Publication Restriction temporaireLearn, compare, search : one sawmill’s search for the best cutting patterns across and/or trees(Springer, 2023-10-25) Ménard, Marc-André; Morin, Michael; Khachan, Mohammed; Gaudreault, Jonathan; Quimper, Claude-GuyA sawmilling process scans a wood log and must establish a series of cutting and rotating operations to perform in order to obtain the set of lumbers having the most value. The search space can be expressed as an and/or tree. Providing an optimal solution, however, may take too much time. The complete search for all possibilities can take several minutes per log and there is no guarantee that a high-value cut for a log will be encountered early in the process. Furthermore, sawmills usually have several hundred logs to process and the available computing time is limited. We propose to learn the best branching decisions from previous wood logs and define a metric to compare two wood logs in order to branch first on the options that worked well for similar logs. This approach (Learn, Compare, Search, or LCS) can be injected into the search process, whether we use a basic Depth-First Search (DFS) or the state-of-the-art Monte Carlo Tree Search (MCTS). Experiments were carried on by modifying an industrial wood cutting simulator. When computation time is limited to five seconds, LCS reduced the lost value by 47.42% when using DFS and by 17.86% when using MCTS. Publication Accès libreEffect of confinement on the hydrodynamic performance of a fully-passive oscillating-foil turbine(2022-03-15) Mann, Sierra; Dumas, Guy; Oshkai, PeterAn experimental study was conducted to assess the effects of flow confinement on the hydrodynamic performance of a fully-passive oscillating-foil turbine prototype at a Reynolds number of 19,000. Quantifying confinement effects is necessary for comparison of model-scale confined experiments to full-scale unconfined performance. The experiments were performed using a NACA0015 foil with an aspect ratio of 7.5 in a water tunnel equipped with adjustable lateral walls. The foil was undergoing passive oscillations in pitch and heave degrees-of-freedom. The kinematic parameters of the foil oscillations and its energy harvesting performance were measured at eight blockage ratios, ranging from 21% to 60%. Quantitative flow imaging was performed using particle image velocimetry (PIV), at three confinement levels, to observe the timing of the leading-edge vortex (LEV) formation and shedding. Loading on the foil was related to the flow structure by calculating the moments of vorticity with respect to the pitching axis of the foil. The efficiency and the power coefficient increased with increasing confinement. This result was expected due to the higher incident velocity on the foil in the presence of the confining walls. At the highest level of confinement, the close proximity of the foil to the walls during parts of the oscillation cycle resulted in a change in the phase lag between the pitching and the heaving components of the foil motion. In turn, this shift in the kinematic parameters led to a sharp decrease in the energy-extraction performance of the turbine. Publication Accès libreOrdonnancement dynamique et contrôle intelligent d'un robot industriel(CIGI Qualita MOSIM, 2023-09-01) Neumann, Anas; Rekik, Monia; Morin, Michael; Hajji, Adnène; Pellerin, RobertNous présentons, dans ce papier, un modèle mathématique pour l'ordonnancement dynamique d'un robot industriel de soudure. Le robot étudié réalise différents procédés en parallèle et dispose de plusieurs stations de chargement, de soudure, ainsi que d'un bras mécanique pour déplacer les pièces. Le robot est sujet à des temps de configuration et de déplacement du bras et des pièces. Nous proposons également une méthode d'optimisation basée sur une heuristique de construction puis d'amélioration locale à multiple voisinage. Cette méthode exploite les différentes capacités du robot : exécution en parallèle, déchargement de pièces moins urgentes, etc. Une série d'expérimentations démontre que notre méthode permet de résoudre des problèmes de taille réaliste de 190 opérations en temps réel (moins d'une seconde) insolvables à l'optimalité. Notre approche obtient aussi une solution optimale pour des instances de petite taille. Publication Accès libreSupervised recommendations of gas metal arc welding parameters(Canadian artificial intelligence association, 2023-06-05) Picherit, Tom; Lampron, Louis-Philip; Morin, Michael; Caron-Guillemette, Gabriel; Gaudreault, JonathanIn gas metal arc welding, a weld quality and performance depends on many parameters. Selecting the right ones can be complex, even for an expert. One generally proceeds through trial and error to find a good set of parameters. Therefore, the current experts’ method is not optimized and can require a lot of time and materials. We propose using supervised learning techniques to help experts in their decision-making. To that extent, a two-part recommendation system is proposed. The first step is dedicated to identify, through classification, the number of weld passes. The second one suggests the seven remaining parameter values for each pass: layer, amperage, voltage, wire feed rate, frequency offset, trimming and welding speed. After extracting data from historical Welding Procedure Specification forms, we tested 11 different supervised learning algorithms. The recommendation system is able to provide good results for all the different settings mentioned above even if the data is noisy due to the heuristic nature of the experts’ process. The best classification model is CatBoost with 82.22% average F1 Weighted-Score and the best regression models are Extra Trees or a boosting algorithm with a reduced mean absolute percentage error compared to our baseline. Publication Accès libreExplaining the results of an optimization-based decision support system : a machine learning approach(EDP Sciences, 2017-11-08) Morin, Michael; Thomopoulos, Rallou; Abi-Zeid, Irène; Léger, Maxime; Grondin, François; Pleau, MartinIn this paper, we present work conducted in order to explain the results of a commercial software used for real-time decision support for the flow management of a combined wastewater network. This tool is deployed in many major cities and is used on a daily basis. We apply decision trees to build rules for classifying and interpreting the solutions of the optimization model. Our main goal is to build a classifier that would help a user understand why a proposed solution is good and why other solutions are worse. We demonstrate the feasibility of the approach to our industrial application by generating a large dataset of feasible solutions and classifying them as satisfactory or unsatisfactory based on whether the objective function is a certain percentage higher than the optimal (minimum) objective. We evaluate the performance of the learned classifier on unseen examples. Our results show that our approach is very promising according to reactions from analysts and potential users. Publication Accès libreVers une planification multicritère dans le cadre de missions de recherche et sauvetage terrestres(2011-01-01) Abi-Zeid, Irène; Morin, Michael; Nguyen, Thanh TungLes opérations de recherche et sauvetage nécessitent l'allocation efficace des ressources disponibles dans le but de retrouver un objet de recherche en situation critique (e.g., les survivants d'un incident aéronautique). L'état d'avancement des travaux sur une méthode de planification multicritère des opérations de recherches en milieu terrestre utilisant des outils de système d'informations géographiques, des méthodes de discrétisations par graphes de visibilité et d'accessibilité, des métaheuristiques ainsi que la théorie de la recherche est présentée. Publication Accès libreDecision support for planning maritime search and rescue operations in Canada(SciTePress, 2019-01-01) Abi-Zeid, Irène; Morin, Michael; Nilo, OscarIn this project we constructed and evaluated research artifacts to support Search and Rescue (SAR) mission coordinators in planning searches for missing persons or objects at sea. An iterative heuristic based optimization model was formulated and implemented in a prototype that is integrated in a Decision Support System. Using representative examples, we show that the new planning method can help coordinators with the complex task of allocating search resources to search areas in a way that maximizes the chances of finding survivors quickly. Although developed for the Canadian Coast Guard, our method can be used in other countries. We followed Design Science Research guidelines and our design process was according to the Design Science Research Methodology. The research entry point was client and context initiated and beta testing with users is planned in the spring of 2019. It is expected that our innovative artifacts will contribute to improving the SAR system and saving more lives. Publication Accès libreA kNN approach based on ICP metrics for 3D scans matching : an application to the sawing process(Elsevier, 2021-11-09) Chabanet, Sylvain; Thomas, Philippe; El-Haouzi, Hind Bril; Morin, Michael; Gaudreault, JonathanThe Canadian wood industry use sawing simulators to digitally break a log into a basket of lumbers. However, those simulators tend to be computationally intensive. In some cases, this renders them impractical as decision support tools. Such a use case is the problem of dispatching large volume of wood to several sawmills in order to maximise total yield in dollars. Fast machine learning metamodels were recently proposed to address this issue. However, the approach needs a feature extraction step which could result in a loss of information. Conversely, it was proposed to directly make use of the raw information, available in the 3D scans of the logs typically used by a recent sawmill simulator, in order to retain that information. Here, we improve upon that method by reducing the computational cost incidental with the processing of those raw scans. Publication Accès libreNeural network architectures and feature extraction for lumber production prediction(Canadian Artificial Intelligence Association, 2021-06-08) Martineau, Vincent; Morin, Michael; Gaudreault, Jonathan; Thomas, Philippe; El-Haouzid, Hind Bril; Antonie, Luiza; Moradian Zadeh, PooyaWe tackle the problem of predicting the lumber products resulting from the break down of the logs at a given sawmill. Although previous studies have shown that supervised learning is well suited for that prediction problem, to our knowledge, there exists only one approach using the 3D log scans as inputs and it is based on the iterative closest-point algorithm. In this paper, we evaluate the combination of neural network architectures (multilayer perceptron, residual network and PointNet) and log representation as input (industry know-how-based features, 2D projections, and 3D point clouds) in the context of lumber production prediction. Our study not only shows that it is possible to predict the output of a sawmill using neural networks, but also that there is value in combining industry know-how-based features and 3D point clouds in various network architectures. Publication Accès libreVine copula-based data generation for machine learning with an application to industrial processes(2022-12-02) Sexton, Jean-Thomas; Morin, Michael; Gaudreault, JonathanSynthetic data generation of industrial processes exhibiting non-stationarity and complex, non-linear dependencies between their inputs and outputs is a challenging task. We argue that vine copula models are particularly well suited for this problem and present a method combining limited available data and expert knowledge in order to generate synthetic data by conditionally sampling from a C-Vine, a type of vine copula. We demonstrate our approach by generating synthetic data for a high-speed, sophisticated lumber finishing machine called a wood planer. Publication Accès libreRelaxation of the optimal search path problem with the cop and robber game(2014-09-01) Simard, Frédéric; Morin, Michael; Quimper, Claude-Guy; Laviolette, François; Desharnais, JoséeIn the Optimal Search Path problem from search theory, the objective is to find a finite length searcher’s path that maximizes the probability of detecting a lost wanderer on a graph. We introduce a novel bound on the probability of finding the wanderer in the remaining search time and discuss how this bound is derived from a relaxation of the problem into a game of cop and robber from graph theory. We demonstrate the efficiency of this bound on a constraint programming model of the problem. Publication Accès libreSearch and surveillance in emergency situations : a GIS based approach to construct optimal visibility graphs(ISCRAM, 2013) Morin, Michael; Abi-Zeid, Irène; Nguyen-Dang, Thanh-Tung; Lamontagne, Luc; Maupin, Patrick; Comes, T.; Friedrich, F.; Fortier, S.; Geldermann, J.; Yang, L.We present a methodology to construct optimal visibility graphs from vector and raster terrain data based on the integration of Geographic Information Systems, computational geometry, and integer linear programming. In an emergency situation, the ability to observe an environment, completely or partially, is crucial when searching an area for survivors, missing persons, intruders or anomalies. We first analyze inter-visibility using computational geometry and GIS functions. Then, we optimize the visibility graphs by choosing vertices in a way to either maximize coverage with a given number of watchers or to minimize the number of watchers needed for full coverage. Publication Accès libreDecision Support for Search and Rescue Response Planning(ISCRAM, 2017-05) Morin, Michael; Abi-Zeid, Irène; Quimper, Claude-Guy; Nilo, Oscar; Comes, Tina; Bénaben, Frédérick; Hanachi, Chihab; Lauras, Matthieu; Montarnal, AuréliePlanning, controlling and coordinating search and rescue operations is complex and time is crucial for survivors who must be found quickly. The search planning phase is especially important when the location of the incident is unknown. We propose, implement, solve, and evaluate mathematical models for the multiple rectangular search area problem. The objective is to define optimal or near-optimal feasible search areas for the available search and rescue units that maximize the probability of success. We compare our new model to an existing model on problem instances of realistic size. Our results show that we are able to generate, in a reasonable time, near optimal operationally feasible plans for searches conducted in vast open spaces. In an operational context, this research can increase the chances of finding survivors. Ultimately, as our models get implemented in the Canadian Coast Guard search planning tool, this can translate into more lives being saved. Publication RestreintA 0.13μm CMOS SoC for simultaneous multichannel optogenetics and electrophysiological brain recording(IEEE, 2018-03-12) Gagnon-Turcotte, Gabriel; Ethier, Christian; De Koninck, Yves; Gosselin, BenoitOptogenetics and multi-unit electrophysiological recording are state-of-the-art approaches in neuroscience to observe neural microcircuits in vivo . Thereby, brain-implantable devices incorporating optical stimulation and low-noise data acquisition means have been designed based on custom integrated circuits (IC) to study the brain of small freely behaving laboratory animals. However, no existing IC provides multichannel optogenetic photo-stimulation along with multiunit electrophysiological recording capability within the same die [2-5]. They also lack critical features: they are not multichannel and/or do not include an ADC , or they address only one signal modality [5-6], i.e., either local field potentials (LFP) or action potentials (AP). In this paper, we report an IC for simultaneous multichannel optogenetics and electrophysiological recording addressing both LFP and AP signals all at once. This 0.13μm CMOS chip, which includes 4/10 stimulation/recording channels, is enclosed inside a small wireless optogenetic platform, and is demonstrated with simultaneous in vivo optical stimulation and electrophysiological recordings with a virally mediated Channelrhodopsin-2 (ChR2) rat. Publication RestreintWeight-loss trajectories following sleeve gastrectomy : how much eating behaviors matter?(Wiley, 2022-11-21) Legendre, Maxime; Guenette, Andrée-Anne; Bégin, CatherineBackground: Since 2013, sleeve gastrectomy (SG) has been the most practiced bariatric procedure in Canada. The SG yields good shortterm weight loss results with low complication rates, but some patients experience less weight loss and even weight regain in the long term. This may be partly explained by postoperative maladaptive eating behaviors (MEB). This study aimed (1) to explore the effect of SG on MEB and (2) to explore the impact of MEB on weight-loss trajectories. Publication Accès librePreliminary development of an active planar upper limb rehabilitation robotic device(Washington, DC : Rehabilitation Engineering and Assistive Technology Society of North America (RESNA), 2022-07-13) Lemire, Gabrielle; Latour, Simon; Blanchette, Andréanne; Flamand, Véronique; Campeau-Lecours, AlexandreThis paper presents the development of a low-cost active planar upper limb rehabilitation robotic device, which aims to help in the rehabilitation process of people living with movement disorders. Many people living with conditions such as cerebral palsy, stroke, spinal cord injury or muscular dystrophy experience upper limb impairments (muscle spasticity, lack of selective motor control, muscle weakness or tremors), and require physical and occupational therapy to maintain or gain motor performance. The proposed device is designed to be fixed on a table. Direct current (DC) motors control the two degrees of freedom (DOF) of the mechanism. The user interacts with the device using a handle. The device is designed so that the handle stays in the same orientation all the time. The device offers different levels of assistance to guide planar movements, going from a complete assistance, where the user is guided by the mechanism that performs predefined movements recorded by the therapist, to the addition of resistance during the movement, where the user moves the end effector without the help of the mechanism and the latter adds perturbations.