Ali Karci

MODENAR: Multi-objective differential evolution algorithm for mining numeric association rules

In this paper, a Pareto-based multi-objective differential evolution (DE) algorithm is proposed as a search strategy for mining accurate and comprehensible numeric association rules (ARs) which are optimal in the wider sense that no other rules are superior to them when all objectives are simultaneously considered. The proposed DE guided the search of ARs toward the global Pareto-optimal set while maintaining adequate population diversity to capture as many high-quality ARs as possible. ARs mining problem is formulated as a four-objective optimization problem. Support, confidence value and the comprehensibility of the rule are maximization objectives while the amplitude of the intervals which conforms the itemset and rule is minimization objective. It has been designed to simultaneously search for intervals of numeric attributes and the discovery of ARs which these intervals conform in only single run of DE. Contrary to the methods used as usual, ARs are directly mined without generating frequent itemsets. The proposed DE performs a database-independent approach which does not rely upon the minimum support and the minimum confidence thresholds which are hard to determine for each database. The efficiency of the proposed DE is validated upon synthetic and real databases.

Theory of Saplings Growing Up Algorithm

The saplings sowing and growing up algorithm (SGA) was inspired by a natural events --- evolution of growing up of trees. This algorithm contains two phases: Sowing Phase and Growing up Phase. In this paper, the theoretical foundations of SGA were determined. SGA is defined as a computational model, and it was depicted that there are a collection of Turing Machines for simulating SGA.

Imitation of Bee Reproduction as a Crossover Operator in Genetic Algorithms

There are lots of methods inpired by the natural observations (i.e. fuzzy logic, artificial neural networks, genetic algorithms, simulated annealing algorithms, etc.) This paper proposes a novel crossover operator type inspired by the sexual intercourses of honey bees. The method selects a specific chromo- some in present population as queen bee. While the selected queen bee is one parent of crossover, all the remaining chromosomes have the chance to be next parent for crossover in each generation once. For this purposes, we defined three honey bee crossover methods: In the first method, the chromosome with the best fitness score is queen honey bee and it is a fixed parent for crossover in the current generation. The second method handles the chromosome with the worst fitness score. Finally, queen bee is changed sequentially in each genera- tion.

Novelty in the Generation of Initial Population for Genetic Algorithms

This paper presents a method of generating the initial population of genetic algorithms (GAs) for continuous global optimization by using upper and lower bounds of variables instead of a pseudo-random sequence. In order to make population lead to a more reliable solution, the generated initial population is much more evenly distributed, which can avoid causing rapid clustering around an arbitrary local optimal. Another important point is that the simplicity of a population illustrates the more symmetry, self-similarity, repetitions, periodicity such that they guide the computational process to go ahead to desired aim. We design a GA based on this initial population for global numerical optimization with continuous variables. So, the obtained population is more evenly distributed and resulting GA process is more robust. We executed the proposed algorithm to solve 3 benchmark problems with 128 dimensions and very large number of local minimums. The results showed that the proposed algorithm can find optimal or near-to-optimal solutions.

Efficient automatic exact motif discovery algorithms for biological sequences

ObjectiveThis paper presents an algorithm for the solution of the motif discovery problem (MDP). Methods and materialsMotif discovery problem can be considered in two cases: motifs with insertions/deletions, and motifs without insertions/deletions. The first group motifs can be found by stochastic and approximated methods. The second group can be found by using stochastic and approximated methods, but also deterministic method. We proved that the second group motifs can be found with a deterministic algorithm, and so, it can be said that the second motifs finding is a P-type problem as proved in this paper. Results and conclusionsAn algorithm was proposed in this paper for motif discovery problem. The proposed algorithm finds all motifs which are occurred in the sequence at least two times, and it also finds motifs of various sizes. Due to this case, this algorithm is regarded as Automatic Exact Motif Discovery Algorithm. All motifs of different sizes can be found with this algorithm, and this case was proven in this paper. It shown that automatic exact motif discovery is a P-type problem in this paper. The application of the proposed algorithm has been shown that this algorithm is superior to MEME, MEME3, Motif Sampler, WEEDER, CONSENSUS, AlignACE.

Continuous rotation invariant features for gradient-based texture classification

Four highly discriminative and continuous rotation invariant methods are proposed.We use the Hessian matrix and Gaussian derivative filters.Verified on the CUReT, KTH-TIPS, KTH-TIPS2-a, UIUC and Brodatz texture datasets. Extracting rotation invariant features is a valuable technique for the effective classification of rotation invariant texture. The Histograms of Oriented Gradients (HOG) algorithm has been proved to be theoretically simple, and has been applied in many areas. Also, the co-occurrence HOG (CoHOG) algorithm provides a unified description including both statistical and differential properties of a texture patch. However, HOG and CoHOG have some shortcomings: they discard some important texture information and are not invariant to rotation. In this paper, based on the original HOG and CoHOG algorithms, four novel feature extraction methods are proposed. The first method uses Gaussian derivative filters named GDF-HOG. The second and the third methods use eigenvalues of the Hessian matrix named Eig(Hess)-HOG and Eig(Hess)-CoHOG, respectively. The fourth method exploits the Gaussian and means curvatures to calculate curvatures of the image surface named GM-CoHOG. We have empirically shown that the proposed novel extended HOG and CoHOG methods provide useful information for rotation invariance. The classification results are compared with original HOG and CoHOG algorithms methods on the CUReT, KTH-TIPS, KTH-TIPS2-a and UIUC datasets show that proposed four methods achieve best classification result on all datasets. In addition, we make a comparison with several well-known descriptors. The experiments of rotation invariant analysis are carried out on the Brodatz dataset, and promising results are obtained from those experiments.

Cricket behaviour-based evolutionary computation technique in solving engineering optimization problems

Meta-heuristicalgorithms are widely used in various areas such as engineering, statistics, industrial, image processing, artificial intelligence etc. In this study, the Cricket algorithm which is a novel nature-inspired meta-heuristic algorithm approach which can be used for the solution of some global engineering optimization problems was introduced. This novel approach is a meta-heuristic method that arose from the inspiration of the behaviour of crickets in the nature. It has a structure for the use in the solution of various problems. In the development stage of the algorithm, the good aspects of the Bat, Particle Swarm Optimization and Firefly were experimented for being applied to this algorithm. In addition to this, because of the fact that these insects intercommunicate through sound, the physical principles of sound propagation in the nature were practiced in the algorithm. Thanks to this, the compliance of the algorithm to real life tried to be provided. This new developed approach was applied on the familiar global engineering problems and the obtained results were compared with the results of the algorithm applied to these problems.

Natural Inspired Computational Intelligence Method: Saplings Growing up Algorithm

In this paper, we proposed a new computational method inspired by the cultivating and growing up saplings (trees). Sowing saplings in the nature consists of two steps: Sowing saplings, growing up of saplings (branching, mating, and vaccinating). We inspired by this natural process and developed a computational method which is called sowing and growing up of samplings optimization - saplings growing up algorithm (SGuA). This method contains two phases: sowing phase and growing up phase. The mating operator is a global search operator by exchanging information in the two saplings. Branching operator is a local search operator by changing the branches of a sapling probabilistically. Vaccinating operator is a search operator by using dissimilar saplings. After application of the proposed method to benchmark functions, we observed that this method is superior to genetic algorithms in case of finding better solutions and number of function evaluations.

New interconnection networks: Fibonacci cube and extended Fibonacci cubes based hierarchic networks

Ghose et al. (1995) developed interconnection networks which use hypercubes as the basic building blocks and Duh et al. (1995) used folded hypercubes as the basic building blocks to construct interconnection networks. We used the Fibonacci cube and extended Fibonacci cubes as the basic building blocks to construct new hierarchic interconnection networks. The obtained interconnection networks are better than the Fibonacci cube and extended Fibonacci cubes with respect to average edge connectivity. They are also better than the hypercube and hierarchical cubic network with respect to the network costs.

Sensor Node Deployment Based on Electromagnetism-Like Algorithm in Mobile Wireless Sensor Networks

The dynamic deployment of sensors in wireless networks significantly affects the performance of the network. However, the efficient application of dynamic deployments which determines the positions of the sensors within the network increases the coverage area of the network. As a result of this, dynamic deployment increases the efficiency of the wireless sensor networks (WSNs). In this paper, dynamic deployment was applied to WSNs which consist of mobile sensors by aiming at increasing the coverage area of the network with electromagnetism-like (EM) algorithm which is a population-based optimization algorithm. A new approach has been improved in calculating the coverage rate of the sensors by using binary detection model so as to carry out the dynamic deployments of sensors and it has been thought to reach realistic results efficiently. Simulation results have shown that the EM algorithm can be preferred in the dynamic deployment of mobile sensors within the wireless networks.