Skip to search boxSkip to navigationSkip to main content

Understanding human behavior through smart home IoT data analysis: patterns and insights

Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Sustainable Development Goals

  • SDG 7 - Affordable and Clean Energy
    SDG 7 Affordable and Clean Energy

Abstract

This paper outlines the preprocessing methods and utilisation of clustering algorithms on a dataset [1] capturing individual tasks within a household (via energy consumption and reactive sensors). The analysis spans seven months that includes multi-sensor readings from a single household. In an effort to identify patterns through Human Activity Recognition (HAR), various clustering algorithms were applied to refined data to compare their respective outcomes. Hence, the paper examines multiple clustering algorithms suitable for the dataset exceeding 800,000 instances after preprocessing. It delves into the real-world applications of smart home data and conducts initial experiments where feasible, comparing results to uncover patterns indicative of user habits and changes therein. The study emphasises the potential for early intervention, particularly in identifying deviations to assist individuals such as those with dementia.

Publication Information

Output type

Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 29-43 (15 pages)

Publication milestones

  • Published - 22/07/2025

Publication status

Published - 22/07/2025

Edition

317

Publisher

Springer, Japan, India, Australia, Germany, United States, United Arab Emirates, Austria, Switzerland, Italy, China, United Kingdom, Netherlands, Brazil, France, Singapore

Publication series

  • Publication series name: Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
    ISSN (Print): 1867-8211
    ISSN (Electronic): 1867-822X
    Volume: 617 LNICST

ISBN (Print)

9783031925160

ISBN (Electronic)

97830319251775

External Publication IDs

  • handle.net: 10547/626418
  • Scopus: 105012241665

Host publication title

Cloud Computing - 12th EAI International Conference, CloudComp 2024, Proceedings

Host publication editors

  • Xiaohua Feng
  • Patrick Siarry
  • Liangxiu Han
  • Longzhi Yang

Access to documents

Publication metrics