期刊文献+

基于智能手表的人体行为识别研究 被引量:4

Research of human behavior recognition based on smart watch
下载PDF
导出
摘要 针对现有人体行为识别系统识别精度不高,且不便于日常使用的缺点,提出了一种用于智能手表的神经网络分类算法。采用基于PCA的特征提取方法对Apple Watch智能手表采集到的三轴加速度数据进行特征提取,结合动量-自适应学习率BP神经网络分类算法有效识别出了行走、慢跑、上楼梯、下楼梯四种行为,识别准确率达到82.36%。与朴素贝叶斯算法和决策树分类算法进行对比实验,结果显示基于PCA的神经网络分类算法进行人体行为识别准确率更高。 Most of the existing human behavior recognition systems aren't convenient for daily use andcan't recognize different behavior effectively. In this paper, a neural network classification algorithm isproposed based on smart watch. A feature extraction method based on principal component analysis(PCA) is used to extract features from three axis acceleration data collected from Apple Watch. A BPneural network classification algorithm with momentum and adaptive learning-rate is used to recognizewalking, jogging, upstairs and downstairs effectively, and the recognition accuracy reaches 82.36%.Compared with the Naive Bayes and Decision tree algorithms, the experimental results show that theneural network algorithm based on PCA has better recognition accuracy.
出处 《电子设计工程》 2017年第4期27-31,共5页 Electronic Design Engineering
基金 河南省重点科技攻关项目(152102210249) 中国教育科研网下一代互联网技术创新项目(NGII20150704)
关键词 智能手表 人体行为识别 BP神经网络 主成分分析 smart watch behavior recognition BP neural network PCA
  • 相关文献

参考文献7

二级参考文献54

  • 1宋浩然,廖文帅,赵一鸣.基于加速度传感器ADXL330的高精度计步器[J].传感技术学报,2006,19(4):1005-1008. 被引量:35
  • 2岳田利,彭帮柱,袁亚宏,高振鹏,张菡,赵志华.基于主成分分析法的苹果酒香气质量评价模型的构建[J].农业工程学报,2007,23(6):223-227. 被引量:86
  • 3林松毅,刘静波,叶海青.主成分分析方法在保健食品功能学评价中的应用研究[J].食品科学,2007,28(9):546-548. 被引量:8
  • 4李华,刘勇强,郭安鹊,梁新红,康文怀,陶永胜.运用多元统计分析确定葡萄酒感官特性的描述符[J].中国食品学报,2007,7(4):114-119. 被引量:27
  • 5QIAN Hui-min, MAO Yao-bin, XIANG Wen-be, et al. Recognition of human activities using SVM muhi-class classifier [ J ]. Pattern Recognition Letters,2010,31 (2) :100-111.
  • 6ZAFAR A K, WON S. Abnormal human activity recognition system based on R-transform and kernel discriminant technique for elderly home care[J]. Consumer Electronics,2011,58(4) :1843-1850.
  • 7ADITHYAN P, BHARGAVI R, VAIDEHI V. Abnormal human ac- tivity recognition using SVM based approach [ C ]//Proc of Interna- tional Conference on Recent Trends in Information Technology. 2012: 97-102.
  • 8HE Jin, LI Hua-ming, TAN Jin-dong. Real-time daily activity classi- fication with wireless sensor networks using hidden Markov model [ C ]//Proc of the 29th Annual International Conference of IEEE En- gineering in Medicine and Biology Society. Piscataway : IEEE Press, 2007:3192-3195.
  • 9WEI Hong-xing, HE Jin, TAN Jin-dong. Layered hidden Markov models for real-time daily activity monitoring using body sensor net- works [ J ]. Knowledge and Information Systems, 2011,29 ( 2 ) : 479-494.
  • 10DEREK H H, ZHANG Xian-xing, YIN Jie, et al. Abnormal activity recognition based on HDP-HMM models [ C ]//Proc of the 21 st Inter- national Joint Conference on Artificial Intelligence. San Francisco: Morgan Kaufmann Publishing ,2009 : 1715-1720.

共引文献131

同被引文献26

引证文献4

二级引证文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部