Representation Learning for Wearable-Based Applications in the Case of Missing Data

TL;DR

This paper explores the use of transformer-based representation learning to improve missing data imputation in wearable sensor signals, highlighting the benefits and limitations of this approach in real-world scenarios.

Contribution

It introduces a transformer model for imputing missing wearable data and compares its performance with traditional statistical methods, providing insights into effective strategies for handling missing data.

Findings

Transformers outperform baseline methods for signals with frequent changes.

Imputation performance varies with signal type and masking ratios.

Hybrid imputation strategies enhance downstream classification accuracy.

Abstract

Wearable devices continuously collect sensor data and use it to infer an individual's behavior, such as sleep, physical activity, and emotions. Despite the significant interest and advancements in this field, modeling multimodal sensor data in real-world environments is still challenging due to low data quality and limited data annotations. In this work, we investigate representation learning for imputing missing wearable data and compare it with state-of-the-art statistical approaches. We investigate the performance of the transformer model on 10 physiological and behavioral signals with different masking ratios. Our results show that transformers outperform baselines for missing data imputation of signals that change more frequently, but not for monotonic signals. We further investigate the impact of imputation strategies and masking rations on downstream classification tasks. Our study provides insights for the design and development of masking-based self-supervised learning tasks and advocates the adoption of hybrid-based imputation strategies to address the challenge of missing data in wearable devices.