IoT based Human Activity Recognition using Deep learning

Authors

  • Salman Siddiqui Jamia Millia Islamia image/svg+xml
  • Anwar Ahmad Jamia Millia Islamia image/svg+xml
  • Ankur Varshney Amdocs Development Center India LLP, Gurgaon, Haryana, India

DOI:

https://doi.org/10.4108/eetcasa.v9i1.2682

Keywords:

Artificial intelligence, Internet of things, MoveNet, Pose estimation, Machine learning

Abstract

Artificial intelligence and the Internet of things (IoT) are the fastest and latest growing technologies that can handle a huge amount of data in computing services. This paper presents a smart human activity recognition system based on IoT that can be used for surveillance purposes working as IoT-based armour. Pose estimation model viz. MoveNet has been employed to extract the anatomical key points from RGB video frames. Different subjects from different camera angles were employed to make the approach person-independent. Diverse Machine learning models such as Decision tree, support vector machines, XGboost, and random forest classifiers were employed using extracted keypoints for training the model for estimating human activity during posture estimation monitoring. SMS are sent to the designated person with the raising of buzzer alarm in case of anomalous behaviour detection.

Downloads

Published

20-04-2023

How to Cite

1.
Siddiqui S, Ahmad A, Varshney A. IoT based Human Activity Recognition using Deep learning. EAI Endorsed Trans Context Aware Syst App [Internet]. 2023 Apr. 20 [cited 2024 Jun. 16];9. Available from: https://publications.eai.eu/index.php/casa/article/view/2682