Human activity monitoring based on hidden Markov models using a smartphone

This paper presents an human sensing (HS) system based on Hidden Markov Models (HMMs) for classifying physical activities: walking, walking-upstairs, walking-downstairs, sitting, standing and lying down. The system includes a feature extractor (developed by the authors and presented in a previous work), an HMMs training module and an HAR module. All experiments have been done using a publicly available dataset named UCI Human Activity Recognition Using Smartphones. The final results using HMMs obtain comparable results to other recognition methods. Some improvements have been obtained when considering a discriminative HMM training procedure. The best result obtains an activity recognition error rate (ARER) of 2.5%. This work is focused on independent activity recognition and extends other works from the same authors focused on activity segmentation and feature extraction.

[1]  Bruno Ando,et al.  Autonomous sensors: From standard to advanced solutions [Instrumentation notes] , 2010, IEEE Instrumentation & Measurement Magazine.

[2]  Davide Anguita,et al.  Energy Efficient Smartphone-Based Activity Recognition using Fixed-Point Arithmetic , 2013, J. Univers. Comput. Sci..

[3]  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.

[4]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[5]  Steve Young,et al.  The HTK book , 1995 .

[6]  Rubén San-Segundo-Hernández,et al.  HMM Adaptation for Improving a Human Activity Recognition System , 2016, Algorithms.

[7]  Rubén San-Segundo-Hernández,et al.  Segmenting human activities based on HMMs using smartphone inertial sensors , 2016, Pervasive Mob. Comput..

[8]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[9]  Rubén San-Segundo-Hernández,et al.  Frequency features and GMM-UBM approach for gait-based person identification using smartphone inertial signals , 2016, Pattern Recognit. Lett..

[10]  W. Marsden.  I and J , 2012 .

[11]  Jeen-Shing Wang,et al.  Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers , 2008, Pattern Recognit. Lett..

[12]  Bruno Ando,et al.  Autonomous Sensors: from Standard to Advanced Solutions , 2010 .

[13]  Arne Leijon,et al.  Continuous Hidden Markov Model for Pedestrian Activity Classification and Gait Analysis , 2013, IEEE Transactions on Instrumentation and Measurement.

[14]  Daniel Povey,et al.  Large scale discriminative training of hidden Markov models for speech recognition , 2002, Comput. Speech Lang..

[15]  Alessandro Ferrero.  Strategic plans [president's perspectives] , 2008 .

[16]  Y.-K. Lee,et al.  Human Activity Recognition via an Accelerometer-Enabled-Smartphone Using Kernel Discriminant Analysis , 2010, 2010 5th International Conference on Future Information Technology.

[17]  Dimitrios Makrakis,et al.  Sensor-based information appliances , 2000 .

[18]  Fernando Fernández Martínez,et al.  Feature extraction from smartphone inertial signals for human activity segmentation , 2016, Signal Process..