Spiridon D. Likothanassis

Applying evolutionary computation to the school timetabling problem: The Greek case

In this contribution, an adaptive algorithm based on evolutionary computation techniques is designed, developed and applied to the timetabling problem of educational organizations. Specifically, the proposed algorithm has been used in order to create feasible and efficient timetables for high schools in Greece. The algorithm has been tested exhaustively with real-world input data coming from many different high schools and has been compared with several other effective techniques in order to demonstrate its efficiency and superior performance. Simulation results showed that the algorithm is able to construct a feasible and very efficient timetable more quickly and easily compared to other techniques, thus preventing disagreements and arguments among teachers and assisting each school to operate with its full resources from the beginning of the academic year. Except from that, due to its inherent adaptive behavior it can be used each time satisfying different specific constraints, in order to lead to timetables, thus meeting the different needs that each school may have.

Exchange-Rates Forecasting: A Hybrid Algorithm Based onGenetically Optimized Adaptive Neural Networks

The use of neural networks trained by a new hybrid algorithm is employed on forecasting the Greek Foreign Exchange-Rate Market. Four major currencies, namely the U.S. Dollar (USD), the Deutsche Mark (DEM), the French Franc (FF) and the British Pound (GBP), versus the Greek Drachma, were used as experimental data. The proposed algorithm combines genetic algorithms and a training method based on the localized Extended Kalman Filter (EKF), in order to evolve the structure and train Multi-Layered Perceptron (MLP) neural networks. The goal of this effort is to predict, as accurately as possible, exchange-rates future behavior. Simulation results show that the method gives highly successful results, while the diversification of the structure between the four currencies has no effect on the performance.

Nonlinear model structure identification of complex biomedical data using a genetic-programming-based technique

In this contribution, a genetic programming (GP)-based technique, which combines the ability of GP to explore both automatically and effectively, the whole set of candidate model structures and the robustness of evolutionary multimodel partitioning filters, is presented. The method is applied to the nonlinear system identification problem of complex biomedical data. Simulation results show that the algorithm identifies the true model and the true values of the unknown parameters for each different model structure, thus assisting the GP technique to converge more quickly to the (near) optimal model structure. The method has all the known advantages of the evolutionary multimodel partitioning filters, that is, it is not restricted to the Gaussian case; it is applicable to on-line/adaptive operation and is computationally efficient. Furthermore, it can be realized in a parallel processing fashion, a fact which makes it amenable to very large scale integration implementation.

A genetic algorithm approach to school timetabling

An adaptive algorithm based on computational intelligence techniques is designed, developed and applied to the timetabling problem of educational organizations. The proposed genetic algorithm is used in order to create feasible and efficient timetables for high schools in Greece. In order to demonstrate the efficiency of the proposed genetic algorithm, exhaustive experiments with real-world input data coming from many different high schools in the city of Patras have been conducted. As well as that, in order to demonstrate the superior performance of the proposed algorithm, we compare its experimental results with the results obtained by another effective algorithm applied to the same problem. Simulation results showed that the proposed algorithm outperforms other existing attempts. However, the most significant contribution of the paper is that the proposed algorithm allows for criteria adaptation, thus producing different timetables for different constraints priorities. So, the proposed approach, due to its inherent adaptive capabilities, can be used, each time satisfying different specific constraints, in order to lead to different timetables, thus meeting the different needs that each school may have.

A generic applied evolutionary hybrid technique

In this contribution, a generic applied evolutionary hybrid technique that combines the effectiveness of adaptive multimodel partitioning filters and genetic algorithm (GAs) robustness has been designed, developed, and applied in real-world adaptive system modeling and information mining problems. The method can be applied to linear and nonlinear real-world data, is not restricted to the Gaussian case, is computationally efficient, and is applicable to online/adaptive operation. Furthermore, it can be realized in a parallel processing fashion, a fact that makes it amenable to very large scale integration (VLSI) implementation.

AR model identification with unknown process order

A method for simultaneous autoregressive (AR) model order selection and identification is proposed, which is based on the adaptive Lainiotis filter (ALF). The method is not restricted to the Gaussian case, is applicable to online/adaptive operation, and is computationally efficient. It can be realized in a parallel processing fashion. The AR model order selection and identification problem is reformulated so that it can be fitted into the framework of a state space under uncertainty estimation problem framework. The ALF is briefly presented and its application to the specific problem is discussed. Simulation examples are presented to demonstrate the superior performance of the method in comparison with previously reported ones. >

Genetically determined variable structure multiple model estimation

In this paper, the multimodel partitioning theory is combined with genetic algorithms to produce a new generation of multimodel partitioning filters, whose structure varies to conform to a model set being determined dynamically and on-line by using a suitably designed genetic algorithm. The proposed algorithm does not require any knowledge of the model switching law, is practically implementable, and exhibits superior performance compared with a fixed-structure multimodel partitioning filter (MMPF), as indicated by simulation experiments.

Which clustering algorithm is better for predicting protein complexes

BackgroundProtein-Protein interactions (PPI) play a key role in determining the outcome of most cellular processes. The correct identification and characterization of protein interactions and the networks, which they comprise, is critical for understanding the molecular mechanisms within the cell. Large-scale techniques such as pull down assays and tandem affinity purification are used in order to detect protein interactions in an organism. Today, relatively new high-throughput methods like yeast two hybrid, mass spectrometry, microarrays, and phage display are also used to reveal protein interaction networks.ResultsIn this paper we evaluated four different clustering algorithms using six different interaction datasets. We parameterized the MCL, Spectral, RNSC and Affinity Propagation algorithms and applied them to six PPI datasets produced experimentally by Yeast 2 Hybrid (Y2H) and Tandem Affinity Purification (TAP) methods. The predicted clusters, so called protein complexes, were then compared and benchmarked with already known complexes stored in published databases.ConclusionsWhile results may differ upon parameterization, the MCL and RNSC algorithms seem to be more promising and more accurate at predicting PPI complexes. Moreover, they predict more complexes than other reviewed algorithms in absolute numbers. On the other hand the spectral clustering algorithm achieves the highest valid prediction rate in our experiments. However, it is nearly always outperformed by both RNSC and MCL in terms of the geometrical accuracy while it generates the fewest valid clusters than any other reviewed algorithm. This article demonstrates various metrics to evaluate the accuracy of such predictions as they are presented in the text below. Supplementary material can be found at: http://www.bioacademy.gr/bioinformatics/projects/ppireview.htm

An Evolutionary Annealing Approach to Graph Coloring

This paper presents a new heuristic algorithm for the graph coloring problem based on a combination of genetic algorithms and simulated annealing. Our algorithm exploits a novel crossover operator for graph coloring. Moreover, we investigate various ways in which simulated annealing can be used to enhance the performance of an evolutionary algorithm. Experiments performed on various collections of instances have justified the potential of this approach. We also discuss some possible enhancements and directions for further research.

Kernel-based self-organized maps trained with supervised bias for gene expression data analysis.

Clustering is a popular data analysis technique that aims to provide insight into the structure of the data and aids at the discovery of functional classes. Gene expression analysis, utilizes clustering techniques extensively. These techniques accomplish the grouping of genes with similar expression patterns into clusters [6, 11, 18, 19]. Such approaches unravel relations between genes and help to deduce their biological role, since genes of similar function tend to display similar expression patterns.