Cost-effective Elderly Fall Detection with Symmetry Transformer Networks

Bing Li, Wei Cui, Yanru Chen, Joey Tianyi Zhou, Zhenghua Chen, Yuli Li, Min Wu

Abstract: Elderly fall detection aims at automatically detecting fall actions, a major public health problem for the elderly. Existing fall detection methods are cost-ineffective - a satisfactory performance is commonly traded by high costs in device access/deployment and positive record acquirement. In this paper, we set out to devise a WiFi-based elderly fall detection approach in a cost-effective manner - being high in detection accuracy, and low in costs of device access and positively -annotated data. Specifically, our system builds on commercial WiFi, a ubiquitously available device, which greatly saves device access and deployment costs. To extract the nuanced and implicit features due to the low signal-to-noise ratio of WiFi signals, we propose symmetry Transformer networks, a variant of Transformer to facilitate better feature representation learning. Meanwhile, to overcome the positive scarcity and low inter-environment transferability brought by Transformer, we propose a novel two-stage training scheme, where the representation learning is performed in an unsupervised manner. This unveils a transferability property that reduces the requirements on positive instances in training the resulting model. Empirical evaluation demonstrates our cost-effective desideratum while achieving superior performance compared with state-of-the-art models.