This research focuses on the comparison of posture recognition, using a data mining classification approach on the skeleton data stream obtained from Kinect camera. We classified four standard postures including Stand, Sit, Sit on floor and Lie Down. We compared six classifiers, namely, decision tree, neural network, naïve Bayes, support vector machine, logistic regression and random forest in order to find a suitable classifier. Our best results can correctly classify the postures with 97.88% accuracy, 97.40% sensitivity, and 0.991 ROC area under curve using Max-Min normalization with a decision tree classifier on four transformed attributes. Our future work will use the knowledge obtained to classify a wider range of postures of the elderly while watching television, to be a part of a bigger effort to monitor and study elderly behavior at home.
Human posture classification in near real time is a significant challenge in various fields of research. Recently, the use of the Microsoft Kinect system for 3D skeleton detection has shown to be of promise. This work compares four common classifiers and the use of a hybrid approach for classification. The results show that the use of a hybrid genetic algorithm and random forest classifier is able to provide fast and robust human posture classification. Finally, to aid in further development of posture detection, a comprehensive human posture data set while watching television has been generated in this work for benchmarking purpose and made available publicly at http://dlab.sit.kmutt.ac.th/index.php/human-posture-datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.