Clustering Algorithm for Human Behavior Recognition based on Biosignals Analysis

Time series unsupervised clustering has shown to be accurate in various domains and there is an increased interest in time series clustering algorithms for human behavior recognition. We have developed an algorithm for biosignals clustering, which captures the general morphology of signal’s cycles in one mean wave. In this chapter we further validate and consolidate it and make a quantitative comparison with a state-of-the-art algorithm which uses distances between data’s cepstral coefficients to cluster the same biosignals. We were able to successfully replicate the cepstral coefficients algorithm and the comparison showed that our mean wave approach is more accurate for the type of signals analyzed, having a 19% higher accuracy value. We also tested the mean wave algorithm with biosignals with three different activities in it, and achieved an accuracy of 96.9%. Finally, we performed a noise immunity test with a synthetic signal and noticed that the algorithm remained stable for signal-to- noise ratios higher than 2, only decreasing its accuracy with noise of amplitude equal to the signal. The necessary validation tests performed in this study confirmed the high accuracy level of the developed clustering algorithm for biosignals which express human behavior.