• Home
  • Search
  • Segment-Based Unsupervised Learning Method in Sensor-Based Human Activity Recognition
  • Cite Icon3
  • https://doi.org/10.3390/s23208449Copy DOI Icon

Segment-Based Unsupervised Learning Method in Sensor-Based Human Activity Recognition

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Sensor-based human activity recognition (HAR) is a task to recognize human activities, and HAR has an important role in analyzing human behavior such as in the healthcare field. HAR is typically implemented using traditional machine learning methods. In contrast to traditional machine learning methods, deep learning models can be trained end-to-end with automatic feature extraction from raw sensor data. Therefore, deep learning models can adapt to various situations. However, deep learning models require substantial amounts of training data, and annotating activity labels to construct a training dataset is cost-intensive due to the need for human labor. In this study, we focused on the continuity of activities and propose a segment-based unsupervised deep learning method for HAR using accelerometer sensor data. We define segment data as sensor data measured at one time, and this includes only a single activity. To collect the segment data, we propose a measurement method where the users only need to annotate the starting, changing, and ending points of their activity rather than the activity label. We developed a new segment-based SimCLR, which uses pairs of segment data, and propose a method that combines segment-based SimCLR with SDFD. We investigated the effectiveness of feature representations obtained by training the linear layer with fixed weights obtained by unsupervised learning methods. As a result, we demonstrated that the proposed combined method acquires generalized feature representations. The results of transfer learning on different datasets suggest that the proposed method is robust to the sampling frequency of the sensor data, although it requires more training data than other methods.

Loading PDF

Similar Papers
  • Conference Article
  • Citations2

Unsupervised Representation Learning Method In Sensor Based Human Activity Recognition

  • Sep 09, 2022
  • Koki Takenaka +1
  • Research Article
  • Citations1

Conv-ScaleNet: A Multiscale Convolutional Model for Federated Human Activity Recognition

  • Sep 08, 2025
  • AI
  • Xian Wu Ting +4
  • Research Article
  • Citations8

A novel semi-supervised multi-view clustering framework for screening Parkinson's disease.

  • Jan 01, 2020
  • Mathematical Biosciences and Engineering
  • Xiaobo Zhang +4
  • Book Chapter
  • Citations6

Chapter 14 - A study on smartphone sensor-based Human Activity Recognition using deep learning approaches

  • Jan 01, 2021
  • Handbook of Computational Intelligence in Biomedical Engineering and Healthcare
  • Riktim Mondal +5
  • Research Article
  • Citations4

Probabilistic knowledge infusion through symbolic features for context-aware activity recognition

  • Mar 17, 2023
  • Pervasive and Mobile Computing
  • Luca Arrotta +2
  • Conference Article
  • Citations3

Deep Learning Models for Daily Living Activity Recognition based on Wearable Inertial Sensors

  • Jun 22, 2022
  • Sakorn Mekruksavanich +3
  • Research Article
  • Citations73

Sensor Data Augmentation by Resampling in Contrastive Learning for Human Activity Recognition

  • Dec 01, 2022
  • IEEE Sensors Journal
  • Jinqiang Wang +5
  • PDF
  • Research Article
  • Citations158

Sensor-Based Human Activity Recognition with Spatio-Temporal Deep Learning

  • Mar 18, 2021
  • Sensors (Basel, Switzerland)
  • Ohoud Nafea +3
  • Research Article
  • Citations5

Multihead-Res-SE Residual Network with Attention for Human Activity Recognition

  • Aug 27, 2024
  • Electronics
  • Hongbo Kang +3
  • Conference Article
  • Citations6

Knowledge Infusion for Context-Aware Sensor-Based Human Activity Recognition

  • Jun 01, 2022
  • Luca Arrotta +2
  • PDF
  • Research Article
  • Citations35

A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch Sensors

  • Jul 17, 2023
  • Computers
  • Sakorn Mekruksavanich +1
  • Research Article
  • Citations1

Expanding the Horizons of 1-D Tasks: Leveraging 2-D Convolutional Neural Networks Pretrained by ImageNet

  • Oct 01, 2024
  • IEEE Internet of Things Journal
  • Zhao Zhongkai +2
  • PDF
  • Research Article
  • Citations74

Sensor-Based Human Activity Recognition Using Deep Stacked Multilayered Perceptron Model

  • Jan 01, 2020
  • IEEE Access
  • Furqan Rustam +6
  • Research Article
  • Citations7

Unsupervised learning on scientific ocean drilling datasets from the South China Sea

  • Jun 04, 2018
  • Frontiers of Earth Science
  • Kevin C Tse +4
  • Research Article

Multi-task deep transfer learning for complicated seismic dynamic response prediction in slope systems

  • Mar 01, 2026
  • Geoscience Frontiers
  • Xu Han +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.