GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery

TL;DR

GenHAR is a novel framework that improves cross-domain human activity recognition by learning domain-invariant features, enhancing accuracy and efficiency, and successfully deploying in real-world logistics scenarios.

Contribution

GenHAR introduces a sensor data tokenization and correlation learning approach, along with selective masking and attention mechanisms, to enhance HAR generalization across domains.

Findings

GenHAR outperforms state-of-the-art methods by 9.97% in accuracy.

GenHAR reduces floating point operations by 6.4 times.

GenHAR detects 2.15 billion activities in real-world deployment.

Abstract

Human Activity Recognition (HAR) has shown remarkable effectiveness in various applications, such as smart healthcare and intelligent manufacturing. However, a major challenge faced by HAR is the distribution shift across different sensor data domains, which often leads to decreased performance when deployed for real-world applications. To address this issue, this paper introduces GenHAR, a novel framework designed to mitigate the domain gap by learning domain-invariant sensor representations. GenHAR aims to enhance the generalization capabilities of HAR on target domains purely with data from the source domain. The key novelty of GenHAR lies in two aspects. Firstly, GenHAR tokenizes sensor data and learns correlations among frequency sensor channel dimensions to improve the robustness of HAR models. Secondly, GenHAR improves the efficiency via selective masking and an efficient attention mechanism. We conduct a systematic analysis of GenHAR by comparing it with state-of-the-art HAR methods on real-world human activity datasets. Results show that GenHAR outperforms state-of-the-art methods by 9.97% in accuracy, and reduces Floating Point Operations by 6.4 times. Moreover, we deploy GenHAR at a leading logistics company in 4 cities, and have detected 2.15 billion real-time activities. We release our code at: https://github.com/Sensor-FoundationModel/GenHAR.