CoChat

Attention-Guided Time-Channel Masking for Self-Supervised Human Activity Recognition via Masked Sensor Data Reconstruction

Yang, Long, Yang, Po, Peng, Xiyang, Wang, Xulong, Qi, Jun · 2025 · 2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)

The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.

Abstract

With the widespread deployment of sensors in portable devices such as smartphones and smartwatches, sensor-based human activity recognition (HAR) has emerged as a key research focus in the field of ubiquitous computing. However, the sequential nature of sensor data makes manual annotation extremely labor-intensive and time-consuming, severely limiting the scalability of traditional supervised learning approaches. To address this challenge, self-supervised learning (SSL) has become a highly promising alternative by enabling the extraction of effective feature representations from large amounts of unlabeled data.In this work, we propose a novel attention-guided time-channel masking strategy for self-supervised learning in HAR tasks. Unlike traditional random masking methods, our approach utilizes multi-head attention mechanisms to dynamically select and mask the most discriminative portions of the sequence, thereby guiding the model to learn deeper structural patterns and salient features within the data. Extensive experiments conducted on three public datasets — MotionSense, USC-HAD, and UCI-HAR — demonstrate that our method significantly outperforms both traditional random masking and fully supervised baselines in terms of macro-averaged F1-score and classification accuracy. Furthermore, ablation studies validate the robustness and effectiveness of the proposed attention-guided masking strategy under different masking ratios, with particularly notable advantages observed at lower masking rates. These results collectively confirm the effectiveness and potential applicability of our method for enhancing self-supervised representation learning in HAR tasks.

Overview

Integrity signals

Registry

Crossref · 10.1109/indin64977.2025.11278998

Cites

20 of 20 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 20 references

Research works printed but not linked: 1

  1. Anguita, 2013, A public domain dataset for human activity recognition using smartphones, Esann, 3, 3

Cited by

Still being checked.

Metadata

Authors
Yang, L., Yang, P., Peng, X., Wang, X., & Qi, J.
Affiliations
  • Yunnan University (CN)
  • University of Sheffield (GB)
  • Xi’an Jiaotong-Liverpool University (CN)
Venue
2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)
Publisher
IEEE
Published
2025-07-12
Pages
1-6
ISSN
1935-4576 (ISSN-L)
OpenAlex
W7118591002
Cited by
0
References
19
FWCI
0.00
Type
conference paper
Language
en
Open access
closed
Locations
IEEE International Conference on Industrial Informatics (INDIN) (publishedVersion)
Funders
  • Yunnan Provincial Department of Education
  • National Natural Science Foundation of China
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
  • Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
human activity recognition, self-supervised learning, multi-head attention, sensor data reconstruction, wearable sensors, unlabeled data, representation learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Attention-Guided Time-Channel Masking for Self-Supervised Human Activity Recognition via Masked Sensor Data Reconstruction. https://app.cochat.ai/papers/10.1109/indin64977.2025.11278998
The paper
Yang, L., Yang, P., Peng, X., Wang, X., & Qi, J. (2025). Attention-Guided Time-Channel Masking for Self-Supervised Human Activity Recognition via Masked Sensor Data Reconstruction. 2025 IEEE 23rd International Conference on Industrial Informatics (INDIN). https://doi.org/10.1109/indin64977.2025.11278998

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.