Toward Dignity-Aware AI: Next-Generation Elderly Monitoring from Fall Detection to ADL

2025-11-12

AI Summary

Addressing the scarcity of Activities of Daily Living (ADL) data, privacy sensitivity, and challenges in edge deployment for elderly monitoring. Method: We propose a dignity-centered federated learning paradigm that enables privacy-preserving, lightweight, and embeddable AI systems—spanning from fall detection to fine-grained ADL recognition. Our approach integrates GAN-driven non-IID data augmentation, an edge-optimized federated training framework, and real-time on-device inference deployment on the Jetson Orin Nano. Results: Evaluated on the SISFall dataset, the system achieves high accuracy (fall detection F1-score > 0.98) and low latency (<150 ms), while ensuring privacy and operational efficiency. It establishes the first reproducible end-edge-cloud collaborative technical pathway for unobtrusive, privacy-respecting, full-scenario behavioral understanding of older adults.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Bias, Fairness & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

This position paper envisions a next-generation elderly monitoring system that moves beyond fall detection toward the broader goal of Activities of Daily Living (ADL) recognition. Our ultimate aim is to design privacy-preserving, edge-deployed, and federated AI systems that can robustly detect and understand daily routines, supporting independence and dignity in aging societies. At present, ADL-specific datasets are still under collection. As a preliminary step, we demonstrate feasibility through experiments using the SISFall dataset and its GAN-augmented variants, treating fall detection as a proxy task. We report initial results on federated learning with non-IID conditions, and embedded deployment on Jetson Orin Nano devices. We then outline open challenges such as domain shift, data scarcity, and privacy risks, and propose directions toward full ADL monitoring in smart-room environments. This work highlights the transition from single-task detection to comprehensive daily activity recognition, providing both early evidence and a roadmap for sustainable and human-centered elderly care AI.

Problem

• Developing comprehensive elderly monitoring systems beyond fall detection
• Creating privacy-preserving AI for daily activity recognition in smart homes
• Addressing data scarcity and domain shift in elderly care applications

Innovation

• Federated learning with non-IID conditions
• Edge deployment on Jetson Orin Nano
• GAN-augmented datasets for fall detection