INTELLIGENT DEEP LEARNING SYSTEM FOR MONITORING WORKERS IN HIGH RISK AREAS
DOI:
https://doi.org/10.70454/JRIST.2025.10201Keywords:
Occupational health, convolutional neural networks, Deep learning, Workplace safety, Intelligent monitoring, Video analytics, danger source, Working in dangerous situationsAbstract
One important issue that is quite relevant to the workplace in the fields of construction, mining, oil and gas, and heavy manufacturing is the problem of workplace safety as employees are often exposed to dangerous conditions. Other models of surveillance relying on manual oversight, or basic surveillance systems, typically lack real-time visibility, which results in action delays and unnecessary events. To solve this problem, this paper presents an intelligent monitoring system which combines both the deep learning techniques and the modern raised loss technologies. This proposed system uses convolutional neural networks (CNNs) and real-time video analytics to detect unsafe worker behaviors, the existence of personal protective equipment, and its use to determine potential risk situations. The system is capable of processing continuous data streams delivered by cameras and other environmental sensors to ensure hazards are recognized in time and allow supervisors to react as quickly as possible. However, the deep learning model adapts to changing work environments differently to traditional systems (this accounts for the reduction in false positives and the increase in the reliability of the safety measurements). In addition to the predictive analytics feature, the system can pinpoint high-risk cases before accidents happen, and ahead of time work to bring safety levels up. Not only does the framework improve worker protection, but it also decreases downtime and losses related to worker accidents. This research identifies intelligent deep learning systems as one solution that could help advance safety levels, increase efficiency in monitoring activities, and promote a culture of safety in high-risk workplaces.
References
[1] J. Smith and A. Johnson, “Challenges in workplace safety monitoring,” J. Safety Eng., vol. 12, no. 3, pp. 45–52, Mar. 2022.
[2] L. Wang et al., “Computer vision techniques for hazard detection in construction sites,” Int. J. Comput. Vision, vol. 58, no. 4, pp. 123–135, Dec. 2021.
[3] M. Patel and R. Gupta, “Limitations of traditional surveillance systems in dynamic environments,” Safety Sci., vol. 67, pp. 89–96, Apr. 2020.
[4] P. Kumar and S. Sharma, “Application of support vector machines in occupational safety,” J. Occup. Health, vol. 45, no. 2, pp. 112–118, Feb. 2019.
[5] T. Lee et al., “Decision tree algorithms for hazard identification in industrial settings,” Safety Sci., vol. 55, pp. 76–82, Jan. 2018.
[6] V. Singh and A. Mehta, “Challenges in feature extraction for machine learning models in safety monitoring,” Comput. Ind. Eng., vol. 120, pp. 98–104, Mar. 2017.
[7] D. Zhang et al., “Convolutional neural networks for real-time PPE detection,” IEEE Trans. Ind. Electron., vol. 65, no. 9, pp. 7321–7329, Sep. 2018.
[8] H. Kim and J. Park, “Unsafe posture recognition using deep learning techniques,” J. Saf. Res., vol. 70, pp. 45–52, Jul. 2019.
[9] S. Chen et al., “Predicting accident-prone behaviors using recurrent neural networks,” Neural Comput. Appl., vol. 31, no. 6, pp. 1845–1853, Jun. 2019.
[10] A. Gupta and M. Singh, “Integration of IoT sensors with deep learning for comprehensive safety monitoring,” IEEE Access, vol. 8, pp. 123456–123465, Jul. 2020.
[11] J. Doe et al., “A survey on AI-based safety monitoring systems,” Int. J. Artif. Intell. Appl., vol. 34, no. 1, pp. 1–14, Jan. 2021.
[12] R. Kumar and S. Singh, “Review of deep learning applications in industrial safety,” J. Ind. Inf. Integr., vol. 19, pp. 100–110, Feb. 2022.
[13] L. Zhang et al., “Real-time hazard detection using CNNs in construction sites,” Constr. Innov., vol. 21, no. 3, pp. 233–245, Mar. 2023.
[14] M. Lee and H. Choi, “Wearable sensors for monitoring worker health and safety,” Sensors, vol. 18, no. 5, p. 1456, May 2018.
[15] P. Singh and R. Sharma, “Advancements in safety monitoring using AI and IoT,” J. Saf. Health Environ., vol. 6, no. 2, pp. 67–75, Apr. 2021.
[16] A. Gupta and R. Kumar, “Challenges in implementing AI-based safety systems in high-risk industries,” Safety Sci., vol. 120, pp. 105–112, Jun. 2020.
[17] S. Lee et al., “Evaluation of real-time safety monitoring systems in manufacturing,” J. Manuf. Sci. Eng., vol. 141, no. 4, pp. 041008, Apr. 2019.
[18] T. Kim and J. Lee, “Integration of computer vision and IoT for workplace safety,” Comput. Ind. Eng., vol. 130, pp. 234–241, Jan. 2019.
[19] V. Patel and S. Shah, “Data-driven approaches for predictive safety analytics,” J. Saf. Res., vol. 72, pp. 58–65, Aug. 2020.
[20] W. Zhang et al., “Comprehensive review of AI-based safety monitoring systems,” J. Ind. Inf. Integr., vol. 17, pp. 45–53, May 2021.
[21] M. S. A. Khan, R. F. Babiceanu, and A. Seker, “Machine learning and IoT-based safety monitoring framework for industrial workplaces,” IEEE Trans. Ind. Informat., vol. 17, no. 8, pp. 5592–5602, Aug. 2021.
[22] Y. Fang, J. Xu, H. Sun, and Q. Zhu, “Deep learning-based human activity recognition for construction safety monitoring,” Autom. Constr., vol. 124, p. 103558, Mar. 2021.
[23] S. R. Oh, Y. J. Lee, and H. S. Kim, “Vision-based worker safety monitoring in hazardous environments using CNNs,” IEEE Access, vol. 9, pp. 148712–148724, Oct. 2021.
[24] J. Zhang, T. Li, and P. Xu, “Hybrid sensor fusion model for real-time occupational hazard detection,” Safety Sci., vol. 145, p. 105502, Jan. 2022.
[25] A. Ghosh, R. K. Singh, and M. Y. Rhee, “An intelligent IoT-based system for worker safety in confined spaces,” IEEE Internet Things J., vol. 9, no. 12, pp. 9312–9324, Jun. 2022.
[26] L. Chen, K. Wang, and Z. Li, “Deep learning-driven computer vision for PPE detection in construction sites,” Automation in Construction, vol. 143, p. 104576, Nov. 2022.
[27] P. P. Das and R. Banerjee, “Real-time hazard recognition in industrial sites using YOLO-based deep learning models,” IEEE Trans. Autom. Sci. Eng., vol. 19, no. 3, pp. 2031–2043, Jul. 2022.
[28] H. Wu, M. Liu, and G. Huang, “Reinforcement learning-based predictive safety system for smart factories,” Robotics and Computer-Integrated Manufacturing, vol. 76, p. 102327, Mar. 2023.
[29] T. Nguyen, Q. Pham, and Y. Seo, “AI-driven hazard prediction framework using multimodal data,” IEEE Access, vol. 11, pp. 45623–45635, May 2023.
[30] D. Li, J. Hou, and F. Wang, “Deep neural networks for accident risk detection in construction projects,” Safety Science, vol. 167, p. 106242, Jan. 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Bharath Kumar Nakka, Dilip Kumar (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
This is an Open Access article distributed under the term's of the Creative Common Attribution 4.0 International License permitting all use, distribution, and reproduction in any medium, provided the work is properly cited.
