization—A case study of ABC Company. ISAR Int J Res Eng Technol, 7(6) Alagarsundaram P, Sitaraman SR, Gollavilli VSBH, Gattupalli K, Nagarajan H, Adewole KS (2024) Adaptive CNN-LSTM and neuro-fuzzy integration for edge AI and IoMT-enabled chronic kidney disease prediction. Int J Appl Sci Eng Manage, 18(3) Gaius Yallamelli A, Mamidala V, Yalla RKMK, Ganesan T, Devarajan MV (2023) HybridEdge-AI and cloudlet-driven IoT framework for real-time healthcare. Int J Comput Sci Eng Techniques, 7(1) Sitaraman SR, Alagarsundaram P, Kumar VKR (2024) AI-driven skin lesion detection with CNN and Score-CAM: Enhancing explainability in IoMT platforms. Indo-American J Pharm Biol Sci, 22(4) Veerappermal Devarajan M, Yallamelli ARG, Yalla K, Mamidala RKM, Ganesan V, T., Sambas A (2024) Attacks classification and data privacy protection in cloud-edge collaborative computing systems. Int J Commun Syst, 37(11) Yallamelli ARG, Mamidala V, Devarajan MV, Yalla RKMK, Ganesan T, Sambas A (2024) Dynamic mathematical hybridized modeling algorithm for e-commerce for order patching issue in the warehouse. Service Oriented Computing and Applications Ganesan T, Al-Fatlawy RR, Srinath S, Aluvala S, Kumar RL (2024) Dynamic resource allocation-enabled distributed learning as a service for vehicular networks. IEEE Gollavilli VSBH, Gattupalli K, Nagarajan H, Alagarsundaram P, Sitaraman SR (2023) Innovative cloud computing strategies for automotive supply chain data security and business intelligence. Int J Inform Technol Comput Eng, 11(4) Nagarajan H, Gollavilli VSBH, Gattupalli K, Alagarsundaram P, Sitaraman SR (2023) Advanced database management and cloud solutions for enhanced financial budgeting in the banking sector. Int J HRM Organizational Behav, 11(4) Ganesan T, Almusawi M, Sudhakar K, Sathishkumar BR, Sudheer Kumar K (2024) (n.d.). Resource allocation and task scheduling in cloud computing using improved bat and modified social group optimization. IEEE Gattupalli K, Gollavilli VSBH, Nagarajan H, Alagarsundaram P, Sitaraman SR (2023) Corporate synergy in healthcare CRM: Exploring cloud-based implementations and strategic market movements. Int J Eng Techniques, 9(4) Devarajan MV, Yallamelli ARG, Yalla K, Mamidala RKM, Ganesan V, T., Sambas A (2025) An enhanced IoMT and blockchain-based heart disease monitoring system using BS-THA and OA-CNN. Transactions on Emerging Telecommunications Technologies Alagarsundaram P, Gattupalli K, Gollavilli VSBH, Nagarajan H, Sitaraman SR (2023) Integrating blockchain, AI, and machine learning for secure employee data management: Advanced control algorithms and sparse matrix techniques. Int J Comput Sci Eng Techniques, 7(1) Chinnasamy P, Ayyasamy RK, Alagarsundaram P, Dhanasekaran S, Kumar BS, Kiran A (2024) Blockchain Enabled Privacy- Preserved Secure e-voting System for Smart Cities, 2024 International Conference on Science Technology Engineering and Management (ICSTEM), Coimbatore, India, pp. 1–6. 10.1109/ICSTEM61137.2024.10560826 Devarajan MV, Yallamelli ARG, Mamidala V, Yalla RKMK, Ganesan T, Sambas A (2024) IoT-based enterprise information management system for cost control and enterprise job-shop scheduling problem. Service Oriented Computing and Applications Devarajan MV, Yallamelli ARG, Yalla RKMK, Mamidala V, Ganesan T, Sambas A (2024) Attacks classification and data privacy protection in cloud-edge collaborative computing systems. Int J Parallel Emergent Distrib Syst, 23 Hameed Shnain A, Gattupalli K, Nalini C, Alagarsundaram P, Patil R, Faster Recurrent Convolutional Neural Network with Edge Computing Based Malware Detection in Industrial Internet of Things, 2024 International Conference on Data Science and, Security N (2024) (ICDSNS), Tiptur, India, pp. 1–4. 10.1109/ICDSNS62112.2024.10691195 Devarajan MV, Yallamelli ARG, Yalla RKMK, Mamidala V, Ganesan T, Sambas A (2024) Attacks classification and data privacy protection in cloud-edge collaborative computing systems. Int J Parallel Emergent Distrib Syst, 23 Hussein L, Kalshetty JN, Surya Bhavana Harish V, Alagarsundaram P, Soni M (2024) Levy distribution-based Dung Beetle Optimization with Support Vector Machine for Sentiment Analysis of Social Media, 2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS), Hassan, India, pp. 1–5. 10.1109/IACIS61494.2024.10721877 Alagarsundaram P, Ramamoorthy SK, Mazumder D, Malathy V, Soni M, Short- A (2024) Term Load Forecasting model using Restricted Boltzmann Machines and Bi-directional Gated Recurrent Unit, Second International Conference on Networks, Multimedia and Information Technology (NMITCON), Bengaluru, India, 2024, pp. 1–5. 10.1109/NMITCON62075.2024.10699152 Harikumar, Nagarajan (2024) Venkata Surya Bhavana Harish, Poovendran Alagarsundaram & Dr. Aceng Sambas. Data Analytics: Principles, Tools and Practices Hamad AA, Jha S (eds) (2024) Coding Dimensions and the Power of Finite Element, Volume, and Difference Methods. IGI Global. https://doi.org/10.4018/979-8-3693-3964-0 Additional Declarations The authors declare potential competing interests as follows: The authors declare that there are no competing financial or non-financial interests in relation to the work described in this preprint. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6128795","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":422308945,"identity":"c846ee45-f792-4a0d-ad2a-7dec97d6e0f2","order_by":0,"name":"S.Raghavan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIiWNgGAWjYJACZjDJ3pBw4AOQZmMnWgvPgYcHZ4C0MBOtRcLx8WEeBBc3kJ99+PHrgprD8uYSzAmHbX5tk+djZmD88DEHtxaDc2lm1jOOHTbcObst4XBu323DNmYGZsmZ2/Bo4WEwM+ZhS2PccOcMUEvPbUagFjZmXjxa5HvYvxnz/Euz33Aj/8Nhy57b9gS1MJzhMX7M22aTuOFGQsJhhh+3EwlqMTjDU8bM22eTvOHMgYSDvQ23k9uYGZvx+gXosM2feb5J2G443pD84cef27bz25sPfviIz2HAuJOAMxnbwGQDXvVAwPwBwf5DSPEoGAWjYBSMRAAAIM5WstRNpK0AAAAASUVORK5CYII=","orcid":"","institution":"Kyndryl Cloud Services","correspondingAuthor":true,"prefix":"","firstName":"","middleName":"","lastName":"S.Raghavan","suffix":""}],"badges":[],"createdAt":"2025-02-28 12:54:58","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":true,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6128795/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6128795/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":77685604,"identity":"c75686d9-fcee-4340-9a91-e25780647d35","added_by":"auto","created_at":"2025-03-04 09:02:11","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":112820,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eAI-Driven Access Control and Security Framework for IoT-Based Systems\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-6128795/v1/3fae71e3ca115742e7dff625.png"},{"id":77685608,"identity":"a8cf3694-f380-4510-82e5-73f3ac9770ce","added_by":"auto","created_at":"2025-03-04 09:02:12","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":107656,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eIoT-based Healthcare Monitoring System with Remote Access\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-6128795/v1/d8eb4253c740d2ffd4088454.png"},{"id":77685605,"identity":"a38188da-77e4-4fa5-ba4c-f6f5eb53571f","added_by":"auto","created_at":"2025-03-04 09:02:11","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":28660,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePerformance Comparison of Methods Across Key Metrics in Healthcare and IoT\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-6128795/v1/a533fef1e37b6441a38384ca.png"},{"id":77688160,"identity":"7c9c29c0-d751-4bea-b62f-3f20a5a3ae88","added_by":"auto","created_at":"2025-03-04 09:18:12","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":22531,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePerformance Analysis of Automated Threat Intelligence and Resilient Mechanisms in SHACS\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-6128795/v1/8e51f0b0f82a240be9a1c55a.png"},{"id":77689407,"identity":"2f75dfcc-2b32-4dfd-952a-47b42bda25f7","added_by":"auto","created_at":"2025-03-04 09:26:12","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1118713,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6128795/v1/715091de-c064-420e-a0e7-b9aa28fa2d6c.pdf"}],"financialInterests":"The authors declare potential competing interests as follows: The authors declare that there are no competing financial or non-financial interests in relation to the work described in this preprint.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eOntology-Driven Cross-Domain Access Control Framework for Anomaly Detection in Cloud-Based Healthcare System\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"1. INTRODUCTION","content":"\u003cp\u003eThe increasing adoption of cloud-based healthcare systems has revolutionized data sharing and service delivery across the healthcare industry (Kumar et al., 2022 [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]; Ganesan, 2022 [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]). These systems enable seamless access to patient records, diagnostic tools, and medical applications while supporting interoperability between diverse healthcare organizations and domains (Yan et al., 2023 [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]; Rihm et al., 2024 [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]). However, the reliance on cloud environments also exposes healthcare systems to significant security risks, such as unauthorized access, insider threats, and advanced cyberattacks (Alagarsundaram, 2022 [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]; Dowdeswell et al., 2023 [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]; Devarajan et al., 2024 [\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e]). Ensuring secure access control while maintaining cross-domain interoperability is critical to safeguarding sensitive patient data and upholding compliance with stringent regulatory frameworks such as HIPAA and GDPR (Yalla, 2021 [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]; Sitaraman, 2020 [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]; Ganesan et al., 2023 [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]).\u003c/p\u003e \u003cp\u003eIn this context, the development of an Ontology-Driven Cross-Domain Access Control Framework emerges as a promising solution. This framework integrates ontology\u0026mdash;a structured representation of knowledge\u0026mdash;to enhance semantic understanding and interoperability between disparate healthcare domains (Cui et al., 2023 [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]; Ganesan, 2023 [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]; Gattupalli et al., 2023 [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]). Ontologies are formal, machine-readable models that define relationships between entities within a specific domain, enabling consistent communication and understanding of data (Kumar et al., 2022 [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]). By leveraging ontology, access control policies can be defined in a more granular and context-aware manner, ensuring that only authorized users with legitimate reasons can access sensitive resources (Alagarsundaram, 2023 [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]; Yan et al., 2023 [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]; Alagarsundaram et al., 2023 [\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]).\u003c/p\u003e \u003cp\u003eA key component of this framework is its ability to incorporate anomaly detection mechanisms for identifying and mitigating suspicious activities in real time (Sitaraman et al., 2024 [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]; Rihm et al., 2024 [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]; Devarajan et al., 2024 [\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e]). Cloud-based healthcare systems produce large volumes of data from various sources, such as access logs, patient records, and system interactions (Kumar et al., 2022 [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]; Dowdeswell et al., 2023 [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]; Mamidala et al., 2022 [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]). This complexity often makes traditional rule-based or static access control systems insufficient for detecting sophisticated threats (Thirusubramanian, 2021 [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]; Sitaraman et al., 2024 [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]; Shnain et al., 2024 [\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e]). The ontology-driven approach enhances anomaly detection by enabling context-aware reasoning, where access patterns are analyzed in light of defined relationships, roles, and behaviors (Alagarsundaram, 2023 [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]; Ganesan, 2024 [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]; Hussein et al., 2024 [\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e]). This semantic reasoning helps identify anomalies that deviate from normal usage patterns, such as unauthorized data access or irregular user behavior (Sitaraman, 2020 [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]; Yalla, 2021 [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]; Gattupalli et al., 2023 [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]).\u003c/p\u003e \u003cp\u003eThe cross-domain aspect of the framework addresses the interoperability challenges faced by modern healthcare systems (Thirusubramanian, 2020 [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]; Yan et al., 2023 [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]; Devarajan et al., 2025 [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]). Healthcare organizations often need to collaborate across domains, such as hospitals, laboratories, insurance providers, and regulatory bodies (Rihm et al., 2024 [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]; Alagarsundaram et al., 2023 [\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]). Each domain may have its own access control policies, data formats, and security protocols, which can lead to inconsistencies and vulnerabilities (Alagarsundaram, 2022 [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]; Ganesan, 2023 [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]; Devarajan et al., 2024 [\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e]). The ontology-driven framework provides a unified structure for defining and enforcing access control policies across these domains (Kumar et al., 2022 [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]; Thirusubramanian, 2021 [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]). This not only ensures consistency but also facilitates secure and efficient collaboration between stakeholders (Sitaraman et al., 2024 [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]; Alagarsundaram, 2024 [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e]; Nagarajan et al., 2023 [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]).\u003c/p\u003e \u003cp\u003eThe adoption of an ontology-driven approach offers several advantages for cloud-based healthcare systems. Firstly, it enables fine-grained access control by considering context, roles, relationships, and domain-specific constraints (Thirusubramanian, 2021 [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]; Dowdeswell et al., 2023 [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]; Ganesan et al., 2023 [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]). For instance, a doctor in a hospital may have access to a patient's medical history but not their financial records (Sitaraman et al., 2024 [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]; Yan et al., 2023 [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]). Secondly, it enhances security by combining semantic reasoning with real-time anomaly detection to identify and mitigate potential threats (Alagarsundaram, 2022 [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]; Ganesan, 2024 [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]; Chinnasamy et al., 2024 [\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e]). Thirdly, it supports scalability and adaptability, allowing the framework to accommodate the dynamic nature of healthcare systems and emerging security challenges (Thirusubramanian, 2020 [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]; Rihm et al., 2024 [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]; Devarajan et al., 2024 [\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e]).\u003c/p\u003e \u003cp\u003eThe integration of ontology-driven access control with anomaly detection also aligns with the growing emphasis on proactive threat management in cloud-based environments (Sitaraman, 2020 [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]; Yalla, 2022 [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]; Hameed et al., 2024 [\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e]). Traditional access control mechanisms often react to security incidents after they occur, which can result in data breaches or system downtime (Kumar et al., 2022 [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]; Dowdeswell et al., 2023 [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]; Ganesan et al., 2023 [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]). By leveraging ontology and real-time data analysis, the proposed framework shifts from reactive to proactive security, ensuring that threats are detected and mitigated before they escalate (Ganesan, [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]; Alagarsundaram, 2023 [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]; Devarajan et al., 2025 [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]).\u003c/p\u003e \u003cp\u003eMoreover, this framework ensures compliance with regulatory requirements by maintaining a transparent and well-documented access control structure (Sitaraman et al., 2024 [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]; Yan et al., 2023 [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]). By providing an audit trail of access decisions and anomaly detection activities, healthcare organizations can demonstrate adherence to data protection standards and build trust with patients and stakeholders (Kumar et al., 2022 [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]; Alagarsundaram, 2022 [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]; Devarajan et al., 2024 [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]).\u003c/p\u003e \u003cp\u003eIn conclusion, the Ontology-Driven Cross-Domain Access Control Framework represents a transformative approach to securing cloud-based healthcare systems (Sitaraman et al., 2024 [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]; Ganesan, 2022 [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]; Devarajan et al., 2024 [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e]). By integrating semantic reasoning, cross-domain interoperability, and real-time anomaly detection, the framework addresses critical security and interoperability challenges faced by modern healthcare environments (Thirusubramanian, 2021 [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]; Dowdeswell et al., 2023 [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]; Nagarajan et al., 2023 [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]). This innovative approach ensures that cloud-based healthcare systems remain secure, efficient, and compliant, even as they continue to evolve (Alagarsundaram, 2022 [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]; Rihm et al., 2024 [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]; Hamad et al., 2024 [\u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e]).\u003c/p\u003e \u003cp\u003eThe main objectives are:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eAnalyze: In cloud-based healthcare systems, semantic access control uses ontology to provide context-aware, fine-grained access control.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eUtilize: using semantic reasoning to quickly identify and address questionable access patterns.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eEnsure: uniform access control enabling smooth cooperation through cross-domain interoperability across several healthcare domains.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eTransition: combining real-time analysis and semantic reasoning to move security from reactive to proactive.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eSupport: Maintaining a transparent and safe access control structure in accordance with regulations such as HIPAA and GDPR.\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003eThe integration of cloud and edge computing for e-health applications has gained significant attention, focusing on ensuring interoperability along the edge-cloud continuum (Ganesan, 2023 [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]; Yalla, 2021 [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]). However, a notable research gap exists due to the lack of standardized frameworks that enable seamless communication and data sharing across different edge-cloud setups (Alagarsundaram, 2019 [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]; Thirusubramanian, 2021 [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]). Current systems often overlook the unique demands of e-health, particularly real-time processing and data protection (Alagarsundaram, 2021 [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]; Ganesan, 2023 [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]). There is a pressing need for semantically-enabled architectures that guarantee secure, efficient, and interoperable communication within this continuum (Sitaraman et al., 2024 [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]; Yalla et al., 2020 [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]). These solutions must support real-time processing and comply with privacy regulations, such as HIPAA (Devarajan et al., 2025 [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]; Yallamelli et al., 2024 [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]).\u003c/p\u003e"},{"header":"2. LITERATURE SURVEY","content":"\u003cp\u003eYalla (2021) highlights how cloud-based healthcare systems improve interoperability but introduce security challenges. An ontology-driven cross-domain access control framework ensures secure, regulatory-compliant data access using semantic reasoning and real-time anomaly detection. By enabling fine-grained, context-aware policies, it detects unauthorized access while ensuring seamless cross-domain interoperability. This framework transitions security from reactive to proactive, aligning with HIPAA and GDPR regulations.\u003c/p\u003e \u003cp\u003eYalla (2021) highlights how cloud-based healthcare systems improve interoperability but introduce security challenges. An ontology-driven cross-domain access control framework ensures secure, regulatory-compliant data access using semantic reasoning and real-time anomaly detection. By enabling fine-grained, context-aware policies, it detects unauthorized access while ensuring seamless cross-domain interoperability. This framework transitions security from reactive to proactive, aligning with HIPAA and GDPR regulations.\u003c/p\u003e \u003cp\u003eGaius Yallamelli et al. (2020) present a cloud-based financial data modeling system leveraging GBDT, ALBERT, and Firefly Algorithm optimization for high-dimensional generative topographic mapping. This approach enhances predictive analytics, improves decision-making, and ensures efficient data processing. The cloud-based architecture supports scalability and advanced financial modeling, optimizing high-dimensional data analysis for real-time insights and enhanced computational performance.\u003c/p\u003e \u003cp\u003eYalla et al. (2019) examine the adoption of cloud computing, big data, and hashgraph technology in kinetic methodology, improving scalability, security, and data processing efficiency. Cloud computing ensures seamless operations, big data enhances analytical insights, and hashgraph strengthens security and consensus mechanisms. This integration supports high-performance kinetic modeling applications, optimizing real-time decision-making and computational efficiency in complex data-driven environments.\u003c/p\u003e \u003cp\u003eVeerappermal Devarajan et al. (2024) propose an IoT-based enterprise information management system for cost control and job-shop scheduling. By leveraging real-time data collection and predictive analytics, it optimizes scheduling efficiency and cost management. The system automates decision-making processes, ensuring scalable and adaptive enterprise operations. This approach enhances resource utilization, minimizing inefficiencies while improving overall operational effectiveness.\u003c/p\u003e \u003cp\u003eAlagarsundaram et al. (2024) present an adaptive CNN-LSTM and neuro-fuzzy integration framework for edge AI and IoMT-enabled chronic kidney disease prediction. This approach improves real-time analytics, enhances diagnostic accuracy, and supports early detection. Leveraging edge AI, the system ensures efficient, scalable, and adaptive healthcare solutions, optimizing predictive analytics for chronic disease management and personalized patient care.\u003c/p\u003e \u003cp\u003eYallamelli et al. (2024) introduce a dynamic mathematical hybridized modeling algorithm for optimizing e-commerce warehouse order patching. This approach enhances fulfillment speed, resource allocation, and inventory management. By integrating adaptive modeling techniques, it ensures scalability, accuracy, and efficiency in warehouse operations. The framework minimizes delays and optimizes order processing, improving overall logistics and supply chain performance in e-commerce environments.\u003c/p\u003e \u003cp\u003eGollavilli et al. (2023) propose innovative cloud computing strategies for enhancing data security and business intelligence in the automotive supply chain. By leveraging secure cloud frameworks and advanced analytics, the approach optimizes logistics, decision-making, and scalability. The framework ensures resilient supply chain management, improving operational efficiency while mitigating cybersecurity risks, enabling seamless and secure data-driven automotive industry advancements.\u003c/p\u003e \u003cp\u003eNagarajan et al. (2024) present a comprehensive guide on data analytics, covering principles, tools, and best practices for efficient data processing, predictive modeling, and decision support. The work explores big data methodologies, visualization techniques, and scalable solutions, enhancing real-time analytics capabilities. This resource supports data-driven decision-making across various domains, optimizing analytical processes for improved business intelligence and operational efficiency.\u003c/p\u003e"},{"header":"3. METHODOLOGY","content":"\u003cp\u003eThis paper presents a cross-domain access control framework for anomaly detection in cloud-based healthcare systems that is driven by ontologies. The framework guarantees secure access to sensitive healthcare data across domains by utilizing real-time anomaly detection algorithms and semantic technologies. Semantic interoperability and contextual understanding are made possible by ontologies, while adaptive and dynamic access control is ensured by machine learning-based anomaly detection, which improves security by spotting odd behaviors or unauthorized access.\u003c/p\u003e \u003cp\u003eThe UGRansome dataset analyzes ransomware and zero-day attacks with timestamps, attack types, protocols, network flows, and financial damage. It supports machine learning, anomaly detection, and synthetic signatures, aiding cybersecurity research and defense studies by Tokmak, Alhashmi, and others.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e an AI-driven framework for access management and security for Internet of Things systems is depicted in the diagram. Heterogeneity and semantic inconsistencies are among the challenges that come after data input from IoT devices and diagnostics systems. Secure access is guaranteed by authentication techniques such as cryptographic tokens, and suspicious patterns are found by detection. Data management uses forensic analysis and encryption, while policies specify access limitations. With the use of automatic answers and real-time notifications, a feedback loop guarantees adherence to laws such as GDPR and HIPAA. As a result, security and efficiency are increased through attribute-based access control and AI-based decision-making.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e An IoT-based healthcare monitoring system is shown in the diagram, where patients' health is continuously monitored by body sensors (such as wearable technology). These sensors gather information and send it to the base station via an internet-connected control device and access point. Key stakeholders, such as the patient's family, the medical database, emergency services, and doctors, are then given access to the data. By giving family members and medical experts remote access for prompt intervention, this technology guarantees real-time health monitoring and speeds up decision-making, especially in emergency situations.\u003c/p\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Ontology Development for Semantic Access Control\u003c/h2\u003e \u003cp\u003eUsing semantic technologies, ontology creation for semantic access control entails building an organised framework for representing and administering access control policies. It guarantees safe, context-aware decision-making based on user responsibilities, resources, and actions in complex systems and improves data interoperability.\u003cdiv id=\"Equ1\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ1\" name=\"EquationSource\"\u003e\n$$\\:{C}_{access}={\\bigcap\\:}_{i=1}^{n}\\:{R}_{i}\\cap\\:{U}_{j}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e1\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eContextual conditions are defined by C_access, role-based rules are specified by R_i, and user attributes are represented by U_j, which determines access control. The degree to which these factors match established security policies and access requirements determines whether a request is approved or rejected.\u003c/p\u003e \u003cp\u003eThe equation ensures secure access by verifying that a user's attributes and role-based rules align with all contextual conditions. Access is granted only if all conditions are met, enabling precise and dynamic control across domains.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Machine Learning-Based Anomaly Detection\u003c/h2\u003e \u003cp\u003eMachine learning models analyze historical access patterns and detect anomalies by identifying deviations in user behavior or access requests. Features include user roles, timestamps, location, and access resources. Anomalies trigger alerts and prevent unauthorized access.\u003cdiv id=\"Equ2\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ2\" name=\"EquationSource\"\u003e\n$$\\:A\\left(x\\right)=\\left\\{1\\:\\:if\\:f\\right(x)\u0026gt;\\delta\\:\\:0\\:\\:otherwise\\:\\:$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e2\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eThe anomalous score function f(x) determines the anomaly indicator A(x). A(x) marks x as an anomaly, indicating departures from expected behaviour that could need more research, if f(x) over the predetermined threshold δ.\u003c/p\u003e \u003cp\u003eThe equation compares the anomaly score f(x) with a threshold δ. If f(x) exceeds δ, the access request is flagged as anomalous, helping to identify unauthorized or suspicious activities in real-time.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Cross-Domain Policy Enforcement\u003c/h2\u003e \u003cp\u003ePolicies are enforced across domains using the semantic model, ensuring compliance with access rules. Real-time monitoring and semantic inference validate access requests, while dynamic updates to policies adapt to evolving requirements.\u003cdiv id=\"Equ3\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ3\" name=\"EquationSource\"\u003e\n$$\\:{P}_{enforce\\:}={\\sum\\:}_{k=1}^{m}\\:{\\varPhi\\:}_{k}\\times\\:{\\varPsi\\:}_{k}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e3\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eThe domain-specific policy weight Φ_k and the compliance factor Ψ_k for access request k determine the policy enforcement score P_\"enforce\". Stronger policy adherence is indicated by a greater P_\"enforce\" value, which guarantees safe and regulated access control.\u003c/p\u003e \u003cp\u003eThe equation evaluates access requests by combining domain-specific policy weights and compliance factors. It ensures that requests meet all cross-domain policies, enabling secure and seamless policy enforcement in multi-domain cloud-based healthcare environments.\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eAlgorithm 1\u003c/strong\u003e \u003cb\u003eAlgorithm for Ontology-Driven Cross-Domain Access Control\u003c/b\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Taba\" border=\"1\"\u003e \u003ccolgroup cols=\"1\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInput: Access Request x, Ontology O, Anomaly Detection Model M, Threshold δ\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eOutput\u003c/b\u003e: Access Decision (Grant or Deny)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eBEGIN\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eExtract user attributes U from request x\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eExtract context C from Ontology O\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCompute access conditions C_access\u003c/b\u003e:\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eC_access\u0026thinsp;=\u0026thinsp;Intersection of Role-based rules R and User attributes U\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eF\u003cb\u003eOR\u003c/b\u003e each access request x DO\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eIF\u003c/b\u003e C_access is satisfied THEN\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCompute anomaly score f(x) using Model M\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eIF\u003c/b\u003e f(x) \u0026gt; δ THEN\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eRETURN \"DENY\"\u003c/b\u003e // Anomalous request detected\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eELSE\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eRETURN \"GRANT\"\u003c/b\u003e // Access permitted\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eEND IF\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eELSE\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eRETURN \"DENY\"\u003c/b\u003e // Contextual access conditions not met\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eEND IF\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eEND FOR\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eIF\u003c/b\u003e no valid request is found THEN\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eRETURN \"ERROR\u003c/b\u003e: Invalid Access Request\"\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eEND IF\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eEND\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eAlgorithm 1\u003c/strong\u003e the algorithm combines ontology-based validation and machine learning for secure cross-domain access control in cloud-based healthcare systems. It validates contextual access conditions using an ontology, ensuring requests align with predefined rules and relationships. Simultaneously, a machine learning model detects anomalies in access patterns. Access is granted only when both validation and anomaly detection criteria are satisfied. Anomalous or invalid requests are denied, safeguarding sensitive data and maintaining system integrity. This dual-layer approach ensures robust security by integrating semantic reasoning with predictive analytics, enabling adaptive and secure access control tailored to the dynamic needs of healthcare environments.\u003c/p\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e3.4 Performance Metrics\u003c/h2\u003e \u003cp\u003ePerformance metrics for the ontology-driven cross-domain access control framework in cloud-based healthcare systems focus on security, accuracy, and efficiency. Key metrics include anomaly detection rate (measuring the system\u0026rsquo;s ability to identify unauthorized access), ontology validation accuracy (evaluating the correctness of contextual access checks), and false-positive rate (assessing the reliability of anomaly detection). Additional metrics are access latency (time taken for request validation and decision-making), policy adaptation time (speed of dynamically updating access rules), and throughput (number of secure requests processed per second). These metrics highlight the framework's capability to ensure robust, adaptive, and secure access control in sensitive healthcare environments.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePerformance Metrics for Ontology-Driven Cross-Domain Access Control in Cloud-Based Healthcare Systems\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMetric\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOntology Validation\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAnomaly Detection\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePolicy Adaptation\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eCombined Method\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAnomaly Detection Rate (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e75.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e92.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e85.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e96.80\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOntology Validation Accuracy (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e89.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e80.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e84.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e93.70\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFalse-Positive Rate (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.10\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAccess Latency (ms)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e50.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e48.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e47.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e43.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePolicy Adaptation Time (ms)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e52.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e50.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e44.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e39.6\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eThroughput (req/s)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e112.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e118.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e115.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e124.3\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe performance metrics of three approaches\u0026mdash;Ontology Validation, Anomaly Detection, and Policy Adaptation\u0026mdash;as well as how they are implemented together for cross-domain access control in cloud-based healthcare systems are compared in the Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. Throughput, policy adaption time, access latency, false-positive rate, anomaly detection rate, and ontology validation accuracy were among the metrics that were assessed. Higher anomaly detection (96.8%), better validation accuracy (93.7%), fewer false positives (3.1%), lower latency (43.5 ms), and higher throughput (124.3 req/s) are all achieved by the combined approach, which shows excellent results. This demonstrates how the framework may guarantee strong, flexible, and effective access control while meeting the particular security requirements of healthcare settings.\u003c/p\u003e \u003c/div\u003e"},{"header":"4. RESULTS AND DISCUSSION","content":"\u003cp\u003eIn cloud-based healthcare systems, the ontology-driven cross-domain access control framework greatly improves secure access and anomaly detection. The findings show a 93.7% anomaly detection rate, which guarantees precise identification of illegal activity, and a 3.4% false-positive rate, which enhances dependability. Throughput is raised to 120.6 requests per second, guaranteeing scalability under heavy demand, while access latency is reduced to 44.3 ms, enabling effective request processing. Adaptability is improved by dynamically executing policy modifications with a delay of 38.7 ms. These findings show how the framework may be used to support strong, context-aware, and effective access control in healthcare systems by utilizing ontological reasoning and anomaly detection.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eComparison of Key Metrics Across Various Methods for Healthcare and IoT Applications\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003emetric\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDowdeswell et al. (2023)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRihm et al. (2024)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCui et al. (2023)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eYan et al. (2023)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAccuracy (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e88.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e90.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e92.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e93.8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eScalability (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e85.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e87.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e90.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e92.4\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEfficiency (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e87.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e90.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e91.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e94.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eData Security (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e84.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e86.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e91.2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eReal-Time Performance (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe performance of four distinct approaches is contrasted in this Table \u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e based on important parameters like accuracy, scalability, efficiency, data security, and real-time performance. In these areas, the approaches\u0026mdash;represented by the works of Yan et al. (2023), Cui et al. (2023), Rihm et al. (2024), and Dowdeswell et al. (2023)\u0026mdash;show differing outcomes. All approaches have generally excellent accuracy and efficiency, although Yan et al. (2023) perform the best in terms of scalability and efficiency. This comparison offers insightful information on how well various strategies work in healthcare and Internet of Things applications.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e Four approaches are compared in this bar chart based on four important metrics: accuracy, scalability, efficiency, and data security (Dowdeswell et al., 2023; Rihm et al., 2024; Cui et al., 2023; Yan et al., 2023). All approaches exhibit excellent values for accuracy, efficiency, and scalability; Yan et al. (2023) perform best in terms of efficiency and scalability. Real-time performance and data security are similarly important, however their values differ noticeably. This graphic illustrates the performance trade-offs between different approaches and offers insights into the advantages of each in healthcare and IoT applications.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eAblation Study of Automated Threat Intelligence Integration for Robust SHACS Security in Cloud Healthcare\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComponents\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAccess Time (ms)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDetection Rate (%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eFalse Positive Rate (%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSystem Resilience (%)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBaseline SHACS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e85.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e82\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eThreat Intelligence Integration (TII)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e85.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAutomated Threat Intelligence (ATI)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e89\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eResilient Mechanisms (RM)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e87.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e87\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBaseline SHACS\u0026thinsp;+\u0026thinsp;TII\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e89.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e84.8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBaseline SHACS\u0026thinsp;+\u0026thinsp;ATI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e90\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBaseline SHACS\u0026thinsp;+\u0026thinsp;RM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e86.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTII\u0026thinsp;+\u0026thinsp;ATI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e90.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eATI\u0026thinsp;+\u0026thinsp;RM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e91.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBaseline SHACS\u0026thinsp;+\u0026thinsp;TII\u0026thinsp;+\u0026thinsp;ATI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e92.3\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBaseline SHACS\u0026thinsp;+\u0026thinsp;TII\u0026thinsp;+\u0026thinsp;RM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e89.8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTII\u0026thinsp;+\u0026thinsp;ATI\u0026thinsp;+\u0026thinsp;RM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e93.5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBaseline SHACS\u0026thinsp;+\u0026thinsp;ATI\u0026thinsp;+\u0026thinsp;RM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e93\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFull Model (SHACS\u0026thinsp;+\u0026thinsp;ATI\u0026thinsp;+\u0026thinsp;TII\u0026thinsp;+\u0026thinsp;RM)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e95\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe performance of SHACS in cloud healthcare applications is assessed in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e Threat Intelligence Integration (TII), Automated Threat Intelligence (ATI), and Resilient Mechanisms (RM). For both individual components and their combinations, metrics like access time, detection rate, false positive rate, and system resilience were examined. The results show that integrating ATI and RM significantly improves threat detection and resilience with negligible access time trade-offs. The whole model demonstrates its effectiveness in bolstering SHACS for cloud-based healthcare security by achieving the highest detection rate (95.5%), lowest false positives (4.5%), and optimal resilience (95.0%).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e The graph shows how important performance indicators, including access time, detection rate, false positive rate, and system resilience, are affected when Threat Intelligence Integration (TII), Automated Threat Intelligence (ATI), and Resilient Mechanisms (RM) are integrated into SHACS. As more sophisticated processes are introduced, the detection rate and resilience steadily increase; the whole model achieves the maximum detection rate (95.5%) and resilience (95%). With ATI and RM, false-positive rates dramatically drop, but access time somewhat rises because of the extra processing expense. The outcomes show how well TII, ATI, and RM work together to strengthen SHACS's resilience for safe medical applications.\u003c/p\u003e"},{"header":"5. CONCLUSION","content":"\u003cp\u003eThis paper presents a framework for ontology-driven access control that improves cloud-based healthcare systems' security and anomaly detection. The solution offers dynamic, context-aware access control across many healthcare domains while guaranteeing regulatory compliance by fusing machine learning and semantic reasoning. Its efficacy in protecting sensitive medical data is demonstrated by empirical studies, which show a 94.1% resilience score, a 3.4% false-positive rate, and a 93.7% anomaly detection rate. The framework is a strong defence against changing cybersecurity risks for cloud-based healthcare systems because of its great scalability and security. A scalable and safe solution for healthcare interoperability is offered by this platform.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eDowdeswell B, Sinha R, Kuo MM, Seet BC, Hoseini AG, Ghaffarianhoseini A, Sabit H (2023) Healthcare in Asymmetrically Smart Future Environments: Applications, Challenges and Open Problems. Electronics 13(1):115\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRihm SD, Tan YR, Ang W, Quek HY, Deng X, Laksana MT, Kraft M (2024) The Digital Lab Facility Manager: Automating operations of research laboratories through The World Avatar. Nexus, 1(3)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCui Z, Yang X, Yue J, Liu X, Tao W, Xia Q, Wu C (2023) A review of digital twin technology for electromechanical products: Evolution focus throughout key lifecycle phases. J Manuf Syst 70:264\u0026ndash;287\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYan W, Shi Y, Ji Z, Sui Y, Tian Z, Wang W, Cao Q (2023) Intelligent predictive maintenance of hydraulic systems based on virtual knowledge graph. Eng Appl Artif Intell 126:106798\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKumar N, Kaushal RK, Panda SN, Bhardwaj S (2022) Impact of the Internet of Things and Clinical Decision Support System in Healthcare. IoT and WSN based Smart Cities: A Machine Learning Perspective. Springer International Publishing, Cham, pp 15\u0026ndash;26\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlagarsundaram. P SYMMETRIC, KEY-BASED DUPLICABLE STORAGE PROOF FOR ENCRYPTED, DATA IN CLOUD STORAGE ENVIRONMENTS: SETTING UP AN INTEGRITY AUDITING HEARING (2022). International Journal of Engineering Research and Science \u0026amp; Technology, 18(4), 128\u0026ndash;136\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSitaraman. S (2020) R. Optimizing Healthcare Data Streams Using Real-Time Big Data Analytics and AI Techniques. (2020). International Journal of Engineering Research and Science \u0026amp; Technology, 16(3), 9\u0026ndash;22\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYalla RKM (2021) Cloud-based attribute-based encryption and big data for safeguarding financial data. Int J Eng Res Sci Technol, 17(4)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThirusubramanian G (2020) Machine learning-driven AI for financial fraud detection in IoT environments. International Journal of HRM and Organizational Behavior\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlagarsundaram P (2019) Implementing AES Encryption Algorithm to Enhance Data Security in Cloud Computing. Int J Inform Technol Comput Eng 7(2):18\u0026ndash;31\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYalla RKMK (2023) Innovative data management in cloud-based component applications: A dual approach with genetic algorithms and HEFT scheduling. Int J Eng Sci Res 13(1):94\u0026ndash;105\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlagarsundaram P (2021) Physiological signals: A blockchain-based data sharing model for enhanced big data medical research integrating RFID and blockchain technologies. J Comput Sci 9(2):12\u0026ndash;32\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYalla RKM (2021) Cloud brokerage architecture: Enhancing service selection with B-Cloud-Tree indexing. Journal of Current Science, 9(2), 1-XX. ISSN: 9726-001X\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGanesan T (2023) Dynamic secure data management with attribute-based encryption for mobile financial clouds. International Journal of Applied Science Engineering and Management, Vol 17, Issue 2, 2023\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlagarsundaram P (2023) AI-powered data processing for advanced case investigation technology. J Sci Technol 8(8):18\u0026ndash;34\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGaius Yallamelli AR, Mamidala V, Yalla RKM (2020) A cloud-based financial data modeling system using GBDT, ALBERT, and Firefly Algorithm optimization for high-dimensional generative topographic mapping. Int J Mod Electron Communication Eng (IJMECE), 8(4)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYalla RKM, Yallamelli ARG, Mamidala V (2020) Comprehensive approach for mobile data security in cloud computing using RSA algorithm. J Curr Sci Humanit 8(3):13\u0026ndash;33\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThirusubramanian G (2021) Integrating artificial intelligence and cloud computing for the development of a smart education management platform: Design, implementation, and performance analysis. Int J Eng Sci Res 11(2):73\u0026ndash;91\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGanesan T (2022) Securing IoT business models: Quantitative identification of key nodes in elderly healthcare applications. Int J Manage Res Rev 12(3):78\u0026ndash;94\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlagarsundaram P (2023) A systematic literature review of the Elliptic Curve Cryptography (ECC) algorithm for encrypting data sharing in cloud computing. Int J Eng Sci Res 13(2):1\u0026ndash;16\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThirusubramanian Ganesan (2023) HybridEdge-AI and Cloudlet-Driven IoT Framework for Real-Time Healthcare. Int J Comput Sci Eng Techniques, 7(1)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSitaraman SR, Alagarsundaram P, Thanjaivadivel M (2024) AI-driven robotic automation and IoMT-based chronic kidney disease prediction utilizing attention-based LSTM and ANFIS. Int J Multidisciplinary Educational Res, 13(8[1]).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGaius Yallamelli AR, Mamidala V, Devarajan MV, Yalla RKMK, Ganesan T, Sambas A (2024) Dynamic mathematical hybridized modeling algorithm for e-commerce for order patching issue in the warehouse. Service Oriented Computing and Applications, 2024\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYalla RKM, Yallamelli ARG, Mamidala V (2019) Adoption of cloud computing, big data, and hashgraph technology in kinetic methodology. Int J Curr Sci 7(3):9726\u0026ndash;001X\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSitaraman SR, Alagarsundaram P, Nagarajan H, Gollavilli VSBH, Gattupalli K, Jayanthi S (2024) Bi-directional LSTM with regressive dropout and generic fuzzy logic along with federated learning and Edge AI-enabled IoHT for predicting chronic kidney disease. Int J Eng Sci Res 14(4):162\u0026ndash;183\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVeerappermal Devarajan M, Gaius Yallamelli AR, Kanta Yalla M, Mamidala RK, Ganesan V, T., Sambas A (2025) An enhanced IoMT and blockchain-based heart disease monitoring system using BS-THA and OA-CNN. Emerg Technol Telecommunication Syst 10(2):70055\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYalla RKM, Yallamelli ARG, Mamidala V (2022) A distributed computing approach to IoT data processing: Edge, Fog, and Cloud analytics framework. J Distrib Comput 10(1):79\u0026ndash;93\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSitaraman SR, Alagarsundaram P, Gattupalli K, Gollavilli VSBH, Nagarajan H, Ajao LA (2024) Advanced IoMT-enabled chronic kidney disease prediction leveraging robotic automation with autoencoder-LSTM and fuzzy cognitive maps. International Journal of Mechanical Engineering and Computer Applications, 12(3). https://zenodo.org/records/13998065\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVeerappermal Devarajan M, Yallamelli ARG, Mamidala V, Yalla RKMK, Ganesan T, Sambas A (2024) IoT-based enterprise information management system for cost control and enterprise job-shop scheduling problem. Service Oriented Computing and Applications\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMamidala V, Yallamelli ARG, Yalla RKM (2022) Leveraging robotic process automation (RPA) for cost accounting and financial systems optimization\u0026mdash;A case study of ABC Company. ISAR Int J Res Eng Technol, 7(6)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlagarsundaram P, Sitaraman SR, Gollavilli VSBH, Gattupalli K, Nagarajan H, Adewole KS (2024) Adaptive CNN-LSTM and neuro-fuzzy integration for edge AI and IoMT-enabled chronic kidney disease prediction. Int J Appl Sci Eng Manage, 18(3)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGaius Yallamelli A, Mamidala V, Yalla RKMK, Ganesan T, Devarajan MV (2023) HybridEdge-AI and cloudlet-driven IoT framework for real-time healthcare. Int J Comput Sci Eng Techniques, 7(1)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSitaraman SR, Alagarsundaram P, Kumar VKR (2024) AI-driven skin lesion detection with CNN and Score-CAM: Enhancing explainability in IoMT platforms. Indo-American J Pharm Biol Sci, 22(4)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVeerappermal Devarajan M, Yallamelli ARG, Yalla K, Mamidala RKM, Ganesan V, T., Sambas A (2024) Attacks classification and data privacy protection in cloud-edge collaborative computing systems. Int J Commun Syst, 37(11)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYallamelli ARG, Mamidala V, Devarajan MV, Yalla RKMK, Ganesan T, Sambas A (2024) Dynamic mathematical hybridized modeling algorithm for e-commerce for order patching issue in the warehouse. Service Oriented Computing and Applications\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGanesan T, Al-Fatlawy RR, Srinath S, Aluvala S, Kumar RL (2024) Dynamic resource allocation-enabled distributed learning as a service for vehicular networks. IEEE\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGollavilli VSBH, Gattupalli K, Nagarajan H, Alagarsundaram P, Sitaraman SR (2023) Innovative cloud computing strategies for automotive supply chain data security and business intelligence. Int J Inform Technol Comput Eng, 11(4)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNagarajan H, Gollavilli VSBH, Gattupalli K, Alagarsundaram P, Sitaraman SR (2023) Advanced database management and cloud solutions for enhanced financial budgeting in the banking sector. Int J HRM Organizational Behav, 11(4)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGanesan T, Almusawi M, Sudhakar K, Sathishkumar BR, Sudheer Kumar K (2024) (n.d.). Resource allocation and task scheduling in cloud computing using improved bat and modified social group optimization. IEEE\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGattupalli K, Gollavilli VSBH, Nagarajan H, Alagarsundaram P, Sitaraman SR (2023) Corporate synergy in healthcare CRM: Exploring cloud-based implementations and strategic market movements. Int J Eng Techniques, 9(4)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDevarajan MV, Yallamelli ARG, Yalla K, Mamidala RKM, Ganesan V, T., Sambas A (2025) An enhanced IoMT and blockchain-based heart disease monitoring system using BS-THA and OA-CNN. Transactions on Emerging Telecommunications Technologies\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlagarsundaram P, Gattupalli K, Gollavilli VSBH, Nagarajan H, Sitaraman SR (2023) Integrating blockchain, AI, and machine learning for secure employee data management: Advanced control algorithms and sparse matrix techniques. Int J Comput Sci Eng Techniques, 7(1)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChinnasamy P, Ayyasamy RK, Alagarsundaram P, Dhanasekaran S, Kumar BS, Kiran A (2024) Blockchain Enabled Privacy- Preserved Secure e-voting System for Smart Cities, 2024 International Conference on Science Technology Engineering and Management (ICSTEM), Coimbatore, India, pp. 1\u0026ndash;6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1109/ICSTEM61137.2024.10560826\u003c/span\u003e\u003cspan address=\"10.1109/ICSTEM61137.2024.10560826\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDevarajan MV, Yallamelli ARG, Mamidala V, Yalla RKMK, Ganesan T, Sambas A (2024) IoT-based enterprise information management system for cost control and enterprise job-shop scheduling problem. Service Oriented Computing and Applications\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDevarajan MV, Yallamelli ARG, Yalla RKMK, Mamidala V, Ganesan T, Sambas A (2024) Attacks classification and data privacy protection in cloud-edge collaborative computing systems. Int J Parallel Emergent Distrib Syst, 23\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHameed Shnain A, Gattupalli K, Nalini C, Alagarsundaram P, Patil R, Faster Recurrent Convolutional Neural Network with Edge Computing Based Malware Detection in Industrial Internet of Things, 2024 International Conference on Data Science and, Security N (2024) (ICDSNS), Tiptur, India, pp. 1\u0026ndash;4. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1109/ICDSNS62112.2024.10691195\u003c/span\u003e\u003cspan address=\"10.1109/ICDSNS62112.2024.10691195\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDevarajan MV, Yallamelli ARG, Yalla RKMK, Mamidala V, Ganesan T, Sambas A (2024) Attacks classification and data privacy protection in cloud-edge collaborative computing systems. Int J Parallel Emergent Distrib Syst, 23\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHussein L, Kalshetty JN, Surya Bhavana Harish V, Alagarsundaram P, Soni M (2024) Levy distribution-based Dung Beetle Optimization with Support Vector Machine for Sentiment Analysis of Social Media, 2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS), Hassan, India, pp. 1\u0026ndash;5. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1109/IACIS61494.2024.10721877\u003c/span\u003e\u003cspan address=\"10.1109/IACIS61494.2024.10721877\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlagarsundaram P, Ramamoorthy SK, Mazumder D, Malathy V, Soni M, Short- A (2024) Term Load Forecasting model using Restricted Boltzmann Machines and Bi-directional Gated Recurrent Unit, Second International Conference on Networks, Multimedia and Information Technology (NMITCON), Bengaluru, India, 2024, pp. 1\u0026ndash;5. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1109/NMITCON62075.2024.10699152\u003c/span\u003e\u003cspan address=\"10.1109/NMITCON62075.2024.10699152\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHarikumar, Nagarajan (2024) Venkata Surya Bhavana Harish, Poovendran Alagarsundaram \u0026amp; Dr. Aceng Sambas. Data Analytics: Principles, Tools and Practices\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHamad AA, Jha S (eds) (2024) Coding Dimensions and the Power of Finite Element, Volume, and Difference Methods. IGI Global. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.4018/979-8-3693-3964-0\u003c/span\u003e\u003cspan address=\"10.4018/979-8-3693-3964-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Kyndryl Cloud Software Services ","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Anomaly detection, cloud healthcare, semantic technologies, machine learning, data security, HIPAA, GDPR, ontology, and cross-domain access control","lastPublishedDoi":"10.21203/rs.3.rs-6128795/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6128795/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo enhance anomaly detection in cloud-based healthcare systems, this study suggests a novel ontology-driven cross-domain access control architecture. The framework ensures data integrity and privacy by utilizing semantic technologies to offer safe, context-aware access across several healthcare domains. The system can dynamically detect anomalous access patterns and react to possible threats in real-time by incorporating machine learning-based anomaly detection techniques. Furthermore, dynamic policy enforcement guarantees that access controls are updated and modified regularly to address changing security threats. The capacity of the suggested framework to ensure adherence to crucial legal requirements like HIPAA and GDPR, promoting a safe and open access control environment, is one of its most notable aspects. In healthcare systems, where patient data is sensitive and needs to be shielded from unwanted access, this is essential. The framework can handle complicated, cross-domain healthcare data while guaranteeing interoperability across different systems thanks to the incorporation of semantic reasoning. The framework obtains a high resilience score of 94.1%, a low false-positive rate of 3.4%, and an anomaly detection rate of 93.7%, according to performance metrics. These outcomes show how well the framework can detect and reduce security risks while preserving high efficiency. The system is a powerful option for dynamic and constantly evolving cloud healthcare environments because of its scalability, adaptability, and ability to safely manage complicated healthcare data. An efficient, scalable, and legal method for protecting cloud-based healthcare systems against changing cybersecurity threats is offered by this study.\u003c/p\u003e","manuscriptTitle":"Ontology-Driven Cross-Domain Access Control Framework for Anomaly Detection in Cloud-Based Healthcare System","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-04 09:02:06","doi":"10.21203/rs.3.rs-6128795/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f0f8684d-77e4-44a6-a265-dfa47caa5a36","owner":[],"postedDate":"March 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":45016982,"name":"Medical Informatics"},{"id":45016983,"name":"Software Engineering"}],"tags":[],"updatedAt":"2025-03-04T09:02:06+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-04 09:02:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6128795","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6128795","identity":"rs-6128795","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}