基于改进SVM分类器的动作识别方法
作者:
基金项目:

中央高校基本科研业务费科研专项资助项目(CDJZR12110009)。


A gesture-recognition algorithm based on improved SVM
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [16]
  • |
  • 相似文献 [20]
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    利用智能手机加速度传感器信号,提出一种改进的动作识别方法以降低传统动作识别方法的复杂程度,提高识别率。在特征提取时用盲选法,即用PCA(principal component analysis)进行特征值的降维和去除多维间的干扰,而所选特征没有对应的物理意义;并在分类识别中将遗传算法应用到SVM(support vector machine)分类器参数优化中。通过实验表明,该方法能够对日常的走路、站立、跑及上下楼等动作进行准确的识别。

    Abstract:

    An improved action recognition method is proposed based on the signals acquired by a smart phone acceleration sensor to reduce the complexity of the traditional action recognition method and enhance the recognition rate. The blind selection method is applied in feature extraction stage, which means using principal component analysis (PCA) method to reduce dimensionality and eliminate multi-dimensional interference, while the selected features have no corresponding physical significance. In classification and identification, the genetic algorithm is used to optimize support vector machine (SVM) classifier. Experimental results indicate that the proposed method can accurately recognize actions such as walking, standing, running and climbing stairs.

    参考文献
    [1] Maurer U,Rowe A,Smailagic A,et al.eWatch:a wearable sensor and notification platform[C]//Proceedings of The International Workshop on Wearable and Implantable Body Sensor Networks,April 3-5,2006,Cambridge,MA.[S.l.]:IEEE,2006:142-145.
    [2] 李月香,刘燕,袁涛,等.基于加速度信号的走路模式多级分类算法[J].电子学报,2009,37(8):1794-1798. LI Yuexiang,LIU Yan,,YUAN Tao,et al.Multiple classifierbased walking pattern recognizing algorithm using acceleration signals[J].Acta Electronica Sinica,2009,37(8):1794-1798.(in Chinese)
    [3] He Z Y, Jin L W.Activity recognition from acceleration data using AR model representation and SVM[C]//Proceedinds of 2008 International Conference on Machine Learning and Cybernetics,July 12-15,2008,Kunming,China.[S.l.]:IEEE,2008:2245-2250.
    [4] Nam Y Y,Park J W.Child activity recognition based on cooperative fusion model of a triaxial accelerometer and a barometric pressure sensor[J].IEEE Journal of Biomedical and Health Informatics,2013,17(2):420-426..
    [5] Qian H M,Mao Y B,Xiang W B,et al.Recognition of human activities using SVM multi-class classifier[J].Pattern Recognition Letters,2010,31(2):100-111.
    [6] Song S K.,Jang J,Park S.An efficient method for activity recognition of the elderly using tilt signals of tri-axial acceleration sensor[C]//ICOST 2008 Proceedings of the 6th international conference on Smart Homes and Health Telematics,June 28-July 2,2008,IA,USA.[S.l.]:Springer Berlin Heidelberg,2008,5120:99-104.
    [7] 程琼,庄留杰,付波.基于傅立叶描述子和人工神经网络的步态识别[J].武汉理工大学学报,2008,30(1):127-128.(in Chinese) CHENG Qiong,ZHUANG Liujie,FU Bo.Gait recognition based on fourier descriptors and artificial neural network[J].Journal of Wuhan University of Technology,2008,30(1):127-128.
    [8] 徐川龙.基于三维加速度传感器的人体行为识别[D].杭州:浙江工业大学,2013. XU Chuanlong.Activity recognition method based on triaxial accelerometer[D].Hangzhou:Zhejiang University of Technology,2013.(in Chinese)
    [9] 李丹,陈焱焱,姚志明,等.基于三轴加速度传感器的人体日常体力活动识别系统设计[J].仪表技术,2013,30(9):1-5. LI Dan,CHEN Yanyan,YAO Zhiming,et al.The design of human daily physical activity recognition system based on three axis acceleration sensor[J].Instrumentation Technology,2013,30(9):1-5.(in Chinese)
    [10] 薛洋.基于单个加速度传感器的人体运动模式识别[D].广州:华南理工大学,2011. XUE Yang.Human motion patterns recognition based on single triaxial accelerometer[D].Guangzhou:South China University of Technology,2011.(in Chinese)
    [11] Yang M J,Zheng H R,Wang H Y,et al.Combining feature ranking with PC A:An application to gait analysis[C]//2010 International Conference on Machine Learning and Cybernetics,July 11-14,2010,Qingdao,China.[S.l.]:IEEE,2010:494-499.
    [12] He Z Y,Jin L W.Activity recognition from acceleration data based on discrete consine transform and SVM[C]//2009 IEEE International Conference on Systems,October 11-14,San Antonio,TX.[S.l.]:IEEE,2009:5041-5044.
    [13] 王书舟.支持向量机方法及其应用研究[D].哈尔滨:哈尔滨工业大学,2009. WANG Shuzhou.Support vector machine(SVM)method and its application research[D].Harbin:Harbin Institute of Technology,2009.(in Chinese)
    [14] Albayrak M,Allahverdi N.Development a new mutation operator to solve the traveling salesman problem by aid of genetic algorithms[J].Expert System With Application,2011,38(3):1313-1320.
    [15] He Y,Hui C W.A binary coding genetic algorithm for multi-purpose process scheduling:a case study[J].Chemical Engineering Science,2010,65(16):4816-4828.
    [16] Wang L,Tang D B.Animproved adaptive genetic algorithm based on hormone modulation mechanism for Job-shop scheduling problem[J].Expert Systems with Applications,2011,38(6):7243-7250.
引用本文

王见,陈义,邓帅.基于改进SVM分类器的动作识别方法[J].重庆大学学报,2016,39(1):12-17.

复制
分享
文章指标
  • 点击次数:1492
  • 下载次数: 0
  • HTML阅读次数: 431
  • 引用次数: 0
历史
  • 收稿日期:2015-09-02
  • 在线发布日期: 2016-05-06
文章二维码