Integrating Temporal Context into Streaming Data for Human Activity Recognition in Smart Home
This work addresses the problem of enabling independent living for the elderly through more accurate activity monitoring in smart homes, representing an incremental improvement by enhancing existing feature weighting methods with temporal context.
The paper tackled the challenge of leveraging temporal information in human activity recognition from passive sensors in smart homes by clustering activities into time-of-day segments and encoding temporal features, resulting in improved accuracy and F1-scores over state-of-the-art methods in three out of four real-world datasets, with the highest gains in low-data regimes.
With the global population ageing, it is crucial to enable individuals to live independently and safely in their homes. Using ubiquitous sensors such as Passive InfraRed sensors (PIR) and door sensors is drawing increasing interest for monitoring daily activities and facilitating preventative healthcare interventions for the elderly. Human Activity Recognition (HAR) from passive sensors mostly relies on traditional machine learning and includes data segmentation, feature extraction, and classification. While techniques like Sensor Weighting Mutual Information (SWMI) capture spatial context in a feature vector, effectively leveraging temporal information remains a challenge. We tackle this by clustering activities into morning, afternoon, and night, and encoding them into the feature weighting method calculating distinct mutual information matrices. We further propose to extend the feature vector by incorporating time of day and day of week as cyclical temporal features, as well as adding a feature to track the user's location. The experiments show improved accuracy and F1-score over existing state-of-the-art methods in three out of four real-world datasets, with highest gains in a low-data regime. These results highlight the potential of our approach for developing effective smart home solutions to support ageing in place.