Papers by Bernard Manderick
Springer eBooks, 1996
In order to apply genetic algorithms (GAs) successfully to a given problem one has to find a good... more In order to apply genetic algorithms (GAs) successfully to a given problem one has to find a good representation for potential solutions to that problem. Roughly speaking a good representation is one where building blocks for the problem's solution are relatively insensitive to crossover disruption, ie, the building blocks have short defining lengths. However, such a representation is difficult to find if heuristic or background knowledge about the problem is lacking.
International Journal of Design & Nature and Ecodynamics, Jul 31, 2016
Clustering of high-dimensional biological big data is incredibly difficult and challenging task, ... more Clustering of high-dimensional biological big data is incredibly difficult and challenging task, as the data space is often too big and too messy. The conventional clustering methods can be inefficient and ineffective on high-dimensional biological big data, because traditional distance measures may be dominated by the noise in many dimensions. An additional challenge in biological big data is that we need to find not only the clusters of instances (genes), but also for each cluster a set of features (conditions) that manifest the cluster. In this paper, we propose an ensemble clustering approach with feature selection and grouping for clustering high-dimensional biological big data. It uses two well-approved clustering methods: (a) k-means clustering and (b) similarity-based clustering. This approach selects the most relevant features in the dataset and grouping them into subset of features to overcome the problems associated with the traditional clustering methods. Also, we applied biclustering on each cluster that generated by ensemble clustering to find the sub-matrices in the biological data by the mean squared residue scores. We have applied the proposed clustering method on unlabeled genomic data (148 Exome datasets) of Brugada syndrome to discover previously unknown data patterns. Experiments verify that the proposed clustering method achieved high performance clustering results on high-dimensional biological big data.
ABSTRACT In the stochastic multivariate multi-armed bandit, arms generate a vector of stochastic ... more ABSTRACT In the stochastic multivariate multi-armed bandit, arms generate a vector of stochastic normal rewards, one per objective, instead of a single scalar reward. As a result, there is not only one optimal arm, but there is a set of optimal arms (Pareto front) using Pareto dominance relation. The goal of an agent is to trade-off between exploration and ex-ploitation. Exploration means finding the Pareto front and exploitation means selecting fairly or evenly the optimal arms. We propose annealing-Pareto algorithm that trades-off between exploration and exploitation by using a decaying parameter in combination with Pareto domi-nance relation. We compare experimentally Pareto-KG, Pareto-UCB1 and annealing-Pareto on multi-objective normal distributions and we conclude that the annealing-Pareto is the best performing algorithm.
Handbook of Evolutionary Computation
Skip to main content. VUB Artificial Intelligence Lab. Search form. Search. You are here. Home. F... more Skip to main content. VUB Artificial Intelligence Lab. Search form. Search. You are here. Home. Fitness landscapes. Title, Fitness landscapes. Publication Type, Book Chapter. Year of Publication, 1997. Authors, Deb, K, Altenberg, L, Manderick, B, Mitchell, M, Forrest, S. Book Title, Handbook of Evolutionary Computation. Google Scholar. General Info. Home; Members; News; Contact. Research. Publications; Topics; Projects; Software. For Students. Courses 2011-2012; Thesis Proposals. Links. ...
Particle & Particle Systems Characterization, 2002
The feasibility of the inversion of laser diffraction data for size and shape distribution by neu... more The feasibility of the inversion of laser diffraction data for size and shape distribution by neural networks has been investigated by computer simulation. The size and shape density distributions are represented by only four parameters: the peak positions and the full width at half maximum. Compared to the approach whereby the distributions are represented by a histogram with 30 grid points, the results are an order of magnitude less accurate.
Abstract. In this paper domain knowledge based feature representation and weighting approaches ar... more Abstract. In this paper domain knowledge based feature representation and weighting approaches are proposed for interaction article classification (IAC) task. IAC is a specific text classification application in biological domain and tries to find out which articles describe protein interactions. However, the existing feature representation and weighting scheme commonly used for text mining are not well suited for IAC. We capture and use biological domain knowledge, ie gene mentions also known as protein or gene named entities, to ...
Semi-Markovian causal models (SMCMs) are a recent formalism proposed for performing causal infere... more Semi-Markovian causal models (SMCMs) are a recent formalism proposed for performing causal inference in Bayesian networks with latent variables. At this time, they have only been studied from a theoretical point of view. However, if we want to use these models in practice, some additional questions have to be answered, ie how to actually perform causal inference, how to efficiently perform classical probabilistic inference, and how to determine the structure and the parameters of these models from data? In this ...
Proc. 4 th International Conference on Genetic Algorithms, 1991
Skip to main content. VUB Artificial Intelligence Lab. Search form. Search. You are here. Home. A... more Skip to main content. VUB Artificial Intelligence Lab. Search form. Search. You are here. Home. A massively parallel genetic algorithm. Title, A massively parallel genetic algorithm. Publication Type, Journal Article. Year of Publication, 1991. ...
Uploads
Papers by Bernard Manderick