Activity Recognition Using Hierarchical Hidden Markov Models on a Smartphone with 3D Accelerometer

As smartphone users have been increased, studies using mobile sensors on smartphone have been investigated in recent years. Activity recognition is one of the active research topics, which can be used for providing users the adaptive services with mobile devices. In this paper, an activity recognition system on a smartphone is proposed where the uncertain time-series acceleration signal is analyzed by using hierarchical hidden Markov models. In order to address the limitations on the memory storage and computational power of the mobile devices, the recognition models are designed hierarchy as actions and activities. We implemented the real-time activity recognition application on a smartphone with the Google android platform, and conducted experiments as well. Experimental results showed the feasibility of the proposed method.

[1]  Kevin B. Korb,et al.  Bayesian Artificial Intelligence , 2004, Computer science and data analysis series.

[2]  Ian F. Akyildiz,et al.  Wireless sensor networks , 2007 .

[3]  Jake K. Aggarwal,et al.  A hierarchical Bayesian network for event recognition of human actions and interactions , 2004, Multimedia Systems.

[4]  Luca Benini,et al.  Activity Recognition from On-Body Sensors: Accuracy-Power Trade-Off by Dynamic Sensor Selection , 2008, EWSN.

[5]  Richard Frisby,et al.  Comparison of Feature Classification Algorithm for Activity Recognition Based on Accelerometer and Heart Rate Data , 2009 .

[6]  Yueting Zhuang.  Advances in Multimedia Information Processing - PCM 2006, 7th Pacific Rim Conference on Multimedia, Hangzhou, China, November 2-4, 2006, Proceedings , 2006, PCM.

[7]  Norbert Gyorbíró,et al.  An Activity Recognition System For Mobile Phones , 2009, Mob. Networks Appl..

[8]  Sa-kwang Song,et al.  A Phone for Human Activity Recognition Using Triaxial Acceleration Sensor , 2008, 2008 Digest of Technical Papers - International Conference on Consumer Electronics.

[9]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[10]  Antonio Krüger,et al.  Exploring the Design Space of Context-aware Recommender Systems that Suggest Mobile Applications , 2010 .

[11]  Tarek F. Abdelzaher,et al.  SATIRE: a software architecture for smart AtTIRE , 2006, MobiSys '06.

[12]  Daniel Zelterman,et al.  Bayesian Artificial Intelligence , 2005, Technometrics.

[13]  Juan M. Corchado,et al.  Hybrid learning machines , 2009, Neurocomputing.

[14]  Andreas Wendemuth,et al.  Hierarchical HMM-based semantic concept labeling model , 2008, 2008 IEEE Spoken Language Technology Workshop.

[15]  Michael Roberts,et al.  Activity-based serendipitous recommendations with the Magitti mobile leisure guide , 2008, CHI.

[16]  Wei-Hua Andrew Wang,et al.  Dynamic Gesture Recognition Based on Dynamic Bayesian Networks , 2007 .

[17]  Matthias Rauterberg,et al.  Entertainment Computing – ICEC 2007 , 2007, Lecture Notes in Computer Science.

[18]  Jeen-Shing Wang,et al.  Activity Recognition Using One Triaxial Accelerometer: A Neuro-fuzzy Classifier with Feature Reduction , 2007, ICEC.

[19]  Sung-Bae Cho,et al.  Activity Recognition based on Multi-modal Sensors using Dynamic Bayesian Networks , 2009 .

[20]  Gary M. Weiss,et al.  Activity recognition using cell phone accelerometers , 2011, SKDD.

[21]  Deborah Estrin,et al.  Improving activity classification for health applications on mobile devices using active and semi-supervised learning , 2010, 2010 4th International Conference on Pervasive Computing Technologies for Healthcare.

[22]  Emilio Corchado,et al.  Hybrid intelligent algorithms and applications , 2010, Inf. Sci..

[23]  Youtian Du,et al.  Interacting Activity Recognition Using Hierarchical Durational-State Dynamic Bayesian Network , 2006, PCM.