Time filter

Source Type

Chicoutimi, Canada

Eddine Khodja D.,British Petroleum | Simard S.,UQAC | Beguenan R.,Royal Military College of Canada
Control Engineering and Applied Informatics

In this paper, an approximation of sigmoid function in polynomial form has been proposed, then this function is optimized in order to implement that on FPGA using the Xilinx library. This implementation aim is to contribute in the hardware integration solutions in the areas such as monitoring, diagnosis, maintenance and control of power system as well as industrial processes. Since the Simulink library provided by Xilinx, has all the blocks that are necessary for the design of Artificial Neural Networks except a few functions such as sigmoid function. Tests results for control and diagnosis with FPGA Device are satisfactory. Source

Quilliot A.,CNRS Laboratory of Informatics, Modeling and Optimization of Systems | Rebaine D.,UQAC
2014 Federated Conference on Computer Science and Information Systems, FedCSIS 2014

We present here new results and algorithms for the Linear Arrangement Problem (LAP). We first propose a new lower bound, which links LAP with the Max Cut Problem, and derive a LIP model as well as a branch/bound algorithm for the general case. Then we focus on the case of interval graphs: we first show that our lower bound is tight for unit interval graphs, and derive an efficient polynomial time approximation algorithm for general interval graphs. © 2014 Polish Information Processing Society. Source

Brahem M.B.,University of Quebec at Chicoutimi | Ayena J.C.,UQAC | Otis M.J.D.,center | Menelas B.-A.J.,UQAC
Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015

Degradation of postural control observed with aging is responsible for balance problems in the elderly, especially during the activity of walking. This gradual loss of performance generates abnormal gait, and therefore increases the risk of falling. This risk worsens in people with neuronal pathologies like Parkinson and Ataxia diseases. Many clinical tests are used for fall assessment such as the Timed up and go (TUG) test. Recently, many works have improved this test by using instrumentation, especially body-worn sensors. However, during the instrumented TUG (iTUG) test, the type of ground can influence risk of falling. In this paper, we present a new methodology for fall risk assessment based on quantitative gait parameters measurement in order to improve instrumented TUG test. The proposed measurement unit is used on different types of ground, which is known to affect human gait. The methodology is closer to the real walking environment and therefore enhances ability to differentiate risks level. Our system assesses the risk of falling's level by quantitative measurement of intrinsic gait parameters using fuzzy logic. He is also able to measure environmental parameters such as temperature, humidity and atmospheric pressure for a better evaluation of the risk in activities of daily living (ADL). © 2015 IEEE. Source

Moutacalli M.T.,UQAC | Bouzouane A.,UQAC | Bouchard B.,UQAC
8th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2015 - Proceedings

Activity recognition is the most challenging stage of technological assistance which offers automatic support, when needed, to elderly and disabled people such as Alzheimer's patients living in smart homes. Many approaches and techniques were proposed for activity recognition while other technological assistance stages were barely explored. In this paper, after presenting our activity recognition approach and explaining how the artificial agent will use it to decide when to intervene offering help, we use time series forecasting in order to better choose the intervention time. © 2015 ACM. Source

Moutacalli M.T.,UQAC | Bouzouane A.,UQAC | Bouchard B.,UQAC
Journal of Ambient Intelligence and Humanized Computing

The many disadvantages of traditional assistance available to elderly and persons with cognitive dysfunction such as patients with Alzheimer’s disease have motivated the research of Technological assistance. The artificial agent, who will support the caregiver, is equipped with hardware and software resources that enable it to observe, analyze, infer and support, when needed, the assisted person. In this paper, we present the various stages of Technological assistance and propose a new algorithm for the step of activities models detection. We also explore an activity prediction step using time series. The experiments were conducted on real data recorded at LIARA smart home and the results are satisfactory. © 2015, Springer-Verlag Berlin Heidelberg. Source

Discover hidden collaborations