Long-term Activities Segmentation using Viterbi Algorithm with a k-minimum-consecutive-states Constraint

Abstract In the last years, several works have made use of acceleration sensors to recognize simple physical activities like: walking, running, sleeping, falling, etc. Many of them rely on segmenting the data into fixed time windows and computing time domain and/or frequency domain features to train a classifier. A long-term activity is composed of a collection of simple activities and may last from a few minutes to several hours (e.g., shopping, exercising, working, etc.). Since long-term activities are more complex and their duration varies greatly, generating fixed length segments is not suitable. For this type of activities the segmentation should be done dynamically. In this work we propose the use of the Viterbi algorithm on a Hidden Markov Model with the addition of a k-minimum-consecutive-states constraint to perform the long-term activity recognition and segmentation from accelerometer data. This constraint allows the algorithm to perform a more informed search by incorporating prior knowledge about the minimum duration of each long-term activity . Our experiments showed good results for the activity recognition task and it was demonstrated that the accuracy was significantly increased by adding the k-minimum-consecutive-states constraint.

[1]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[2]  Bernt Schiele,et al.  Scalable Recognition of Daily Activities with Wearable Sensors , 2007, LoCA.

[3]  Angelo M. Sabatini,et al.  Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers , 2010, Sensors.

[4]  Ian H. Witten,et al.  Data mining - practical machine learning tools and techniques, Second Edition , 2005, The Morgan Kaufmann series in data management systems.

[5]  Ian Witten,et al.  Data Mining , 2000 .

[6]  Andrew J. Viterbi,et al.  Error bounds for convolutional codes and an asymptotically optimum decoding algorithm , 1967, IEEE Trans. Inf. Theory.

[7]  Ramón F. Brena,et al.  Long-Term Activity Recognition from Accelerometer Data , 2013 .

[8]  Mi Zhang,et al.  Motion primitive-based human activity recognition using a bag-of-features approach , 2012, IHI '12.

[9]  Huosheng Hu,et al.  CES-513 Stages for Developing Control Systems using EMG and EEG Signals: A survey , 2011 .

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

[11]  Jian Lu,et al.  epSICAR: An Emerging Patterns based approach to sequential, interleaved and Concurrent Activity Recognition , 2009, 2009 IEEE International Conference on Pervasive Computing and Communications.

[12]  Bernt Schiele,et al.  Discovery of activity patterns using topic models , 2008 .

[13]  Van Nostrand,et al.  Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm , 1967 .

[14]  Juan-Luis Gorricho,et al.  Activity Recognition from Accelerometer Data on a Mobile Phone , 2009, IWANN.

[15]  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.

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

[17]  Jr. G. Forney,et al.  The viterbi algorithm , 1973 .

[18]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .