Chercheur·e du réseau


Faculté des sciences
Mounir Boukadoum
Professeur.e
Université du Québec à Montréal (UQÀM)
Faculté des sciences
Département d'informatique
Intérêts de recherche
  • Intelligence artificielle
  • Intelligence computationnelle
  • Conception automatique du matériel et du logiciel
Informations générales
Numéro de téléphone : 
(514) 987-3000 x4565
Numéro de local : 
PK-4540
Principales réalisations
Pattern recognition based on HD-sEMG spatial features extraction for an efficient proportional control of a robotic arm

To enable an efficient alternative control of an assistive robotic arm using electromyographic (EMG) signals, the control method must simultaneously provide both the direction and the velocity. However, the contraction variations of the forearm muscles, used to proportionally control the device’s velocity using a regression method, can disturb the accuracy of the classification used to estimate its direction at the same time. In this paper, the original set of spatial features takes advantage of the 2D structure of an 8 × 8 high-density surface EMG (HD-sEMG) sensor to perform a high accuracy classification while improving the robustness to the contraction variations. Based on the HD-sEMG sensor, different muscular activity images are extracted by applying different spatial filters.

Computer-Aided Diagnosis System for Alzheimer's Disease Using Fuzzy-Possibilistic Tissue Segmentation and SVM Classification

We describe a computer-aided diagnosis (CAD) system for discriminating patients suffering from Alzheimer's disease (AD) dementia and healthy patients. It is based on: 1) a clustering process to assess white matter, gray matter and cerebrospinal fluid volumes from noisy anatomical magnetic resonance (MR) and functional positron emission tomography (PET) brain images 1 1The MR and PET data used in this work were obtained from the Alzheimer's disease Neuroimaging Initiative (ADNI) database (http://adni.loni.usc.edu/).; 2) a classification process that distinguishes the brain images of normal and AD patients. The clustering stage consists of three steps: First, the fuzzy c-means (FCM) algorithm is used for a fuzzy partition of the initial class centroids. Second, fuzzy tissue maps are computed using a possibilistic C-means (PCM) algorithm that uses the FCM partition to obtain the final image clusters.

Fully parallel FPGA Implementation of an Artificial Neural Network Tuned by Genetic Algorithm

An artificial neural network (ANN)-based method for radio-frequency analog circuit synthesis is implemented on a field-programmable gate array (FPGA). The ANN has four hidden layers, with fifteen neurons per hidden layer, and its hyper parameters are tuned by an auxiliary genetic algorithm (GA) that uses deterministic tournament for generation renewal with minimal hardware. The presented work actualizes the inherently parallel nature of ANN processes, doing away with optimizing vector manipulations by conventional serial hardware. Instead, the effort is put on minimizing the resources used by each neuron and maximizing their collective processing power. Moreover, the GA algorithm for hyper parameter tuning is implemented as a parallel process as well. The proposed architecture is validated on a concrete problem, showing its ability to learn the solution to a problem and generalize it to new instances.

Affiliations