phat 18: e1

Research Article

A comparative analysis of classification techniques for human activity recognition using wearable sensors and smart-phones

Download72 downloads
  • @ARTICLE{10.4108/eai.2-11-2021.171752,
        author={Umair Saeed and Kamlesh Kumar and Asif Ali Laghari and Mansoor Ahmed Khuhro and Noman Islam and Ghulam Muhammad Shaikh and Fahad Hussain and Aftab Ahmed Shaikh},
        title={A comparative analysis of classification techniques for human activity recognition using wearable sensors and smart-phones},
        journal={EAI Endorsed Transactions on Pervasive Health and Technology: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={PHAT},
        year={2021},
        month={11},
        keywords={Human activity recognition, multi-class classification, Smart-phone, Wearable sensors, Classifiers, Sensor devices, Business intelligence},
        doi={10.4108/eai.2-11-2021.171752}
    }
    
  • Umair Saeed
    Kamlesh Kumar
    Asif Ali Laghari
    Mansoor Ahmed Khuhro
    Noman Islam
    Ghulam Muhammad Shaikh
    Fahad Hussain
    Aftab Ahmed Shaikh
    Year: 2021
    A comparative analysis of classification techniques for human activity recognition using wearable sensors and smart-phones
    PHAT
    EAI
    DOI: 10.4108/eai.2-11-2021.171752
Umair Saeed1, Kamlesh Kumar1, Asif Ali Laghari1,*, Mansoor Ahmed Khuhro1, Noman Islam2, Ghulam Muhammad Shaikh3, Fahad Hussain1, Aftab Ahmed Shaikh1
  • 1: Sindh Madressatul Islam University, Aiwan-e-Tijarat Road, Karachi, Sindh 74000, Pakistan
  • 2: Iqra University Gulshan Campus, Gulshan-e-Iqbal, Karachi, Sindh, Pakistan
  • 3: Bahria University Karachi Campus, Karachi, Sindh 74000, Pakistan
*Contact email: asif.laghari@smiu.edu.pk

Abstract

INTRODUCTION: In these days, the usage of smart-phones and wearable sensors have increased at an exceptional rate. These smart devices are equipped with different sensors such as gyroscope, accelerometer and GPS. By using these sensors to analyze the activity of the end-user, behavioural characteristics of the user can be captured.

OBJECTIVES: Although smart-phone and wearable devices provide a platform for conducting social, psychological and physical studies, they still have several limitations and challenges.

METHODS: This paper provides a comparative analysis of different classical Machine Learning and Deep Learning algorithms and discusses their accuracy and efficiency for human activity recognition (HAR).

RESULTS and CONCLUSION: The paper has primarily used the data captured using wireless sensor devices placed on different parts of a human body, and then compared the results for different classifiers. The conclusion shows that Deep learning schemes are extremely accurate and efficient in comparison with classical machine learning techniques.