Pervasive Computing and Computer Human Interaction |
|
|
|
|
Topic based feature construction for activity recognition |
GUO Hao dong, CHEN Ling, DING Yong feng, CHEN Gen cai |
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China |
|
|
Abstract A topic based feature construction method was proposed to address the problem that traditional activity recognition methods based on feature extraction heavily depend on the domain knowledge of researchers and the quantity of the training dataset. Based on Symbolic Aggregate approXimation (SAX), the proposed method employed a topic model to discover activity patterns. After preprocessed by dimensionality reduction techniques and symbolic aggregate approximation, the acceleration data were used as document set for the topic model. Pattern mining was completed through topical model to reduce the dimensions of the document data and construct the latent topic related vectors, then vector space model (VSM) was utilized to classify different activities. Results show that SAX based topic model can be well applied on activity recognition, and the proposed method is more effective to improve the recognition accuracy than feature extraction based method and motif discovery based method.
|
Published: 01 June 2016
|
|
运动识别中基于主题的特征构建方法
针对传统基于特征提取的运动识别方法很大程度上依赖研究者的领域知识和训练样本的规模问题,提出一种基于主题的特征构建方法,使用基于符号化聚合近似(SAX)的主题模型对运动模式进行建模.使用降维的方法对加速度原始信号进行预处理,结合时序数据符号化聚合近似化的方法,将SAX化后的时序数据集作为主题分析的文档集.通过主题模型进行模式挖掘,实现文档数据的降维效果,构造隐主题相关的向量,并通过建立空间向量模型(VSM)进行运动识别.实验结果表明:基于符号化聚合近似的主题分析方法可以很好地应用于运动识别,并且与传统基于特征提取的方法和基于模体发现的方法相比,活动识别率明显提升.
|
|
[1] BAO L, INTILLE S. Activity recognition from userannotated acceleration data [C] ∥ Proceedings of International Conference on Pervasive Computing. Vienna: Springer Berlin Heidelberg, 2004: 117.
[2] LARA O, LABRADOR M. A survey on human activity recognition using wearable sensors\[J\]. IEEE Communications Surveys and Tutorials, 2013, 15(3): 1192-1209.
[3] SUN X, LU Z, HU W, et al. SymDetector: detecting soundrelated respiratory symptoms using smartphones [C] ∥ Proceedings of UbiComp. Osaka: ACM, 2015: 97-108.
[4] GREEF L, GOEL M, SEO M et al. Bilicam: using mobile phones to monitor newborn jaundice [C] ∥ Proceedings of UbiComp. Seattle: ACM, 2014: 331-342.
[5] WANG R, HARARI G, HAO P, et al. SmartGPA: how smartphones can assess and predict academic performance of college students [C] ∥ Proceedings of UbiComp. Osaka: ACM, 2015: 295-306.
[6] YE J, STEVENSON G, DOBSON S. KCAR: a knowledgedriven approach for concurrent activity recognition [J]. Pervasive and Mobile Computing, 2015, 19: 47-70.
[7] KWAPISZ J R, WEISS G M, MOORE S A. Activity recognition using cell phone accelerometers [J]. ACM SigKDD Explorations Newsletter, 2011, 12(2): 74-82.
[8] RAVI N, DANDEKAR N, MYSORE P, et al. Activity recognition from accelerometer data [C] ∥ Proceedings of AAAI. Pittsburgh: AAAI, 2005: 1541-1546.
[9] GUO H, CHEN L, SHEN Y, et al. Activity recognition exploiting classifier level fusion of acceleration and physiological signals [C] ∥ Proceedings of UbiComp Adjunct. Seattle: ACM, 2014: 63-66.
[10] PARKKA, J, ERMES M, KORPIPAA P, et al. Activity classification using realistic data from wearable sensors [J]. IEEE Transactions on Information Technology in Biomedicine, 2006, 10(1): 119-128.
[11] 王荣,章韵,陈建新.基于三轴加速度传感器的人体跌倒检测系统设计与实现[J].计算机应用, 2012,32(5): 1450-1452.
WANG Rong, ZHANG Yun, CHEN Jianxin, Design and implementation of fall detection system using triaxis accelerometer [J]. Journal of Computer Applications, 2012, 32(5): 1450-1452.
[12] 王昌喜,杨先军,徐强,等.基于三维加速度传感器的上肢动作识别系统[J].传感技术学报,2010, 23(6): 816-819.
WANG Changxi, YANG Xianjun, XU Qiang, et al. Motion recognition system for upper limbs based on 3D acceleration sensors [J]. Chinese Journal of Sensor and Actuators, 2010, 23(6): 816-819.
[13] MINNEN D, ISBELL C, ESSA I, et al. Detecting subdimensional motifs: an efficient algorithm for generalized multivariate pattern discovery [C] ∥ Proceedings of ICDM. Omaha: IEEE, 2007: 601-606.
[14] LIN J, KEOGH E, PATEL P, et al.. Finding motifs in time series [C] ∥ Proceedings of Workshop on Temporal Data Mining, ACM KDD. Edmonton: ACM, 2002: 53-68.
[15] GUO H, CHEN L, CHEN G, et al. Smartphonebased activity recognition independent of device orientation and placement [J]. International Journal of Communication Systems, 2015.
[16] 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.
HOU Cangjian, CHEN Ling, LV Mingqi, et al. Accelerationbased activity recognition independent of device orientation and placement [J]. Computer Science, 2014, 41(10): 76-79.
[17] LIN J, KEOGH E, WEI L, et al. Experiencing SAX: A novel symbolic representation of time series [J]. Data Mining Knowledge Discovery, 2007, 15(2): 107-144.
[18] HUYNH T, FRITZ M, SCHIELE B. Discovery of activity patterns using topic models [C] ∥ Proceedings of UbiComp. Seoul: ACM, 2008: 1019.
[19] BLEI D M, NG A Y, JORDAN M I. Latent dirichlet allocation [J]. The Journal of machine Learning research, 2003, 3: 993-1022.
[20] HEINRICH G. Parameter estimation for text analysis [R]. Santa Cruz: University of California, 2005. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|