Skip to main navigation Skip to search Skip to main content

Improvement of Human Activity Recognition (HAR) Performance by Utilizing LSTM in the Structure of Progressive Learning

  • Hacettepe University
  • Istanbul University - Cerrahpaşa

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

Abstract

Human Activity Recognition is a crucial area of research in many applications. However, training deep neural network-based models can be expensive and time-consuming. This paper introduces a progressive learning-based approach designed to not only reduce dimensionality but also maintain high accuracy. The proposed method replaces extensive sensor data with four extracted features, derived using a CNN-LSTM-based model trained on the WISDM dataset comprising six activity classes. The extracted features are fed into machine learning algorithms and achieve 97.73% accuracy.

Original languageEnglish
Title of host publication2024 12th International Scientific Conference on Computer Science, COMSCI 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350392166
DOIs
Publication statusPublished - 2024
Event12th International Scientific Conference on Computer Science, COMSCI 2024 - Sozopol, Bulgaria
Duration: 13 Sept 202415 Sept 2024

Publication series

Name2024 12th International Scientific Conference on Computer Science, COMSCI 2024 - Proceedings

Conference

Conference12th International Scientific Conference on Computer Science, COMSCI 2024
Country/TerritoryBulgaria
CitySozopol
Period13/09/2415/09/24

Keywords

  • Convolutional Neural network
  • Human Activity Recognition
  • LR
  • LSTM
  • Progressive learning
  • SVM

Fingerprint

Dive into the research topics of 'Improvement of Human Activity Recognition (HAR) Performance by Utilizing LSTM in the Structure of Progressive Learning'. Together they form a unique fingerprint.

Cite this