A Class Incremental Extreme Learning Machine for Activity Recognition

Automatic activity recognition is an important problem in cognitive systems. Mobile phone-based activity recognition is an attractive research topic because it is unobtrusive. There are many activity recognition models that can infer a user’s activity from sensor data. However, most of them lack class incremental learning abilities. That is, the trained models can only recognize activities that were included in the training phase, and new activities cannot be added in a follow-up phase. We propose a class incremental extreme learning machine (CIELM). It (1) builds an activity recognition model from labeled samples using an extreme learning machine algorithm without iterations; (2) adds new output nodes that correspond to new activities; and (3) only requires labeled samples of new activities and not previously used training data. We have tested the method using activity data. Our results demonstrated that the CIELM algorithm is stable and can achieve a similar recognition accuracy to the batch learning method.

[1]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[2]  Vincent M. Stanford,et al.  Wearable Computing Goes Live in Industry , 2002, IEEE Pervasive Comput..

[3]  John M. Henderson,et al.  Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion , 2011, Cognitive Computation.

[4]  Shanshan Chen,et al.  Unsupervised activity clustering to estimate energy expenditure with a single body sensor , 2013, 2013 IEEE International Conference on Body Sensor Networks.

[5]  Diogo R. Ferreira,et al.  Preprocessing techniques for context recognition from accelerometer data , 2010, Personal and Ubiquitous Computing.

[6]  Yiqiang Chen,et al.  Surrounding context and episode awareness using dynamic Bluetooth data , 2012, UbiComp '12.

[7]  John C. Platt.  A Resource-Allocating Network for Function Interpolation , 1991, Neural Computation.

[8]  Sangeeta Bhattacharya,et al.  Jog Falls: A Pervasive Healthcare Platform for Diabetes Management , 2010, Pervasive.

[9]  Yiqiang Chen,et al.  Cross-People Mobile-Phone Based Activity Recognition , 2011, IJCAI.

[10]  Ye Xu,et al.  Enabling large-scale human activity inference on smartphones using community similarity networks (csn) , 2011, UbiComp '11.

[11]  Fanglin Chen,et al.  Unobtrusive sleep monitoring using smartphones , 2013, 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops.

[12]  Narasimhan Sundararajan,et al.  An efficient sequential learning algorithm for growing and pruning RBF (GAP-RBF) networks , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Leslie G. Valiant,et al.  Cognitive computation , 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

[14]  Erik Cambria,et al.  Sentic Computing: Techniques, Tools, and Applications , 2012 .

[15]  Daniel Roggen,et al.  Designing and sharing activity recognition systems across platforms , 2011 .

[16]  Paul Lukowicz,et al.  Performance metrics for activity recognition , 2011, TIST.

[17]  Shuangquan Wang,et al.  Online sequential ELM based transfer learning for transportation mode recognition , 2013, 2013 IEEE Conference on Cybernetics and Intelligent Systems (CIS).

[18]  Yiqiang Chen,et al.  MINING USER GOALS FOR INDOOR LOCATION‐BASED SERVICES WITH LOW ENERGY AND HIGH QoS , 2010, Comput. Intell..

[19]  Erik Cambria,et al.  Common Sense Knowledge for Handwritten Chinese Text Recognition , 2013, Cognitive Computation.

[20]  Agata Brajdic,et al.  Walk detection and step counting on unconstrained smartphones , 2013, UbiComp.

[21]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[22]  Shuangquan Wang,et al.  Extreme learning machine-based device displacement free activity recognition model , 2012, Soft Comput..

[23]  Björn W. Schuller,et al.  Bidirectional LSTM Networks for Context-Sensitive Keyword Detection in a Cognitive Virtual Agent Framework , 2010, Cognitive Computation.

[24]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[25]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[26]  Andrew T. Campbell,et al.  Cooperative Communities (CoCo): Exploiting Social Networks for Large-scale Modeling of Human Behavior , 2011 .

[27]  Shuangquan Wang,et al.  Inferring social contextual behavior from bluetooth traces , 2013, UbiComp.

[28]  Ye Xu,et al.  Exploiting Social Networks for Large-Scale Human Behavior Modeling , 2011, IEEE Pervasive Computing.