Realization of wearable sensors-based human activity recognition with an augmented feature group

Feature extraction is a critical stage in human activity recognition. The information carried in features directly affects the classification performance. This paper explores a new group of features for activity recognition, which have not been broadly applied in previous works in this field. The newly introduced features are related to the attitude of the on-body devices, being extracted from both time-domain and frequency-domain. Based on the collected data, we implemented certain standard data mining techniques, e.g., the Minimum-Redundancy-Maximum-Relevance (mRMR) algorithm for feature selection, and Support Vector Machine (SVM) for classification, to evaluate the performance of the hypothesis. The comparison studies suggest the augmented features perform better than the commonly used features, giving a higher recognition accuracy of 93.46%. Exploring new features without adding more sensors, while improving the accuracy significantly, enables an efficient extraction of features from limited availability of sensors.

[1]  Valentina Bianchi,et al.  MuSA: Wearable Multi Sensor Assistant for Human Activity Recognition and Indoor Localization , 2015 .

[2]  Victor Callaghan,et al.  An Efficient Feature Selection Method for Activity Classification , 2014, 2014 International Conference on Intelligent Environments.

[3]  Majid Sarrafzadeh,et al.  Determining the Single Best Axis for Exercise Repetition Recognition and Counting on SmartWatches , 2014, 2014 11th International Conference on Wearable and Implantable Body Sensor Networks.

[4]  Özlem Durmaz Incel,et al.  Multimodal Wireless Sensor Network-Based Ambient Assisted Living in Real Homes with Multiple Residents , 2014, Sensors.

[5]  Hristijan Gjoreski,et al.  Activity/Posture Recognition using Wearable Sensors Placed on Different Body Locations , 2011 .

[6]  H. Abdi,et al.  Principal component analysis , 2010 .

[7]  Joan Cabestany,et al.  SVM-based posture identification with a single waist-located triaxial accelerometer , 2013, Expert Syst. Appl..

[8]  Shuangquan Wang,et al.  b-COELM: A fast, lightweight and accurate activity recognition model for mini-wearable devices , 2014, Pervasive Mob. Comput..

[9]  Hongnian Yu,et al.  A practical multi-sensor activity recognition system for home-based care , 2014, Decis. Support Syst..

[10]  Jane Labadin,et al.  Feature selection based on mutual information , 2015, 2015 9th International Conference on IT in Asia (CITA).

[11]  Nadia Magnenat-Thalmann,et al.  Fall Detection Based on Body Part Tracking Using a Depth Camera , 2015, IEEE Journal of Biomedical and Health Informatics.

[12]  Basel Kikhia,et al.  Optimal Placement of Accelerometers for the Detection of Everyday Activities , 2013, Sensors.

[13]  Bernt Schiele,et al.  A tutorial on human activity recognition using body-worn inertial sensors , 2014, CSUR.

[14]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[15]  Tanja Schultz,et al.  Recognizing Hand and Finger Gestures with IMU based Motion and EMG based Muscle Activity Sensing , 2015, BIOSIGNALS.

[16]  Donald Y. C. Lie,et al.  A real-time fall detection system using a wearable gait analysis sensor and a Support Vector Machine (SVM) classifier , 2015, 2015 Eighth International Conference on Mobile Computing and Ubiquitous Networking (ICMU).

[17]  Nigel H. Lovell,et al.  Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring , 2006, IEEE Transactions on Information Technology in Biomedicine.

[18]  Gavin Brown,et al.  Conditional Likelihood Maximisation: A Unifying Framework for Information Theoretic Feature Selection , 2012, J. Mach. Learn. Res..