Robust Human Activity Recognition Using Smartphone Sensors via CT-PCA and Online SVM

被引:157
作者
Chen, Zhenghua [1 ]
Zhu, Qingchang [1 ]
Soh, Yeng Chai [1 ]
Zhang, Le [2 ]
机构
[1] Nanyang Technol Univ, Dept Elect & Elect Engn, Singapore 639798, Singapore
[2] UIUC, ADSC, Singapore Based Res Ctr, Singapore 138632, Singapore
基金
新加坡国家研究基金会;
关键词
Coordinate transformation; human activity recognition; online support vector machine (OSVM); principal component analysis (PCA); smartphone sensors; CLASSIFICATION; ACCELEROMETER; TRACKING;
D O I
10.1109/TII.2017.2712746
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Human activity recognition using either wearable devices or smartphones can benefit various applications including healthcare, fitness, smart home, etc. Instead of using wearable devices which are intrusive and require extra cost, we shall leverage on modern smartphones embedded with a variety of sensors. Due to the flexibility of using smartphones, the recognition accuracy will degrade with orientation, placement, and subject variations. In this paper, we propose a robust human activity recognition system in terms of orientation, placement, and subject variations based on coordinate transformation and principal component analysis (CT-PCA) and online support vector machine (OSVM). The proposed CT-PCA scheme is utilized to eliminate the effect of orientation variations. Experiments show that the proposed scheme significantly improves the activity recognition accuracy and outperforms the state-ofthe- art methods on leave one orientation out experiments, which demonstrates the generalization ability of the proposed scheme on the data from unseen orientations. We also show the effectiveness of this scheme on placement and subject variations. However, the inherent difference of signal properties for different placement and subject dramatically reduces the recognition accuracy, especially for different placement. Thus, we present an efficient OSVM algorithm, that is, online-independent support vector machine (OISVM), which utilizes a small portion of data from the unseen placement or subject to online update the parameters of the SVM algorithm. The experimental results demonstrate the effectiveness of this OISVM algorithm on placement and subject variations.
引用
收藏
页码:3070 / 3080
页数:11
相关论文
共 39 条
[1]  
Abu Alsheikh M, 2016, IEEE NETWORK, V30, P22, DOI 10.1109/MNET.2016.7474340
[2]   Designing a Robust Activity Recognition Framework for Health and Exergaming Using Wearable Sensors [J].
Alshurafa, Nabil ;
Xu, Wenyao ;
Liu, Jason J. ;
Huang, Ming-Chun ;
Mortazavi, Bobak ;
Roberts, Christian K. ;
Sarrafzadeh, Majid .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2014, 18 (05) :1636-1646
[3]  
[Anonymous], 2002, Principal components analysis
[4]  
[Anonymous], SENSOR MANAGER TUTOR
[5]  
[Anonymous], 2010, P 7 INT C UB INT COM
[6]  
[Anonymous], 2006, Matrix, DOI [10.1093/jxb/erm298, DOI 10.1093/JXB/ERM298]
[7]   Human activity recognition using multidimensional indexing [J].
Ben-Arie, J ;
Wang, ZQ ;
Pandit, P ;
Rajaram, S .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (08) :1091-1104
[8]   On the use of ensemble of classifiers for accelerometer-based activity recognition [J].
Catal, Cagatay ;
Tufekci, Selin ;
Pirmit, Elif ;
Kocabag, Guner .
APPLIED SOFT COMPUTING, 2015, 37 :1018-1022
[9]   Applications of support vector machines to cancer classification with microarray data [J].
Chu, F ;
Wang, LP .
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2005, 15 (06) :475-484
[10]   3-D Posture and Gesture Recognition for Interactivity in Smart Spaces [J].
Cuong Tran ;
Trivedi, Mohan Manubhai .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2012, 8 (01) :178-187