IMU-based Human Activity Recognition using Machine Learning and Deep Learning models

Saad Alkharji, Aysha Alteneiji, Kin Poon

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

    3 Scopus citations

    Abstract

    Research into Human Activity Recognition (HAR) with wearable sensors is attracting a lot of attention due to its wide range of applications. In this paper, we use a microcontroller with an integrated Inertial Measurement Unit (IMU) to design various Machine Learning (ML) and Deep Learning (DL) models. Five different activities were captured: walking, walking up a staircase, walking down a staircase, jumping, and falling. Both ML and DL models were trained on a variety of IMU data. A comparison was performed among the models based on their accuracy scores and confusion matrices to determine the most effective one. The proposed LSTM model achieved an accuracy score of 99% when trained with accelerometer and gyroscope data from the IMU.

    Original languageBritish English
    Title of host publication2023 6th International Conference on Signal Processing and Information Security, ICSPIS 2023
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages62-66
    Number of pages5
    ISBN (Electronic)9798350329599
    DOIs
    StatePublished - 2023
    Event6th International Conference on Signal Processing and Information Security, ICSPIS 2023 - Dubai, United Arab Emirates
    Duration: 8 Nov 20239 Nov 2023

    Publication series

    Name2023 6th International Conference on Signal Processing and Information Security, ICSPIS 2023

    Conference

    Conference6th International Conference on Signal Processing and Information Security, ICSPIS 2023
    Country/TerritoryUnited Arab Emirates
    CityDubai
    Period8/11/239/11/23

    Keywords

    • Deep Learning
    • Human Activity Recognition
    • IMU Sensor
    • Machine Learning

    Fingerprint

    Dive into the research topics of 'IMU-based Human Activity Recognition using Machine Learning and Deep Learning models'. Together they form a unique fingerprint.

    Cite this