Study of Activity Recognition Dataset Using Combined Probabilistic and Instance Based Algorithms

Abstract

Wide range of applications involve classification process where supervised learningapproaches play a significant role. Improvement of classification accuracy is one ofthe tasks which is most frequently carried out by researchers worldwide. This paperdescribes selected statistical and instance-based approaches and presents hybrid classifierfor Human Activity Recognition. Obtained results outperform solely applicationof each algorithm paradigm to the dataset and strengths the hypothesis for improvingclassification accuracy by using ensembles of classifiers.