Rider Re-Route Suggestions Using Demand Forecasting Based on Passenger's Routes

Rider Re-Route Suggestions Using Demand Forecasting Based on Passenger's Routes | 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 Article Rider Re-Route Suggestions Using Demand Forecasting Based on Passenger's Routes Dharun Sivakumar, Bairavel S, Suriyalakshmi V C, Sricharan A This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4149049/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 Through data analysis and internet networking, ride-sharing can be optimized with the aim of revolutionizing urban transportation. It addresses the common issue of lone commuters by connecting "riders" and "passengers" through an intelligent platform that suggests alternative routes based on passenger demand. The primary goals are to boost urban mobility efficiency, reduce trip costs, and increase sustainability. The project is divided into components for rider and passenger registration, demand forecasts, matchmaking, and route optimization. The results demonstrate that the suggested deviations offer similar travel times, considerable cost savings, and improved customer satisfaction. Cutting back on single-occupancy car use is in line with environmental objectives. This concept offers a data-driven solution to transportation problems, which might drastically alter how people move around cities. Social science/Development studies Scientific community and society/Developing world Urban transportation ride-sharing data analysis internet networking commuter matchmaking demand forecasting urban mobility Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 I. INTRODUCTION The "Rider Re-route Suggestions Using Demand Forecasting Based on Passenger's Routes" program addresses issues related to urban transportation while optimizing efficiency and avoiding environmental consequences by utilizing shared transportation and state-of-the-art technology. The project aims to maximize rider-passenger matching by focusing on two distinct user groups: "A" who rides motorcycles alone and "B" who is looking for inexpensive transportation. By creating a platform for communication between passengers and frequent riders, the effort recommends alternate routes for Group A based on demand estimates derived from Group B's preferences. The major objective is to design shared pathways that lower travel costs for both sides, encourage sustainability, and mitigate the carbon footprint of urban transportation. The difficulty, though, is in choosing the best paths from a variety of options with somewhat different lengths but comparable beginning and ending locations. The experiment highlights the significance of comprehending passenger demand outside normal commuter routes in order to assure efficient matching. Through the recommendation of routes that correspond with group B's high-demand preferences, the effort aims to optimize prospects for mutual benefit and transform urban transportation into a more sustainable and eco-friendly model. The set of paper is mentioned below, Section Ⅱ presents and discuss the related literature works. The proposed system methodology and the algorithm processing are presented in Section Ⅲ. The results of the system are discussed in Section IV and finally, the paper is concluded with Section Ⅴ. II. RELATED WORKS The history of passenger transport may be traced back to the earliest human civilizations when humans depended mostly on foot travel and animals for movement. The development of steam locomotives and ships during the Industrial Revolution enabled faster and more efficient transport. The twentieth century witnessed the spread of vehicles, urbanization, and the construction of modern public transportation networks, all of which presented issues in optimizing routes and timetables for effective passenger service. As the twenty-first century progressed, the digital revolution and the rise of the internet and smartphones heralded a new age. These developments permitted the collection of large amounts of data pertaining to passenger movements. Simultaneously, the area of transportation research began emphasizing data-driven decision-making. This change was aided by several ground-breaking scientific projects. Zhang et al.'s "DNEAT" investigated origin-destination demand prediction utilizing dynamic node-edge attention networks, with an emphasis on temporal and geographical interdependence. Chen et al.'s paper "Multitask Learning and GCN-Based Taxi Demand Prediction" used multitask learning with Graph Convolutional Networks (GCN) to anticipate taxi demand in a road network. Sohani Liyanage et al. predicted bus passenger demand using artificial neural networks and smart card data, therefore improving public transport services. Understanding the importance of passenger demand forecasting for efficient route suggestions and rider-passenger matching, Banerjee, N. et al.'s "Passenger Demand Forecasting in Scheduled Transportation" and Cyril, A. et al.'s "Modelling and Forecasting Bus Passenger Demand Using Time Series Method" provided insights into demand prediction techniques. Furthermore, "Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network" by Ke, J. et al. looked at forecasting passenger locations and demand patterns, which might help with efficient matching techniques. "Clustering and Forecasting Urban Bus Passenger Demand with a Combination of Time Series Models" by Marias-Collado, I. et al. strongly matched with the project's objectives by accurately anticipating passenger demand patterns and emphasizing data-driven decision-making. Abdi, A., et al. (2021) undertake a thorough examination of travel and arrival-time prediction methodologies, providing light on crucial areas that are directly related to the project's performance. To insure the design's success, precise trip time cast is essential as it helps determine dependable divergences. By gaining further knowledge, the action will be suitable to offer riders and passengers more precise recommendations, adding the effectiveness of civic transportation as a whole. Online network- position public transportation demand estimate handed by Zhong,C., et al.( 2023) is largely material to the pretensions of the design. Route optimization and successful matching depend on real- time demand prognostications for public transportation. With the use of this exploration, public transportation dynamics may be effectively managed, icing that the design can effectively acclimate to variations in demand and enhance the overall stoner experience. Using these information, the trouble addresses the real- time transportation requirements of contemporary metropolises, leading the way in technological advancements. exercising demand vaticinations and passenger routes, it focuses on riderre-routing suggestions, satisfying the growing demand for effective and environmentally friendly transportation options. perfecting passenger gests, reducing environmental impact, and reducing business traffic are the overarching pretensions of this trouble. The program steers data- driven perceptivity toward further effective and sustainable mobility results, marking a positive turn in the ongoing history of passenger transportation. III. PROPOSED METHOD The methodology chapter provides a synopsis of the approach that is taken in this project to obtain the results. The design, strategies, data preparation and analysis techniques, security and safety measures, environmental effects, implementation and other factors. This study uses the Google Maps API to retrieve the routes information for both passengers and riders. Google Maps API is efficient in collection multiple possible routes for the same from and to locations. Data about the user experience, passenger satisfaction and other feedback can be obtained through surveys, interviews and other measures. The approach goes into detail on data analysis, with a focus on clustering for demand-supply matching. It emphasizes algorithms, distance measurements, and data pretreatment techniques. To ensure active user participation, user engagement strategies which include gamification, promotional campaigns, and feedback mechanisms are covered in detail. With an emphasis on responsible data collecting and user privacy, ethical issues are essential. An environmental impact evaluation compares the decrease in carbon emissions and the usage of single-occupancy vehicles with the aims of sustainability and scalability of the system. The approach goes into detail on data analysis, with a focus on clustering for demand-supply matching. It emphasizes algorithms, distance measurements, and data pretreatment techniques. To ensure active user participation, user engagement strategies which include gamification, promotional campaigns, and feedback mechanisms are covered in detail. With an emphasis on responsible data collecting and user privacy, ethical issues are essential. An environmental impact evaluation compares the decrease in carbon emissions and the usage of single-occupancy vehicles with the aims of sustainability and scalability of the system. The processing of the proposed system is shown in Fig. 1 . A. Dataset The dataset is generated manually as the application is not implemented and is to be used in the ecosystem. The dataset contains Rider and passenger routes in tables. The columns of the tables are shown below in Tables 1 and 2. TABLE I. Mock Dataset For Prototype Riders Routes Passengers Routes • Pickup location • Drop location • Pickup time • Pickup location • Drop location TABLE II. Actual Dataset Riders Routes Passengers Routes · Id · userId · startLocation · endDestination · steps · distance · startTime · duration · Id · userId · startLocation · endDestination · steps Each table has several columns that store information related to the routes taken by riders and passengers. Let's break down the structure of these tables: 1) Riders Routes Table: · Id: A unique identifier for each route in the table. · userId: Identifies the user or rider associated with the route. · startLocation: Indicates the starting point or location of the route. · endDestination: Specifies the final destination or endpoint of the route. · steps: Likely contains information about the specific steps or directions to follow for the route. · distance: Records the distance of the route, which could be measured in miles, kilometers, or another unit. · startTime: Represents the time at which the route starts. · duration: Indicates the duration of the route, possibly in minutes or hours. 2) Passengers Routes Table: · Id: A unique identifier for each route in the table. · userId: Identifies the user or passenger associated with the route. · startLocation: Indicates the starting point or location of the route. · endDestination: Specifies the final destination or endpoint of the route. · steps: Likely contains information about the specific steps or directions for the route. This dataset structure is essential for storing and organizing the route information of both riders and passengers. To use this dataset effectively, it would populate these tables with 18 actual data, and then this can perform various data analysis and optimization tasks based on this information to achieve the project's objectives. Figure 2 shows the exact dataset of the riders’ route. Clustering Analysis for Demand-Supply Matching 1) INPUTS : · Riders' route data (supply) · Passengers' route data (demand) · Number of clusters (k) 2) METHODOLOGY Step 1: Start. Step 2: Collect and preprocess rider’s and passengers’ route data. Step 3: Apply Clustering Algorithm: A. Initialize k centroids randomly. B. Iterate until convergence or a defined number of iterations: a. Assign each route to the nearest centroid based on distance metrics. b. Calculate new centroids as the mean of assigned routes. Step 4: Analyze Clusters: A. Calculate cluster characteristics: a. The average distance of routes within each cluster to its centroid. b. Total passenger demand within each cluster. B. Identify clusters with high demand and low rider presence. C. Identify clusters with mismatches or unmet demand. Step 5: Suggest Alternate Routes: A. For clusters with high demand and low rider existence: a. Analyze the routes within the cluster. b. Suggest alternate routes that can help the demand while maintaining similar ride period. B. Generate a list of suggested alternate routes for riders. Step 6: Output: A. List of suggested alternate routes for the riders. Step 7: End Equations to calculate for clustering algorithms are mentioned below. Euclidean Distance : The Euclidean distance, which is the distance in Euclidean space between two points, is usually used to determine the distance between cluster centroids and data points. The distance between x and c, the centroid, in a multidimensional space of dimension n: Updating Centroids : The procedure of using the data points given to a cluster to determine its new centroid. If a cluster is made up of data points x1, x2, x3, x4, x5, xm, and so on, the new centroid c can be found in this way: In this case, ci represents the i-th component of the centroid, and xij represents the i-th component of the j-th data point. Cluster Assignment : Calculating the distance between a given data point and the cluster to which it fits. The cluster with the closest centroid is found using data point x: Convergence Criteria : When the centroids no longer vary noticeably across iterations, the algorithm is said to have converged. An often-used criterion for convergence is to see if the centroids have changed more than a certain amount. To determine the need by enumerating unique passenger routes a collection of unique passenger routes is represented mathematically by the formula below. The cardinality of the set (R), or the total number of unique elements in the set, may be used to compute the number of different passenger routes, D: The demand is represented by D and the cardinality of the set of different passenger routes that is, the number of unique routes is represented by |R| The proposed project entails gathering and preparing data as well as initializing the cluster centroids. This would be repeated until convergence or a certain number of iterations were reached. The centroid is computed for each route in rider and passenger data by computing distance metrics. Following that, the routes are assigned to the appropriate cluster. For each cluster, new centroids are calculated as the mean of routes inside the cluster. Each cluster's overall passenger demand is also computed. Clusters with a high and low presence of riders are detected. Along the way, the routes are added to a list. Figure 3 depicts this work. IV. RESULTS AND DISCUSSION This research aims to revolutionize urban transport by providing route ideas based on passenger demand to improve efficiency, cost-effectiveness, and sustainability. It addresses the frequent issue of solo commuting in metropolitan areas by attempting to seamlessly link riders and passengers via an innovative platform. This method decreases travel expenses for both parties while also helping to minimize the carbon footprint associated with urban transit. Congestion and environmental issues in today's urban scene necessitate efficient and sustainable transportation options. This research proposes a game-changing platform that uses technology to assure more sustainable and cost-effective mobility, imagining a future in which urban transit is both efficient and ecologically responsible. Modules for rider and passenger registration, locating riders, match-making, and route suggestions are among the project's components. The indicated network includes demand forecasting grounded on Google Maps API data, allowing for the discovery of routes with fat demand and the recommendation of alternate routes for passengers without significantly affecting trip field. Two main tables," Riders Routes" and" Passenger Routes," which hold all-important data matching route details, user IDs, start and finish locales, distance, duration, and trip way, are part of the study's database armature. The quality and delicacy of the data are essential to the design's success. The fashion focuses on demand- force matching clustering analysis, beginning with data collection and preprocessing and developing to gathering styles. The exploration detects clusters with high demand but low rider presence, and different routes are proposed to handle redundant demand while keeping cool commute fields. The applicability of the action resides in its implicit to transfigure civic conveyance by diving lone commuting, high trip charges, and carbon emigrations. It provides competitive trip times, significant cost savings, helped user joy, and a grand drop in single- occupation car use, all of which pitch in to sustainability and fit with the design's environmental points. In conclusion, the data- run civic ride optimization network provides a road to further cost- efficient, maintainable, and easy civic commuting. It has the implicit to revise the way people travel inside metropolises by utilizing technology, data breakdown, and participated mobility, guiding to a grown and additional economically possible civic tomorrow. A. Requirements Specification 1) System Requirements a) Operating System: · Windows: Windows 7 or later · macOS: macOS 10.9 or later · Linux: Most modern Linux distributions b) Processor: · Windows and Linux: Intel Pentium 4 processor or later with SSE2 support (or) AMD Athlon XP or AMD Athlon 64 processors · macOS: Intel processor c) RAM: At least 2 GB of RAM (4 GB or more recommended) 2) Software Requirements To process this system, the following technologies and techniques are needed. TABLE III. Software Requirements Headings Tools/Technology FRONT END TOOLS React Native/ JS BACK-END TOOLS Python MARKUP LANGUAGES JSX MIDDLEWARE TECHNOLOGIES Firebase, Google Maps API SCRIPTING LANGUAGES JavaScript, Python PACKAGES NEEDED PYTHON: Pandas, NumPy, Matplotlib, Sklearn, Random, ortools. JS: @react-google-maps/api IDE Visual studio code B. Contribution to the Research Work 1) The Optimization of Urban Transportation: The Optimization of Urban Transportation employing data deconstruction and an internet connection, the action offers a extreme path to civic conveyance by giving routes grounded on passenger demand. By doing this, civic transportation networks are bettered, getting more sustainable and effective. 2) Single- residency Vehicle Reduction: Downgrading the number of single- residency cars and single commuters is one of the main objects of the action. By linking motorists and passengers, it promotes participated mobility and significantly lowers the operation of single- residency cars. This has significant ramifications for reducing the impact on the terrain and business traffic. 3) Cost Savings: The data demonstrates that suggested detours usually lead to considerable savings for passengers as well as riders. This financial benefit contributes to the urban commuters' economic well-being, which is particularly crucial in a society where transportation costs might be considerable. 4) Environmental Longevity: By reducing the use of single-occupancy automobiles, the idea is strongly related to environmental sustainability goals. In view of growing environmental concerns, it aids in lowering carbon emissions and the overall environmental impact of urban mobility. 5) Efficiency and User Satisfaction: The study's technique improves urban transportation efficiency by better matching riders and passengers. This leads to faster travel times and more consumer satisfaction, resulting in a more convenient and appealing commuting experience. C. Comparison Table 4 shows state of an art comparison of the proposed system and other systems. TABLE IV. State of n Art Comparision Research Work (Year) Focus Algorithm Dataset Limitations Proposed System Demand prediction and Route optimization Clustering Analysis for Demand-Supply Matching Rider and passenger routes Privacy Issues, User Adoption [3] Zhang et al. (2021) Dynamic Node-Edge Attention Network Dynamic Node-Edge Attention Network Chengdu dataset, New York dataset. Limited to urban areas, scalability issues [4] Chen et al. (2020) Multitask Learning and GCN-Based Prediction GCN Traffic and Taxi Demand Data Reliant on historical data, need for real-time updates [2] Sohani Liyanage et al. (2022) AI-Based Neural Network Models ANN Smart Card Data Limited to buses, may not cover all urban modes of transport [8] Mariñas-Collado et al. (2022) Clustering and Forecasting Bus Demand Clustering Urban Bus Passenger Data Limited to buses and clustering is based on historical patterns [12] Abdi et al. (2021) Travel and Arrival-Time Prediction Various Prediction Models Traffic Data Limited to travel time predictions [13] Halyal et al. (2022) Forecasting Public Transit Demand Neural Networks Public Transit Demand Data Primarily focused on public transit D. Output The above graph in Figure 4 shows the demand of the passenger according to the routes. The y-axis is the demand scale and the x-axis is the routes of the passengers. The graph here clearly explains that the highest demand is for “E” to “A” location. This output (Figure 5) represents the weight of all possible routes that are used by the passengers. The route with highest weight is the route with most demand and vice versa. In this output the route 'E-A' has the most demand with weight as 134 and the route 'F-A' has the least demand relative to other routes with a weight of 86. In this output, the route ‘E-A’ is identified as the most demanded route. From the suggested route, it is identified that the route ‘E-A’ is covered by the rider. This route is suggested to the rider, by which the frequency of rider’s pickup is increased and the passenger gets benefited. V. CONCLUSION AND FUTURE SCOPE To sum up, this research offers a data-driven approach to improving urban transportation by effectively matching passengers and riders. It provides a route to more affordable, environmentally friendly, and conveniently located urban commuting by addressing the issues of lone commuting, expensive travel expenses, and carbon emissions. This project can change the way people navigate around the city. It can reduce the cost spent on transport and make the urban future sustainable. It has its limitations and needs improvement to do well in the long run. As the future of transportation evolves this project can bring a good change for the future of urban mobility. A. Limitation of the proposed system 1) Data Reliance: The design's success depends on the vacuity and delicacy of data, particularly from the Google Maps API. Due to incorrect route recommendations, deficient or inaccurate data may affect the quality of the service. 2) Privacy firms: As a result of the platform collecting user data, insulation issues arise. The design must address these problems to ensure the security of user rights and data. The right balance between data collection and insulation may be hard to achieve. 3) User Acceptance: Satisfying guests to convert from their being forms of transportation to shared mobility may prove to be a challenging task. Some people may be resistant to change or doubtful about the benefits of the proposed system. B. Future Scope This project still needs to look into implicit exploration directions in lift-sharing and civic transportation effectiveness. One of them is exercising state-of-the-art machine literacy ways similar to deep literacy and neural networks to offer more accurate route recommendations. Incorporating real-time data sources, understanding commuter gestures, and optimizing route recommendations grounded on stoner preferences are imperative. Studies can also look at the smooth integration of multimodal transportation options, enhance environmental impact assessment styles, and probe cost-effectiveness, policy impulses, and nonsupervisory fabrics. Data security and stoner sequestration must be considered in unborn exploration. Civic mobility results will continue to advance in these disciplines. References Banerjee, N., Morton, A., Akartunalı, K. (2020). "Passenger demand forecasting in scheduled transportation." European Journal of Operational Research, Volume 286, Issue 3, pp. 797-810, ISSN 0377-2217. Liyanage, S., Abduljabbar, R., Dia, H., Tsai, P-W. (2022). "AI-based neural network models for bus passenger demand forecasting using smart card data." Journal of Urban Management, Volume 11, Issue 3, pp. 365-380, ISSN 2226-5856. Zhang, D., Xiao, F., Shen, M., Zhong, S. (2021). "DNEAT: A novel dynamic node-edge attention network for origin-destination demand prediction." Transportation Research Part C: Emerging Technologies, Volume 122, pp. 102851, ISSN 0968-090X. Chen, Z., Zhao, B., Wang, Y., Duan, Z., & Zhao, X. (2020). "Multitask learning and GCN-based taxi demand prediction for a traffic road network." Sensors, Volume 20(13), pp.3776. Cyril, A., Mulangi, R. H., George, V. (2018). "Modelling and Forecasting Bus Passenger Demand using Time Series Method." In 2018 7th International Conference on Reliability, Infocom Technologies, and Optimization (Trends and Future Directions) (ICRITO), Noida, India, pp. 460-466. Faridai, S., Juraeva, R.S., Darovskikh, S.N., Qodirov, Sh.Sh. (2021). "Neural Network Model for Predicting Passenger Congestion to Optimize Traffic Management for Urban Public Transport." Вестник ЮУрГУ. Серия: Компьютерные технологии, управление, радиоэлектроника, 2021. Ke, J., Qin, X., Yang, H., Zheng, Z., Zhu, Z., & Ye, J. (2021). "Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network." Transportation Research Part C: Emerging Technologies, 122, 102858. Mariñas-Collado, I., Sipols, A.E., Santos-Martín, M.T., Frutos-Bernal, E. (2022). "Clustering and Forecasting Urban Bus Passenger Demand with a Combination of Time Series Models." Mathematics, Volume 10, pp.2670. Yadav, R. K., Kishor, G., Himanshu, K., Kashyap, K. (2020). "Comparative Analysis of Route Planning Algorithms on Road Networks." In 2020 5th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, pp. 401-406. Zhang, P., Ma, W., Qian, S. (2022). "Cluster analysis of day-to-day traffic data in networks." Transportation Research Part C: Emerging Technologies, Volume 144, pp. 103882, ISSN 0968-090X. 37 Bazant, M., Akhtar, M., Moridpour, S. (2021). "A Review of Traffic Congestion Prediction Using Artificial Intelligence." Journal of Advanced Transportation, Volume 2021, SP - 8878011, ISSN 0197-6729. Abdi, A., Amrit, C. (2021). "A review of travel and arrival-time prediction methods on road networks: classification, challenges and opportunities." PeerJ Comput Sci, 7, e689. doi: 10.7717/peerj-cs.689. Halyal, S., Mulangi, R. H., Harsha, M.M. (2022). "Forecasting public transit passenger demand: With neural networks using APC data." Case Studies on Transport Policy, Volume 10, Issue 2, pp. 965-975, ISSN 2213-624X. Zhong, C., Wu, P., Zhang, Q., Ma, Z. (2023). "Online prediction of network-level public transport demand based on principle component analysis." Communications in Transportation Research, Volume 3, 100093, ISSN 2772-4247. Halvorsen, A., Koutsopoulos, H.N., Ma, Z., et al. (2020). “Demand management of congested public transport systems: a conceptual framework and application using smart card data." Transportation, 47, 2337–2365. Jiang, W., Ma, Z., Koutsopoulos, H.N. (2022). "Deep learning for short-term origin–destination passenger flow prediction under partial observability in urban railway systems." Neural Comput & Applic, 34, 4813–4830. Tedjopurnomo, D.A., Bao, Z., Zheng, B., Choudhury, F.M., Qin, A.K. (2020). "A survey on modern deep neural network for traffic prediction: Trends, methods, and challenges." IEEE Transactions on Knowledge and Data Engineering, 34(4), 1544-1561. Xie, Z., Lv, W., Huang, S., Lu, Z., Du, B., Huang, R. (2020). "Sequential Graph Neural Network for Urban Road Traffic Speed Prediction." IEEE Access, 8, 63349-63358. Additional Declarations There is NO Competing Interest. 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-4149049","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":284267164,"identity":"b6719971-4bad-41f2-82f9-4ed7eb3af0b8","order_by":0,"name":"Dharun Sivakumar","email":"data:image/png;base64,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","orcid":"","institution":"KCG College of technology","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Dharun","middleName":"","lastName":"Sivakumar","suffix":""},{"id":284267165,"identity":"80d7dfd4-adba-45bb-96ed-5ab44a194c66","order_by":1,"name":"Bairavel S","email":"","orcid":"","institution":"kcg college of technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Bairavel","middleName":"","lastName":"S","suffix":""},{"id":284267166,"identity":"18162230-8abf-40f4-9164-38f722bd74e0","order_by":2,"name":"Suriyalakshmi V C","email":"","orcid":"","institution":"KCG College of technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Suriyalakshmi","middleName":"V","lastName":"C","suffix":""},{"id":284267167,"identity":"8bad5efb-2aab-4e05-8596-cdb59c975d88","order_by":3,"name":"Sricharan A","email":"","orcid":"","institution":"KCG College of technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Sricharan","middleName":"","lastName":"A","suffix":""}],"badges":[],"createdAt":"2024-03-22 10:41:45","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false,"coiExplicitlySet":false},"doi":"10.21203/rs.3.rs-4149049/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4149049/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54674867,"identity":"02f421ef-cd3b-4e75-a99f-097a4e4586a0","added_by":"auto","created_at":"2024-04-15 06:23:57","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":92546,"visible":true,"origin":"","legend":"\u003cp\u003eArchitecture of the proposed system.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-4149049/v1/d321a1cab434ec60b3f886ed.png"},{"id":54674865,"identity":"f1b39417-a581-4ed5-98ce-7374377575be","added_by":"auto","created_at":"2024-04-15 06:23:57","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":108566,"visible":true,"origin":"","legend":"\u003cp\u003eRider Dataset\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-4149049/v1/3a4d25e1c70535a19ea4a71b.png"},{"id":54674866,"identity":"74a88620-e000-4fc2-b892-3000c79c5c89","added_by":"auto","created_at":"2024-04-15 06:23:57","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":38696,"visible":true,"origin":"","legend":"\u003cp\u003eWorkflow of the system\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-4149049/v1/befdb576368a646f003604f5.png"},{"id":54675421,"identity":"0615e68b-78f3-40aa-b114-9be1a044edf0","added_by":"auto","created_at":"2024-04-15 06:31:57","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":88029,"visible":true,"origin":"","legend":"\u003cp\u003eGraph of Passenger Demand.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-4149049/v1/f78977a10ea4e2970a94b02e.png"},{"id":54674870,"identity":"ea9103c7-44f8-400a-b257-fc32a7373e2a","added_by":"auto","created_at":"2024-04-15 06:23:57","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":203042,"visible":true,"origin":"","legend":"\u003cp\u003eDemand Analysis\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-4149049/v1/cb775d37a89b220e9e4be57e.png"},{"id":54674869,"identity":"be4f6307-63ff-4136-99a8-77faacc8b6d6","added_by":"auto","created_at":"2024-04-15 06:23:57","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":80952,"visible":true,"origin":"","legend":"\u003cp\u003eFinal Suggested Route\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-4149049/v1/029fea6b99d24412e1ebab64.png"},{"id":54675815,"identity":"8f48d484-04b6-41a4-819e-5b963a61f1ca","added_by":"auto","created_at":"2024-04-15 06:39:58","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1106773,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4149049/v1/eb45ac8a-d18f-4c5e-b5b7-56d4742e4208.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Rider Re-Route Suggestions Using Demand Forecasting Based on Passenger's Routes","fulltext":[{"header":"I.\tINTRODUCTION","content":"\u003cp\u003eThe \"Rider Re-route Suggestions Using Demand Forecasting Based on Passenger's Routes\" program addresses issues related to urban transportation while optimizing efficiency and avoiding environmental consequences by utilizing shared transportation and state-of-the-art technology. The project aims to maximize rider-passenger matching by focusing on two distinct user groups: \"A\" who rides motorcycles alone and \"B\" who is looking for inexpensive transportation. By creating a platform for communication between passengers and frequent riders, the effort recommends alternate routes for Group A based on demand estimates derived from Group B's preferences. The major objective is to design shared pathways that lower travel costs for both sides, encourage sustainability, and mitigate the carbon footprint of urban transportation. The difficulty, though, is in choosing the best paths from a variety of options with somewhat different lengths but comparable beginning and ending locations. The experiment highlights the significance of comprehending passenger demand outside normal commuter routes in order to assure efficient matching. Through the recommendation of routes that correspond with group B's high-demand preferences, the effort aims to optimize prospects for mutual benefit and transform urban transportation into a more sustainable and eco-friendly model.\u003c/p\u003e \u003cp\u003eThe set of paper is mentioned below, Section Ⅱ presents and discuss the related literature works. The proposed system methodology and the algorithm processing are presented in Section Ⅲ. The results of the system are discussed in Section IV and finally, the paper is concluded with Section Ⅴ.\u003c/p\u003e"},{"header":"II.\tRELATED WORKS","content":"\u003cp\u003eThe history of passenger transport may be traced back to the earliest human civilizations when humans depended mostly on foot travel and animals for movement. The development of steam locomotives and ships during the Industrial Revolution enabled faster and more efficient transport. The twentieth century witnessed the spread of vehicles, urbanization, and the construction of modern public transportation networks, all of which presented issues in optimizing routes and timetables for effective passenger service. As the twenty-first century progressed, the digital revolution and the rise of the internet and smartphones heralded a new age. These developments permitted the collection of large amounts of data pertaining to passenger movements. Simultaneously, the area of transportation research began emphasizing data-driven decision-making. This change was aided by several ground-breaking scientific projects. Zhang et al.'s \"DNEAT\" investigated origin-destination demand prediction utilizing dynamic node-edge attention networks, with an emphasis on temporal and geographical interdependence. Chen et al.'s paper \"Multitask Learning and GCN-Based Taxi Demand Prediction\" used multitask learning with Graph Convolutional Networks (GCN) to anticipate taxi demand in a road network. Sohani Liyanage et al. predicted bus passenger demand using artificial neural networks and smart card data, therefore improving public transport services. Understanding the importance of passenger demand forecasting for efficient route suggestions and rider-passenger matching, Banerjee, N. et al.'s \"Passenger Demand Forecasting in Scheduled Transportation\" and Cyril, A. et al.'s \"Modelling and Forecasting Bus Passenger Demand Using Time Series Method\" provided insights into demand prediction techniques. Furthermore, \"Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network\" by Ke, J. et al. looked at forecasting passenger locations and demand patterns, which might help with efficient matching techniques. \"Clustering and Forecasting Urban Bus Passenger Demand with a Combination of Time Series Models\" by Marias-Collado, I. et al. strongly matched with the project's objectives by accurately anticipating passenger demand patterns and emphasizing data-driven decision-making. Abdi, A., et al. (2021) undertake a thorough examination of travel and arrival-time prediction methodologies, providing light on crucial areas that are directly related to the project's performance. To insure the design's success, precise trip time cast is essential as it helps determine dependable divergences. By gaining further knowledge, the action will be suitable to offer riders and passengers more precise recommendations, adding the effectiveness of civic transportation as a whole. Online network- position public transportation demand estimate handed by Zhong,C., et al.( 2023) is largely material to the pretensions of the design. Route optimization and successful matching depend on real- time demand prognostications for public transportation. With the use of this exploration, public transportation dynamics may be effectively managed, icing that the design can effectively acclimate to variations in demand and enhance the overall stoner experience. Using these information, the trouble addresses the real- time transportation requirements of contemporary metropolises, leading the way in technological advancements. exercising demand vaticinations and passenger routes, it focuses on riderre-routing suggestions, satisfying the growing demand for effective and environmentally friendly transportation options. perfecting passenger gests, reducing environmental impact, and reducing business traffic are the overarching pretensions of this trouble. The program steers data- driven perceptivity toward further effective and sustainable mobility results, marking a positive turn in the ongoing history of passenger transportation.\u003c/p\u003e"},{"header":"III. PROPOSED METHOD ","content":"\u003cp\u003eThe methodology chapter provides a synopsis of the approach that is taken in this project to obtain the results. The design, strategies, data preparation and analysis techniques, security and safety measures, environmental effects, implementation and other factors. This study uses the Google Maps API to retrieve the routes information for both passengers and riders. Google Maps API is efficient in collection multiple possible routes for the same from and to locations. Data about the user experience, passenger satisfaction and other feedback can be obtained through surveys, interviews and other measures. The approach goes into detail on data analysis, with a focus on clustering for demand-supply matching. It emphasizes algorithms, distance measurements, and data pretreatment techniques. To ensure active user participation, user engagement strategies which include gamification, promotional campaigns, and feedback mechanisms are covered in detail. With an emphasis on responsible data collecting and user privacy, ethical issues are essential. An environmental impact evaluation compares the decrease in carbon emissions and the usage of single-occupancy vehicles with the aims of sustainability and scalability of the system. The approach goes into detail on data analysis, with a focus on clustering for demand-supply matching. It emphasizes algorithms, distance measurements, and data pretreatment techniques. To ensure active user participation, user engagement strategies which include gamification, promotional campaigns, and feedback mechanisms are covered in detail. With an emphasis on responsible data collecting and user privacy, ethical issues are essential. An environmental impact evaluation compares the decrease in carbon emissions and the usage of single-occupancy vehicles with the aims of sustainability and scalability of the system. The processing of the proposed system is shown in Fig. \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eA. Dataset\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eThe dataset is generated manually as the application is not implemented and is to be used in the ecosystem. The dataset contains Rider and passenger routes in tables. The columns of the tables are shown below in Tables 1 and 2.\u003c/p\u003e\n\u003cp\u003eTABLE I. Mock Dataset For Prototype\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n \u003ctable id=\"Taba\" border=\"1\"\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eRiders Routes\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003ePassengers Routes\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026bull; Pickup location\u003c/p\u003e\n \u003cp\u003e\u0026bull; Drop location\u003c/p\u003e\n \u003cp\u003e\u0026bull; Pickup time\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u0026bull; Pickup location\u003c/p\u003e\n \u003cp\u003e\u0026bull; Drop location\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eTABLE II. \u003cspan type=\"SmallCaps\" name=\"Emphasis\"\u003eActual Dataset\u003c/span\u003e\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"321\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"49.84423676012461%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp; Riders Routes\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"50.15576323987539%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003ePassengers Routes\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"49.84423676012461%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;Id\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;userId\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;startLocation\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;endDestination\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;steps\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;distance\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;startTime\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;duration\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"50.15576323987539%\" valign=\"top\"\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;Id\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;userId\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;startLocation\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;endDestination\u003c/p\u003e\n \u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;steps\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eEach table has several columns that store information related to the routes taken by riders and passengers. Let\u0026apos;s break down the structure of these tables:\u003c/p\u003e\n\u003ch3\u003e1) \u0026nbsp;Riders Routes Table:\u003c/h3\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;Id: A unique identifier for each route in the table.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;userId: Identifies the user or rider associated with the route.\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;startLocation: Indicates the starting point or location of the route.\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;endDestination: Specifies the final destination or endpoint of the route.\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;steps: Likely contains information about the specific steps or directions to follow for the route.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;distance: Records the distance of the route, which could be measured in miles, kilometers, or another unit.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;startTime: Represents the time at which the route starts.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;duration: Indicates the duration of the route, possibly in minutes or hours.\u0026nbsp;\u003c/p\u003e\n\u003ch3\u003e2) \u0026nbsp;Passengers Routes Table:\u003c/h3\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;Id: A unique identifier for each route in the table.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;userId: Identifies the user or passenger associated with the route.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;startLocation: Indicates the starting point or location of the route.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;endDestination: Specifies the final destination or endpoint of the route.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp;steps: Likely contains information about the specific steps or directions for the route.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThis dataset structure is essential for storing and organizing the route information of both riders and passengers. To use this dataset effectively, it would populate these tables with 18 actual data, and then this can perform various data analysis and optimization tasks based on this information to achieve the project\u0026apos;s objectives. Figure \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e shows the exact dataset of the riders\u0026rsquo; route.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eClustering Analysis for Demand-Supply Matching\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e1) INPUTS\u003c/em\u003e:\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;Riders\u0026apos; route data (supply)\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;Passengers\u0026apos; route data (demand)\u003c/p\u003e\n\u003cp\u003e\u0026middot; \u0026nbsp; \u0026nbsp; \u0026nbsp;Number of clusters (k)\u003c/p\u003e\n\u003ch3\u003e2) \u0026nbsp;METHODOLOGY\u003c/h3\u003e\n\u003cp\u003eStep 1: Start.\u003c/p\u003e\n\u003cp\u003eStep 2: Collect and preprocess rider\u0026rsquo;s and passengers\u0026rsquo; route data.\u003c/p\u003e\n\u003cp\u003eStep 3: Apply Clustering Algorithm:\u003c/p\u003e\n\u003cp\u003eA. Initialize k centroids randomly.\u003c/p\u003e\n\u003cp\u003eB. Iterate until convergence or a defined number of iterations:\u003c/p\u003e\n\u003cp\u003ea. Assign each route to the nearest centroid based on distance metrics.\u003c/p\u003e\n\u003cp\u003eb. Calculate new centroids as the mean of assigned routes.\u003c/p\u003e\n\u003cp\u003eStep 4: Analyze Clusters:\u003c/p\u003e\n\u003cp\u003eA. Calculate cluster characteristics:\u003c/p\u003e\n\u003cp\u003ea. The average distance of routes within each cluster to its centroid.\u003c/p\u003e\n\u003cp\u003eb. Total passenger demand within each cluster.\u003c/p\u003e\n\u003cp\u003eB. Identify clusters with high demand and low rider presence.\u003c/p\u003e\n\u003cp\u003eC. Identify clusters with mismatches or unmet demand.\u003c/p\u003e\n\u003cp\u003eStep 5: Suggest Alternate Routes:\u003c/p\u003e\n\u003cp\u003eA. For clusters with high demand and low rider existence:\u003c/p\u003e\n\u003cp\u003ea. Analyze the routes within the cluster.\u003c/p\u003e\n\u003cp\u003eb. Suggest alternate routes that can help the demand while maintaining similar ride period.\u003c/p\u003e\n\u003cp\u003eB. Generate a list of suggested alternate routes for riders.\u003c/p\u003e\n\u003cp\u003eStep 6: Output:\u003c/p\u003e\n\u003cp\u003eA. List of suggested alternate routes for the riders.\u003c/p\u003e\n\u003cp\u003eStep 7: End\u003c/p\u003e\n\u003cp\u003eEquations to calculate for clustering algorithms are mentioned below.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEuclidean Distance\u003c/strong\u003e: The Euclidean distance, which is the distance in Euclidean space between two points, is usually used to determine the distance between cluster centroids and data points. The distance between x and c, the centroid, in a multidimensional space of dimension n:\u003c/p\u003e\n\u003cp\u003e\u003cimg src=\"data:image/png;base64,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\"\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eUpdating Centroids\u003c/strong\u003e: The procedure of using the data points given to a cluster to determine its new centroid. If a cluster is made up of data points x1, x2, x3, x4, x5, xm, and so on, the new centroid c can be found in this way:\u003c/p\u003e\u003cspan\u003e\n \u003cp\u003e\u003cimg src=\"data:image/png;base64,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\"\u003e\u003c/p\u003e\n\u003c/span\u003e\n\u003cp\u003eIn this case, ci represents the i-th component of the centroid, and xij represents the i-th component of the j-th data point.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCluster Assignment\u003c/strong\u003e: Calculating the distance between a given data point and the cluster to which it fits. The cluster with the closest centroid is found using data point x:\u003c/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cimg src=\"data:image/png;base64,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\"\u003e\u003c/p\u003e\u003cspan\u003e\n \u003cp\u003e\u003cstrong\u003eConvergence Criteria\u003c/strong\u003e: When the centroids no longer vary noticeably across iterations, the algorithm is said to have converged. An often-used criterion for convergence is to see if the centroids have changed more than a certain amount.\u003c/p\u003e\n \u003cp\u003eTo determine the need by enumerating unique passenger routes a collection of unique passenger routes is represented mathematically by the formula below. The cardinality of the set (R), or the total number of unique elements in the set, may be used to compute the number of different passenger routes, D:\u003c/p\u003e\n\u003c/span\u003e\n\u003cp\u003e\u003cimg src=\"data:image/png;base64,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\"\u003e\u003c/p\u003e\n\u003cp\u003eThe demand is represented by D and the cardinality of the set of different passenger routes that is, the number of unique routes is represented by |R| \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe proposed project entails gathering and preparing data as well as initializing the cluster centroids. This would be repeated until convergence or a certain number of iterations were reached. The centroid is computed for each route in rider and passenger data by computing distance metrics. Following that, the routes are assigned to the appropriate cluster. For each cluster, new centroids are calculated as the mean of routes inside the cluster. Each cluster\u0026apos;s overall passenger demand is also computed. Clusters with a high and low presence of riders are detected. Along the way, the routes are added to a list. Figure 3 depicts this work.\u003c/p\u003e"},{"header":"IV. RESULTS AND DISCUSSION ","content":"\u003cp\u003eThis research aims to revolutionize urban transport by providing route ideas based on passenger demand to improve efficiency, cost-effectiveness, and sustainability. It addresses the frequent issue of solo commuting in metropolitan areas by attempting to seamlessly link riders and passengers via an innovative platform. This method decreases travel expenses for both parties while also helping to minimize the carbon footprint associated with urban transit. Congestion and environmental issues in today\u0026apos;s urban scene necessitate efficient and sustainable transportation options. This research proposes a game-changing platform that uses technology to assure more sustainable and cost-effective mobility, imagining a future in which urban transit is both efficient and ecologically responsible. Modules for rider and passenger registration, locating riders, match-making, and route suggestions are among the project\u0026apos;s components. The indicated network includes demand forecasting grounded on Google Maps API data, allowing for the discovery of routes with fat demand and the recommendation of alternate routes for passengers without significantly affecting trip field. Two main tables,\u0026quot; Riders Routes\u0026quot; and\u0026quot; Passenger Routes,\u0026quot; which hold all-important data matching route details, user IDs, start and finish locales, distance, duration, and trip way, are part of the study\u0026apos;s database armature. The quality and delicacy of the data are essential to the design\u0026apos;s success. The fashion focuses on demand- force matching clustering analysis, beginning with data collection and preprocessing and developing to gathering styles. The exploration detects clusters with high demand but low rider presence, and different routes are proposed to handle redundant demand while keeping cool commute fields. The applicability of the action resides in its implicit to transfigure civic conveyance by diving lone commuting, high trip charges, and carbon emigrations. It provides competitive trip times, significant cost savings, helped user joy, and a grand drop in single- occupation car use, all of which pitch in to sustainability and fit with the design\u0026apos;s environmental points. In conclusion, the data- run civic ride optimization network provides a road to further cost- efficient, maintainable, and easy civic commuting. It has the implicit to revise the way people travel inside metropolises by utilizing technology, data breakdown, and participated mobility, guiding to a grown and additional economically possible civic tomorrow.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eA. \u0026nbsp; Requirements Specification\u003c/strong\u003e\u003c/p\u003e\n\u003ch3\u003e1)\u0026nbsp;\u0026nbsp;System Requirements\u003c/h3\u003e\n\u003ch4\u003ea)\u0026nbsp;Operating System:\u003c/h4\u003e\n\u003ch4\u003e\u0026middot;\u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Windows: Windows 7 or later\u0026nbsp;\u003c/h4\u003e\n\u003ch4\u003e\u0026middot;\u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;macOS: macOS 10.9 or later\u0026nbsp;\u003c/h4\u003e\n\u003ch4\u003e\u0026middot;\u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Linux: Most modern Linux distributions\u0026nbsp;\u003c/h4\u003e\n\u003ch4\u003eb)\u0026nbsp;Processor:\u003c/h4\u003e\n\u003ch4\u003e\u0026middot;\u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Windows and Linux: Intel Pentium 4 processor or later with SSE2 support (or) AMD Athlon XP or AMD Athlon 64 processors\u0026nbsp;\u003c/h4\u003e\n\u003ch4\u003e\u0026middot;\u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;macOS: Intel processor\u0026nbsp;\u003c/h4\u003e\n\u003ch4\u003ec)\u0026nbsp;RAM: At least 2 GB of RAM (4 GB or more recommended)\u0026nbsp;\u003c/h4\u003e\n\u003ch3\u003e2)\u0026nbsp;\u0026nbsp;Software Requirements\u003c/h3\u003e\n\u003cp\u003eTo process this system, the following technologies and techniques are needed.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTABLE III. \u0026nbsp; \u0026nbsp;\u0026nbsp;Software \u0026nbsp;Requirements\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"318\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"41.37931034482759%\"\u003e\n \u003cp\u003e\u003cstrong\u003eHeadings\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"58.62068965517241%\"\u003e\n \u003cp\u003e\u003cstrong\u003eTools/Technology\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"41.37931034482759%\" valign=\"top\"\u003e\n \u003cp\u003eFRONT END TOOLS\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"58.62068965517241%\"\u003e\n \u003cp\u003eReact Native/ JS\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"41.37931034482759%\" valign=\"top\"\u003e\n \u003cp\u003eBACK-END TOOLS\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"58.62068965517241%\"\u003e\n \u003cp\u003ePython\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"41.37931034482759%\" valign=\"top\"\u003e\n \u003cp\u003eMARKUP LANGUAGES\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"58.62068965517241%\"\u003e\n \u003cp\u003eJSX\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"41.37931034482759%\" valign=\"top\"\u003e\n \u003cp\u003eMIDDLEWARE\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eTECHNOLOGIES\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"58.62068965517241%\"\u003e\n \u003cp\u003eFirebase, Google Maps API\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"41.37931034482759%\" valign=\"top\"\u003e\n \u003cp\u003eSCRIPTING LANGUAGES\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"58.62068965517241%\"\u003e\n \u003cp\u003eJavaScript, Python\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"41.37931034482759%\" valign=\"top\"\u003e\n \u003cp\u003ePACKAGES NEEDED\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"58.62068965517241%\" valign=\"top\"\u003e\n \u003cp\u003ePYTHON: Pandas, NumPy, Matplotlib, Sklearn, Random, ortools.\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eJS: @react-google-maps/api\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"41.37931034482759%\" valign=\"top\"\u003e\n \u003cp\u003eIDE\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"58.62068965517241%\"\u003e\n \u003cp\u003eVisual studio code\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003ch2\u003eB. \u0026nbsp; Contribution to the Research Work\u003c/h2\u003e\n\u003cp\u003e1) \u0026nbsp;The Optimization of Urban Transportation: The Optimization of Urban Transportation employing data deconstruction and an internet connection, the action offers a extreme path to civic conveyance by giving routes grounded on passenger demand. By doing this, civic transportation networks are bettered, getting more sustainable and effective.\u003c/p\u003e\n\u003cp\u003e2) \u0026nbsp;Single- residency Vehicle Reduction: Downgrading the number of single- residency cars and single commuters is one of the main objects of the action. By linking motorists and passengers, it promotes participated mobility and significantly lowers the operation of single- residency cars. This has significant ramifications for reducing the impact on the terrain and business traffic.\u003c/p\u003e\n\u003cp\u003e3) \u0026nbsp;Cost Savings: The data demonstrates that suggested detours usually lead to considerable savings for passengers as well as riders. This financial benefit contributes to the urban commuters\u0026apos; economic well-being, which is particularly crucial in a society where transportation costs might be considerable.\u003c/p\u003e\n\u003cp\u003e4) \u0026nbsp;Environmental Longevity: By reducing the use of single-occupancy automobiles, the idea is strongly related to environmental sustainability goals. In view of growing environmental concerns, it aids in lowering carbon emissions and the overall environmental impact of urban mobility.\u003c/p\u003e\n\u003cp\u003e5) \u0026nbsp;Efficiency and User Satisfaction: The study\u0026apos;s technique improves urban transportation efficiency by better matching riders and passengers. This leads to faster travel times and more consumer satisfaction, resulting in a more convenient and appealing commuting experience.\u003c/p\u003e\n\u003cp\u003eC. \u0026nbsp;Comparison\u003c/p\u003e\n\u003cp\u003eTable 4 shows state of an art comparison of the proposed system and other systems.\u003c/p\u003e\n\u003cp\u003eTABLE IV. State of n Art Comparision\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"321\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"17.5%\"\u003e\n \u003cp\u003e\u003cstrong\u003eResearch Work (Year)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003e\u003cstrong\u003eFocus\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003e\u003cstrong\u003eAlgorithm\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003e\u003cstrong\u003eDataset\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003e\u003cstrong\u003eLimitations\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"17.5%\"\u003e\n \u003cp\u003eProposed System\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eDemand prediction and Route optimization\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eClustering Analysis for Demand-Supply Matching\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eRider and passenger routes\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003ePrivacy Issues,\u003c/p\u003e\n \u003cp\u003eUser Adoption\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"17.5%\"\u003e\n \u003cp\u003e[3] Zhang et al. (2021)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eDynamic Node-Edge Attention Network\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eDynamic Node-Edge Attention Network\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eChengdu dataset, New York dataset.\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eLimited to urban areas, scalability issues\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"17.5%\"\u003e\n \u003cp\u003e[4] Chen et al. (2020)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eMultitask Learning and GCN-Based Prediction\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eGCN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eTraffic and Taxi Demand Data\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eReliant on historical data, need for real-time updates\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"17.5%\"\u003e\n \u003cp\u003e[2] Sohani Liyanage et al. (2022)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eAI-Based Neural Network Models\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eANN\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eSmart Card Data\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eLimited to buses, may not cover all urban modes of transport\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"17.5%\"\u003e\n \u003cp\u003e[8] Mari\u0026ntilde;as-Collado et al. (2022)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eClustering and Forecasting Bus Demand\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eClustering\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eUrban Bus Passenger Data\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eLimited to buses and clustering is based on historical patterns\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"17.5%\"\u003e\n \u003cp\u003e[12] Abdi et al. (2021)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eTravel and Arrival-Time Prediction\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eVarious Prediction Models\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eTraffic Data\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eLimited to travel time predictions\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"17.5%\"\u003e\n \u003cp\u003e[13] Halyal et al. (2022)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eForecasting Public Transit Demand\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003eNeural Networks\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003ePublic Transit Demand Data\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"20.625%\"\u003e\n \u003cp\u003ePrimarily focused on public transit\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eD. \u0026nbsp;Output\u003c/p\u003e\n\u003cp\u003eThe above graph in Figure 4 shows the demand of the passenger according to the routes. The y-axis is the demand scale and the x-axis is the routes of the passengers. The graph here clearly explains that the highest demand is for \u0026ldquo;E\u0026rdquo; to \u0026ldquo;A\u0026rdquo; location.\u003c/p\u003e\n\u003cp\u003eThis output (Figure 5) \u0026nbsp; represents the weight of all possible routes that are used by the passengers. The route with highest weight is the route with most demand and vice versa. In this output the route \u0026apos;E-A\u0026apos; has the most demand with weight as 134 and the route \u0026apos;F-A\u0026apos; has the least demand relative to other routes with a weight of 86.\u003c/p\u003e\n\u003cp\u003eIn this output, the route \u0026lsquo;E-A\u0026rsquo; is identified as the most demanded route. From the suggested route, it is identified that the route \u0026lsquo;E-A\u0026rsquo; is covered by the rider. This route is suggested to the rider, by which the frequency of rider\u0026rsquo;s pickup is increased and the passenger gets benefited.\u003c/p\u003e"},{"header":"V.\tCONCLUSION AND FUTURE SCOPE","content":"\u003cp\u003eTo sum up, this research offers a data-driven approach to improving urban transportation by effectively matching passengers and riders. It provides a route to more affordable, environmentally friendly, and conveniently located urban commuting by addressing the issues of lone commuting, expensive travel expenses, and carbon emissions. This project can change the way people navigate around the city. It can reduce the cost spent on transport and make the urban future sustainable. It has its limitations and needs improvement to do well in the long run. As the future of transportation evolves this project can bring a good change for the future of urban mobility.\u003c/p\u003e\n\u003ch2\u003eA. \u0026nbsp; Limitation of the proposed system\u003c/h2\u003e\n\u003cp\u003e1) \u0026nbsp;Data Reliance: The design\u0026apos;s success depends on the vacuity and delicacy of data, particularly from the Google Maps API. Due to incorrect route recommendations, deficient or inaccurate data may affect the quality of the service.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e2) \u0026nbsp; Privacy firms: As a result of the platform collecting user data, insulation issues arise. The design must address these problems to ensure the security of user rights and data. The right balance between data collection and insulation may be hard to achieve.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e3) \u0026nbsp; User Acceptance: \u0026nbsp;Satisfying guests to convert from their being forms of transportation to shared mobility may prove to be a challenging task. Some people may be resistant to change or doubtful about the benefits of the proposed system.\u003c/p\u003e\n\u003ch2\u003eB. \u0026nbsp; Future Scope\u003c/h2\u003e\n\u003cp\u003eThis project still needs to look into implicit exploration directions in lift-sharing and civic transportation effectiveness. One of them is exercising state-of-the-art machine literacy ways similar to deep literacy and neural networks to offer more accurate route recommendations. Incorporating real-time data sources, understanding commuter gestures, and optimizing route recommendations grounded on stoner preferences are imperative. Studies can also look at the smooth integration of multimodal transportation options, enhance environmental impact assessment styles, and probe cost-effectiveness, policy impulses, and nonsupervisory fabrics. Data security and stoner sequestration must be considered in unborn exploration. Civic mobility results will continue to advance in these disciplines.\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eBanerjee, N., Morton, A., Akartunalı, K. (2020). \u0026quot;Passenger demand forecasting in scheduled transportation.\u0026quot; European Journal of Operational Research, Volume 286, Issue 3, pp. 797-810, ISSN 0377-2217. \u003c/li\u003e\n\u003cli\u003eLiyanage, S., Abduljabbar, R., Dia, H., Tsai, P-W. (2022). \u0026quot;AI-based neural network models for bus passenger demand forecasting using smart card data.\u0026quot; Journal of Urban Management, Volume 11, Issue 3, pp. 365-380, ISSN 2226-5856. \u003c/li\u003e\n\u003cli\u003eZhang, D., Xiao, F., Shen, M., Zhong, S. (2021). \u0026quot;DNEAT: A novel dynamic node-edge attention network for origin-destination demand prediction.\u0026quot; Transportation Research Part C: Emerging Technologies, Volume 122, pp. 102851, ISSN 0968-090X. \u003c/li\u003e\n\u003cli\u003eChen, Z., Zhao, B., Wang, Y., Duan, Z., \u0026amp; Zhao, X. (2020). \u0026quot;Multitask learning and GCN-based taxi demand prediction for a traffic road network.\u0026quot; Sensors, Volume 20(13), pp.3776.\u003c/li\u003e\n\u003cli\u003eCyril, A., Mulangi, R. H., George, V. (2018). \u0026quot;Modelling and Forecasting Bus Passenger Demand using Time Series Method.\u0026quot; In 2018 7th International Conference on Reliability, Infocom Technologies, and Optimization (Trends and Future Directions) (ICRITO), Noida, India, pp. 460-466.\u003c/li\u003e\n\u003cli\u003eFaridai, S., Juraeva, R.S., Darovskikh, S.N., Qodirov, Sh.Sh. (2021). \u0026quot;Neural Network Model for Predicting Passenger Congestion to Optimize Traffic Management for Urban Public Transport.\u0026quot; Вестник ЮУрГУ. Серия: Компьютерные технологии, управление, радиоэлектроника, 2021.\u003c/li\u003e\n\u003cli\u003eKe, J., Qin, X., Yang, H., Zheng, Z., Zhu, Z., \u0026amp; Ye, J. (2021). \u0026quot;Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network.\u0026quot; Transportation Research Part C: Emerging Technologies, 122, 102858.\u003c/li\u003e\n\u003cli\u003eMari\u0026ntilde;as-Collado, I., Sipols, A.E., Santos-Mart\u0026iacute;n, M.T., Frutos-Bernal, E. (2022). \u0026quot;Clustering and Forecasting Urban Bus Passenger Demand with a Combination of Time Series Models.\u0026quot; Mathematics, Volume 10, pp.2670. \u003c/li\u003e\n\u003cli\u003eYadav, R. K., Kishor, G., Himanshu, K., Kashyap, K. (2020). \u0026quot;Comparative Analysis of Route Planning Algorithms on Road Networks.\u0026quot; In 2020 5th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, pp. 401-406. \u003c/li\u003e\n\u003cli\u003eZhang, P., Ma, W., Qian, S. (2022). \u0026quot;Cluster analysis of day-to-day traffic data in networks.\u0026quot; Transportation Research Part C: Emerging Technologies, Volume 144, pp. 103882, ISSN 0968-090X. 37\u003c/li\u003e\n\u003cli\u003eBazant, M., Akhtar, M., Moridpour, S. (2021). \u0026quot;A Review of Traffic Congestion Prediction Using Artificial Intelligence.\u0026quot; Journal of Advanced Transportation, Volume 2021, SP - 8878011, ISSN 0197-6729. \u003c/li\u003e\n\u003cli\u003eAbdi, A., Amrit, C. (2021). \u0026quot;A review of travel and arrival-time prediction methods on road networks: classification, challenges and opportunities.\u0026quot; PeerJ Comput Sci, 7, e689. doi: 10.7717/peerj-cs.689. \u003c/li\u003e\n\u003cli\u003eHalyal, S., Mulangi, R. H., Harsha, M.M. (2022). \u0026quot;Forecasting public transit passenger demand: With neural networks using APC data.\u0026quot; Case Studies on Transport Policy, Volume 10, Issue 2, pp. 965-975, ISSN 2213-624X.\u003c/li\u003e\n\u003cli\u003eZhong, C., Wu, P., Zhang, Q., Ma, Z. (2023). \u0026quot;Online prediction of network-level public transport demand based on principle component analysis.\u0026quot; Communications in Transportation Research, Volume 3, 100093, ISSN 2772-4247. \u003c/li\u003e\n\u003cli\u003eHalvorsen, A., Koutsopoulos, H.N., Ma, Z., et al. (2020). \u0026ldquo;Demand management of congested public transport systems: a conceptual framework and application using smart card data.\u0026quot; Transportation, 47, 2337\u0026ndash;2365.\u003c/li\u003e\n\u003cli\u003eJiang, W., Ma, Z., Koutsopoulos, H.N. (2022). \u0026quot;Deep learning for short-term origin\u0026ndash;destination passenger flow prediction under partial observability in urban railway systems.\u0026quot; Neural Comput \u0026amp; Applic, 34, 4813\u0026ndash;4830. \u003c/li\u003e\n\u003cli\u003eTedjopurnomo, D.A., Bao, Z., Zheng, B., Choudhury, F.M., Qin, A.K. (2020). \u0026quot;A survey on modern deep neural network for traffic prediction: Trends, methods, and challenges.\u0026quot; IEEE Transactions on Knowledge and Data Engineering, 34(4), 1544-1561.\u003c/li\u003e\n\u003cli\u003eXie, Z., Lv, W., Huang, S., Lu, Z., Du, B., Huang, R. (2020). \u0026quot;Sequential Graph Neural Network for Urban Road Traffic Speed Prediction.\u0026quot; IEEE Access, 8, 63349-63358.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","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":"Urban transportation, ride-sharing, data analysis, internet networking, commuter matchmaking, demand forecasting, urban mobility","lastPublishedDoi":"10.21203/rs.3.rs-4149049/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4149049/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eThrough data analysis and internet networking, ride-sharing can be optimized with the aim of revolutionizing urban transportation. It addresses the common issue of lone commuters by connecting \"riders\" and \"passengers\" through an intelligent platform that suggests alternative routes based on passenger demand. The primary goals are to boost urban mobility efficiency, reduce trip costs, and increase sustainability. The project is divided into components for rider and passenger registration, demand forecasts, matchmaking, and route optimization. The results demonstrate that the suggested deviations offer similar travel times, considerable cost savings, and improved customer satisfaction. Cutting back on single-occupancy car use is in line with environmental objectives. This concept offers a data-driven solution to transportation problems, which might drastically alter how people move around cities.\u003c/strong\u003e\u003c/p\u003e","manuscriptTitle":"Rider Re-Route Suggestions Using Demand Forecasting Based on Passenger's Routes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-15 06:23:52","doi":"10.21203/rs.3.rs-4149049/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":"35439ae8-8f38-4eae-9a96-1fc6eb51a700","owner":[],"postedDate":"April 15th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":29926080,"name":"Social science/Development studies"},{"id":29926081,"name":"Scientific community and society/Developing world"}],"tags":[],"updatedAt":"2024-04-15T06:23:52+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-15 06:23:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4149049","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4149049","identity":"rs-4149049","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}