计算机科学 ›› 2017, Vol. 44 ›› Issue (2): 313-316.doi: 10.11896/j.issn.1002-137X.2017.02.054
宋辉,王忠民
SONG Hui and WANG Zhong-min
摘要： 为了提高移动用户行为识别的准确率,提出一种基于压缩感知的行为识别方法,其可对原始加速度数据或压缩后的加速度数据进行行为识别。依据压缩感知理论中可以由冗余字典重构数据的原理,将原始三轴加速度数据作为训练样本构造冗余字典,基于该字典求解最小l1范数得到待识别样本的稀疏系数,根据稀疏系数计算并选取最小残差值对应的行为作为识别结果。实验结果表明,该方法识别移动用户行为的准确率可达82.64%,高于传统方法的识别准确率,且对随机投影压缩后的行为数据也具有良好的识别效果。
| [1] SHOAIB M,BOSCH S,INCEL O D, et al.A Survey of Online Activity Recognition Using Mobile Phones[J].Sensors,2015,15(1):2059-2085. [2] HOSEINI-TABATABAEI S A,GLUHAK A,TAFAZOLLI R.A survey on smart phone-based systems for opportunistic user context recognition[J].ACM Computing Surveys (CSUR),2013,45(3):1-51. [3] SHOAIB M,BOSCH S,DURMAZLNCEL O,et al.Fusion ofSmartphone Motion Sensors for Physical Activity Recognition[J].Sensors,2014,14(6):10146-10176. [4] HOU C J,CHEN L,LV M Q,et al.Acceleration-based Activity Recognition Independent of Device Orientation and Placement[J].Computer Science,2014,41(10):76-79.(in Chinese) 侯仓健,陈岭,吕明琪,等.基于加速度传感器的放置方式和位置无关运动识别[J].计算机科学,2014,41(10):76-79. [5] ZHANG M ,SAWCHUK A A.A Feature Selection-based Fra-mework for Human Activity Recognition Using Wearable Multimodal Sensors[C]∥International Conference on Body Area Networks.Beijing,2011. [6] WANG Z M,CAO D.A Feature Selection Method for Behavior Recognition Based on Ant Colony Algorithm[J].Journal of Xi’an University of Posts and Telecommunications,2014,19(1):73-77.(in Chinese) 王忠民,曹栋.基于蚁群算法的行为识别特征优选方法[J].西安邮电大学学报,2014,19(1):73-77. [7] ZHANG M,SAWCHUK A A.Human Daily Activity Recognition With Sparse Representation Using Wearable Sensors[J].IEEE Journal of Biomedical and Health Informatics,2013,17(3):553-560. [8] WU W Y,ZAHGN M,SAWCHUK A A,et al.Co-Recognition of Human Activity and Sensor Location via Compressed Sensing in Wearable Body Sensor Networks[C]∥Ninth International Conference on Wearable and Implantable Body Sensor Networks.London,2012. [9] XIAO L,LI R F,LUO J.Recognition of Human Activity Based on Compressed Sensing in Body Sensor Networks[J].Journal of Electronics & Information Technology,2013,35(1):119-125.(in Chinese) 肖玲,李仁发,罗娟.体域网中一种基于压缩感知的人体行为识别方法[J].电子与信息学报,2013,35(1):119-125. [10] SONG H,WANG Z M.Activity Recognition with Mobile Phone Accelerometers by Using Sparse Matrix Dictionary Method[J].Application Research of Computers,2015,32(9):2590-2592.(in Chinese) 宋辉,王忠民.基于稀疏矩阵字典的移动用户行为识别方法[J].计算机应用研究,2015,32(9):2590-2592. [11] DONOBO D.Compressed Sensing[J].IEEE Transactions on Information Theory,2006,52(4):1289-1306. [12] BARANIUK R,CANDES E,ELAD M,et al.Applications ofSparse Representation and Compressive Sensing [Scanning the Issue][J].Proceedings of The IEEE,2010,98(6):906-909. [13] CANDS E,TAO T.Decoding by linear programming[J].IEEE Transactions on Information Theory,2005,51(12):4203-4215. [14] CANDES E,ROMBERG J, TAO T.Robust Uncertainty Principles:Exact Signal Reconstruction from Highly Incomplete Frequency Information[J].IEEE Transactions on Information Theory,2006,52(2):489-509. [15] AKIMURA D,KAWAHARA Y,ASAMI T.Compressed Sen-sing Method for Human Activity Sensing using Mobile Phone Accelerometers[C]∥Ninth International Conference on Networked Sensing Systems.Belgium,2012. [16] CANDES E,CALTECH J R.l1-Magic:Recovery of Sparse Signals via Convex Programming[EB/OL].(2005-10-1) [2009-01-29].http://statweb.stanford.edu/~candes/l1magic/ downloads/l1magic.pdf. |
| No related articles found! |
|
||
首页