Innovative Edge Computing for Real-Time Video Surveillance and Taekwondo Training Enhancement
The constantly growing volume of data created globally makes it impossible for the centralised cloud computing method to provide low-latency, high-efficiency surveillance camera services. In order to alleviate transmission pressure, the load on the main cloud server, and the end to end latency of th...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek
2025-01-01
|
| Series: | Tehnički Vjesnik |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/471015 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846099351364960256 |
|---|---|
| author | Nithya S. Samaya Pillai Iyengar Poobalan A. Parameswari A. |
| author_facet | Nithya S. Samaya Pillai Iyengar Poobalan A. Parameswari A. |
| author_sort | Nithya S. |
| collection | DOAJ |
| description | The constantly growing volume of data created globally makes it impossible for the centralised cloud computing method to provide low-latency, high-efficiency surveillance camera services. In order to alleviate transmission pressure, the load on the main cloud server, and the end to end latency of the video surveillance system, a distributed computing architecture is developed that immediately analyzes peripheral video data. By lowering the probability of tracker drift or malfunction in the videos, the suggested Enhanced Multiple Instance Learning with Whale Optimization Technique (EMIL-WOM) enables the classifier to extract the features with lower computing costs and shorter computation times. For various scenarios, the optimised neural network generates computation models, which are then logically placed in edge devices. The level of Taekwondo is chosen to address the uneven teaching quality for the goal of real-time analysis as society develops. To solve the teaching challenges in the Taekwondo learning process and improve the calibre of Taekwondo, the researcher conducted particular study in relation to the tactile learning theory. This research uses scientific and technological resources as a guide to assess technical actions and strategies and apply them to specific educational experiments for testing. This work analyses and recommends a way for making innovative services based on the edge computing paradigm. This experimental technique eliminates several interoperability and service scalability issues with conventional design. The suggested EMIL-WOM achieves 96.5% accuracy, 56.1% computational complexity, 32.4% RMSE, 24.1% RAE, 30% MAE, and 45.3 seconds of response time when compared to existing approaches. |
| format | Article |
| id | doaj-art-a532838a9f4f4ed79881e74e5c7ee73b |
| institution | Kabale University |
| issn | 1330-3651 1848-6339 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek |
| record_format | Article |
| series | Tehnički Vjesnik |
| spelling | doaj-art-a532838a9f4f4ed79881e74e5c7ee73b2024-12-31T15:44:22ZengFaculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in OsijekTehnički Vjesnik1330-36511848-63392025-01-0132191610.17559/TV-20240506001521Innovative Edge Computing for Real-Time Video Surveillance and Taekwondo Training EnhancementNithya S.0Samaya Pillai Iyengar1Poobalan A.2Parameswari A.3Department of Information Technology, PSNA College of Engineering and Technology (Autonomous), Dindigul-624622Symbiosis Institute of Digital and Telecom Management, Symbiosis International (Deemed University), Pune, Maharashtra, IndiaDepartment of Computer Science and Engineering, University College of Engineering, Dindigul, IndiaDepartment of ECE, Adithya Institute of Technology, CoimbatoreThe constantly growing volume of data created globally makes it impossible for the centralised cloud computing method to provide low-latency, high-efficiency surveillance camera services. In order to alleviate transmission pressure, the load on the main cloud server, and the end to end latency of the video surveillance system, a distributed computing architecture is developed that immediately analyzes peripheral video data. By lowering the probability of tracker drift or malfunction in the videos, the suggested Enhanced Multiple Instance Learning with Whale Optimization Technique (EMIL-WOM) enables the classifier to extract the features with lower computing costs and shorter computation times. For various scenarios, the optimised neural network generates computation models, which are then logically placed in edge devices. The level of Taekwondo is chosen to address the uneven teaching quality for the goal of real-time analysis as society develops. To solve the teaching challenges in the Taekwondo learning process and improve the calibre of Taekwondo, the researcher conducted particular study in relation to the tactile learning theory. This research uses scientific and technological resources as a guide to assess technical actions and strategies and apply them to specific educational experiments for testing. This work analyses and recommends a way for making innovative services based on the edge computing paradigm. This experimental technique eliminates several interoperability and service scalability issues with conventional design. The suggested EMIL-WOM achieves 96.5% accuracy, 56.1% computational complexity, 32.4% RMSE, 24.1% RAE, 30% MAE, and 45.3 seconds of response time when compared to existing approaches.https://hrcak.srce.hr/file/471015edge computingenhanced multiple instance learningfeature extractionvideo surveillancewhale optimization method |
| spellingShingle | Nithya S. Samaya Pillai Iyengar Poobalan A. Parameswari A. Innovative Edge Computing for Real-Time Video Surveillance and Taekwondo Training Enhancement Tehnički Vjesnik edge computing enhanced multiple instance learning feature extraction video surveillance whale optimization method |
| title | Innovative Edge Computing for Real-Time Video Surveillance and Taekwondo Training Enhancement |
| title_full | Innovative Edge Computing for Real-Time Video Surveillance and Taekwondo Training Enhancement |
| title_fullStr | Innovative Edge Computing for Real-Time Video Surveillance and Taekwondo Training Enhancement |
| title_full_unstemmed | Innovative Edge Computing for Real-Time Video Surveillance and Taekwondo Training Enhancement |
| title_short | Innovative Edge Computing for Real-Time Video Surveillance and Taekwondo Training Enhancement |
| title_sort | innovative edge computing for real time video surveillance and taekwondo training enhancement |
| topic | edge computing enhanced multiple instance learning feature extraction video surveillance whale optimization method |
| url | https://hrcak.srce.hr/file/471015 |
| work_keys_str_mv | AT nithyas innovativeedgecomputingforrealtimevideosurveillanceandtaekwondotrainingenhancement AT samayapillaiiyengar innovativeedgecomputingforrealtimevideosurveillanceandtaekwondotrainingenhancement AT poobalana innovativeedgecomputingforrealtimevideosurveillanceandtaekwondotrainingenhancement AT parameswaria innovativeedgecomputingforrealtimevideosurveillanceandtaekwondotrainingenhancement |