GRU-based Attention Mechanism for Human Activity Recognition

Sensor data based Human Activity Recognition (HAR) has gained interest due to its application in practical field. With increasing number of approaches incorporating feature learning of sequential time-series sensor data, in particular the deep learning based ones has performed reasonably in uniform labeled data distribution scenario. However, most of these methods do not capture properly the temporal context of time-steps in sequential time-series data. Moreover, the situation becomes worse for imbalanced class distribution which is a usual case for HAR using body-worn sensor devices. To solve this issues, we have integrated hierarchical attention mechanism with recurrent units of neural network in order to obtain temporal context within the time-steps of data sequence. The introduced model in this paper has achieved better performance with respect to the well-defined evaluation metrics in both uniform and imbalanced class distribution than the existing state-of-the-art deep learning based model.