Application of Dynamic Image Simulation Based on Optical Sensor Networks in Optimizing the Quality of Physical Education Course Videos

Application of Dynamic Image Simulation Based on Optical Sensor Networks in Optimizing the Quality of Physical Education Course Videos | 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 Application of Dynamic Image Simulation Based on Optical Sensor Networks in Optimizing the Quality of Physical Education Course Videos Dongwei Lv This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3852350/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract With the development of video physical education course management simulation, in order to improve the quality of video transmission, this study proposes a video transmission technology based on optical flow estimation network. Firstly, an optical flow estimation network model is established, which can automatically extract optical flow information from input video and estimate object motion by analyzing pixel displacement between successive images. Then, according to the optical flow information, the video frame is repaired and compensated to reduce the information loss and quality degradation in video transmission. The experimental results show that the video transmission technology based on optical flow estimation network can significantly improve the quality and stability of video. Compared with the traditional video transmission method, this technology has better adaptability and robustness in the case of low network bandwidth or network congestion, and provides high quality and stable video transmission, which provides strong support for the application of distance education and sports course management simulation. optical flow estimation network Video transmission technology Video teaching Physical education curriculum management Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 1 Introduction In recent years, with the rapid development of communication technology, communication devices have greatly improved. In computer network environments, due to the huge amount of data and the variety of request types, previous calculations cannot adapt to the current requirements (Jameel et al. 2018). Therefore, cloud technology has emerged and attracted great attention from people. Cloud computing is a new concept first proposed by Google in 2006. Cloud computing is a virtual technology based approach that aggregates massive and scattered physical resources into a vast resource pool (Rashid and Chaturvedi 2019). Based on this, it provides users with various services such as storage, networking, computing, and applications according to their specific needs. After experiencing three computing methods, cloud computing tasks abstract multiple server resources, allowing users to quickly obtain resources according to their own needs and achieve the same user experience as actual physical machines (Varghese and Buyya 2018). The development of technology has accelerated our steps towards the information age. Information education should be widely promoted, which conveys the idea of integrating information with various subject courses. More and more physical education teachers are beginning to realize the importance of applying these two technologies to physical education teaching (Casey and MacPhail 2018). However, how to perfectly combine these two technologies to form a new teaching method has never become a feasible method, and on the basis of information technology, We have also implemented online video sports courses that are closely integrated with course teaching, which can meet the learning needs of theoretical knowledge and increase students' time for practice in the classroom (Tomlinson et al. 2020). We also receive personalized guidance from teachers, which is conducive to students' deepening and consolidation of knowledge and is in line with their lifestyle and learning habits. Moreover, online video has already achieved success in other fields. This has brought new hope to our physical education teaching. The use of "online sports video courses" has changed the previous teaching mode, increased students' time for technical action training in physical education classrooms, effectively promoted teachers' individualized teaching, and better met students' personal development needs, which is consistent with China's talent cultivation strategy (Belt and Lowenthal 2021). In fact, exercise has always been a very important component in the healthy growth process of teenagers. Research has shown that after comprehensive consideration of students' physiological and psychological characteristics, it has been found that college students are in the most critical period in terms of physiology, psychology, cognition, morality, and emotions. During this period, students' physical development speed is the fastest, and their minds are gradually maturing (Baldwin 2019). Combined with their physiological and psychological characteristics, it can be seen that during this period, students have stronger subjectivity in external things, and their self-evaluation ability is continuously improving. They will gradually shift from dependence and passivity to autonomy and initiative, and they will develop a strong interest in new things (Siller et al. 2018). 2 Related work The cloud computing market size has exceeded $ 300 billion in 2021. Since 1950, the application of cloud computing has mainly focused on academia and military institutions. Since 1950, cloud computing technology has made significant progress, and its overall service quality has also greatly improved, bringing more choices to corporate institutions (Ali et al. 2021). So far, the development of cloud computing has been closely related to the progress of internet and business technology. Literature research shows that computers in the future can be sold as a service like electricity and water. This is a brilliant idea, but like other excellent ideas, it is ahead of that era, so in the coming decades, although this idea has attracted great attention, the corresponding technology has not caught up with it (Yoo and Kim 2018). Until 1999, Salesforce.com became an important milestone in the field of cloud computing, leading a new technology that allowed businesses to publish applications on a simple site. However, this technology was only applicable to professionals and mainstream software companies. The literature points out the introduction of a business service called EC2, which allows small organizations and individual users to rent computers in the cloud and run their computer applications on it (Rimba et al. 2020). The literature first published a cloud computing application for enterprises and collaborated with other companies to provide users with a browser-based cloud service (Alashhab et al. 2021). Next is Microsoft's Azure, which provides users with a secure and convenient service, both from Microsoft and Google. Also in 2009, with the release of the "Alibaba Cloud" platform, "Alibaba Cloud" was officially established. In addition, Huawei, Dawn, and Yunchuang Big Data are all committed to cloud related applications, driving the progress of the cloud industry. After years of development, cloud computing has formed a relatively mature business model and gradually become the main driving force behind the digital process of Chinese society. The literature proposes an improved particle swarm optimization algorithm, which utilizes microbial genetic algorithm to reduce the solution space in the initial stage and utilizes dynamic inertia weights to improve the integration accuracy of the algorithm in the later stage (Wang et al. 2018). The literature indicates that this algorithm absorbs the strong local optimization ability of the restricted search algorithm and exits the local optimal solution as soon as possible (Wang et al. 2021). In existing research, literature has proposed multi-objective optimization algorithms, which use two optimization methods, Brown and PSO, to mix the optimal solutions of the two populations, and then compare them with the original scheme to obtain the optimal solution. The literature points out that users should make online appointments for designated coaches, pay fees online, and directly enjoy services such as guidance and accompanying training (Wang and Wang 2020). The literature suggests that the development and promotion of apps should create a good business model and profit model, prioritizing the specificity of the product and the functional development of user consumption patterns, with the product itself as the starting point for profitability (Luong et al. 2020). The literature points out that with the gradual coverage of 5G networks, the mobile internet is taking up a lot of people's time, and sports fans are browsing sports information through mobile applications (Alalwan et al. 2018). However, although sports users choose the content category of the sports information application homepage, there is a significant difference between choosing the text title category and the video title category, with users choosing more text title categories. The literature suggests that a good sports user group should be established from the perspective of sports app development, and a good user group relationship should be built in the development and operation of functions (Zhu 2022). In the operation, selection, and use of sports users, sports apps may experience gatherings of "small communities" and "small circles". 3 Cloud computing 3.1 Theoretical basis Optical flow estimation network can analyze the video sequence and estimate the trajectory of the object accurately. Through optical flow estimation network, the motion information of different objects in video is obtained, and the task scheduling algorithm is further optimized. Based on the detected motion information, the task that requires more computing resources is identified and assigned to a VM with more computing power to meet the task's computing resource requirements. Optical flow estimation networks can also be applied during video transmission to help recover motion blur and transmit lost video content. Through optical flow estimation of the video sequence, the motion of the object is accurately predicted and compensated during the video reconstruction. For users, the biggest cost when executing tasks in cloud computing is the cost of virtual machines. When executing tasks, the expenses incurred by using virtual machines are charged based on the number of pricing time units used. If there are insufficient certificate time units, an upward rounding process is required. The execution cost E cost of a set of tasks on virtual machine ve can be expressed by the following Eq. ( 1 ), where TE represents the usage time of a set of tasks on virtual machine v: $${Ecost}_{k}=⌈{TE}_{k}/{cet}_{k}⌉\times {ce}_{k}$$ 1 Therefore, the cost of the entire task set can be represented by the total cost processed by formula ( 2 ), where C cost represents the total communication cost of the task set: $$\text{C}\text{O}\text{S}\text{T}=\text{C}\text{o}\text{s}\text{t}+{\sum }_{1}^{\text{m}}\text{E}{\text{c}\text{o}\text{s}\text{t}}_{\text{k}}$$ 2 These median nodes are assigned priority based on the rank value, that is, the highest priority is given to the newly generated median node with the highest rank value, and the priority of the remaining median nodes is calculated using formula ( 3 ). After calculating the priority of these nodes, they are added to the task list in descending order. Afterwards, this was the case until all nodes were added to the task list. $$\text{P}\text{r}\text{i}\text{o}\text{r}\text{i}\text{t}\text{y}\left({\tau }_{i}\right)=\underset{{\tau }_{k}\in {pre}\left({\tau }_{i}\right)}{\text{max}}{\text{c}}_{\text{k},\text{i}}+{\stackrel{-}{\text{w}}}_{\text{i}}+\underset{{\tau }_{j}\in pre\left({\tau }_{i}\right)}{\text{m}\text{a}\text{x}}{\text{c}}_{\text{i},\text{j}}$$ 3 The article points out a new algorithm that can ensure both the execution cost of the task itself and the information transmission cost between tasks. This algorithm takes the sum of the longest communication cost from the current node to the previous node, the average execution cost of the task itself, and the longest communication cost from the current node to the next node as the final task priority. Traverse all virtual machines, select the virtual machine MV (zi) with the lowest cost based on the calculated execution cost and data transmission cost (zi, vk) of task zi in the virtual machine, and assign tasks to it. Cost (zi, vk) only represents the cost caused by the execution and data transmission of a single task in a virtual machine, while the total cost of cloud resources for a task set is determined based on the occupation time and data transmission of the task set on each virtual machine. Due to idle time, the total cost of cloud resources in a task set cannot be simply accumulated by the total cost of each task. $$\text{C}\text{o}\text{s}\text{t}({\tau }_{i},{v}_{k})=⌈\text{w}({\tau }_{i},{v}_{k})/{\text{c}\text{e}\text{t}}_{\text{k}}⌉\times {\text{c}\text{e}}_{\text{k}}+⌈{\text{T}\text{C}}_{{\tau }_{i},{v}_{k}}/\text{c}\text{c}\text{t}⌉\times \text{c}\text{c}$$ 4 Update the cumulative lease time of z in virtual machine EV (zi). $${VT}_{min-cost}\left(EV\right({\tau }_{i}\left)\right)=EST({\tau }_{i},MV({\tau }_{i}\left)\right)+w({\tau }_{i},MV({\tau }_{i}\left)\right)$$ 5 If an appropriate interval task is not selected for addition, but for the sake of earlier actual completion time, update the cumulative lease time in EV (zi) according to the formula, where AFT (zi) is the actual completion time of the task in the formula $${VT}_{insert}\left(EV\right({\tau }_{i}\left)\right)=AFT\left({\tau }_{i}\right)=\underset{k}{\text{min}}\left\{EST\right({\tau }_{i},{v}_{k})+w({\tau }_{i},{v}_{k}\left)\right\}$$ 6 Autoregressive models are common models used to predict time series, in which the time value of t is linked to its historical value and separated from the prediction error of t-i. This system is called an automatic regression model. The model containing the following structure is called a P-level regression model, as detailed below. $${X}_{t}={\phi }_{0}+\sum _{i=1}^{p}{\phi }_{i}*{X}_{t-1}+{\epsilon }_{t}$$ 7 The grey system theory applies a method of generating behavioral characteristic data of the system, which can achieve higher prediction accuracy for data with changes limited to a certain range. GM ( 1 , 1 ) has certain applicability in various modes and can predict periodic and non periodic sequences. The formula for determining the parameters is as follows: $$\text{Y}={[{\text{x}}_{2}^{\left(0\right)},{\text{x}}_{3}^{\left(0\right)},...,{\text{x}}_{\text{n}}^{\left(0\right)}]}^{\text{T}}$$ 8 The formula for predicting finite Boltzmann machines using differential equations is as follows: $$\text{E}(\text{v},\text{h})=-\sum _{\text{i}=1}^{\text{p}}\sum _{\text{j}=1}^{\text{q}}{\text{v}}_{\text{i}}{\text{w}}_{\text{i},\text{j}}{\text{h}}_{\text{j}}-\sum _{\text{i}=1}^{\text{p}}{\text{a}}_{\text{i}}{\text{v}}_{\text{i}}-\sum _{\text{j}=1}^{\text{q}}{\text{b}}_{\text{j}}{\text{h}}_{\text{j}}$$ 9 Equation ( 10 ) is the calculation formula for calculating unit 1 from the visible state, Eq. (11) is the calculation formula for reconstructing hidden layer unit 1 from the hidden layer state, and Eq. (11) is the calculation formula for reconstructing hidden layer unit 1 from the reconstructed visible layer state. $$\text{p}({\text{h}}_{\text{j}}^{\left(0\right)}=1\left|{\text{v}}^{\left(0\right)}\right.)=\frac{1}{1+\text{e}\text{x}\text{p}(-\sum _{\text{i}=1}^{\text{P}}{v}_{i}^{t+1}{\text{x}}_{\text{i},\text{j}}-{\text{b}}_{\text{j}})}$$ 10 3.2 Experimental Testing As shown in Fig. 1 , from the initial 1.4 to the final 0.4, there is a trend of slowing down. The larger the weight of the algorithm, the more suitable it is for global optimization. If the inertia weight becomes smaller, then the advantage of slow reduction is more conducive to local optimization and ensures the accuracy of local search. Figure 2 shows the comparison of the completion time of tasks with different numbers of tasks in three different methods. This method can effectively solve the problem of low convergence rate in traditional particle swarm optimization algorithm processing tasks, thereby increasing the efficiency of cloud computing. At the same time, it can still maintain a relatively optimal scheduling effect while maintaining good robustness despite the continuous increase in processing task volume. Figure 3 shows the consumption situation of each node. The energy consumption of node 1 is 683, and the energy consumption of node 3 is 875. 2 is 432, and node 4 is 234. When the energy exceeds the upper limit, node 1 randomly predicts that it will migrate to node 2 in advance, causing an increase in node 2. Node 1 remains below the threshold, while node 3 is above the threshold, resulting in a "hot spot" phenomenon. Node 1 remains below the threshold, while node 3 exceeds the energy consumption threshold, and node 3 exhibits a "hot spot" phenomenon. Based on the above analysis, we propose that it can solve the problem of servers. As shown in Table 1 , when the number of consecutive predictions is 3, the accuracy of predicting 100 and 1000 times is 100%. However, if the number of consecutive predictions is 4 or 5, the accuracy of prediction will gradually decrease. Due to the longer the prediction time, the smaller the impact. If the error exceeds the set value, the prediction will become invalid. Correspondingly, the number of consecutive predictions can be set to 3. As shown in Table 1 . Table 1 Number of Correct Predictions number of times 3 4 5 100 100% 99.9% 98.89% 1000 100% 99.97% 99.95% 4 Online video sports course management 4.1 Design of online video sports course system Drawing on a certain school as the experimental object and following the idea of leading learning cases, in the design of physical education courses, the teaching mode based on online video physical education courses has added a guarantee system of "guiding, helping, and promoting learning". Fully integrate the tutorial concept to avoid the problem of unclear prioritization of key and difficult points in the pre class autonomous learning process. Design the teaching process as shown in Fig. 4 : In the classroom, the teacher arranges the teaching content reasonably based on their actual situation, and in the classroom, allows students to demonstrate the technical actions before class. After the students' demonstration, the teachers gave accurate evaluations. At this stage, the students' focus is the highest because they are learning new things and full of freshness. Secondly, because students have a strong sense of self-esteem, they want to show their best in front of their teachers and classmates. Therefore, teachers can point out their mistakes and provide correct demonstrations at this time, which will greatly help improve their skills and skills. Afterwards, the teacher will also focus on explaining and demonstrating slightly complex action techniques. The teacher then organizes students to carry out the next learning activities, allowing them to practice and correct their mistakes on their own, while the teacher guides them on the side. After the student activity is completed, holding several more competitions can liven up the class atmosphere; Secondly, teachers can assess students and provide necessary rewards and punishments. Online teaching experience. Optical flow estimation network can estimate the motion trajectory and speed of objects in video by analyzing the motion of pixels between successive frames. In video physical education lessons, this technology can be used to track subtle changes in student movement and posture, allowing for more accurate assessment and monitoring of student athletic performance. Through the optical flow estimation network, teachers can observe and analyze videos of physical education homework completed by students at home in real time. Through the visualization of movement trajectories, teachers can identify the problems that students may have in movement and the room for improvement, and give targeted guidance and suggestions in time. For example, if a student's step in a long jump is unsteady, the optical flow estimation network can help the teacher determine if the student needs to strengthen the balance and coordination of the leg movements. In addition to teacher supervision, parents can also evaluate and supervise the completion of students' homework through the optical flow estimation network. By observing the movement track in the video, parents can judge whether the student has completed the task in accordance with the correct posture and movement, and give recognition or correction in time. Students themselves can also improve their technique and enhance their self-evaluation ability by observing their own movement trajectories. By comparing their movement trajectories with standard postures, students can find their mistakes and shortcomings and try to correct them. The optical flow estimation network can be a powerful tool for students to train and adjust themselves and help them improve their technical level. In teaching, students actively improve their technical skills under the guidance of the teacher, practice continuously, and reach proficiency; In the post class transition stage, what needs to be done is to further strengthen the proficiency and automation level of the movements, achieve a seamless completion of the movements, and the movements should be in line with the standards. The main job content is to assign homework for college physical education. Under the supervision of parents and random sampling by teachers, it is necessary to supervise and urge students to complete them in a timely manner, and consolidate their movement skills, as shown in Fig. 5 : The important source of intelligent teaching and online video sports learning is the sports learning resource library. It is necessary to classify and organize sports project technology micro lesson videos, health and nutrition PPTs, sports physiology and biochemistry, etc., and put them into storage. Guided by daily applications, it integrates the integrated design and implementation of high-quality sports courses from multiple channels of the Internet of Things around every link of sports courses and teaching, Build a network platform for the integrated development of physical education curriculum teaching both inside and outside the classroom, and ultimately build a shared curriculum content system that is consistent with national standards and adapted to the actual teaching situation. Attract institutions such as social initiatives and e-learning to participate in the construction of various public sports courses. Integrate the existing physical education curriculum resources of platforms such as online open courses and Sina open courses into the open resource library. As shown in Fig. 6 . Sports learning environment perception online video sports tools should be able to provide timely feedback on the sports learning and exercise environment conditions where college students are located, such as the temperature of sports venues, saturation of exercise participants, air quality, and location information. The main body of physical education learning in sports learning community connected universities is college students, and the activities they participate in, such as physical education learning and exercise, all exist in virtual or real learning communities. In addition, smart technologies such as mobile media can maintain close contact with the learning community, allowing for interaction and communication at any time. For example, participating in physical education classes includes selective classes and WeChat classes; For example, the community in which they exercise is a group of like-minded classmates or friends who frequently participate in club activities, as well as a WeChat group for club activities. 4.2 Online Video Sports Course System Testing A survey was conducted on the emotional attitudes of 76 students towards using online video competitive teaching systems. The results showed that compared to other online platforms, students are more inclined to use online video competitive teaching systems. It can be seen that this article meets the students' wishes. A survey on the emotional attitudes of three teachers who use online video sports teaching systems shows that compared to other online platforms, teachers prefer to use online video sports teaching systems, which is in line with students' wishes. 5 Conclusion Through the application of optical flow estimation network, more accurate motion tracking and posture recognition can be realized, and personalized movement guidance and feedback can be provided for students. Optical flow estimation network can realize real-time analysis and evaluation of physical movements, help teachers better understand students' performance, and carry out effective teaching guidance. Video transmission optimization through optical flow estimation network can improve the efficiency and stability of video transmission and provide better learning experience for students. However, in order to give full play to the advantages of video transmission technology based on optical flow estimation network, universities need to strengthen the research and application of related technologies. The establishment of sound research teams and laboratories and the training of teachers with knowledge and skills in the application of optical flow estimation networks are all important steps. Colleges and universities also need to pay attention to students' physical and mental health and all-round development, pay attention to cultivating students' health awareness and healthy habits, and provide students with broad development space and diversified physical exercise methods. In practice, colleges and universities should pay attention to the in-depth implementation of teaching reform, attach importance to students' subjectivity in teaching activities, and give full play to students' initiative and creativity. Colleges and universities need to balance the focus of teaching development, take the improvement of students' skills, active participation, healthy development of body and mind and strengthening individual social adaptability as the basic goals, and comprehensively promote the implementation of teaching reform. Therefore, the video transmission technology based on optical flow estimation network will bring important opportunities and challenges to college physical education in the simulation of video physical education course management. The application of optical flow estimation network is helpful to optimize students' learning experience and teaching effect, and improve the quality and effect of physical education. Colleges and universities should actively explore the innovative application of optical flow estimation network technology in the field of physical education in order to meet the needs of quality education and help students achieve better development in learning. Declarations Author contributions Dongwei Lv has contributed to the paper’s analysis, discussion, writing, and revision. Fund The authors have not disclosed any funding. Data availability The data will be available upon request. Conflict of interest The authors declare that they have no competing interests. Ethical approval Not applicable. References Jameel F, Hamid Z, Jabeen F, Zeadally S, Javed M A (2018) A survey of device-to-device communications: Research issues and challenges. IEEE Communications Surveys & Tutorials 20(3):2133-2168 Rashid A, Chaturvedi A (2019) Cloud computing characteristics and services: a brief review. International Journal of Computer Sciences and Engineering 7(2):421-426 Varghese B, Buyya R (2018) Next generation cloud computing: New trends and research directions. Future Generation Computer Systems 79:849-861 Abdel-Basset M, Mohamed M, Chang V (2018) NMCDA: A framework for evaluating cloud computing services. Future Generation Computer Systems 86:12-29 Dang L M, Piran M J, Han D, Min K, Moon H (2019) A survey on internet of things and cloud computing for healthcare. Electronics 8(7):768 Casey A, MacPhail A (2018) Adopting a models-based approach to teaching physical education. Physical Education and Sport Pedagogy 23(3):294-310 Tomlinson O W, Shelley J, Trott J, Bowhay B, Chauhan R, Sheldon C D (2020) The feasibility of online video calling to engage patients with cystic fibrosis in exercise training. Journal of telemedicine and telecare 26(6):356-364 Belt E S, Lowenthal P R (2021) Video use in online and blended courses: A qualitative synthesis. Distance Education 42(3):410-440 Baldwin S J (2019) Assimilation in online course design. American Journal of Distance Education 33(3):195-211 Siller M, Hotez E, Swanson M, Delavenne A, Hutman T, Sigman M (2018) Parent coaching increases the parents’ capacity for reflection and self-evaluation: results from a clinical trial in autism. Attachment & human development 20(3):287-308 Ali O, Shrestha A, Osmanaj V, Muhammed S (2021) Cloud computing technology adoption: an evaluation of key factors in local governments. Information Technology & People 34(2):666-703 Yoo S K, Kim B Y (2018) A decision-making model for adopting a cloud computing system. Sustainability 10(8):2952 Rimba P, Tran A B, Weber I, Staples M, Ponomarev A, Xu X (2020) Quantifying the cost of distrust: Comparing blockchain and cloud services for business process execution. Information Systems Frontiers 22:489-507 Alashhab Z R, Anbar M, Singh M M, Leau Y B, Al-Sai Z A, Alhayja’a S A (2021) Impact of coronavirus pandemic crisis on technologies and cloud computing applications. Journal of Electronic Science and Technology 19(1):100059 Wang D, Tan D, Liu L (2018) Particle swarm optimization algorithm: an overview. Soft computing 22:387-408 Wang F, Zhang H, Zhou A (2021) A particle swarm optimization algorithm for mixed-variable optimization problems. Swarm and Evolutionary Computation 60:100808 Zhang Y, Zhang Y, Zhao X, Zhang Z, Chen H (2020) Design and data analysis of sports information acquisition system based on internet of medical things. IEEE Access 8:84792-84805 Wang K, Wang X (2020) Providing sports venues on mainland China: Implications for promoting leisure-time physical activity and national fitness policies. International Journal of Environmental Research and Public Health 17(14):5136 Luong H X, Thanh T T, Tran T H (2020) Antimicrobial peptides–Advances in development of therapeutic applications. Life sciences 260:118407 Alalwan A A, Baabdullah A M, Rana N P, Tamilmani K, Dwivedi Y K (2018) Examining adoption of mobile internet in Saudi Arabia: Extending TAM with perceived enjoyment, innovativeness and trust. Technology in Society 55:100-110 Zhu C (2022) Exploring the role of sports APP in (campus fitness) intelligent solutions using data fusion algorithm and internet of things. International Journal of Grid and Utility Computing 13(1):40-48 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 02 Feb, 2024 Reviews received at journal 14 Jan, 2024 Reviewers agreed at journal 11 Jan, 2024 Reviewers invited by journal 11 Jan, 2024 Editor assigned by journal 11 Jan, 2024 Submission checks completed at journal 11 Jan, 2024 First submitted to journal 10 Jan, 2024 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-3852350","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":266634031,"identity":"88d4476d-e423-4338-bcda-7d82337586cf","order_by":0,"name":"Dongwei Lv","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA90lEQVRIiWNgGAWjYBACPgbG5gcfKmx4+Pkb238kVEjIyRPSwsbA3GY440yajOSMwwckPpyxMDZsIKiFvUGat+2QjcGBtATJmW0ViQwHCGmRSGww5mE7wGNw4IyBMe88iQTGBuaHj24Q0PJwDs8dHsnDPQbJvNsk8tgZ2IyNc/Bp4TnYYPBG4hkPH9CWw0AtxYwNPGzShLRI8Bgc5mE4kGPYzDsHaOkBQlrYGxskeRIO8wgcSEtmnNlAnBZgIB9I4wEG8jGGD8ckjA2bCfiFn5n98YOP/2zsgVHZxpBQUycnz9788DE+LVgAM2nKR8EoGAWjYBRgAQDlJk63I4udGAAAAABJRU5ErkJggg==","orcid":"","institution":"South China Agricultural University","correspondingAuthor":true,"prefix":"","firstName":"Dongwei","middleName":"","lastName":"Lv","suffix":""}],"badges":[],"createdAt":"2024-01-11 04:59:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3852350/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3852350/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":49644051,"identity":"aa29dcf4-e3a0-435f-8808-7bf2eb794967","added_by":"auto","created_at":"2024-01-15 20:11:33","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":282585,"visible":true,"origin":"","legend":"\u003cp\u003eInertia Weight Change Curve\u003c/p\u003e","description":"","filename":"1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3852350/v1/c29c97b651bafc6fef81e3bc.jpg"},{"id":49643399,"identity":"cb96f430-0822-4cd1-aa48-430f55287d0d","added_by":"auto","created_at":"2024-01-15 20:03:33","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":338644,"visible":true,"origin":"","legend":"\u003cp\u003eComparison of Three Algorithms for Different Tasks\u003c/p\u003e","description":"","filename":"2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3852350/v1/057bff772d93dc03ea68eb7a.jpg"},{"id":49643401,"identity":"63fbf163-bdc9-4a0c-a92e-ad4b486bc62b","added_by":"auto","created_at":"2024-01-15 20:03:33","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":205620,"visible":true,"origin":"","legend":"\u003cp\u003eNode Energy Consumption Values\u003c/p\u003e","description":"","filename":"3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3852350/v1/8755c9026ac78d0568a4112d.jpg"},{"id":49643404,"identity":"5ae18fab-5762-4a05-adf7-d4f151293430","added_by":"auto","created_at":"2024-01-15 20:03:34","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":272811,"visible":true,"origin":"","legend":"\u003cp\u003eTeaching process of online video sports courses\u003c/p\u003e","description":"","filename":"4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3852350/v1/ee45560372d79ad040ac184a.jpg"},{"id":49643403,"identity":"f429c9be-4537-4cde-8a2c-08f5e72be439","added_by":"auto","created_at":"2024-01-15 20:03:33","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":173461,"visible":true,"origin":"","legend":"\u003cp\u003eSchematic diagram of teaching mode design for online video sports courses\u003c/p\u003e","description":"","filename":"5.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3852350/v1/f6138d73664944995c8ea180.jpg"},{"id":49643402,"identity":"f1e3334d-db2b-49bb-afd5-0875c46c60b7","added_by":"auto","created_at":"2024-01-15 20:03:33","extension":"jpg","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":258065,"visible":true,"origin":"","legend":"\u003cp\u003eSports Online Video Learning Resource Library\u003c/p\u003e","description":"","filename":"6.jpg","url":"https://assets-eu.researchsquare.com/files/rs-3852350/v1/11c7fdc61218f092d9914ead.jpg"},{"id":49644406,"identity":"883add02-81b3-461f-a62a-e7a5903c0309","added_by":"auto","created_at":"2024-01-15 20:19:35","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":935399,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3852350/v1/ef8229d6-1189-4ed4-bc00-ba91e624598b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Application of Dynamic Image Simulation Based on Optical Sensor Networks in Optimizing the Quality of Physical Education Course Videos","fulltext":[{"header":"1 Introduction","content":"\u003cp\u003eIn recent years, with the rapid development of communication technology, communication devices have greatly improved. In computer network environments, due to the huge amount of data and the variety of request types, previous calculations cannot adapt to the current requirements (Jameel et al. 2018). Therefore, cloud technology has emerged and attracted great attention from people. Cloud computing is a new concept first proposed by Google in 2006. Cloud computing is a virtual technology based approach that aggregates massive and scattered physical resources into a vast resource pool (Rashid and Chaturvedi 2019). Based on this, it provides users with various services such as storage, networking, computing, and applications according to their specific needs. After experiencing three computing methods, cloud computing tasks abstract multiple server resources, allowing users to quickly obtain resources according to their own needs and achieve the same user experience as actual physical machines (Varghese and Buyya 2018). The development of technology has accelerated our steps towards the information age. Information education should be widely promoted, which conveys the idea of integrating information with various subject courses. More and more physical education teachers are beginning to realize the importance of applying these two technologies to physical education teaching (Casey and MacPhail 2018). However, how to perfectly combine these two technologies to form a new teaching method has never become a feasible method, and on the basis of information technology, We have also implemented online video sports courses that are closely integrated with course teaching, which can meet the learning needs of theoretical knowledge and increase students' time for practice in the classroom (Tomlinson et al. 2020). We also receive personalized guidance from teachers, which is conducive to students' deepening and consolidation of knowledge and is in line with their lifestyle and learning habits. Moreover, online video has already achieved success in other fields. This has brought new hope to our physical education teaching. The use of \"online sports video courses\" has changed the previous teaching mode, increased students' time for technical action training in physical education classrooms, effectively promoted teachers' individualized teaching, and better met students' personal development needs, which is consistent with China's talent cultivation strategy (Belt and Lowenthal 2021). In fact, exercise has always been a very important component in the healthy growth process of teenagers. Research has shown that after comprehensive consideration of students' physiological and psychological characteristics, it has been found that college students are in the most critical period in terms of physiology, psychology, cognition, morality, and emotions. During this period, students' physical development speed is the fastest, and their minds are gradually maturing (Baldwin 2019). Combined with their physiological and psychological characteristics, it can be seen that during this period, students have stronger subjectivity in external things, and their self-evaluation ability is continuously improving. They will gradually shift from dependence and passivity to autonomy and initiative, and they will develop a strong interest in new things (Siller et al. 2018).\u003c/p\u003e"},{"header":"2 Related work","content":"\u003cp\u003eThe cloud computing market size has exceeded \u003cspan\u003e$\u003c/span\u003e300\u0026nbsp;billion in 2021. Since 1950, the application of cloud computing has mainly focused on academia and military institutions. Since 1950, cloud computing technology has made significant progress, and its overall service quality has also greatly improved, bringing more choices to corporate institutions (Ali et al. 2021). So far, the development of cloud computing has been closely related to the progress of internet and business technology. Literature research shows that computers in the future can be sold as a service like electricity and water. This is a brilliant idea, but like other excellent ideas, it is ahead of that era, so in the coming decades, although this idea has attracted great attention, the corresponding technology has not caught up with it (Yoo and Kim 2018). Until 1999, Salesforce.com became an important milestone in the field of cloud computing, leading a new technology that allowed businesses to publish applications on a simple site. However, this technology was only applicable to professionals and mainstream software companies. The literature points out the introduction of a business service called EC2, which allows small organizations and individual users to rent computers in the cloud and run their computer applications on it (Rimba et al. 2020). The literature first published a cloud computing application for enterprises and collaborated with other companies to provide users with a browser-based cloud service (Alashhab et al. 2021). Next is Microsoft's Azure, which provides users with a secure and convenient service, both from Microsoft and Google. Also in 2009, with the release of the \"Alibaba Cloud\" platform, \"Alibaba Cloud\" was officially established. In addition, Huawei, Dawn, and Yunchuang Big Data are all committed to cloud related applications, driving the progress of the cloud industry. After years of development, cloud computing has formed a relatively mature business model and gradually become the main driving force behind the digital process of Chinese society. The literature proposes an improved particle swarm optimization algorithm, which utilizes microbial genetic algorithm to reduce the solution space in the initial stage and utilizes dynamic inertia weights to improve the integration accuracy of the algorithm in the later stage (Wang et al. 2018). The literature indicates that this algorithm absorbs the strong local optimization ability of the restricted search algorithm and exits the local optimal solution as soon as possible (Wang et al. 2021). In existing research, literature has proposed multi-objective optimization algorithms, which use two optimization methods, Brown and PSO, to mix the optimal solutions of the two populations, and then compare them with the original scheme to obtain the optimal solution. The literature points out that users should make online appointments for designated coaches, pay fees online, and directly enjoy services such as guidance and accompanying training (Wang and Wang 2020). The literature suggests that the development and promotion of apps should create a good business model and profit model, prioritizing the specificity of the product and the functional development of user consumption patterns, with the product itself as the starting point for profitability (Luong et al. 2020). The literature points out that with the gradual coverage of 5G networks, the mobile internet is taking up a lot of people's time, and sports fans are browsing sports information through mobile applications (Alalwan et al. 2018). However, although sports users choose the content category of the sports information application homepage, there is a significant difference between choosing the text title category and the video title category, with users choosing more text title categories. The literature suggests that a good sports user group should be established from the perspective of sports app development, and a good user group relationship should be built in the development and operation of functions (Zhu 2022). In the operation, selection, and use of sports users, sports apps may experience gatherings of \"small communities\" and \"small circles\".\u003c/p\u003e"},{"header":"3 Cloud computing","content":"\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Theoretical basis\u003c/h2\u003e \u003cp\u003eOptical flow estimation network can analyze the video sequence and estimate the trajectory of the object accurately. Through optical flow estimation network, the motion information of different objects in video is obtained, and the task scheduling algorithm is further optimized. Based on the detected motion information, the task that requires more computing resources is identified and assigned to a VM with more computing power to meet the task's computing resource requirements. Optical flow estimation networks can also be applied during video transmission to help recover motion blur and transmit lost video content. Through optical flow estimation of the video sequence, the motion of the object is accurately predicted and compensated during the video reconstruction.\u003c/p\u003e \u003cp\u003eFor users, the biggest cost when executing tasks in cloud computing is the cost of virtual machines. When executing tasks, the expenses incurred by using virtual machines are charged based on the number of pricing time units used. If there are insufficient certificate time units, an upward rounding process is required. The execution cost E\u003csub\u003ecost\u003c/sub\u003e of a set of tasks on virtual machine ve can be expressed by the following Eq.\u0026nbsp;(\u003cspan refid=\"Equ1\" class=\"InternalRef\"\u003e1\u003c/span\u003e), where TE represents the usage time of a set of tasks on virtual machine v:\u003cdiv id=\"Equ1\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ1\" name=\"EquationSource\"\u003e\n$${Ecost}_{k}=\u0026lceil;{TE}_{k}/{cet}_{k}\u0026rceil;\\times {ce}_{k}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e1\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eTherefore, the cost of the entire task set can be represented by the total cost processed by formula (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e), where C\u003csub\u003ecost\u003c/sub\u003e represents the total communication cost of the task set:\u003cdiv id=\"Equ2\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ2\" name=\"EquationSource\"\u003e\n$$\\text{C}\\text{O}\\text{S}\\text{T}=\\text{C}\\text{o}\\text{s}\\text{t}+{\\sum }_{1}^{\\text{m}}\\text{E}{\\text{c}\\text{o}\\text{s}\\text{t}}_{\\text{k}}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e2\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eThese median nodes are assigned priority based on the rank value, that is, the highest priority is given to the newly generated median node with the highest rank value, and the priority of the remaining median nodes is calculated using formula (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e). After calculating the priority of these nodes, they are added to the task list in descending order. Afterwards, this was the case until all nodes were added to the task list.\u003cdiv id=\"Equ3\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ3\" name=\"EquationSource\"\u003e\n$$\\text{P}\\text{r}\\text{i}\\text{o}\\text{r}\\text{i}\\text{t}\\text{y}\\left({\\tau }_{i}\\right)=\\underset{{\\tau }_{k}\\in {pre}\\left({\\tau }_{i}\\right)}{\\text{max}}{\\text{c}}_{\\text{k},\\text{i}}+{\\stackrel{-}{\\text{w}}}_{\\text{i}}+\\underset{{\\tau }_{j}\\in pre\\left({\\tau }_{i}\\right)}{\\text{m}\\text{a}\\text{x}}{\\text{c}}_{\\text{i},\\text{j}}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e3\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eThe article points out a new algorithm that can ensure both the execution cost of the task itself and the information transmission cost between tasks. This algorithm takes the sum of the longest communication cost from the current node to the previous node, the average execution cost of the task itself, and the longest communication cost from the current node to the next node as the final task priority. Traverse all virtual machines, select the virtual machine MV (zi) with the lowest cost based on the calculated execution cost and data transmission cost (zi, vk) of task zi in the virtual machine, and assign tasks to it. Cost (zi, vk) only represents the cost caused by the execution and data transmission of a single task in a virtual machine, while the total cost of cloud resources for a task set is determined based on the occupation time and data transmission of the task set on each virtual machine. Due to idle time, the total cost of cloud resources in a task set cannot be simply accumulated by the total cost of each task.\u003cdiv id=\"Equ4\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ4\" name=\"EquationSource\"\u003e\n$$\\text{C}\\text{o}\\text{s}\\text{t}({\\tau }_{i},{v}_{k})=\u0026lceil;\\text{w}({\\tau }_{i},{v}_{k})/{\\text{c}\\text{e}\\text{t}}_{\\text{k}}\u0026rceil;\\times {\\text{c}\\text{e}}_{\\text{k}}+\u0026lceil;{\\text{T}\\text{C}}_{{\\tau }_{i},{v}_{k}}/\\text{c}\\text{c}\\text{t}\u0026rceil;\\times \\text{c}\\text{c}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e4\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eUpdate the cumulative lease time of z in virtual machine EV (zi).\u003cdiv id=\"Equ5\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ5\" name=\"EquationSource\"\u003e\n$${VT}_{min-cost}\\left(EV\\right({\\tau }_{i}\\left)\\right)=EST({\\tau }_{i},MV({\\tau }_{i}\\left)\\right)+w({\\tau }_{i},MV({\\tau }_{i}\\left)\\right)$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e5\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eIf an appropriate interval task is not selected for addition, but for the sake of earlier actual completion time, update the cumulative lease time in EV (zi) according to the formula, where AFT (zi) is the actual completion time of the task in the formula\u003cdiv id=\"Equ6\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ6\" name=\"EquationSource\"\u003e\n$${VT}_{insert}\\left(EV\\right({\\tau }_{i}\\left)\\right)=AFT\\left({\\tau }_{i}\\right)=\\underset{k}{\\text{min}}\\left\\{EST\\right({\\tau }_{i},{v}_{k})+w({\\tau }_{i},{v}_{k}\\left)\\right\\}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e6\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eAutoregressive models are common models used to predict time series, in which the time value of t is linked to its historical value and separated from the prediction error of t-i. This system is called an automatic regression model. The model containing the following structure is called a P-level regression model, as detailed below.\u003cdiv id=\"Equ7\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ7\" name=\"EquationSource\"\u003e\n$${X}_{t}={\\phi }_{0}+\\sum _{i=1}^{p}{\\phi }_{i}*{X}_{t-1}+{\\epsilon }_{t}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e7\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eThe grey system theory applies a method of generating behavioral characteristic data of the system, which can achieve higher prediction accuracy for data with changes limited to a certain range. GM (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) has certain applicability in various modes and can predict periodic and non periodic sequences.\u003c/p\u003e \u003cp\u003eThe formula for determining the parameters is as follows:\u003cdiv id=\"Equ8\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ8\" name=\"EquationSource\"\u003e\n$$\\text{Y}={[{\\text{x}}_{2}^{\\left(0\\right)},{\\text{x}}_{3}^{\\left(0\\right)},...,{\\text{x}}_{\\text{n}}^{\\left(0\\right)}]}^{\\text{T}}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e8\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eThe formula for predicting finite Boltzmann machines using differential equations is as follows:\u003cdiv id=\"Equ9\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ9\" name=\"EquationSource\"\u003e\n$$\\text{E}(\\text{v},\\text{h})=-\\sum _{\\text{i}=1}^{\\text{p}}\\sum _{\\text{j}=1}^{\\text{q}}{\\text{v}}_{\\text{i}}{\\text{w}}_{\\text{i},\\text{j}}{\\text{h}}_{\\text{j}}-\\sum _{\\text{i}=1}^{\\text{p}}{\\text{a}}_{\\text{i}}{\\text{v}}_{\\text{i}}-\\sum _{\\text{j}=1}^{\\text{q}}{\\text{b}}_{\\text{j}}{\\text{h}}_{\\text{j}}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e9\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eEquation (\u003cspan refid=\"Equ10\" class=\"InternalRef\"\u003e10\u003c/span\u003e) is the calculation formula for calculating unit 1 from the visible state, Eq.\u0026nbsp;(11) is the calculation formula for reconstructing hidden layer unit 1 from the hidden layer state, and Eq.\u0026nbsp;(11) is the calculation formula for reconstructing hidden layer unit 1 from the reconstructed visible layer state.\u003cdiv id=\"Equ10\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ10\" name=\"EquationSource\"\u003e\n$$\\text{p}({\\text{h}}_{\\text{j}}^{\\left(0\\right)}=1\\left|{\\text{v}}^{\\left(0\\right)}\\right.)=\\frac{1}{1+\\text{e}\\text{x}\\text{p}(-\\sum _{\\text{i}=1}^{\\text{P}}{v}_{i}^{t+1}{\\text{x}}_{\\text{i},\\text{j}}-{\\text{b}}_{\\text{j}})}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e10\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Experimental Testing\u003c/h2\u003e \u003cp\u003eAs shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, from the initial 1.4 to the final 0.4, there is a trend of slowing down. The larger the weight of the algorithm, the more suitable it is for global optimization. If the inertia weight becomes smaller, then the advantage of slow reduction is more conducive to local optimization and ensures the accuracy of local search.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e shows the comparison of the completion time of tasks with different numbers of tasks in three different methods. This method can effectively solve the problem of low convergence rate in traditional particle swarm optimization algorithm processing tasks, thereby increasing the efficiency of cloud computing. At the same time, it can still maintain a relatively optimal scheduling effect while maintaining good robustness despite the continuous increase in processing task volume.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the consumption situation of each node. The energy consumption of node 1 is 683, and the energy consumption of node 3 is 875. 2 is 432, and node 4 is 234. When the energy exceeds the upper limit, node 1 randomly predicts that it will migrate to node 2 in advance, causing an increase in node 2. Node 1 remains below the threshold, while node 3 is above the threshold, resulting in a \"hot spot\" phenomenon. Node 1 remains below the threshold, while node 3 exceeds the energy consumption threshold, and node 3 exhibits a \"hot spot\" phenomenon. Based on the above analysis, we propose that it can solve the problem of servers. As shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, when the number of consecutive predictions is 3, the accuracy of predicting 100 and 1000 times is 100%. However, if the number of consecutive predictions is 4 or 5, the accuracy of prediction will gradually decrease. Due to the longer the prediction time, the smaller the impact. If the error exceeds the set value, the prediction will become invalid. Correspondingly, the number of consecutive predictions can be set to 3. As shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\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\u003eNumber of Correct Predictions\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" 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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003enumber of times\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e100\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e100%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e99.9%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e98.89%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e100%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e99.97%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e99.95%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"4 Online video sports course management","content":"\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\n\u003ch2\u003e4.1 Design of online video sports course system\u003c/h2\u003e\n\u003cp\u003eDrawing on a certain school as the experimental object and following the idea of leading learning cases, in the design of physical education courses, the teaching mode based on online video physical education courses has added a guarantee system of \"guiding, helping, and promoting learning\". Fully integrate the tutorial concept to avoid the problem of unclear prioritization of key and difficult points in the pre class autonomous learning process. Design the teaching process as shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e:\u003c/p\u003e\n\u003cp\u003eIn the classroom, the teacher arranges the teaching content reasonably based on their actual situation, and in the classroom, allows students to demonstrate the technical actions before class. After the students' demonstration, the teachers gave accurate evaluations. At this stage, the students' focus is the highest because they are learning new things and full of freshness. Secondly, because students have a strong sense of self-esteem, they want to show their best in front of their teachers and classmates. Therefore, teachers can point out their mistakes and provide correct demonstrations at this time, which will greatly help improve their skills and skills. Afterwards, the teacher will also focus on explaining and demonstrating slightly complex action techniques. The teacher then organizes students to carry out the next learning activities, allowing them to practice and correct their mistakes on their own, while the teacher guides them on the side. After the student activity is completed, holding several more competitions can liven up the class atmosphere; Secondly, teachers can assess students and provide necessary rewards and punishments.\u003c/p\u003e\n\u003cp\u003eOnline teaching experience. Optical flow estimation network can estimate the motion trajectory and speed of objects in video by analyzing the motion of pixels between successive frames. In video physical education lessons, this technology can be used to track subtle changes in student movement and posture, allowing for more accurate assessment and monitoring of student athletic performance. Through the optical flow estimation network, teachers can observe and analyze videos of physical education homework completed by students at home in real time. Through the visualization of movement trajectories, teachers can identify the problems that students may have in movement and the room for improvement, and give targeted guidance and suggestions in time. For example, if a student's step in a long jump is unsteady, the optical flow estimation network can help the teacher determine if the student needs to strengthen the balance and coordination of the leg movements. In addition to teacher supervision, parents can also evaluate and supervise the completion of students' homework through the optical flow estimation network. By observing the movement track in the video, parents can judge whether the student has completed the task in accordance with the correct posture and movement, and give recognition or correction in time. Students themselves can also improve their technique and enhance their self-evaluation ability by observing their own movement trajectories. By comparing their movement trajectories with standard postures, students can find their mistakes and shortcomings and try to correct them. The optical flow estimation network can be a powerful tool for students to train and adjust themselves and help them improve their technical level.\u003c/p\u003e\n\u003cp\u003eIn teaching, students actively improve their technical skills under the guidance of the teacher, practice continuously, and reach proficiency; In the post class transition stage, what needs to be done is to further strengthen the proficiency and automation level of the movements, achieve a seamless completion of the movements, and the movements should be in line with the standards. The main job content is to assign homework for college physical education. Under the supervision of parents and random sampling by teachers, it is necessary to supervise and urge students to complete them in a timely manner, and consolidate their movement skills, as shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e:\u003c/p\u003e\n\u003cp\u003eThe important source of intelligent teaching and online video sports learning is the sports learning resource library. It is necessary to classify and organize sports project technology micro lesson videos, health and nutrition PPTs, sports physiology and biochemistry, etc., and put them into storage. Guided by daily applications, it integrates the integrated design and implementation of high-quality sports courses from multiple channels of the Internet of Things around every link of sports courses and teaching, Build a network platform for the integrated development of physical education curriculum teaching both inside and outside the classroom, and ultimately build a shared curriculum content system that is consistent with national standards and adapted to the actual teaching situation.\u003c/p\u003e\n\u003cp\u003eAttract institutions such as social initiatives and e-learning to participate in the construction of various public sports courses. Integrate the existing physical education curriculum resources of platforms such as online open courses and Sina open courses into the open resource library. As shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e.\u003c/p\u003e\n\u003cp\u003eSports learning environment perception online video sports tools should be able to provide timely feedback on the sports learning and exercise environment conditions where college students are located, such as the temperature of sports venues, saturation of exercise participants, air quality, and location information.\u003c/p\u003e\n\u003cp\u003eThe main body of physical education learning in sports learning community connected universities is college students, and the activities they participate in, such as physical education learning and exercise, all exist in virtual or real learning communities. In addition, smart technologies such as mobile media can maintain close contact with the learning community, allowing for interaction and communication at any time. For example, participating in physical education classes includes selective classes and WeChat classes; For example, the community in which they exercise is a group of like-minded classmates or friends who frequently participate in club activities, as well as a WeChat group for club activities.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\n\u003ch2\u003e4.2 Online Video Sports Course System Testing\u003c/h2\u003e\n\u003cp\u003eA survey was conducted on the emotional attitudes of 76 students towards using online video competitive teaching systems. The results showed that compared to other online platforms, students are more inclined to use online video competitive teaching systems. It can be seen that this article meets the students' wishes.\u003c/p\u003e\n\u003cp\u003eA survey on the emotional attitudes of three teachers who use online video sports teaching systems shows that compared to other online platforms, teachers prefer to use online video sports teaching systems, which is in line with students' wishes.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"5 Conclusion","content":"\u003cp\u003eThrough the application of optical flow estimation network, more accurate motion tracking and posture recognition can be realized, and personalized movement guidance and feedback can be provided for students. Optical flow estimation network can realize real-time analysis and evaluation of physical movements, help teachers better understand students' performance, and carry out effective teaching guidance. Video transmission optimization through optical flow estimation network can improve the efficiency and stability of video transmission and provide better learning experience for students. However, in order to give full play to the advantages of video transmission technology based on optical flow estimation network, universities need to strengthen the research and application of related technologies. The establishment of sound research teams and laboratories and the training of teachers with knowledge and skills in the application of optical flow estimation networks are all important steps. Colleges and universities also need to pay attention to students' physical and mental health and all-round development, pay attention to cultivating students' health awareness and healthy habits, and provide students with broad development space and diversified physical exercise methods. In practice, colleges and universities should pay attention to the in-depth implementation of teaching reform, attach importance to students' subjectivity in teaching activities, and give full play to students' initiative and creativity. Colleges and universities need to balance the focus of teaching development, take the improvement of students' skills, active participation, healthy development of body and mind and strengthening individual social adaptability as the basic goals, and comprehensively promote the implementation of teaching reform. Therefore, the video transmission technology based on optical flow estimation network will bring important opportunities and challenges to college physical education in the simulation of video physical education course management. The application of optical flow estimation network is helpful to optimize students' learning experience and teaching effect, and improve the quality and effect of physical education. Colleges and universities should actively explore the innovative application of optical flow estimation network technology in the field of physical education in order to meet the needs of quality education and help students achieve better development in learning.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eDongwei Lv has contributed to the paper\u0026rsquo;s analysis, discussion, writing, and revision.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFund\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors have not disclosed any funding.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data will be available upon request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n \u003cli\u003eJameel F, Hamid Z, Jabeen F, Zeadally S, Javed M A (2018) A survey of device-to-device communications: Research issues and challenges. IEEE Communications Surveys \u0026amp; Tutorials 20(3):2133-2168\u003c/li\u003e\n \u003cli\u003eRashid A, Chaturvedi A (2019) Cloud computing characteristics and services: a brief review. International Journal of Computer Sciences and Engineering 7(2):421-426\u003c/li\u003e\n \u003cli\u003eVarghese B, Buyya R (2018) Next generation cloud computing: New trends and research directions. Future Generation Computer Systems 79:849-861\u003c/li\u003e\n \u003cli\u003eAbdel-Basset M, Mohamed M, Chang V (2018) NMCDA: A framework for evaluating cloud computing services. Future Generation Computer Systems 86:12-29\u003c/li\u003e\n \u003cli\u003eDang L M, Piran M J, Han D, Min K, Moon H (2019) A survey on internet of things and cloud computing for healthcare. Electronics 8(7):768\u003c/li\u003e\n \u003cli\u003eCasey A, MacPhail A (2018) Adopting a models-based approach to teaching physical education. Physical Education and Sport Pedagogy 23(3):294-310\u003c/li\u003e\n \u003cli\u003eTomlinson O W, Shelley J, Trott J, Bowhay B, Chauhan R, Sheldon C D (2020) The feasibility of online video calling to engage patients with cystic fibrosis in exercise training. Journal of telemedicine and telecare 26(6):356-364\u003c/li\u003e\n \u003cli\u003eBelt E S, Lowenthal P R (2021) Video use in online and blended courses: A qualitative synthesis. Distance Education 42(3):410-440\u003c/li\u003e\n \u003cli\u003eBaldwin S J (2019) Assimilation in online course design. American Journal of Distance Education 33(3):195-211\u003c/li\u003e\n \u003cli\u003eSiller M, Hotez E, Swanson M, Delavenne A, Hutman T, Sigman M (2018) Parent coaching increases the parents\u0026rsquo; capacity for reflection and self-evaluation: results from a clinical trial in autism. Attachment \u0026amp; human development 20(3):287-308\u003c/li\u003e\n \u003cli\u003eAli O, Shrestha A, Osmanaj V, Muhammed S (2021) Cloud computing technology adoption: an evaluation of key factors in local governments. Information Technology \u0026amp; People 34(2):666-703\u003c/li\u003e\n \u003cli\u003eYoo S K, Kim B Y (2018) A decision-making model for adopting a cloud computing system. Sustainability 10(8):2952\u003c/li\u003e\n \u003cli\u003eRimba P, Tran A B, Weber I, Staples M, Ponomarev A, Xu X (2020) Quantifying the cost of distrust: Comparing blockchain and cloud services for business process execution. Information Systems Frontiers 22:489-507\u003c/li\u003e\n \u003cli\u003eAlashhab Z R, Anbar M, Singh M M, Leau Y B, Al-Sai Z A, Alhayja\u0026rsquo;a S A (2021) Impact of coronavirus pandemic crisis on technologies and cloud computing applications. Journal of Electronic Science and Technology 19(1):100059\u003c/li\u003e\n \u003cli\u003eWang D, Tan D, Liu L (2018) Particle swarm optimization algorithm: an overview. Soft computing 22:387-408\u003c/li\u003e\n \u003cli\u003eWang F, Zhang H, Zhou A (2021) A particle swarm optimization algorithm for mixed-variable optimization problems. Swarm and Evolutionary Computation 60:100808\u003c/li\u003e\n \u003cli\u003eZhang Y, Zhang Y, Zhao X, Zhang Z, Chen H (2020) Design and data analysis of sports information acquisition system based on internet of medical things. IEEE Access 8:84792-84805\u003c/li\u003e\n \u003cli\u003eWang K, Wang X (2020) Providing sports venues on mainland China: Implications for promoting leisure-time physical activity and national fitness policies. International Journal of Environmental Research and Public Health 17(14):5136\u003c/li\u003e\n \u003cli\u003eLuong H X, Thanh T T, Tran T H (2020) Antimicrobial peptides\u0026ndash;Advances in development of therapeutic applications. Life sciences 260:118407\u003c/li\u003e\n \u003cli\u003eAlalwan A A, Baabdullah A M, Rana N P, Tamilmani K, Dwivedi Y K (2018) Examining adoption of mobile internet in Saudi Arabia: Extending TAM with perceived enjoyment, innovativeness and trust. Technology in Society 55:100-110\u003c/li\u003e\n \u003cli\u003eZhu C (2022) Exploring the role of sports APP in (campus fitness) intelligent solutions using data fusion algorithm and internet of things. International Journal of Grid and Utility Computing 13(1):40-48\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"optical-and-quantum-electronics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"oqel","sideBox":"Learn more about [Optical and Quantum Electronics](https://www.springer.com/journal/11082)","snPcode":"11082","submissionUrl":"https://submission.nature.com/new-submission/11082/3","title":"Optical and Quantum Electronics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"optical flow estimation network, Video transmission technology, Video teaching, Physical education curriculum management","lastPublishedDoi":"10.21203/rs.3.rs-3852350/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3852350/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWith the development of video physical education course management simulation, in order to improve the quality of video transmission, this study proposes a video transmission technology based on optical flow estimation network. Firstly, an optical flow estimation network model is established, which can automatically extract optical flow information from input video and estimate object motion by analyzing pixel displacement between successive images. Then, according to the optical flow information, the video frame is repaired and compensated to reduce the information loss and quality degradation in video transmission. The experimental results show that the video transmission technology based on optical flow estimation network can significantly improve the quality and stability of video. Compared with the traditional video transmission method, this technology has better adaptability and robustness in the case of low network bandwidth or network congestion, and provides high quality and stable video transmission, which provides strong support for the application of distance education and sports course management simulation.\u003c/p\u003e","manuscriptTitle":"Application of Dynamic Image Simulation Based on Optical Sensor Networks in Optimizing the Quality of Physical Education Course Videos","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-15 20:03:29","doi":"10.21203/rs.3.rs-3852350/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-02-02T12:54:48+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-01-15T03:18:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"ebb61725-e5c0-42db-869d-745441f0230b","date":"2024-01-11T21:17:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-11T12:08:28+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-01-11T12:06:54+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-01-11T11:43:50+00:00","index":"","fulltext":""},{"type":"submitted","content":"Optical and Quantum Electronics","date":"2024-01-11T04:57:19+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"optical-and-quantum-electronics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"oqel","sideBox":"Learn more about [Optical and Quantum Electronics](https://www.springer.com/journal/11082)","snPcode":"11082","submissionUrl":"https://submission.nature.com/new-submission/11082/3","title":"Optical and Quantum Electronics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"88e39763-448f-4a23-ac1a-9b70e1240271","owner":[],"postedDate":"January 15th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-02-08T00:17:05+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-15 20:03:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3852350","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3852350","identity":"rs-3852350","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}