| Summary: | This report presents a secure and autonomous solution for detecting falls in bathroom environments, addressing privacy concerns associated with traditional video surveillance systems. The proposed approach integrates machine learning and artificial intelligence algorithms into edge processing devices, enabling real-time decision- making at the network's edge. The system utilizes advanced audio classification models to identify conscious occupants expressing fear when calling for help, complemented by obscured thermal imaging techniques to detect unconscious fallen individuals. The audio classifier employs a Deep Neural Network (DNN) architecture trained on the Toronto Emotional Speech Data Set (TESS), achieving an overall accuracy of 88.22% in recognizing emotions from vocalizations. The thermal image classifier analyses temperature differentials between image pixels, correctly identifying fallen postures with 96% recall and 38% precision when the optimal temperature threshold is applied. Extensive testing and evaluation of the system's performance are conducted, including the construction of a thermal image dataset and the incorporation of background bathroom noise into the audio classification model, reducing the fear detection accuracy to 72.73%. The report provides a comprehensive overview of the system's methodology, hardware and software architectures, data collection and training processes, and presents the results obtained from various test scenarios. Recommendations for future work and potential enhancements are also discussed, highlighting the system's potential for widespread adoption and its contribution to enhancing elderly safety in bathroom environments while prioritizing data privacy and security.
|
|---|