Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition

TL;DR

This paper demonstrates that recent vector quantization techniques can be effectively applied to wearable sensor data, enabling discretized representations that match or surpass continuous data in human activity recognition tasks, with broader implications for symbolic sequence analysis.

Contribution

The paper introduces a novel application of vector quantization to wearable sensor data, showing discretized representations can achieve competitive recognition performance and facilitate advanced symbolic analysis.

Findings

Discretized representations can match or outperform continuous ones in HAR.

Vector quantization enables effective mapping from sensor data to symbolic codes.

Discretized data opens new avenues for symbolic sequence analysis in HAR.

Abstract

Human activity recognition (HAR) in wearable computing is typically based on direct processing of sensor data. Sensor readings are translated into representations, either derived through dedicated preprocessing, or integrated into end-to-end learning. Independent of their origin, for the vast majority of contemporary HAR, those representations are typically continuous in nature. That has not always been the case. In the early days of HAR, discretization approaches have been explored - primarily motivated by the desire to minimize computational requirements, but also with a view on applications beyond mere recognition, such as, activity discovery, fingerprinting, or large-scale search. Those traditional discretization approaches, however, suffer from substantial loss in precision and resolution in the resulting representations with detrimental effects on downstream tasks. Times have changed and in this paper we propose a return to discretized representations. We adopt and apply recent advancements in Vector Quantization (VQ) to wearables applications, which enables us to directly learn a mapping between short spans of sensor data and a codebook of vectors, resulting in recognition performance that is generally on par with their contemporary, continuous counterparts - sometimes surpassing them. Therefore, this work presents a proof-of-concept for demonstrating how effective discrete representations can be derived, enabling applications beyond mere activity classification but also opening up the field to advanced tools for the analysis of symbolic sequences, as they are known, for example, from domains such as natural language processing. Based on an extensive experimental evaluation on a suite of wearables-based benchmark HAR tasks, we demonstrate the potential of our learned discretization scheme and discuss how discretized sensor data analysis can lead to substantial changes in HAR.