Search

In recent years, gender detection has been an important problem in speech analysis, with many different applications. Different features of sound data such as pitch, median, and frequency are used for gender detection. In this study, a feature selection method based on metaheuristic optimization algorithms is proposed for gender detection from voice data. In the proposed method, the feature set representing the voice data in the most appropriate way is selected with optimization algorithms, and gender detection has been implemented with artificial intelligence algorithms using the obtained features. Nature-inspired metaheuristic optimization algorithms, which are capable of solving complex problems, are used to select features from voice data. Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Salp Swarm Algorithm (SSA), and Whale Optimization Algorithm (WOA) have been modeled for the first time for feature selection from voice data. A publicly accessible data set has been used to measure the efficiency of metaheuristic optimization algorithms. The performances of PSO, ACO, SSA, and WOA for feature selection have been compared in terms of three different criteria: fitness function value, accuracy value, and the number of selected features. After feature selection with metaheuristic optimization algorithms, Naive Bayes and Decision Tree algorithms have been applied to the new data sets obtained and the original data set. As a result of the analysis, it was observed that this method which uses metaheuristic optimization algorithms for feature selection increased the success rate in the results obtained with Naive Bayes and Decision Tree algorithms. [ABSTRACT FROM AUTHOR]

Migration is the main process step that enables island-based parallel metaheuristic optimization algorithms to produce successful results. Correct determination of migration parameters, migration rate (MR) and migration range (MI), affects the success of the algorithm. Therefore, studies on determining the values of migration parameters are important. In this study, MR and MI values were determined using a central composite design experimental layout, which is one of the response surface methods. MR and MI values determined according to the experimental layout were applied in the island-based Parallel Migrating Birds Optimization (PMBO) algorithm. According to these results, problem specific models have been created that include the coefficients of MI, MR, MI*MR, MI*MI and MR*MR. After the models were created, the most suitable values of MR and MI parameters were proposed by using the desirability function. Verification experiments were made using the recommended MR and MI values and more successful results were obtained. [ABSTRACT FROM AUTHOR]

Real-world problems in engineering are often nonlinear or constrained design problems. For many reasons, an engineer wants to get the best design, not just any that works properly. The process of determining the best design is called optimization. With optimization, the best design of the problem is determined to achieve a specific objective function by providing the current constraints. In this study, three real-world engineering design problems are tried to be optimized, namely tension/compression spring, welded beam, and pressure vessel designs with various equalities and inequality constraints. In the optimization process, eight different algorithms are used, the best designs are created, and the optimum variables of the problems are determined. Optimization algorithms are selected from evolutionary-based, swarm-based, mathematics-based, and physics-based algorithms, which are sub-branches of metaheuristic algorithms. In addition, the results of the algorithms are compared with each other with the help of convergence curves and box graphs. The grey wolf algorithm is the algorithm that showed the most successful performance in all three problems. Besides, swarm-based, physics-based, and math-based algorithms performed better than other algorithms in optimizing real engineering problems. [ABSTRACT FROM AUTHOR]

Optimization is the selection of the best possible solution (min / max) under certain criteria. For the solution of optimization problems; many approaches have been developed in different classes such as exact solution methods, approximation methods, meta-heuristic techniques. However, the enormous size of real-life problems have led researchers to meta-heuristic techniques that provide acceptable solutions in a short time. In this study, an application has been made with the iterated greedy algorithm, which stands out with its simple structure. Flexible job shop scheduling problem is addressed for application. Basically, the iterative greedy algorithm starts the optimization process with a single solution. The current solution then enters the construction-destruction phase to find a better solution. The solution obtained after this stage is replaced with the incumbent solution according to the previously determined acceptance criteria. This cycle, which consists of two operators, construction and destruction, continues until a certain stopping criterion is met. In this study, a problem-specific critical path-based approach was developed in the construction-destruction phase. In addition, a novel approach based on the acceptance of solutions of decreasing quality depending on the number of iterations is proposed. The aim of this study is to contribute to the limited Turkish literature on the application of meta-heuristic algorithms in various fields. [ABSTRACT FROM AUTHOR]

Classification rules mining is one of the most studied data mining problems. In this article, chemistry based Artificial Chemical Reaction Optimization Algorithm (ACROA) has been for the first time used for mining of generalized classification rules, which is a complex and no well researched generalized variant of classification rules mining where there is more than one goal attribute to be predicted. Furthermore, interestingness measure has been added by performing the adaptations to the algorithm in order to make the rules mined by the algorithm not only accurate and comprehensible but also interesting, surprising, and unexpected. Different rule sets within different databases satisfying different objectives have been flexibly mined by adapting the representation scheme and objective function. Performance of ACROA in classification rules mining within different real public databases have been compared that of genetic algorithm, particle swarm optimization algorithm, and ant colony optimization algorithm. It has shown that performance of ACROA within this special task of data mining is promising. ACROA can be an efficient solution method for different data mining tasks such as association rules mining, clustering rules mining, sequential pattern mining, and etc. [ABSTRACT FROM AUTHOR]

Optimization is the process of finding the best solution of a problem. There are many optimization algorithms proposed for optimization problems. The metaheuristic algorithm can give solutions close to optimum in an acceptable period of time for large-scaled optimization problems. The metaheuristic optimization algorithms are evaluated in seven different groups which are biology-based, physics-based, swarm-based, social-based, music-based, sport-based, and chemistry-based. The swarm-based optimization algorithms have been developed by observing the behaviors of creatures e.g. birds, fishes, cats, bees etc. Data mining is the process of discovery of meaningful and useful data within huge databases. Classification rules mining is one of the most commonly studied data mining problems and with methods for this problem, users can easily understand the rules extracted from databases. In this work, one of the most recent swarm based optimization algorithm, Cat Swarm Optimization (CSO), has been firstly used for classification rules mining within databases composed of numerical or mixed data types automatically. There is not any preprocess for finding true ranges for appropriate attributes of the rules, this has been automatically done by CSO. Furthermore, the used objective function is very flexible and many different objectives can easily be added to. For this purpose, four numerical databases obtained from UCI data warehouse have been used and accurate and comprehensible classification rules have been mined. The results have been compared with the results obtained from Weka program. Although CSO has not been embedded with any improvement and has firstly implemented in this research area, the obtained results seem promising. [ABSTRACT FROM AUTHOR]

In Vehicle Routing Problem with Simultaneous Delivery and Pick-up (VRP_SDP), each customer has both delivery and pick-up demand simultaneously. VRP_SDP is very difficult combinatorial optimization problem. For this reason, in recent years, it is observed studies focused on metaheuristic methods. In this study, a heuristic solution approach based on Bacterial Foraging Optimization Algorithm (BFOA) has been improved and its performance has been evaluated. In the scope of this study VRP_SDP has been solved in order to minimize the total distanced travelled and the results have been tested with the insertion based heuristic that is known in the literature. BFOA obtained good solutions about 24 problems of 40 test problems. [ABSTRACT FROM AUTHOR]