{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T01:06:50Z","timestamp":1711588010364},"reference-count":52,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:00:00Z","timestamp":1711497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the ICT R&D program of MSICT\/IITP","award":["2022-0-00862"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"Video surveillance systems are integral to bolstering safety and security across multiple settings. With the advent of deep learning (DL), a specialization within machine learning (ML), these systems have been significantly augmented to facilitate DL-based video surveillance services with notable precision. Nevertheless, DL-based video surveillance services, which necessitate the tracking of object movement and motion tracking (e.g., to identify unusual object behaviors), can demand a significant portion of computational and memory resources. This includes utilizing GPU computing power for model inference and allocating GPU memory for model loading. To tackle the computational demands inherent in DL-based video surveillance, this study introduces a novel video surveillance management system designed to optimize operational efficiency. At its core, the system is built on a two-tiered edge computing architecture (i.e., client and server through socket transmission). In this architecture, the primary edge (i.e., client side) handles the initial processing tasks, such as object detection, and is connected via a Universal Serial Bus (USB) cable to the Closed-Circuit Television (CCTV) camera, directly at the source of the video feed. This immediate processing reduces the latency of data transfer by detecting objects in real time. Meanwhile, the secondary edge (i.e., server side) plays a vital role by hosting a dynamically controlling threshold module targeted at releasing DL-based models, reducing needless GPU usage. This module is a novel addition that dynamically adjusts the threshold time value required to release DL models. By dynamically optimizing this threshold, the system can effectively manage GPU usage, ensuring resources are allocated efficiently. Moreover, we utilize federated learning (FL) to streamline the training of a Long Short-Term Memory (LSTM) network for predicting imminent object appearances by amalgamating data from diverse camera sources while ensuring data privacy and optimized resource allocation. Furthermore, in contrast to the static threshold values or moving average techniques used in previous approaches for the controlling threshold module, we employ a Deep Q-Network (DQN) methodology to manage threshold values dynamically. This approach efficiently balances the trade-off between GPU memory conservation and the reloading latency of the DL model, which is enabled by incorporating LSTM-derived predictions as inputs to determine the optimal timing for releasing the DL model. The results highlight the potential of our approach to significantly improve the efficiency and effective usage of computational resources in video surveillance systems, opening the door to enhanced security in various domains.<\/jats:p>","DOI":"10.3390\/s24072158","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T17:39:56Z","timestamp":1711561196000},"page":"2158","source":"Crossref","is-referenced-by-count":0,"title":["Deep Reinforcement Learning-Empowered Cost-Effective Federated Video Surveillance Management Framework"],"prefix":"10.3390","volume":"24","author":[{"given":"Dilshod","family":"Bazarov Ravshan Ugli","sequence":"first","affiliation":[{"name":"Department of Computing, Gachon University, Seongnam-si 13120, Republic of Korea"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3709-2933","authenticated-orcid":false,"given":"Alaelddin F. Y.","family":"Mohammed","sequence":"additional","affiliation":[{"name":"Department of International Studies, Dongshin University, 67, Dongshindae-gil, Naju-si 58245, Republic of Korea"}]},{"given":"Taeheum","family":"Na","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI), Yuseong-gu, Daejeon 34129, Republic of Korea"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1102-3905","authenticated-orcid":false,"given":"Joohyung","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computing, Gachon University, Seongnam-si 13120, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Gajjar, V., Gurnani, A., and Khandhediya, Y. (2017, January 22\u201329). Human detection and tracking for video surveillance: A cognitive science approach. Proceedings of the IEEE International Conference on Computer Vision Workshops, Venice, Italy.","DOI":"10.1109\/ICCVW.2017.330"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A fast learning algorithm for deep belief nets","volume":"18","author":"Hinton","year":"2006","journal-title":"Neural Comput."},{"key":"ref_3","unstructured":"Neural Network (2023, September 20). Neural Network. Available online: https:\/\/www.sciencedirect.com\/topics\/mathematics\/neural-network."},{"key":"ref_4","unstructured":"Nagrath, P., Thakur, N., Jain, R., Saini, D., Sharma, N., and Hemanth, J. (2022). IoT for Sustainable Smart Cities and Society, Springer."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zeng, Q. (2023, January 28\u201330). Design and Implementation of Horse Riding Action Monitoring Platform Based on Deep Learning. Proceedings of the 2023 IEEE International Conference on Control, Electronics and Computer Technology (ICCECT), Jilin, China.","DOI":"10.1109\/ICCECT57938.2023.10140852"},{"key":"ref_6","unstructured":"Cao, Z., Hidalgo Martinez, G., Simon, T., Wei, S., and Sheikh, Y.A. (2019). IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hu, Q., Sun, P., Yan, S., Wen, Y., and Zhang, T. (2021, January 14\u201319). Characterization and prediction of deep learning workloads in large-scale gpu datacenters. Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, St. Louis, MI, USA.","DOI":"10.1145\/3458817.3476223"},{"key":"ref_8","unstructured":"Gao, W., Hu, Q., Ye, Z., Sun, P., Wang, X., Luo, Y., Zhang, T., and Wen, Y. (2022). Deep learning workload scheduling in gpu datacenters: Taxonomy, challenges and vision. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e7108","DOI":"10.1002\/cpe.7108","article-title":"KubeSC-RTP: Smart scheduler for Kubernetes platform on CPU-GPU heterogeneous systems","volume":"34","author":"Harichane","year":"2022","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"ref_10","unstructured":"Berral, J.L., Wang, C., and Youssef, A. (2020, January 13). {AI4DL }: Mining Behaviors of Deep Learning Workloads for Resource Management. Proceedings of the 12th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 20), Boston, MA, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kim, J., Lee, J., and Kim, T. (2021). AdaMM: Adaptive Object Movement and Motion Tracking in Hierarchical Edge Computing System. Sensors, 21.","DOI":"10.3390\/s21124089"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ugli, D.B.R., Kim, J., Mohammed, A.F., and Lee, J. (2023). Cognitive Video Surveillance Management in Hierarchical Edge Computing System with Long Short-Term Memory Model. Sensors, 23.","DOI":"10.3390\/s23052869"},{"key":"ref_13","first-page":"1","article-title":"A first look into the carbon footprint of federated learning","volume":"24","author":"Qiu","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"108044","DOI":"10.1016\/j.compchemeng.2022.108044","article-title":"Machine learning-based run-to-run control of a spatial thermal atomic layer etching reactor","volume":"168","author":"Tom","year":"2022","journal-title":"Comput. Chem. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Asad, M., Moustafa, A., and Ito, T. (2021). Federated learning versus classical machine learning: A convergence comparison. arXiv.","DOI":"10.22541\/au.162074596.66890690\/v1"},{"key":"ref_16","first-page":"374","article-title":"Towards federated learning at scale: System design","volume":"1","author":"Bonawitz","year":"2019","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"129965","DOI":"10.1109\/ACCESS.2021.3113824","article-title":"A pose estimation-based fall detection methodology using artificial intelligence edge computing","volume":"9","author":"Chang","year":"2021","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"68482","DOI":"10.1109\/ACCESS.2021.3077499","article-title":"A surveillance video real-time analysis system based on edge-cloud and fl-yolo cooperation in coal mine","volume":"9","author":"Xu","year":"2021","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3195","DOI":"10.1007\/s12652-021-03157-1","article-title":"IoT-based smart healthcare video surveillance system using edge computing","volume":"13","author":"Rajavel","year":"2022","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"160607","DOI":"10.1109\/ACCESS.2021.3131396","article-title":"Low latency deep learning inference model for distributed intelligent IoT edge clusters","volume":"9","author":"Naveen","year":"2021","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e4648","DOI":"10.1002\/ett.4648","article-title":"Memory optimization at Edge for Distributed Convolution Neural Network","volume":"33","author":"Naveen","year":"2022","journal-title":"Trans. Emerg. Telecommun. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"35119","DOI":"10.1007\/s11042-019-08067-1","article-title":"UAV based cost-effective real-time abnormal event detection using edge computing","volume":"78","author":"Alam","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref_24","first-page":"205","article-title":"Visual object detection and tracking using analytical learning approach of validity level","volume":"25","author":"Lee","year":"2019","journal-title":"Intell. Autom. Soft Comput."},{"key":"ref_25","unstructured":"Farahdel, A. (2022). TinySurveillance: A Low-Power Event-Based Surveillance Method for Unmanned Aerial Vehicles. [Ph.D. Thesis, University of Saskatchewan]."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Khan, S.W., Hafeez, Q., Khalid, M.I., Alroobaea, R., Hussain, S., Iqbal, J., Almotiri, J., and Ullah, S.S. (2022). Anomaly detection in traffic surveillance videos using deep learning. Sensors, 22.","DOI":"10.3390\/s22176563"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Noghre, G.A. (2023, January 26\u201330). Privacy-preserving Real-world Video Anomaly Detection. Proceedings of the 2023 IEEE International Conference on Smart Computing (SMARTCOMP), Nashville, TN, USA.","DOI":"10.1109\/SMARTCOMP58114.2023.00067"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"3454167","DOI":"10.1155\/2022\/3454167","article-title":"Vision transformer and deep sequence learning for human activity recognition in surveillance videos","volume":"2022","author":"Hussain","year":"2022","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_29","unstructured":"Noghre, G.A., Pazho, A.D., Katariya, V., and Tabkhi, H. (2023). Understanding the challenges and opportunities of pose-based anomaly detection. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s43762-023-00097-8","article-title":"Understanding Policy and Technical Aspects of AI-Enabled Smart Video Surveillance to Address Public Safety","volume":"3","author":"Ardabili","year":"2023","journal-title":"Comput. Urban Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"14940","DOI":"10.1109\/JIOT.2023.3263725","article-title":"Ancilia: Scalable intelligent video surveillance for the artificial intelligence of things","volume":"10","author":"Pazho","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"288","DOI":"10.26599\/BDMA.2019.9020007","article-title":"Clinical big data and deep learning: Applications, challenges, and future outlooks","volume":"2","author":"Yu","year":"2019","journal-title":"Big Data Min. Anal."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_35","unstructured":"Ammad-Ud-Din, M., Ivannikova, E., Khan, S.A., Oyomno, W., Fu, Q., Tan, K.E., and Flanagan, A. (2019). Federated collaborative filtering for privacy-preserving personalized recommendation system. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Long, G., Tan, Y., Jiang, J., and Zhang, C. (2020). Federated Learning: Privacy and Incentive, Springer.","DOI":"10.1007\/978-3-030-63076-8_17"},{"key":"ref_37","unstructured":"Roy, A.G., Siddiqui, S., P\u00f6lsterl, S., Navab, N., and Wachinger, C. (2019). Braintorrent: A peer-to-peer environment for decentralized federated learning. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Huang, L., Shea, A.L., Qian, H., Masurkar, A., Deng, H., and Liu, D. (2019). Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records. J. Biomed. Inform., 99.","DOI":"10.1016\/j.jbi.2019.103291"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ Digit. Med."},{"key":"ref_40","unstructured":"Hard, A., Rao, K., Mathews, R., Ramaswamy, S., Beaufays, F., Augenstein, S., Eichner, H., Kiddon, C., and Ramage, D. (2018). Federated learning for mobile keyboard prediction. arXiv."},{"key":"ref_41","unstructured":"Sada, A.B., Bouras, M.A., Ma, J., Runhe, H., and Ning, H. (2019, January 5\u20138). A distributed video analytics architecture based on edge-computing and federated learning. Proceedings of the 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC\/PiCom\/CBDCom\/CyberSciTech), Fukuoka, Japan."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Escobar-Naranjo, J., Caiza, G., Ayala, P., Jordan, E., Garcia, C.A., and Garcia, M.V. (2023). Autonomous Navigation of Robots: Optimization with DQN. Appl. Sci., 13.","DOI":"10.3390\/app13127202"},{"key":"ref_43","unstructured":"YOLOv8 ultralytics (2023, October 01). YOLOv8 ultralytics. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"5481","DOI":"10.5194\/gmd-15-5481-2022","article-title":"Root-mean-square error (RMSE) or mean absolute error (MAE): When to use them or not","volume":"15","author":"Hodson","year":"2022","journal-title":"Geosci. Model Dev."},{"key":"ref_45","unstructured":"Root-Mean-Squared Error, Keras Metrics (2023, October 01). Root-Mean-Squared Error, Keras Metrics. Available online: https:\/\/www.tensorflow.org\/api_docs\/python\/tf\/keras\/metrics\/."},{"key":"ref_46","unstructured":"Shi, J., Jain, M., and Narasimhan, G. (2022). Time series forecasting (tsf) using various deep learning models. arXiv."},{"key":"ref_47","unstructured":"Time Series Forecasting (2023, October 01). Time Series Forecasting with Tensorflow. Available online: https:\/\/www.tensorflow.org\/tutorials\/structured_data\/time_series."},{"key":"ref_48","unstructured":"Tokyo\u2014Shinjuku Kabukicho Live Cam (2023, August 05). Tokyo\u2014Shinjuku Kabukicho Live Cam. Available online: https:\/\/www.youtube.com\/@kabukicho-1."},{"key":"ref_49","unstructured":"USA\u2014Downtown Laramie Live cam (2023, August 05). Laramie\u2014Downtown Laramie Live Cam. Available online: https:\/\/www.youtube.com\/watch?v=gicEyI_T8Hk."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Xiao, X., and Feng, X. (2023). Multi-object pedestrian tracking using improved YOLOv8 and OC-SORT. Sensors, 23.","DOI":"10.3390\/s23208439"},{"key":"ref_51","unstructured":"NVIDIA TensorRT (2023, December 05). TensorRT Open Source Software. Available online: https:\/\/developer.nvidia.com\/tensorrt."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Tang, Y., and Qian, Y. (2024). High-speed railway track components inspection framework based on YOLOv8 with high-performance model deployment. High-Speed Railw., in press.","DOI":"10.1016\/j.hspr.2024.02.001"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/7\/2158\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T18:01:29Z","timestamp":1711562489000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/7\/2158"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,27]]},"references-count":52,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["s24072158"],"URL":"https:\/\/doi.org\/10.3390\/s24072158","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,27]]}}}