| Peer-Reviewed

Human Activity Recognition Based on Weighted Sum Method and Combination of Feature Extraction Methods

Received: 26 April 2018     Accepted: 24 May 2018     Published: 13 June 2018
Views:       Downloads:
Abstract

Human Activity Recognition (HAR) is one of the most important areas of computer vision research. The biggest difficulty for HAR system is that the camera could only film in one direction, leading to a shortage of data and low recognition results. This paper focuses on researching and building new models of HAR, including Principal Components Analysis (PCA), Linear discriminant Analysis (LDA) is to reduce the dimensionality and size of data, contributing to high recognition accuracy. First, from the 3D motion data, we conducted a pretreatment and feature extraction of objects. Next, we built a recognition model corresponding to each feature extraction method and we used Support Vector Machine (SVM) model to train. Finally, we used weighted methods to combine the results of the model to train and give the final results. The paper experiment on CMU MOCAP database and the percentage receiving proposed method is higher than that from the previous method.

Published in International Journal of Intelligent Information Systems (Volume 7, Issue 1)
DOI 10.11648/j.ijiis.20180701.13
Page(s) 9-14
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2018. Published by Science Publishing Group

Keywords

Human Activity Recognition, Principal Components Analysis, Linear Discriminant Analysis, Support Vector Machine

References
[1] Aggarwal K, Lu Xia (2014), “Human Activity Recognition from 3D Data-A Review”, Pattern Recognition Letters, Elsevier B. V, USA.
[2] M. Debyeche, J. P Haton, and A. Houacine “A New Vector Quantization front-end Process for Discrete HMM Speech Recognition System” International Science Index Vol: 1, No: 6, 2007.
[3] CMU Graphics Lab Motion Capture Database. Carnegie Mellon University, Pennsylvania, United States. Website: http://mocap.cs.cmu.edu/
[4] Ahmad Jalal, Shaharyar Kamal, Daijin Kim (2014), “A Depth Video Sensor-Based Life-Logging Human Activity Recognition System for Elderly Care in Smart Indoor Environments”, Sensors-2014.
[5] Kohei Arai, Rosa Andrie Asmara (2013), “3D Skeleton model derived from Kinect Depth Sensor Camera andits application to walking style quality evaluations”, IJARAL – International Journal of Advanced in Artificial Intelligence.
[6] Jolliffe, I. T. (2002), “Principal Component Analysis”, Springer.
[7] Alan J. I. (2012), “Linear Discriminant Analysis”, Springer.
[8] Yong Kim, Olivier de Weck “Adaptive Weighted Sum Method for Multiobjective Optimization” 02139, USA
[9] Steinwart, Ingo, Christmann, Andreas (2008), "Support Vector Machines", Springer.
[10] Adistambha K, Ritz C. H, Burnett I. S (2008), “Motion Classification Using Dynamic Time Warping”, ICPR 2008, IEEE.
[11] N. H. V. NGUYEN, M. T. PHAM, P. H. DO, “Marker Selection for Human Activity Recognition Using Combination of Conformal Geometric Algebra and Principal Component Regression”, SoICT 2016.
[12] N. H. V. NGUYEN, M. T. PHAM, P. H. DO, K. TACHIBANA, “The Fast Gaussian distribution based Adaboost algorithm for Face detection”, ISAT-16.
Cite This Article
  • APA Style

    Nang Hung Van Nguyen, Minh Tuan Pham, Nho Dai Ung, Kanta Tachibana. (2018). Human Activity Recognition Based on Weighted Sum Method and Combination of Feature Extraction Methods. International Journal of Intelligent Information Systems, 7(1), 9-14. https://doi.org/10.11648/j.ijiis.20180701.13

    Copy | Download

    ACS Style

    Nang Hung Van Nguyen; Minh Tuan Pham; Nho Dai Ung; Kanta Tachibana. Human Activity Recognition Based on Weighted Sum Method and Combination of Feature Extraction Methods. Int. J. Intell. Inf. Syst. 2018, 7(1), 9-14. doi: 10.11648/j.ijiis.20180701.13

    Copy | Download

    AMA Style

    Nang Hung Van Nguyen, Minh Tuan Pham, Nho Dai Ung, Kanta Tachibana. Human Activity Recognition Based on Weighted Sum Method and Combination of Feature Extraction Methods. Int J Intell Inf Syst. 2018;7(1):9-14. doi: 10.11648/j.ijiis.20180701.13

    Copy | Download

  • @article{10.11648/j.ijiis.20180701.13,
      author = {Nang Hung Van Nguyen and Minh Tuan Pham and Nho Dai Ung and Kanta Tachibana},
      title = {Human Activity Recognition Based on Weighted Sum Method and Combination of Feature Extraction Methods},
      journal = {International Journal of Intelligent Information Systems},
      volume = {7},
      number = {1},
      pages = {9-14},
      doi = {10.11648/j.ijiis.20180701.13},
      url = {https://doi.org/10.11648/j.ijiis.20180701.13},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijiis.20180701.13},
      abstract = {Human Activity Recognition (HAR) is one of the most important areas of computer vision research. The biggest difficulty for HAR system is that the camera could only film in one direction, leading to a shortage of data and low recognition results. This paper focuses on researching and building new models of HAR, including Principal Components Analysis (PCA), Linear discriminant Analysis (LDA) is to reduce the dimensionality and size of data, contributing to high recognition accuracy. First, from the 3D motion data, we conducted a pretreatment and feature extraction of objects. Next, we built a recognition model corresponding to each feature extraction method and we used Support Vector Machine (SVM) model to train. Finally, we used weighted methods to combine the results of the model to train and give the final results. The paper experiment on CMU MOCAP database and the percentage receiving proposed method is higher than that from the previous method.},
     year = {2018}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Human Activity Recognition Based on Weighted Sum Method and Combination of Feature Extraction Methods
    AU  - Nang Hung Van Nguyen
    AU  - Minh Tuan Pham
    AU  - Nho Dai Ung
    AU  - Kanta Tachibana
    Y1  - 2018/06/13
    PY  - 2018
    N1  - https://doi.org/10.11648/j.ijiis.20180701.13
    DO  - 10.11648/j.ijiis.20180701.13
    T2  - International Journal of Intelligent Information Systems
    JF  - International Journal of Intelligent Information Systems
    JO  - International Journal of Intelligent Information Systems
    SP  - 9
    EP  - 14
    PB  - Science Publishing Group
    SN  - 2328-7683
    UR  - https://doi.org/10.11648/j.ijiis.20180701.13
    AB  - Human Activity Recognition (HAR) is one of the most important areas of computer vision research. The biggest difficulty for HAR system is that the camera could only film in one direction, leading to a shortage of data and low recognition results. This paper focuses on researching and building new models of HAR, including Principal Components Analysis (PCA), Linear discriminant Analysis (LDA) is to reduce the dimensionality and size of data, contributing to high recognition accuracy. First, from the 3D motion data, we conducted a pretreatment and feature extraction of objects. Next, we built a recognition model corresponding to each feature extraction method and we used Support Vector Machine (SVM) model to train. Finally, we used weighted methods to combine the results of the model to train and give the final results. The paper experiment on CMU MOCAP database and the percentage receiving proposed method is higher than that from the previous method.
    VL  - 7
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • Faculty of Information Technology, Danang University of Science and Technology, Danang, Vietnam

  • Faculty of Information Technology, Danang University of Science and Technology, Danang, Vietnam

  • Faculty of Information Technology, Danang University of Science and Technology, Danang, Vietnam

  • Faculty of Informatics, Department of Information System and Applied Mathematecs, Kogakuin University, Tokyo, Japan

  • Sections