Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation
This addresses data missingness in health monitoring for researchers, but appears incremental as it applies a novel method to a specific domain.
The paper tackles the problem of imputing missing step count data from wearable sensors by proposing a domain knowledge-informed sparse self-attention model, achieving performance assessed relative to baselines on a large dataset with over 5.5 million hourly observations.
Wearable sensors enable health researchers to continuously collect data pertaining to the physiological state of individuals in real-world settings. However, such data can be subject to extensive missingness due to a complex combination of factors. In this work, we study the problem of imputation of missing step count data, one of the most ubiquitous forms of wearable sensor data. We construct a novel and large scale data set consisting of a training set with over 3 million hourly step count observations and a test set with over 2.5 million hourly step count observations. We propose a domain knowledge-informed sparse self-attention model for this task that captures the temporal multi-scale nature of step-count data. We assess the performance of the model relative to baselines and conduct ablation studies to verify our specific model designs.