计算机应用 ›› 2016, Vol. 36 ›› Issue (12): 3353-3357.DOI: 10.11772/j.issn.1001-9081.2016.12.3353

• 人工智能 • 上一篇    下一篇

高可信度加权的多分类器融合行为识别模型

王忠民, 王科, 贺炎   

  1. 西安邮电大学 计算机学院, 西安 710121
  • 收稿日期:2016-06-06 修回日期:2016-07-01 出版日期:2016-12-10 发布日期:2016-12-08
  • 通讯作者: 王科
  • 作者简介:王忠民(1967-),男,陕西蒲城人,教授,博士,CCF会员,主要研究方向:嵌入式系统、智能信息处理;王科(1988-),女,山西大同人,硕士研究生,主要研究方向:嵌入式系统;贺炎(1980-),女,湖南湘乡人,讲师,硕士,主要研究方向:机器学习、移动搜索。
  • 基金资助:
    国家自然科学基金资助项目(61373116);陕西省教育科学“十二五”规划课题项目(SGH140601);陕西省教育厅项目(15JK1653);西安邮电大学校青年基金资助项目(ZL2014-27)。

Multiple classifier fusion model for activity recognition based on high reliability weighted

WANG Zhongmin, WANG Ke, HE Yan   

  1. School of Computer Science & Technology, Xi'an University of Posts & Telecommunications, Xi'an Shaanxi 710121, China
  • Received:2016-06-06 Revised:2016-07-01 Online:2016-12-10 Published:2016-12-08
  • Supported by:
    This work is partially supported by the National Nature Science Foundation of China (61373116), the 12th Five-Year Plan Program of Shaanxi Province Education Science (SGH140601), the Department of Education Program of Shaanxi Province (15JK1653), the Youth Fund Program of Xi'an University of Posts & Telecommunications (ZL2014-27).

摘要: 为了提高基于智能移动设备的人体日常行为识别准确率,提出一种高可信度加权的多分类器融合行为识别模型(MCFM)。针对不同智能设备内置加速度传感器获取的三轴加速度信息,优选出与人体行为相关度高的特征集作为该模型的输入,将决策树、支持向量机以及反向传播(BP)神经网络三个基分类器通过高可信度加权投票算(HRWV)法训练出一个新的融合分类器。实验结果表明,所提出的分类器融合模型能有效提高行为识别的准确率,对静止、散步、跑步、上楼及下楼五种日常行为的平均识别准确率达到94.88%。

关键词: 行为识别, 三轴加速度, 高可信度加权, 基分类器, 融合分类器

Abstract: To improve the recognition accuracy of human activity based on the smart mobile device, an Multiple Classifier Fusion Model for activity recognition (MCFM) based on high reliability weighting was proposed. According to the triaxial acceleration imformation obtained by different smart device with built-in acceleration sensor, those features of high correlation with human daily activities were extracted from the original acceleration as the input of MCFM. Then the three base classifiers of decision tree, Support Vector Machine (SVM) and Back Propagation (BP) neural network were trained for a new fusion classifier by using the High Reliability Weighted Voting (HRWV) algorithm. The experimental results show that the the proposed classifier fusion model can effectively improve the accuracy of human activity recognition, its average recognition accuracy of the five daily activities (stay, walk, run, stairs, downstairs) reaches 94.88%.

Key words: activity recognition, triaxial acceleration, high reliability weight, base classifier, fusion classifier

中图分类号: