Yazar "Babaoglu, Ismail" seçeneğine göre listele
Listeleniyor 1 - 18 / 18
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Artificial bee colony algorithm with distribution-based update rule(ELSEVIER, 2015) Babaoglu, IsmailIn last decades, lots of nature-inspired optimization algorithms are developed and presented to the literature for solving optimization problems. Generally, these optimization algorithms can be grouped into two categories: evolutionary algorithms and swarm intelligence methods. Evolutionary methods try to improve the candidate solutions (chromosomes) using evolutionary operators such as crossover, mutation. The methods in swarm intelligence category use differential position update rules for obtaining new candidate solutions. The popularity of the swarm intelligence methods has grown since 1990s due to their simplicity, easy adaptation to the problem and effectiveness in solving the nonlinear optimization problems. One of the popular members of swarm intelligence algorithms is artificial bee colony (ABC) algorithm which simulates the intelligent behaviors of real honey bees and uses differential position update rule. When food sources which present possible solutions for the optimization problems gather on the similar points within the search space, differential position update rule can cause a stagnation behavior in the algorithm during the search process. In this paper, a distribution-based solution update rule is proposed for the basic ABC algorithm instead of differential update rule to overcome stagnation behavior of the algorithm. Distribution-based update rule uses the mean and standard deviation of the selected two food sources to obtain a new candidate solution without using any differential-based processes. This approach is therefore prevents the stagnation in the population. The proposed approach is tested on 18 benchmark functions with different characteristics and compared with the basic variants of ABC algorithm and some nature-inspired methods. The experimental results show that the proposed approach produces acceptable and comparable solutions for the numeric problems. (C) 2015 Elsevier B.V. All rights reserved.Öğe Assessment of exercise stress testing with artificial neural network in determining coronary artery disease and predicting lesion localization(PERGAMON-ELSEVIER SCIENCE LTD, 2009) Babaoglu, Ismail; Baykan, Omer Kaan; Aygul, Nazif; Ozdemir, Kurtulus; Bayrak, MehmetThe aim of this study is to show the artificial neural network (ANN) on determination of coronary artery disease existence and localization of lesion based upon exercise stress testing (EST) data. EST and coronary angiography were performed on 330 patients. The data studied acquiring 27 verifying features was normalized employing z-score method. To select training and test data, 10-fold cross-validation methods were involved and multi-layered perceptron neural network was employed for the classification. The interpretation of EST using ANN proved 91%, 73% and 65% diagnostic accuracy for the left main coronary (LMCA), left anterior descending and left circum-flex coronary arteries, respectively. Besides, 69% for the right coronary artery is also predicted. For the LMCA, a 94% negative predictive value (NPV) was obtained. This high percentage of NPV encourages the elimination of LMCA lesions. Some knowledge call also be obtained about lesion localization, besides diagnosing of coronary artery disease by the assessment of EST via ANN. (C) 2007 Elsevier Ltd. All rights reserved.Öğe A color image watermarking scheme based on artificial immune recognition system(PERGAMON-ELSEVIER SCIENCE LTD, 2011) Findik, Oguz; Babaoglu, Ismail; Ulker, ErkanThis study suggests a novel watermarking technique that uses artificial immune recognition system to protect color image's intellectual property rights. The watermark is embedded in the blue channel of a color image. m-bit binary sequence embedded into the color image is used to train artificial immune recognition system. With this composed technique, extracting the watermark which is embedded into the color image is carried out using artificial immune recognition system. It is observed that the composed technique achieves high performance to process of extracting this watermark. The watermark is extracted successfully from the watermarked image after various image processing attacks as well. (C) 2010 Elsevier Ltd. All rights reserved.Öğe Color Image Watermarking Scheme Based on Efficient Preprocessing and Support Vector Machines(SPRINGER-VERLAG BERLIN, 2008) Findik, Oguz; Bayrak, Mehmet; Babaoglu, Ismail; Comak, EmreThis paper suggests a new block based watermarking technique utilizing preprocessing and support vector machine (PPSVMW) to protect color image's intellectual property rights. Binary test set is employed here to train support vector machine (SVM). Before adding binary data into the original image, blocks have been separated into two parts to train SVM for better accuracy. Watermark's I valued bits were randomly added into the first block part and 0 into the second block part. Watermark is embedded by modifying the blue channel pixel value in the middle of each block so that watermarked image could be composed. SVM was trained with set-bits and three other features which are averages of the differences of pixels in three distinct shapes extracted from each block, and hence without the need of original image, it could be extracted. The results of PPSVMW technique proposed in this study were compared with those of the Tsai's technique. Our technique was proved to be more efficient.Öğe Community detection from biological and social networks: A comparative analysis of metaheuristic algorithms(ELSEVIER, 2017) Atay, Yilmaz; Koc, Ismail; Babaoglu, Ismail; Kodaz, HalifeIn 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 BangBig 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. (C) 2016 Elsevier B.V. All rights reserved.Öğe EFFECT OF DISCRETIZATION METHOD ON THE DIAGNOSIS OF PARKINSON'S DISEASE(ICIC INTERNATIONAL, 2011) Kaya, Ersin; Findik, Oguz; Babaoglu, Ismail; Arslan, AhmetImplementing different classification methods, this study analyzes the effect of discretization on the diagnosis of Parkinson's disease. Entropy-based discrelization method is used as the discretization method, and support vector machines, C4.5, k-nearest neighbors and Naive Bayes are used as the classification methods. The diagnosis of Parkinson's disease is implemented without using any preprocessing method. Afterwards, the Parkinson's disease dataset is classified after implementing entropy-based discretization on the dataset. Both results are compared, and it is observed that using discretization method increases the success of classification on the diagnosis of Parkinson's disease by 4.1% to 12.8%.Öğe Galactic Swarm Optimization using Artificial Bee Colony Algorithm(IEEE, 2017) Kaya, Ersin; Babaoglu, Ismail; Kodaz, HalifeGalactic swarm optimization (GSO) algorithm is a novel meta-heuristic algorithm inspired by the motion of stars, galaxies and superclusters of galaxies under the influence of gravity. The GSO algorithm utilizes multiple cycles of exploration and exploitation in two levels. The first level covers the exploration, and different subpopulations of the candidate solutions are used for exploring the search space. The second level covers the exploitation, and best solutions obtained from the subpopulations are considered as a superswarm and used for exploiting the search space. The first implementation of GSO algorithm was presented by using particle swarm optimization algorithm (PSO) algorithm on both first and second levels. This study presents the preliminary results of an implementation of GSO algorithm by using artificial bee colony (ABC) algorithm on the first level and PSO algorithm on the second level. Due to the better exploration characteristics of ABC algorithm over PSO algorithm, this suggestion covers the usage of ABC algorithm on the first level, and the usage of PSO algorithm on the second level. The proposed approach is tested on 20 well-known online available benchmark problems and preliminary results are presented. According to the experimental results, the proposed approach achieves more successful results than the basic GSO approach.Öğe IMPLEMENTATION OF BCH CODING ON ARTIFICIAL NEURAL NETWORK-BASED COLOR IMAGE WATERMARKING(ICIC INTERNATIONAL, 2011) Findik, Oguz; Babaoglu, Ismail; Ulker, ErkanThis study suggests a novel watermarking technique that uses artificial neural networks (ANN) and BCH (Bose, Chaudhuri and Hocquenghem) coding together to protect intellectual property rights of a color image. BCH error correction coding method is used to improve the performance of watermark extracting. With this composed technique, image is divided into sub-blocks, and a bit-sequence which is used to train both ANN and the watermark is added to the selected sub-blocks. In the watermark embedding process, besides embedding the bit-sequence as is, the watermark is embedded by encoding the watermark into the original image through BCH coding method. ANN is trained by using the features obtained from the selected sub-blocks to which the bit-sequence is embedded. The extraction process is implemented by using the trained ANN and the features obtained from the selected sub-blocks to which the encoded watermark is embedded. After the extraction process, the extracted watermark is obtained by using BCH decoding method. The results of the study are obtained by using the watermark as is and by encoding with BCH coding method. By using BCH encoding method, watermark extraction success is considerably increased, especially on the watermark extraction cases with low success rates. The watermark is extracted considerably successfully from the watermarked image after various image processing attacks as well.Öğe An improvement in fruit fly optimization algorithm by using sign parameters(SPRINGER, 2018) Babalik, Ahmet; Iscan, Hazim; Babaoglu, Ismail; Gunduz, MesutThe fruit fly optimization algorithm (FOA) has been developed by inspiring osphresis and vision behaviors of the fruit flies to solve continuous optimization problems. As many researchers know that FOA has some shortcomings, this study presents an improved version of FOA to remove with these shortcomings in order to improve its optimization performance. According to the basic version of FOA, the candidate solutions could not take values those are negative as well as stated in many studies in the literature. In this study, two sign parameters are added into the original FOA to consider not only the positive side of the search space, but also the whole. To experimentally validate the proposed approach, namely signed FOA, SFOA for short, 21 well-known benchmark problems are considered. In order to demonstrate the effectiveness and success of the proposed method, the results of the proposed approach are compared with the results of the original FOA, results of the two different state-of-art versions of particle swarm optimization algorithm, results of the cuckoo search optimization algorithm and results of the firefly optimization algorithm. By analyzing experimental results, it can be said that the proposed approach achieves more successful results on many benchmark problems than the compared methods, and SFOA is presented as more equal and fairer in terms of screening the solution space.Öğe Modern Trends in Arabic Sentiment Analysis: A Survey(ASSOC TRADUCTION AUTOMATIQUE LINGUISTIQUE APPLIQUEE, 2017) Mulki, Hala; Haddad, Hatem; Babaoglu, IsmailThe growth of the Arabic textual content on social media platforms has been caused by the continuous crises in the Arab World evoking the need to analyze the opinions of the public against the ongoing events. Arabic Sentiment Analysis (ASA) is, therefore, becoming the focus of many recent NLP studies. With several Arabic NLP resources being publicly available along with the emergence of deep learning techniques, researchers could handle the complex nature of Arabic language more efficiently. In the last decade, various ASA systems have been built. Yet, their achievements have not been investigated or compared against each other. This survey covers the ASA research carried out during the past five years. We compare and evaluate the performances and give insight into the ability of the created Arabic resources to support the future ASA research.Öğe Multilevel image thresholding selection based on grey wolf optimizer(GAZI UNIV, 2018) Koc, Ismail; Baykan, Omer Kaan; Babaoglu, IsmailMultilevel thresholding is an important image process technique for image processing and pattern recognition. Selecting an optimal threshold value is one of the most crucial phase in image thresholding. While bi-level segmentation contains separating the original image into subdivided sections with help of a threshold value, multilevel segmentation involves multi threshold values. Especially in multilevel image tresholding, the computational time of detailed search increases exponentially with the number of preferred thresholds. For compelling problems, swarm intelligence is known as one of the successful and influential optimization methods. In this paper, the grey wolf optimizer (GWO), a recently proposed swarm-based meta-heuristic which imitates the social leadership and hunting behavior of gray wolves in nature is employed for solving the multilevel image thresholding problem. The experimental results on standard benchmark images indicate that the grey wolf optimizer algorithm is comparable with other state of the art algorithms.Öğe A NOVEL HYBRID CLASSIFICATION METHOD WITH PARTICLE SWARM OPTIMIZATION AND K-NEAREST NEIGHBOR ALGORITHM FOR DIAGNOSIS OF CORONARY ARTERY DISEASE USING EXERCISE STRESS TEST DATA(ICIC INTERNATIONAL, 2012) Babaoglu, Ismail; Findik, Oguz; Ulker, Erkan; Aygul, NazifThe aim of this study is to investigate the effectiveness of a novel hybrid method, particle swarm optimization with k-nearest neighbor classifier (PSOkNN), on determination of coronary artery disease (CAD) existence upon exercise stress testing (EST) data. The PSOkNN method is composed of two steps. At the first step, one particle which demonstrates the whole samples optimally in training dataset is generated for both healthy and unhealthy patients. Then, at the second one, the class of the test sample is determined according to the distance of the test sample to the generated particles utilizing k-nearest neighbor algorithm. To demonstrate the effectiveness of this novel method, the results of PSOkNN are compared with the classification results of the artificial immune recognition system and k-nearest neighbor algorithm. Besides, reliability of the proposed method on determination of CAD existence upon EST data is examined by using classification accuracy, k-fold cross-validation method and Cohen's kappa coefficient.Öğe Preprocessing Impact on Turkish Sentiment Analysis(IEEE, 2018) Mulki, Hala; Haddad, Hatem; Ali, Chedi Bechikh; Babaoglu, IsmailThis paper investigates the impact of preprocessing on sentiment classification of Turkish movies and products reviews. Input datasets were subjected to several combinations of preprocessing techniques. Later, the manipulated reviews were fed to a lexicon-based and a supervised machine learning sentiment classifiers. The achieved results emphasize the positive impact of preprocessing phase on the accuracy of both sentiment classifiers as the baseline was outperformed with a considerable margin especially when stemming, emoji recognition and negation detection tasks were applied.Öğe Smart Bus Station-Passenger Information System(IEEE, 2015) Sungur, Cemil; Babaoglu, Ismail; Sungur, AysegulThe people who use inner city public transportation vehicles want to get information about the current status of the public transportation vehicles and they want to know the travel time of the vehicles both while travelling and waiting at the bus stops. In this study, a smart bus stop-passenger information system was developed in order to enable administers effectively monitor the public transportation system and also enable the people who utilize this system simultaneously observe the information about the location and status of those vehicles. In the designed system, the embedded mini-computer based systems and digital monitors were used in order to instantly present the information related to the travel and transportation in the public transportation vehicles. The instant movement information of the vehicle was transferred to the central server through a GPS module which functions integrated to the embedded computer systems and web services. Moreover, the embedded mini-computer based systems and digital monitors were installed to the bus stops in order to present the information related to the movements of the public transportation vehicle and their approach to the related bus-stop. The mini-computers embedded on the bus stops provide communication with the central server through web services and the bus stops, public transportation vehicles and central server formed information network of the transportation. The software developed to manage the system provided the authorities the advantages of instant status observation, remote-informing and updating related to the management of the status and travel of the public transportation vehicles. Through this developed system, moreover, it was ensured that the position and travel information of the vehicles through the monitors both inside the public transportation vehicles and at the bus stops, increase the life qualities of the people who use the public transport vehicles and facilitate their urban life cycles.Öğe Solving 2D strip packing problem using fruit fly optimization algorithm(ELSEVIER SCIENCE BV, 2017) Babaoglu, IsmailTwo dimensional strip-packing problem (2DSPP) consists of packing a set of rectangular items on one strip with a restriction of a maximal width and height. Because the conventional algorithms are still sub-optimal, the researchers tend towards searching for more successful alternative algorithms to solve 2DSPP. The fruit fly optimization algorithm (FOA), which is one of the recently proposed meta-heuristic algorithms, has been successfully applied on many engineering and mathematical problems. This study presents an implementation of FOA for solving non-oriented 2DSPP. The aim of the study is to find the optimal sequence of the rectangles in a strip, and then to place the rectangles by bottom left fill approach to have the optimal height within a fixed width box. The experiments are concluded on online available set of 2DSPP test problems. The preliminary results of the study are compared with the results of some conventional or heuristic approaches which use the same problem set. The experimental results show the promising results are obtained by FOA on solving 2DSPPs. (c) 2017 The Authors. Published by Elsevier B.V.Öğe Solving Travelling Salesman Problem by Using Optimization Algorithms(KNOWLEDGE E, 2018) Saud, Suhair; Kodaz, Halife; Babaoglu, IsmailThis paper presents the performances of different types of optimization techniques used in artificial intelligence (AI), these are Ant Colony Optimization (ACO), Improved Particle Swarm Optimization with a new operator (IPSO), Shuffled Frog Leaping Algorithms (SFLA) and modified shuffled frog leaping algorithm by using a crossover and mutation operators. They were used to solve the traveling salesman problem (TSP) which is one of the popular and classical route planning problems of research and it is considered as one of the widely known of combinatorial optimization. Combinatorial optimization problems are usually simple to state but very difficult to solve. ACO, PSO, and SFLA are intelligent meta-heuristic optimization algorithms with strong ability to analyze the optimization problems and find the optimal solution. They were tested on benchmark problems from TSPLIB and the test results were compared with each other.Öğe Tunisian Dialect Sentiment Analysis: A Natural Language Processing-based Approach(IPN, CENTRO INVESTIGAVION COMPUTACION, 2018) Mulki, Hala; Haddad, Hatem; Ali, Chedi Bechikh; Babaoglu, IsmailSocial media platforms have been witnessing a significant increase in posts written in the Tunisian dialect since the uprising in Tunisia at the end of 2010. Most of the posted tweets or comments reflect the impressions of the Tunisian public towards social, economical and political major events. These opinions have been tracked, analyzed and evaluated through sentiment analysis systems. In the current study, we investigate the impact of several preprocessing techniques on sentiment analysis using two sentiment classification models: Supervised and lexicon-based. These models were trained on three Tunisian datasets of different sizes and multiple domains. Our results emphasize the positive impact of preprocessing phase on the evaluation measures of both sentiment classifiers as the baseline was significantly outperformed when stemming, emoji recognition and negation detection tasks were applied. Moreover, integrating named entities with these tasks enhanced the lexicon-based classification performance in all datasets and that of the supervised model in medium and small sized datasets.Öğe Utilization of Bat Algorithm for Solving Uncapacitated Facility Location Problem(SPRINGER INTERNATIONAL PUBLISHING AG, 2016) Babaoglu, IsmailThe uncapacitated facility location problem (UFLP) is a location-based binary optimization problem investigated by using various methods in the literature. This study demonstrates a solution methodology for UFLP by a binary version of a novel swarm intelligence method namely bat algorithm (BA). BA is an optimization method employed for solving continuous optimization problems in the literature, suggested by inspiring the echolocation of microbats in nature. As implemented within some studies, sigmoid function is used in BA in order to obtain binary version of the algorithm (BBA) in this study, and then BBA is used for solving UFLP. According to the experimental results, BBA acquires successful results for solving UFLP in terms of solution quality.
