Semi-supervised Discovery of Time-series Templates for Gesture Spotting in Activity Recognition

In human activity recognition, gesture spotting can be achieved by comparing the data from on-body sensors with a set of known gesture templates. This work presents a semi-supervised approach to template discovery in which the Dynamic Time Warping distance measure has been embedded in a classic clustering technique. Clustering is used to find a set of template candidates in an unsupervised manner, which are then evaluated by means of a supervised assessment of their classification performance. A cross-validation test over a benchmark dataset showed that our approach yields good results with the advantage of using a single sensor.

[1]  Paul Lukowicz,et al.  Wearable Activity Tracking in Car Manufacturing , 2008, IEEE Pervasive Computing.

[2]  Ricardo Chavarriaga,et al.  Benchmarking classification techniques using the Opportunity human activity dataset , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[3]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[4]  S. Venkatesh,et al.  Online Context Recognition in Multisensor Systems using Dynamic Time Warping , 2005, 2005 International Conference on Intelligent Sensors, Sensor Networks and Information Processing.

[5]  C. J. van Rijsbergen,et al.  Information Retrieval , 1979, Encyclopedia of GIS.

[6]  Paul Lukowicz,et al.  Collecting complex activity datasets in highly rich networked sensor environments , 2010, 2010 Seventh International Conference on Networked Sensing Systems (INSS).

[7]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[8]  Peter J. Rousseeuw,et al.  Clustering by means of medoids , 1987 .

[9]  M. Mathie,et al.  Detection of daily physical activities using a triaxial accelerometer , 2003, Medical and Biological Engineering and Computing.

[10]  Miguel A. Labrador,et al.  Centinela: A human activity recognition system based on acceleration and vital sign data , 2012, Pervasive Mob. Comput..