AI-powered trustable and explainable fall detection system using transfer learning

Abstract

Accidental falls pose a significant public health challenge, especially among vulnerable populations. To address this issue, comprehensive research on fall detection and rescue systems is essential. Vision-based technologies, with their promising potential, offer an effective means to detect falls. This research paper presents a cutting-edge fall detection methodology aimed at enhancing individual safety and well-being. The proposed methodology utilizes deep neural networks, leveraging their capabilities to drive advancements in fall detection. To overcome data limitations and computational efficiency concerns, this study employ transfer learning by fine-tuning pre-trained models on large-scale image datasets for fall detection. This approach significantly enhances model performance, enabling better generalization and accuracy, especially in real-time applications with constrained resources. Notably, the methodology achieved an impressive test accuracy of 98.15%. Additionally, the incorporation of Explainable Artificial Intelligence (XAI) techniques is used to ensure transparent and trustworthy decision-making in fall detection using deep learning models, especially in critical healthcare contexts for vulnerable individuals. XAI provides valuable insights into complex model architectures and parameters, enabling a deeper understanding of fall identification patterns. To evaluate the effectiveness of this approach, a rigorous experimentation was conducted using a diverse dataset containing real-world fall and non-fall scenarios. The results demonstrate substantial improvements in both accuracy and interpretability, confirming the superiority of this method over conventional fall detection approaches.