Seminar by Dr. Mounim A. El-Yacoubi (Directeur d'études, HDR Telecom Sud-Paris, France)

Speaker: Dr. Mounim A. El-Yacoubi (Directeur d'études, HDR
Telecom Sud-Paris, France)                                                                                                       

Title: Sequential Representation Learning from Online Handwriting for Characterizing Alzheimer’s Disease

Date: Friday June 28th, 2019

Time: 10:00am - 11:30am

Room:  EV3.309

ABSTRACT

We present, in this seminar, a novel paradigm for assessing Alzheimer’s disease by analyzing impairment of handwriting (HW) on tablets, a challenging problem that is still in its infancy. The state of the art is dominated by methods that assume a unique behavioral trend for each cognitive profile, and that extract global kinematic parameters, assessed by standard statistical tests or classification models, for discriminating the neuropathological disorders (Alzheimer’s (AD), Mild Cognitive Impairment (MCI)) from Healthy Controls (HC). Our work tackles these two major limitations as follows. First, instead of considering a unique behavioral pattern for each cognitive profile, we relax this heavy constraint by allowing the emergence of multimodal behavioral patterns. We achieve this by performing semi or unsupervised learning to uncover homogeneous clusters of subjects, and then we analyze how much information these clusters carry on the cognitive profiles. Second, instead of relying on global kinematic parameters, mostly consisting of their average, we refine the encoding by modeling the full dynamics of each parameter, harnessing thereby the rich temporal information inherently characterizing online HW. Thanks to our modeling, we obtain new findings that are the first of their kind on this research field. In particular, a striking finding is revealed: two major clusters are unveiled, one dominated by HC and MCI subjects, and one by MCI and ES-AD, thus revealing that MCI patients have fine motor skills leaning towards either HC’s or ES-AD’s. Our work introduces a new temporal representation learning from HW trajectories that uncovers a rich set of features simultaneously like the full velocity profile, size and slant, fluidity, and shakiness, and reveals, in a naturally explainable way, how these HW features conjointly characterize, with fine and subtle details, the cognitive profiles.

BIO

Mounim A. El-Yacoubi (PhD, University of Rennes, France, 1996) was with the Service de Recherche Technique de la Poste (SRTP) at Nantes, France, from 1992 to 1996, where he developed software for Handwritten Address Recognition that is still running in Automatic French mail sorting machines. He was a visiting researcher for 18 months at the Centre for Pattern Recognition and Machine Intelligence (CENPARMI) in Montreal, Canada, and then an associated professor (1998-2000) at the Catholic University of Parana (PUC-PR) in Curitiba, Brazil. From 2001 to 2008, he was a Senior Software Engineer at Parascript, Boulder (Colorado, USA), a world leader company in automatic processing of handwritten and printed documents (mail, checks, forms), for which he developed real-life software for address, check and form recognition for several countries in the world. Since June 2008, he is a Professor at Telecom SudParis, Institut Polytechnique de Paris. His main interests include Machine Learning, Pattern Recognition, Human Gesture and Activity recognition, Human Robot Interaction, Video Surveillance and Biometrics, Information Retrieval, and Handwriting Analysis and Recognition.