Skip to main navigation Skip to search Skip to main content

Real-life Human Activity Recognition Based on Accelerometer Data from Smartphone Sensors Using CNN-BiGRU Model

  • Sakorn Mekruksavanich
  • , Yongliang Fan
  • , Narit Hnoohom
  • , Anuchit Jitpattanakul
  • University of Phayao
  • Guangxi Technological College of Machinery and Electricity
  • King Mongkut's University of Technology North Bangkok

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Human activity recognition using smartphone sensors is essential for health monitoring and context-aware applications. This study presents a hybrid deep learning model that combines convolutional neural networks (CNNs) and bidirectional gated recurrent units (BiGRUs) to recognize daily activities from tri-axial accelerometer data. The proposed approach is evaluated on the Real-Life Human Activity Recognition (RL-HAR) dataset, which includes data from 19 participants performing four everyday activities under real-world conditions. Raw sensor signals are pre-processed using noise filtering and overlapping sliding-window segmentation. The CNN component extracts spatial features, while the BiGRU component captures bidirectional temporal dependencies. Experimental results from subject-independent 5-fold cross-validation demonstrate that the proposed CNN-BiGRU model achieves 95.84% accuracy and 95.65% F1-score, outperforming both CNN-only and recurrent baseline models.

Original languageEnglish
Title of host publication11th International Conference on Digital Arts, Media and Technology and 9th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI DAMT and NCON 2026
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages688-693
Number of pages6
ISBN (Electronic)9798331576356
DOIs
Publication statusPublished - 2026
Event11th International Conference on Digital Arts, Media and Technology and 9th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI DAMT and NCON 2026 - Chiang Mai, Thailand
Duration: 4 Feb 20267 Feb 2026

Publication series

Name11th International Conference on Digital Arts, Media and Technology and 9th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI DAMT and NCON 2026

Conference

Conference11th International Conference on Digital Arts, Media and Technology and 9th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI DAMT and NCON 2026
Country/TerritoryThailand
CityChiang Mai
Period4/02/267/02/26

Keywords

  • CNN-BiGRU
  • accelerometer
  • deep learning
  • human activity recognition
  • real-life activities
  • smartphone sensors

Fingerprint

Dive into the research topics of 'Real-life Human Activity Recognition Based on Accelerometer Data from Smartphone Sensors Using CNN-BiGRU Model'. Together they form a unique fingerprint.

Cite this