Comparison Study of Inertial Sensor Signal Combination for Human Activity Recognition based on Convolutional Neural Networks

被引:0
|
作者
Nazari, Farhad [1 ]
Mohajer, Navid [1 ]
Nahavandi, Darius [1 ]
Khosravi, Abbas [1 ]
Nahavandi, Saeid [1 ]
机构
[1] Deakin Univ, Inst Intelligent Syst Res & Innovat IISRI, Melbourne, Vic, Australia
关键词
Human Activity Recognition; Assistive Devices; Convolutional Neural Networks; Classification;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Human Activity Recognition (HAR) is one of the essential building blocks of so many applications like security, monitoring, the internet of things and human-robot interaction. The research community has developed various methodologies to detect human activity based on various input types. However, most of the research in the field has been focused on applications other than human-in-the-centre applications. This paper focused on optimising the input signals to maximise the HAR performance from wearable sensors. A model based on Convolutional Neural Networks (CNN) has been proposed and trained on different signal combinations of three Inertial Measurement Units (IMU) that exhibit the movements of the dominant hand, leg and chest of the subject. The results demonstrate k-fold cross-validation accuracy between 99.77 and 99.98% for signals with the modality of 12 or higher. The performance of lower dimension signals, except signals containing information from both chest and ankle, was far inferior, showing between 73 and 85% accuracy.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] DSCNN: Dimension Separable Convolutional Neural Networks for Character Recognition Based on Inertial Sensor Signal
    Peng, Fan
    Zhuang, Zhendong
    Xue, Yang
    [J]. DOCUMENT ANALYSIS AND RECOGNITION, ICDAR 2021, PT III, 2021, 12823 : 538 - 552
  • [2] Convolutional Neural Networks as Means to Identify Apposite Sensor Combination for Human Activity Recognition
    Khan, Muhammad U. S.
    Abbas, Assad
    Ali, Mazhar
    Jawad, Muhammad
    Khan, Samee U.
    [J]. 2018 IEEE/ACM INTERNATIONAL CONFERECE ON CONNECTED HEALTH: APPLICATIONS, SYSTEMS AND ENGINEERING TECHNOLOGIES (CHASE), 2018, : 45 - 50
  • [3] Optimum signal duration for Human Activity Recognition based on Deep Convolutional Neural Networks
    Nazari, Farhad
    Shajari, Arian
    Nahavandi, Darius
    [J]. 18TH ANNUAL IEEE INTERNATIONAL SYSTEMS CONFERENCE, SYSCON 2024, 2024,
  • [4] Human activity recognition based on the inertial information and convolutional neural network
    Li X.
    Liu X.
    Li Y.
    Cao H.
    Chen Y.
    Lin Y.
    Huang X.
    [J]. Shengwu Yixue Gongchengxue Zazhi/Journal of Biomedical Engineering, 2020, 37 (04): : 596 - 601
  • [5] Activity Recognition from Inertial Sensors with Convolutional Neural Networks
    Quang-Do Ha
    Minh-Triet Tran
    [J]. FUTURE DATA AND SECURITY ENGINEERING, 2017, 10646 : 285 - 298
  • [6] Inertial Sensor-based Human Activity Recognition Using Hybrid Deep Neural Networks
    Lei, Zhanzhi
    Xie, Jinfeng
    Xiao, Liang
    [J]. 2021 14TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2021), 2021,
  • [7] Improved Sensor Based Human Activity Recognition via Hybrid Convolutional and Recurrent Neural Networks
    Perez-Gamboa, Sonia
    Sun, Qingquan
    Zhang, Yan
    [J]. 2021 8TH IEEE INTERNATIONAL SYMPOSIUM ON INERTIAL SENSORS AND SYSTEMS (INERTIAL 2021), 2021,
  • [8] Human Activity Recognition with Convolutional Neural Networks
    Bevilacqua, Antonio
    MacDonald, Kyle
    Rangarej, Aamina
    Widjaya, Venessa
    Caulfield, Brian
    Kechadi, Tahar
    [J]. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2018, PT III, 2019, 11053 : 541 - 552
  • [9] Human Activity Recognition Based on Single Sensor Square HV Acceleration Images and Convolutional Neural Networks
    Mario, Munoz-Organero
    [J]. IEEE SENSORS JOURNAL, 2019, 19 (04) : 1487 - 1498
  • [10] Human Activity Recognition Using Convolutional Neural Networks
    Awad, Omer Fawzi
    Ahmed, Saadaldeen Rashid
    Shaker, Atheel Sabih
    Majeed, Duaa A.
    Hussain, Abadal-Salam T.
    Taha, Taha A.
    [J]. FORTHCOMING NETWORKS AND SUSTAINABILITY IN THE AIOT ERA, VOL 1, FONES-AIOT 2024, 2024, 1035 : 258 - 274