Human Activity Recognition from Wearable Sensor Data Using Self-Attention
This work addresses the problem of accurate activity recognition for applications like healthcare or fitness tracking, representing an incremental advancement by applying self-attention to a known bottleneck in existing methods.
The paper tackled the challenge of capturing spatial and temporal dependencies in human activity recognition from wearable sensor data by proposing a self-attention-based neural network model, which achieved significant performance improvements over state-of-the-art models on four benchmark datasets.
Human Activity Recognition from body-worn sensor data poses an inherent challenge in capturing spatial and temporal dependencies of time-series signals. In this regard, the existing recurrent or convolutional or their hybrid models for activity recognition struggle to capture spatio-temporal context from the feature space of sensor reading sequence. To address this complex problem, we propose a self-attention based neural network model that foregoes recurrent architectures and utilizes different types of attention mechanisms to generate higher dimensional feature representation used for classification. We performed extensive experiments on four popular publicly available HAR datasets: PAMAP2, Opportunity, Skoda and USC-HAD. Our model achieve significant performance improvement over recent state-of-the-art models in both benchmark test subjects and Leave-one-subject-out evaluation. We also observe that the sensor attention maps produced by our model is able capture the importance of the modality and placement of the sensors in predicting the different activity classes.