A sequence-to-sequence model-based deep learning approach for recognizing activity of daily living for senior care.

Ensuring the health and safety of independent-living senior citizens is a growing societal concern. Researchers have developed sensor based systems to monitor senior citizens' Activity of Daily Living (ADL), a set of daily activities that can indicate their self-caring ability. However, most ADL monitoring systems are designed for one specific sensor modality, resulting in less generalizable models that is not flexible to account variations in real-life monitoring settings. Current classic machine learning and deep learning methods do not provide a generalizable solution to recognize complex ADLs for different sensor settings. This study proposes a novel Sequence-to-Sequence model based deep-learning framework to recognize complex ADLs leveraging an activity state representation. The proposed activity state representation integrated motion and environment sensor data without labor-intense feature engineering. We evaluated our proposed framework against several state-of-the-art machine learning and deep learning benchmarks. Overall, our approach outperformed baselines in most performance metrics, accurately recognized complex ADLs from different types of sensor input. This framework can generalize to different sensor settings and provide a viable approach to understand senior citizen's daily activity patterns with smart home health monitoring systems.