Browse ORBi by ORBi project

- Background
- Content
- Benefits and challenges
- Legal aspects
- Functions and services
- Team
- Help and tutorials

Contingency ranking with respect to overloads in very large power systems taking into account uncertainty, preventive, and corrective actions ; ; et al in IEEE Transactions on Power Systems (2013) This paper deals with day-ahead security management with respect to a postulated set of contingencies, while taking into account uncertainties about the next day generation/load scenario. In order to help ... [more ▼] This paper deals with day-ahead security management with respect to a postulated set of contingencies, while taking into account uncertainties about the next day generation/load scenario. In order to help the system operator in decision making under uncertainty, we aim at ranking these contingencies into four clusters according to the type of control actions needed to cover the worst uncertainty pattern of each contingency with respect to branch overload. To this end we use a fixed point algorithm that loops over two main modules: a discrete bi-level program (BLV) that computes the worst-case scenario, and a special kind of security constrained optimal power flow (SCOPF) which computes optimal preventive/corrective actions to cover the worst-case. We rely on a DC grid model, as the large number of binary variables, the large size of the problem, and the stringent computational requirements preclude the use of existing mixed integer nonlinear programming (MINLP) solvers. Consequently we solve the SCOPF using a mixed integer linear programming (MILP) solver while the BLV is decomposed into a series of MILPs. We provide numerical results with our approach on a very large European system model with 9241 buses and 5126 contingencies. [less ▲] Detailed reference viewed: 70 (8 ULg)Stratégies d'échantillonnage pour l'apprentissage par renforcement batch Fonteneau, Raphaël ; ; Wehenkel, Louis et al in Revue d'Intelligence Artificielle [=RIA] (2013), 27(2), 171-194 We propose two strategies for experiment selection in the context of batch mode reinforcement learning. The ﬁrst strategy is based on the idea that the most interesting experiments to carry out at some ... [more ▼] We propose two strategies for experiment selection in the context of batch mode reinforcement learning. The ﬁrst strategy is based on the idea that the most interesting experiments to carry out at some stage are those that are the most liable to falsify the current hypothesis about the optimal control policy. We cast this idea in a context where a policy learning algorithm and a model identiﬁcation method are given a priori. The second strategy exploits recently published methods for computing bounds on the return of control policies from a set of trajectories in order to sample the state-action space so as to be able to discriminate between optimal and non-optimal policies. Both strategies are experimentally validated, showing promising results. [less ▲] Detailed reference viewed: 53 (7 ULg)Meta-learning of Exploration/Exploitation Strategies: The Multi-Armed Bandit Case ; Wehenkel, Louis ; Ernst, Damien in Filipe, Joaquim; Fred, Ana (Eds.) Agents and Artificial Intelligence: 4th International Conference, ICAART 2012, Vilamoura, Portugal, February 6-8, 2012. Revised Selected Papers (2013) The exploration/exploitation (E/E) dilemma arises naturally in many subﬁelds of Science. Multi-armed bandit problems formalize this dilemma in its canonical form. Most current research in this ﬁeld ... [more ▼] The exploration/exploitation (E/E) dilemma arises naturally in many subﬁelds of Science. Multi-armed bandit problems formalize this dilemma in its canonical form. Most current research in this ﬁeld focuses on generic solutions that can be applied to a wide range of problems. However, in practice, it is often the case that a form of prior information is available about the speciﬁc class of target problems. Prior knowledge is rarely used in current solutions due to the lack of a systematic approach to incorporate it into the E/E strategy. To address a speciﬁc class of E/E problems, we propose to proceed in three steps: (i) model prior knowledge in the form of a probability distribution over the target class of E/E problems; (ii) choose a large hypothesis space of candidate E/E strategies; and (iii), solve an optimization problem to ﬁnd a candidate E/E strategy of maximal average performance over a sample of problems drawn from the prior distribution. We illustrate this meta-learning approach with two different hypothesis spaces: one where E/E strategies are numerically parameterized and another where E/E strategies are represented as small symbolic formulas. We propose appropriate optimization algorithms for both cases. Our experiments, with two-armed “Bernoulli” bandit problems and various playing budgets, show that the metalearnt E/E strategies outperform generic strategies of the literature (UCB1, UCB1-T UNED, UCB-V, KL-UCB and epsilon-GREEDY); they also evaluate the robustness of the learnt E/E strategies, by tests carried out on arms whose rewards follow a truncated Gaussian distribution. [less ▲] Detailed reference viewed: 32 (8 ULg)Experiments with the interior-point method for solving large scale Optimal Power Flow problems ; Wehenkel, Louis in Electric Power Systems Research (2013), 95 This paper reports extensive results obtained with the interior-point method (IPM) for nonlinear programmes (NLPs) stemming from large-scale and severely constrained classical Optimal Power Flow (OPF) and ... [more ▼] This paper reports extensive results obtained with the interior-point method (IPM) for nonlinear programmes (NLPs) stemming from large-scale and severely constrained classical Optimal Power Flow (OPF) and Security-Constrained Optimal Power Flow (SCOPF) problems. The paper discusses transparently the problems encountered such as convergence reliability and speed issues of the method. [less ▲] Detailed reference viewed: 156 (5 ULg)Survival analysis: finding relevant epistatic SNP pairs using Model- Based Multifactor Dimensionality Reduction Van Lishout, François ; ; et al Conference (2012, December 03) Analyzing the combined effects of genes (and/or environmental factors) on the development of complex diseases is quite challenging, both from the statistical and computational perspective, even using a ... [more ▼] Analyzing the combined effects of genes (and/or environmental factors) on the development of complex diseases is quite challenging, both from the statistical and computational perspective, even using a relatively small number of genetic and non-genetic exposures. Several data-mining methods have been proposed for interaction analysis, among them, the Multifactor Dimensionality Reduction Method (MDR). Model-Based Multifactor Dimensionality Reduction (MB-MDR), a relatively new dimensionality reduction technique, is able to unify the best of both nonparametric and parametric worlds, and has proven its utility in a variety of theoretical and practical settings. Until now, MB-MDR software has only accommodated traits that are measured on a binary or interval scale. Time-to-event data could therefore not be analyzed with the MB-MDR methodology. MB-MDR-3.0.0 overcomes this shortcoming of earlier versions. We show the added value of MB-MDR for censored traits by comparing the implemented strategies with more classical methods such as those based on a parametric regression paradigm. The simulation results are supplemented with an application to real-life data. [less ▲] Detailed reference viewed: 73 (8 ULg)Cautious operation planning under uncertainties Capitanescu, Florin ; ; et al in IEEE Transactions on Power Systems (2012), 27(4), 1859-1869 This paper deals with day-ahead power systems security planning under uncertainties, by posing an optimization problem over a set of power injection scenarios that could show up the next day and modeling ... [more ▼] This paper deals with day-ahead power systems security planning under uncertainties, by posing an optimization problem over a set of power injection scenarios that could show up the next day and modeling the next day's real-time control strategies aiming at ensuring security with respect to contingencies by a combination of preventive and corrective controls. We seek to determine whether and which day-ahead decisions must be taken so that for scenarios over the next day there still exists an acceptable combination of preventive and corrective controls ensuring system security for any postulated contingency. We formulate this task as a three-stage feasibility checking problem, where the first stage corresponds to day-ahead decisions, the second stage to preventive control actions, and the third stage to corrective post-contingency controls. We propose a solution approach based on the problem decomposition into successive optimal power flow (OPF) and security-constrained optimal power flow (SCOPF) problems of a special type. Our approach is illustrated on the Nordic32 system and on a 1203-bus model of a real-life system. [less ▲] Detailed reference viewed: 117 (7 ULg)Policy search in a space of simple closed-form formulas: towards interpretability of reinforcement learning Maes, Francis ; Fonteneau, Raphaël ; Wehenkel, Louis et al in Discovery Science 15th International Conference, DS 2012, Lyon, France, October 29-31, 2012. Proceedings (2012, October) In this paper, we address the problem of computing interpretable solutions to reinforcement learning (RL) problems. To this end, we propose a search algorithm over a space of simple losed-form formulas ... [more ▼] In this paper, we address the problem of computing interpretable solutions to reinforcement learning (RL) problems. To this end, we propose a search algorithm over a space of simple losed-form formulas that are used to rank actions. We formalize the search for a high-performance policy as a multi-armed bandit problem where each arm corresponds to a candidate policy canonically represented by its shortest formula-based representation. Experiments, conducted on standard benchmarks, show that this approach manages to determine both efﬁcient and interpretable solutions. [less ▲] Detailed reference viewed: 35 (12 ULg)A rich internet application for remote visualization, collaborative annotation, and automated analysis of large-scale biomages Marée, Raphaël ; Stevens, Benjamin ; Rollus, Loïc et al Poster (2012, October) Detailed reference viewed: 71 (16 ULg)Operating in the fog: security management under uncertainty ; ; Wehenkel, Louis in IEEE Power & Energy Magazine (2012) Detailed reference viewed: 51 (7 ULg)Embedding Monte Carlo search of features in tree-based ensemble methods Maes, Francis ; Geurts, Pierre ; Wehenkel, Louis in Flach, Peter; De Bie, Tijl; Cristianini, Nello (Eds.) Machine Learning and Knowledge Discovery in Data Bases (2012, September) Feature generation is the problem of automatically constructing good features for a given target learning problem. While most feature generation algorithms belong either to the filter or to the wrapper ... [more ▼] Feature generation is the problem of automatically constructing good features for a given target learning problem. While most feature generation algorithms belong either to the filter or to the wrapper approach, this paper focuses on embedded feature generation. We propose a general scheme to embed feature generation in a wide range of tree-based learning algorithms, including single decision trees, random forests and tree boosting. It is based on the formalization of feature construction as a sequential decision making problem addressed by a tractable Monte Carlo search algorithm coupled with node splitting. This leads to fast algorithms that are applicable to large-scale problems. We empirically analyze the performances of these tree-based learners combined or not with the feature generation capability on several standard datasets. [less ▲] Detailed reference viewed: 62 (8 ULg)Mixtures of Bagged Markov Tree Ensembles Schnitzler, François ; Geurts, Pierre ; Wehenkel, Louis in Cano Utrera, Andrès; Gómez-Olmedo, Manuel; Nielsen, Thomas (Eds.) Proceedings of the 6th European Workshop on Probabilistic Graphical Models (2012, September) Markov trees, a probabilistic graphical model for density estimation, can be expanded in the form of a weighted average of Markov Trees. Learning these mixtures or ensembles from observations can be ... [more ▼] Markov trees, a probabilistic graphical model for density estimation, can be expanded in the form of a weighted average of Markov Trees. Learning these mixtures or ensembles from observations can be performed to reduce the bias or the variance of the estimated model. We propose a new combination of both, where the upper level seeks to reduce bias while the lower level seeks to reduce variance. This algorithm is evaluated empirically on datasets generated from a mixture of Markov trees and from other synthetic densities. [less ▲] Detailed reference viewed: 84 (6 ULg)Exploiting the use of DC SCOPF approximation to improve iterative AC SCOPF algorithms ; Capitanescu, Florin ; et al in IEEE Transactions on Power Systems (2012), 27(3), 1459-1466 This paper focuses on improving the solution techniques for the AC SCOPF problem of active power dispatch by using the DC SCOPF approximation within the SCOPF algorithm. Our approach brings two benefits ... [more ▼] This paper focuses on improving the solution techniques for the AC SCOPF problem of active power dispatch by using the DC SCOPF approximation within the SCOPF algorithm. Our approach brings two benefits compared to benchmark SCOPF algorithms: it speeds-up the solution of an iterative AC SCOPF algorithm thanks to a more efficient identification of binding contingencies, and allows improving the objective by an appropriate choice of a limited number of corrective actions for each contingency. The proposed approach is illustrated on 5 test systems of 60, 118, 300, 1203, and 2746 buses. [less ▲] Detailed reference viewed: 110 (9 ULg)Comparator selection for RPC with many labels Hiard, Samuel ; Geurts, Pierre ; Wehenkel, Louis in ECAI 2012 : 20th European Conference on Artificial Intelligence : 27-31 August 2012, Montpellier, France (2012, August) The Ranking by Pairwise Comparison algorithm (RPC) is a well established label ranking method. However, its complexity is of O(N²) in the number N of labels. We present algorithms for selection, before ... [more ▼] The Ranking by Pairwise Comparison algorithm (RPC) is a well established label ranking method. However, its complexity is of O(N²) in the number N of labels. We present algorithms for selection, before model construction, a subset of comparators of size O(N), to reduce the computational complexity without loss in accuracy. [less ▲] Detailed reference viewed: 96 (23 ULg)Wisdom of crowds for robust gene network inference ; ; et al in Nature Methods (2012), 9 Reconstructing gene regulatory networks from high-throughput data is a long-standing challenge. Through the Dialogue on Reverse Engineering Assessment and Methods (DREAM) project, we performed a ... [more ▼] Reconstructing gene regulatory networks from high-throughput data is a long-standing challenge. Through the Dialogue on Reverse Engineering Assessment and Methods (DREAM) project, we performed a comprehensive blind assessment of over 30 network inference methods on Escherichia coli, Staphylococcus aureus, Saccharomyces cerevisiae and in silico microarray data. We characterize the performance, data requirements and inherent biases of different inference approaches, and we provide guidelines for algorithm application and development. We observed that no single inference method performs optimally across all data sets. In contrast, integration of predictions from multiple inference methods shows robust and high performance across diverse data sets. We thereby constructed high-confidence networks for E. coli and S. aureus, each comprising ~ 1,700 transcriptional interactions at a precision of ~50%. We experimentally tested 53 previously unobserved regulatory interactions in E. coli, of which 23 (43%) were supported. Our results establish community-based methods as a powerful and robust tool for the inference of transcriptional gene regulatory networks. [less ▲] Detailed reference viewed: 217 (35 ULg)Decoding spontaneous brain activity from fMRI using Gaussian Processes: tracking brain reactivation Schrouff, Jessica ; Kussé, Caroline ; Wehenkel, Louis et al in 2012 Second International Workshop on Pattern Recognition in NeuroImaging (PRNI 2012): proceedings (2012, July 03) While Multi-Variate Pattern Analysis techniques based on machine learning have now been regularly applied to neuroimaging data, decoding brain activity is usually performed in highly controlled ... [more ▼] While Multi-Variate Pattern Analysis techniques based on machine learning have now been regularly applied to neuroimaging data, decoding brain activity is usually performed in highly controlled experimental paradigms. In more realistic conditions, the number, sequence and duration of mental states are unpredictably generated by the individual, resulting in complex and imbalanced fMRI data sets. Moreover, in the case of spontaneous brain activity, the mental states can not be linked to any external or internal stimulation, which makes it a highly difficult condition to decode. This study tests the classification of brain activity, acquired on 14 volunteers using fMRI, during mental imagery, a condition in which the number and duration of mental events were not externally imposed but self-generated. Application of the obtained model on rest sessions allowed classifying spontaneous brain activity linked to the task which, overall, correlated with their behavioural performance to the task. [less ▲] Detailed reference viewed: 37 (14 ULg)Inferring gene regulatory networks from genetical genomics data Huynh-Thu, Vân Anh ; ; et al Conference (2012, June 01) Detailed reference viewed: 5 (0 ULg)L1-based compression of random forest models Joly, Arnaud ; Schnitzler, François ; Geurts, Pierre et al in Proceeding of the 21st Belgian-Dutch Conference on Machine Learning (2012, May 24) Random forests are effective supervised learning methods applicable to large-scale datasets. However, the space complexity of tree ensembles, in terms of their total number of nodes, is often prohibitive ... [more ▼] Random forests are effective supervised learning methods applicable to large-scale datasets. However, the space complexity of tree ensembles, in terms of their total number of nodes, is often prohibitive, specially in the context of problems with very high-dimensional input spaces. We propose to study their compressibility by applying a L1-based regularization to the set of indicator functions defined by all their nodes. We show experimentally that preserving or even improving the model accuracy while significantly reducing its space complexity is indeed possible. [less ▲] Detailed reference viewed: 239 (57 ULg)Approximation efficace de mélanges bootstrap d’arbres de Markov pour l’estimation de densité Schnitzler, François ; ; et al in Bougrain, Laurent (Ed.) Actes de la 14e Conférence Francophone sur l'Apprentissage Automatique (CAp 2012) (2012, May 23) Nous considérons des algorithmes pour apprendre des Mélanges bootstrap d'Arbres de Markov pour l'estimation de densité. Pour les problèmes comportant un grand nombre de variables et peu d'observations ... [more ▼] Nous considérons des algorithmes pour apprendre des Mélanges bootstrap d'Arbres de Markov pour l'estimation de densité. Pour les problèmes comportant un grand nombre de variables et peu d'observations, ces mélanges estiment généralement mieux la densité qu'un seul arbre appris au maximum de vraisemblance, mais sont plus coûteux à apprendre. C'est pourquoi nous étudions ici un algorithme pour apprendre ces modèles de manière approchée, afin d'accélérer l'apprentissage sans sacrifier la précision. Plus spécifiquement, nous récupérons lors du calcul d'un premier arbre de Markov les arcs qui constituent de bons candidats pour la structure, et ne considérons que ceux-ci lors de l'apprentissage des arbres suivants. Nous comparons cet algorithme à l'algorithme original de mélange, à un arbre appris au maximum de vraisemblance, à un arbre régularisé et à une autre méthode approchée. [less ▲] Detailed reference viewed: 39 (4 ULg)Supervised learning to tune simulated annealing for in silico protein structure prediction Marcos Alvarez, Alejandro ; Maes, Francis ; Wehenkel, Louis in Verleysen, Michel (Ed.) ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (2012, April 25) Simulated annealing is a widely used stochastic optimization algorithm whose efficiency essentially depends on the proposal distribu- tion used to generate the next search state at each step. We propose ... [more ▼] Simulated annealing is a widely used stochastic optimization algorithm whose efficiency essentially depends on the proposal distribu- tion used to generate the next search state at each step. We propose to adapt this distribution to a family of parametric optimization problems by using supervised machine learning on a sample of search states derived from a set of typical runs of the algorithm over this family. We apply this idea in the context of in silico protein structure prediction. [less ▲] Detailed reference viewed: 145 (35 ULg)Statistical interpretation of machine learning-based feature importance scores for biomarker discovery Huynh-Thu, Vân Anh ; ; Wehenkel, Louis et al in Bioinformatics (2012), 28(13), 1766-1774 Motivation: Univariate statistical tests are widely used for biomarker discovery in bioinformatics. These procedures are simple, fast and their output is easily interpretable by biologists but they can ... [more ▼] Motivation: Univariate statistical tests are widely used for biomarker discovery in bioinformatics. These procedures are simple, fast and their output is easily interpretable by biologists but they can only identify variables that provide a significant amount of information in isolation from the other variables. As biological processes are expected to involve complex interactions between variables, univariate methods thus potentially miss some informative biomarkers. Variable relevance scores provided by machine learning techniques, however, are potentially able to highlight multivariate interacting effects, but unlike the p-values returned by univariate tests, these relevance scores are usually not statistically interpretable. This lack of interpretability hampers the determination of a relevance threshold for extracting a feature subset from the rankings and also prevents the wide adoption of these methods by practicians. Results: We evaluated several, existing and novel, procedures that extract relevant features from rankings derived from machine learning approaches. These procedures replace the relevance scores with measures that can be interpreted in a statistical way, such as p-values, false discovery rates, or family wise error rates, for which it is easier to determine a significance level. Experiments were performed on several artificial problems as well as on real microarray datasets. Although the methods differ in terms of computing times and the tradeoff, they achieve in terms of false positives and false negatives, some of them greatly help in the extraction of truly relevant biomarkers and should thus be of great practical interest for biologists and physicians. As a side conclusion, our experiments also clearly highlight that using model performance as a criterion for feature selection is often counter-productive. [less ▲] Detailed reference viewed: 207 (42 ULg) |
||