casa 24(1): e2

Research Article

IoT based Human Activity Recognition using Deep learning

Download254 downloads
  • @ARTICLE{10.4108/eetcasa.v9i1.2682,
        author={Salman Siddiqui and Anwar Ahmad and Ankur Varshney},
        title={IoT based Human Activity Recognition using Deep learning},
        journal={EAI Endorsed Transactions on Context-aware Systems and Applications},
        volume={9},
        number={1},
        publisher={EAI},
        journal_a={CASA},
        year={2023},
        month={4},
        keywords={Artificial intelligence, Internet of things, MoveNet, Pose estimation, Machine learning},
        doi={10.4108/eetcasa.v9i1.2682}
    }
    
  • Salman Siddiqui
    Anwar Ahmad
    Ankur Varshney
    Year: 2023
    IoT based Human Activity Recognition using Deep learning
    CASA
    EAI
    DOI: 10.4108/eetcasa.v9i1.2682
Salman Siddiqui1,*, Anwar Ahmad1, Ankur Varshney2
  • 1: Jamia Millia Islamia
  • 2: Amdocs Development Center India LLP, Gurgaon, Haryana, India
*Contact email: salman007.rec@gmail.com

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.