期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2013
卷号：10
期号：3
出版社：IJCSI Press
摘要：Parkinson Disease (PD) patients suffer from a disabling phenomenon called Freezing of Gait (FoG), which can be described as if their feet were 'frozen or stuck, but that the top half of their body was still able to move. In this paper, we make a graphical probabilistic modeling study, \Bayesian Belief Network (BBN) approach\ of a previously collected dataset that represents the measurements of acceleration sensors placed on the ankle, knee and hip of PD patients during their walk. In order to know if this is a traditional BBN model or a causal one, we built a FoG Model and tested its causality behavior, first by forming an Epidemiological Approach, and then, by inferring causal relations based on Additive Noise Models (ANM). Consequently, we built a Bayesian Naive Classifier Model related to FoG. The Bayesian belief Network classifier has the ability to identify the onset of freezing of PD patients, during walking using the extracted features. Promising results appeared when testing the BNC classifier models.
关键词：Parkinson Disease; Freezing of Gait; Bayesian Network; Causality; Data Mining; Epidemiology; Classification.
