CoChat

Self-Supervised Representation Learning for Human Activity Recognition Using Inertial Sensor Data

Khatun, Mst. Moushumi, Ahsan, Mohammad Shafat, Al Amin, Md, Eva, Arifa Akter, Sayeema, Anika, Firdaus, Sabiha · 2025 · 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN)

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Abstract

This paper proposes a self-supervised learning framework for Human Activity Recognition (HAR) using inertial sensor data, aiming to reduce dependency on large labeled datasets. Leveraging contrastive learning and a hybrid encoder consisting of 1D convolutional layers and a bidirectional LSTM, the model learns meaningful representations from unlabeled time-series data through a pretext task of distinguishing between augmented views of the same sequence. Extensive experiments on the UCI HAR Dataset demonstrate that our approach achieves a test accuracy of 94.72%, surpassing several supervised baselines such as CNN (91.46%), LSTM (92.35%), and Transformer (93.24%)., and Transformer (93.24 %). The model also achieves a macro-averaged F1-score of 94.45% and AUROC of 97.36%, indicating strong class separability and generalization. Furthermore, it maintains robust performance under noisy and incomplete sensor inputs, with only minor degradations observed under Gaussian noise (F1-score drops to 89.41%) and random dropout (87.93%). These results highlight the effectiveness and scalability of the proposed method for real-world HAR applications, especially in scenarios with limited annotated data.

Overview

Integrity signals

Registry

Crossref · 10.1109/qpain66474.2025.11171865

Cites

0 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

The publisher hasn’t deposited this paper’s reference list.

Research works printed but not linked: 14

  1. 10.3390/s22041476 · DOI · Paper page
  2. 10.3390/app132413009 · DOI
  3. 10.1080/17434440.2021.1988849 · DOI
  4. 10.1080/17434440.2016.1198694 · DOI · Paper page
  5. 10.3390/s23010062 · DOI
  6. 10.3390/info15080491 · DOI
  7. 10.3390/s23094221 · DOI · Paper page
  8. 10.61185/SMIJ.2022.8463 · DOI
  9. 10.1007/s44196-024-00554-0 · DOI
  10. 10.3390/electronics10141685 · DOI · Paper page
  11. 10.1109/ACCESS.2018.2890675 · DOI · Paper page
  12. 10.1007/s00607-021-00928-8 · DOI · Paper page
  13. 10.1016/j.neucom.2019.06.051 · DOI · Paper page
  14. 10.1016/j.knosys.2023.110789 · DOI · Paper page

Cited by

Still being checked.

Metadata

Authors
Khatun, M. M., Ahsan, M. S., Al Amin, M., Eva, A. A., Sayeema, A., & Firdaus, S.
Affiliations
  • Advanced Machine Intelligence Research Lab,Dhaka,Bangladesh,1207
  • Clark University (US)
  • St. Francis College,Brooklyn,New York,USA
  • American International University-Bangladesh (BD)
  • Advanced Machine Intelligence Research Lab,Dhaka,Bangladesh
  • Bangladesh University of Business and Technology (BD)
Venue
2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN)
Publisher
IEEE
Published
2025-07-31
Pages
1-6
OpenAlex
W4414603871
Cited by
0
References
0
FWCI
0.00
Type
conference paper
Language
en
Open access
closed
Locations
  • IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) (publishedVersion)
  • Clark Digital Commons (Clark University) (submittedVersion)
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, inertial data, self-supervised learning, contrastive learning, bidirectional LSTM, data augmentation, noise robustness, incomplete sensor data, UCI HAR dataset

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: Self-Supervised Representation Learning for Human Activity Recognition Using Inertial Sensor Data. https://app.cochat.ai/papers/10.1109/qpain66474.2025.11171865
The paper
Khatun, M. M., Ahsan, M. S., Al Amin, M., Eva, A. A., Sayeema, A., & Firdaus, S. (2025). Self-Supervised Representation Learning for Human Activity Recognition Using Inertial Sensor Data. 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN). https://doi.org/10.1109/qpain66474.2025.11171865

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.