Yilmaz Atay

Community detection from biological and social networks

Display Omitted We propose six metaheuristic optimization algorithms to solve the community detection (CD) problem.The proposed algorithms have been modified in order to use for solving modularity optimization problem which is a discrete optimization problem.The four algorithms (HDSA, BADE, SSGA and BB-BC) have been supported by new techniques or hybrid methods in addition to their original versions.Comparative analyses of the proposed algorithms are performed on the four biological and five social networks.According to acquired experimental results, it has been observed that HDSA is more efficient and competitive than the other algorithms. In order to analyze complex networks to find significant communities, several methods have been proposed in the literature. Modularity optimization is an interesting and valuable approach for detection of network communities in complex networks. Due to characteristics of the problem dealt with in this study, the exact solution methods consume much more time. Therefore, we propose six metaheuristic optimization algorithms, which each contain a modularity optimization approach. These algorithms are the original Bat Algorithm (BA), Gravitational Search Algorithm (GSA), modified Big Bang-Big Crunch algorithm (BB-BC), improved Bat Algorithm based on the Differential Evolutionary algorithm (BADE), effective Hyperheuristic Differential Search Algorithm (HDSA) and Scatter Search algorithm based on the Genetic Algorithm (SSGA). Four of these algorithms (HDSA, BADE, SSGA, BB-BC) contain new methods, whereas the remaining two algorithms (BA and GSA) use original methods. To clearly demonstrate the performance of the proposed algorithms when solving the problems, experimental studies were conducted using nine real-world complex networks - five of which are social networks and the rest of which are biological networks. The algorithms were compared in terms of statistical significance. According to the obtained test results, the HDSA proposed in this study is more efficient and competitive than the other algorithms that were tested.

A New Adaptive Genetic Algorithm for Community Structure Detection

Community structures exist in networks which has complex biological, social, technological and so on structures and contain important information. Networks and community structures in computer systems are presented by graphs and subgraphs respectively. Community structure detection problem is NP-hard problem and especially final results of the best community structures for large-complex networks are unknown. In this paper, to solve community structure detection problem a genetic algorithm-based algorithm, AGA-net, which is one of evolutionary techniques has been proposed. This algorithm which has the property of fast convergence to global best value without being trapped to local optimum has been supported by new parameters. Real-world network which are frequently used in literature has been used as test data and obtained results have been compared with 10 different algorithms. After analyzing the test results it has been observed that the proposed algorithm gives successful results for determination of meaningful communities from complex networks.

A swarm intelligence-based hybrid approach for identifying network modules

Abstract Complex network structures, where real-world systems are modelled, contain important information that can be uncovered. Various studies have been carried out, and many methods have been proposed recently to discover such information by using different network analysis techniques. The discovery of meaningful modules in networks is one of these significant works. In this study, a new hybrid method, which is called uniSFLA, is proposed to determine statistically significant modules within the network. Another significant aspect of this study is to use various objective functions as fitness criteria and compare the results obtained from the tests with each other. The aim is to test the success of various objective functions used to investigate network modules and those defined according to different properties in graphs. The proposed algorithm was tested on real-world networks, and the test results were compared with those of other algorithms from published literature. Considering the experimental results, the method suggested in this work produced significant success in terms of both best and average values. Moreover, the accuracy and quality tests of the conformity values obtained for each objective function were performed with four different cluster evaluation criteria. Finally, in addition to the successful results for the uniSFLA algorithm, the comparative test results of appropriate network modules, obtained using modularity and significance functions, were evaluated by means of various tables and graphs.

Modularity-Based Graph Clustering Using Harmony Search Algorithm

Real-world networks contain variety of meaningful information inside them that can be revealed. These networks can be biological, social, ecological and technological networks. Each of these contains specific information about their field. This information cannot be obtained with simple techniques. Various techniques and algorithms have been developed to uncover useful information from complex relationships inside the network. In this paper, to divide graphs according to modularity measure to subgraphs harmony search algorithm is used which is inspired by music improvisation. This algorithm has been tested with 5 different real-world networks. The obtained quantitative values for each network have been given in the tables. In addition the proposed algorithm, has achieved the best known modularity measure of Zacharys Karate Club network which is commonly used in the literature and the latest subsets generated according to this modularity measure has been given at the end of section V. According to the results obtained from experiments it has been observed that HM algorithm gives faster results on solution of problem addressed in this study than most algorithms like genetic algorithm and bat algorithm. However, the proposed algorithm requires a larger size of harmony memory and more number of iterations for maximum modularity values.

Implementation of CSA with Clone-Mutation Mechanism to the JSSP

—Job Shop scheduling problem (JSSP), which is called NP-Hard, is classified as one of the most difficult problems. Existing methods for the solution of such problems is not enough. Therefore, to solve such problems, some of the artificial intelligence techniques are used. In this study, clonal selection algorithm (CSA), which is one of artificial immune algorithms, is proposed to solve the job shop scheduling problems. In the proposed method the selection of a set of clone and mutation process of selected antibodies were carried out. This method is named after clone-mutation mechanism. The proposed method was applied on some test problems called as Ft06, La01, La03, La04 and La05. Furthermore, the application, in order to understand the effect of the mutation mechanism was executed with values ranging from 0 to 1, and the results are given in the Table VI. The results obtained are compared with the best known makespan values. As a result, the proposed method has been applied successfully in job shop scheduling problems.