Hidden Markov model a tool for recognition of human contexts using sensors of smart mobile phone

A fast and accurate computational model of HMM (Hidden Markov Model) is proposed for Activity Recognition System using inbuilt sensors of Smart Mobile Phone. Twelve features are calculated from the captured data and the feature vectors are divided into two vectors which are used as inputs to HMM. All computational methods follow probability theories and for measuring differences of two probability based events we used K–L divergence of Kullback and Leibler (Ann Math Stat 22(1):79–86, 1951) known as KLD (Kullback & Leibler Divergence). For comparing of feature values of ground truth and that of experimental values, we have developed an algorithm D-HMM (Divisional-HMM, proposed algorithm). Results show better recognition than existing HF-SVM (Hardware Friendly Support Vector Machine) and also better than our previous work of CFT (Conditional Features using Threshold, a method developed for using different schemes of threshold values for selection and matching purposes of feature values).

[1]  J. K. Mandal,et al.  Activity recognition system using inbuilt sensors of smart mobile phone and minimizing feature vectors , 2015, Microsystem Technologies.

[2]  Matt Welsh,et al.  Sensor networks for medical care , 2005, SenSys '05.

[3]  Shunzheng Yu,et al.  Hidden semi-Markov models , 2010, Artif. Intell..

[4]  Dan Schonfeld,et al.  Object Trajectory-Based Activity Classification and Recognition Using Hidden Markov Models , 2007, IEEE Transactions on Image Processing.

[5]  Jonathon Shlens,et al.  A Tutorial on Principal Component Analysis , 2014, ArXiv.

[6]  Miguel A. Patricio,et al.  Recognizing Human Activities from Sensors Using Hidden Markov Models Constructed by Feature Selection Techniques , 2009, Algorithms.

[7]  Sung-Bae Cho,et al.  Activity Recognition Using Hierarchical Hidden Markov Models on a Smartphone with 3D Accelerometer , 2011, HAIS.

[8]  N. Mukherjee,et al.  Computing aspects of monitoring walking disorder using body sensor network and neural network , 2012, 2012 2nd IEEE International Conference on Parallel, Distributed and Grid Computing.

[9]  Jesús Favela,et al.  Activity Recognition for the Smart Hospital , 2008, IEEE Intelligent Systems.

[10]  Weihua Sheng,et al.  Realtime Recognition of Complex Human Daily Activities Using Human Motion and Location Data , 2012, IEEE Transactions on Biomedical Engineering.

[11]  Lindsay I. Smith,et al.  A tutorial on Principal Components Analysis , 2002 .

[12]  Faicel Chamroukhi,et al.  An Unsupervised Approach for Automatic Activity Recognition Based on Hidden Markov Model Regression , 2013, IEEE Transactions on Automation Science and Engineering.

[13]  Guoliang Xing,et al.  PBN: towards practical activity recognition using smartphone-based body sensor networks , 2011, SenSys.

[14]  C.J. De Luca,et al.  A Combined sEMG and Accelerometer System for Monitoring Functional Activity in Stroke , 2009, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[15]  Bogdan Kwolek,et al.  Activity Recognition Using Probabilistic Timed Automata , 2008 .

[16]  Gwenn Englebienne,et al.  An activity monitoring system for elderly care using generative and discriminative models , 2010, Personal and Ubiquitous Computing.

[17]  Jian Lu,et al.  Real-Time Activity Recognition in Wireless Body Sensor Networks: From Simple Gestures to Complex Activities , 2010, 2010 IEEE 16th International Conference on Embedded and Real-Time Computing Systems and Applications.

[18]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

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

[20]  B. Prabhakaran,et al.  Motion fault detection and isolation in Body Sensor Networks , 2011, 2011 IEEE International Conference on Pervasive Computing and Communications (PerCom).