GoldAid: An Integrated Safety System Leveraging IoT and Advanced Algorithms for Rapid Medical Aid in the Golden Hour
Anushka Tripathi, Arpit Sahni, Srikar Somanchi, Sresthavadhani Mantha, Mohammed Hammad Khan, Abhishek Srivastava · IEEE Sensors Journal · 2024
Accidents in industrial environments endanger the lives of workers facing challenging conditions. The major reason for fatal outcomes in such accidents arises from delays in reporting and providing timely medical assistance within the crucial first 60 min (golden hour) after the accidents. In this work, we present a safety system GoldAid that is specifically designed for industries to ensure quick incident reporting and expedite medical assistance within the critical golden hour. The proposed GoldAid system presents a significant integration of multiple sensors to provide fall detection, geo-tracking, long-range wireless communication, hazardous gas detection, vital monitoring, and save our souls (SOS) functionalities within the Internet-of-Things framework. To cover all possible industrial fall scenarios, this work also presents a convolutional neural network (CNN) model and an acceleration-threshold-based method for low-power edge devices. Moreover, to achieve minimum data loss and low latency in real-time incident reporting in a large industrial setup, a strategic model for placing multiple communication gateways is also proposed in this article. A prototype of the proposed GoldAid system is developed, and the experimental results are also presented. Measurement results show that the proposed fall-detection models achieve >98.44% accuracy, and the system achieves a latency of$\lt 3\times 10^{-4}$over a communication range of 300 m while reporting a fall incident in an actual thermal power plant.