Human Activity Recognition using Wearable Sensors: Review, Challenges, Evaluation Benchmark

TL;DR

This paper reviews recent human activity recognition techniques using wearable sensors, highlights the need for standardized evaluation, and proposes a hybrid method that outperforms existing approaches on multiple datasets.

Contribution

It provides an extensive review, applies a standardized benchmark for fair comparison, and introduces an improved hybrid approach for better recognition accuracy.

Findings

The hybrid approach outperforms top techniques on several datasets.

Standardized evaluation reveals performance gaps among methods.

Proposed method combines handcrafted features with neural networks effectively.

Abstract

Recognizing human activity plays a significant role in the advancements of human-interaction applications in healthcare, personal fitness, and smart devices. Many papers presented various techniques for human activity representation that resulted in distinguishable progress. In this study, we conduct an extensive literature review on recent, top-performing techniques in human activity recognition based on wearable sensors. Due to the lack of standardized evaluation and to assess and ensure a fair comparison between the state-of-the-art techniques, we applied a standardized evaluation benchmark on the state-of-the-art techniques using six publicly available data-sets: MHealth, USCHAD, UTD-MHAD, WISDM, WHARF, and OPPORTUNITY. Also, we propose an experimental, improved approach that is a hybrid of enhanced handcrafted features and a neural network architecture which outperformed top-performing techniques with the same standardized evaluation benchmark applied concerning MHealth, USCHAD, UTD-MHAD data-sets.