Prof. J. Rafael Orozco
Universidad de Antioquia, Colombia
Speech, Language, and Movement Processing to Model Parkinson's Disease
Different movement disorders with different origins produce a wide variety of symptoms. In spite of its high prevalence around the world, diagnosis and monitoring of such disorders are still highly subjective, time-consuming, and expensive. Parkinson’s disease (PD) is the second most prevalent movement disorder in the world and medical evaluations used to assess the neurological state of patients cover many different aspects, including activities of daily living, motor aspects, speech, and depression. Automatic evaluation of PD is a challenging task because several bio-signals and modeling methods are required to produce clinically acceptable/practical results. This talk tries to show different approaches that consider several bio-signals (e.g., speech, gait, and handwriting) and methods of Pattern Recognition with the aim to find suitable models for PD diagnosis and monitoring. Results with classical feature extraction and classification methods will be presented together with experiments with CNN and LSTM architectures.
Prof. Juan Rafael Orozco-Arroyave received the B.S. degree in Electronics Engineering from Universidad de Antioquia in 2004, after which he received a postgraduate in Marketing from EAFIT University. In 2011 he was awarded an M.Sc in Telecommunications from Universidad de Antioquia and in 2015 the Ph.D. degree in Electronics Engineering from Universidad de Antioquia (Medellín, Colombia) and in Computer Science from the Friedrich-Alexander-Universität Erlangen-Nürnberg, (Erlangen, Germany). Currently he is a Full Professor at Universidad de Antioquia, leading its GITA Lab and Adjunct Researcher at the Pattern Recognition Lab in the Friedrich-Alexander-Universität Erlangen-Nürnberg. His research interests include Speech Processing, Pattern Recognition, Digital Communications, Digital Signal Processing, and Signals Theory.