Bilgisayar ve Bilişim Fakültesi Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.13091/10834

Browse

Now showing 1 - 20 of 31

Citation - WoS: 6
Citation - Scopus: 9
Ağaç-tohum Algoritmasının Cuda Destekli Grafik İşlem Birimi Üzerinde Paralel Uygulaması
(2018) Çınar, Ahmet Cevahir; Kıran, Mustafa Servet
Son yıllarda toplanan verinin artmasıyla birlikte verimli hesaplama yöntemlerinin de geliştirilmesi ihtiyacı artmaktadır. Çoğunlukla gerçek dünya problemlerinin zor olması sebebiyle optimal çözümü garanti etmese dahi makul zamanda yakın optimal çözümü garanti edebilen sürü zekâsı veya evrimsel hesaplama yöntemlerine olan ilgi de artmaktadır. Diğer bir açıdan seri hesaplama yöntemlerinde verinin veya işlemin paralelleştirilebileceği durumlarda paralel algoritmaların da geliştirilmesi ihtiyacı ortaya çıkmıştır. Bu çalışmada literatüre son yıllarda kazandırılmış olan popülasyon tabanlı ağaç-tohum algoritması ele alınmış ve CUDA platformu içerisinde paralel versiyonu geliştirilmiştir. Algoritmanın paralel versiyonunun performansı kıyas fonksiyonları üzerinde analiz edilmiş ve seri versiyonunun performansı ile karşılaştırılmıştır. Kıyas fonksiyonlarında problem boyutluluğu 10 olarak alınmış ve farklı popülasyon ve blok sayıları altında performans analizi yapılmıştır. Deneysel çalışmalar algoritmanın paralel versiyonunun algoritmanın seri sürümüne göre bazı problemler için 184,65 kata performans artışı sağladığı görülmüştür.
Citation - WoS: 7
Citation - Scopus: 12
Analyzing the Effect of Data Preprocessing Techniques Using Machine Learning Algorithms on the Diagnosis of Covid-19
(Wiley, 2022) Erol, Gizemnur; Uzbaş, Betül; Yücelbaş, Cüneyt; Yücelbaş, Sule
Real-time polymerase chain reaction (RT-PCR) known as the swab test is a diagnostic test that can diagnose COVID-19 disease through respiratory samples in the laboratory. Due to the rapid spread of the coronavirus around the world, the RT-PCR test has become insufficient to get fast results. For this reason, the need for diagnostic methods to fill this gap has arisen and machine learning studies have started in this area. On the other hand, studying medical data is a challenging area because the data it contains is inconsistent, incomplete, difficult to scale, and very large. Additionally, some poor clinical decisions, irrelevant parameters, and limited medical data adversely affect the accuracy of studies performed. Therefore, considering the availability of datasets containing COVID-19 blood parameters, which are less in number than other medical datasets today, it is aimed to improve these existing datasets. In this direction, to obtain more consistent results in COVID-19 machine learning studies, the effect of data preprocessing techniques on the classification of COVID-19 data was investigated in this study. In this study primarily, encoding categorical feature and feature scaling processes were applied to the dataset with 15 features that contain blood data of 279 patients, including gender and age information. Then, the missingness of the dataset was eliminated by using both K-nearest neighbor algorithm (KNN) and chain equations multiple value assignment (MICE) methods. Data balancing has been done with synthetic minority oversampling technique (SMOTE), which is a data balancing method. The effect of data preprocessing techniques on ensemble learning algorithms bagging, AdaBoost, random forest and on popular classifier algorithms KNN classifier, support vector machine, logistic regression, artificial neural network, and decision tree classifiers have been analyzed. The highest accuracies obtained with the bagging classifier were 83.42% and 83.74% with KNN and MICE imputations by applying SMOTE, respectively. On the other hand, the highest accuracy ratio reached with the same classifier without SMOTE was 83.91% for the KNN imputation. In conclusion, certain data preprocessing techniques are examined comparatively and the effect of these data preprocessing techniques on success is presented and the importance of the right combination of data preprocessing to achieve success has been demonstrated by experimental studies.
Citation - WoS: 2
Apneic Events Detection Using Different Features of Airflow Signals
(MEHRAN UNIV ENGINEERING & TECHNOLOGY, 2019) Göğüş, Fatma Zehra; Tezel, Gülay
Apneic-event based sleep disorders are very common and affect greatly the daily life of people. However, diagnosis of these disorders by detecting apneic events are very difficult. Studies show that analyzes of airflow signals are effective in diagnosis of apneic-event based sleep disorders. According to these studies, diagnosis can be performed by detecting the apneic episodes of the airflow signals. This work deals with detection of apneic episodes on airflow signals belonging to Apnea-ECG (Electrocardiogram) and MIT (Massachusetts Institute of Technology) BIH (Bastons's Beth Isreal Hospital) databases. In order to accomplish this task, three representative feature sets namely classic feature set, amplitude feature set and descriptive model feature set were created. The performance of these feature sets were evaluated individually and in combination with the aid of the random forest classifier to detect apneic episodes. Moreover, effective features were selected by OneR Attribute Eval Feature Selection Algorithm to obtain higher performance. Selected 28 features for Apnea-ECG database and 31 features for MIT-BIH database from 54 features were applied to classifier to compare achievements. As a result, the highest classification accuracies were obtained with the usage of effective features as 96.21% for Apnea-ECG database and 92.23% for MIT-BIH database. Kappa values are also quite good (91.80 and 81.96%) and support the classification accuracies for both databases, too. The results of the study are quite promising for determining apneic events on a minute-by-minute basis.
Citation - WoS: 3
Application of Abm To Spectral Features for Emotion Recognition
(MEHRAN UNIV ENGINEERING & TECHNOLOGY, 2018) Demircan, Semiye; Örnek, Humar Kahramanlı
ER (Emotion Recognition) from speech signals has been among the attractive subjects lately. As known feature extraction and feature selection are most important process steps in ER from speech signals. The aim of present study is to select the most relevant spectral feature subset. The proposed method is based on feature selection with optimization algorithm among the features obtained from speech signals. Firstly, MFCC (Mel-Frequency Cepstrum Coefficients) were extracted from the EmoDB. Several statistical values as maximum, minimum, mean, standard deviation, skewness, kurtosis and median were obtained from MFCC. The next process of study was feature selection which was performed in two stages: In the first stage ABM (Agent-Based Modelling) that is hardly applied to this area was applied to actual features. In the second stageOpt-aiNET optimization algorithm was applied in order to choose the agent group giving the best classification success. The last process of the study is classification. ANN (Artificial Neural Network) and 10 cross-validations were used for classification and evaluation. A narrow comprehension with three emotions was performed in the application. As a result, it was seen that the classification accuracy was rising after applying proposed method. The method was shown promising performance with spectral features.
Citation - WoS: 20
Citation - Scopus: 24
A Binary Social Spider Algorithm for Continuous Optimization Task
(SPRINGER, 2020) Baş, Emine; Ülker, Erkan
The social spider algorithm (SSA) is a new heuristic algorithm created on spider behaviors. The original study of this algorithm was proposed to solve continuous problems. In this paper, the binary version of SSA (binary SSA) is introduced to solve binary problems. Currently, there is insufficient focus on the binary version of SSA in the literature. The main part of the binary version is at the transfer function. The transfer function is responsible for mapping continuous search space to discrete search space. In this study, four of the transfer functions divided into two families, S-shaped and V-shaped, are evaluated. Thus, four different variations of binary SSA are formed as binary SSA-Tanh, binary SSA-Sigm, binary SSA-MSigm and binary SSA-Arctan. Two different techniques (SimSSA and LogicSSA) are developed at the candidate solution production schema in binary SSA. SimSSA is used to measure similarities between two binary solutions. With SimSSA, binary SSA's ability to discover new points in search space has been increased. Thus, binary SSA is able to find global optimum instead of local optimums. LogicSSA which is inspired by the logic gates and a popular method in recent years has been used to avoid local minima traps. By these two techniques, the exploration and exploitation capabilities of binary SSA in the binary search space are improved. Eighteen unimodal and multimodal standard benchmark optimization functions are employed to evaluate variations of binary SSA. To select the best variations of binary SSA, a comparative study is presented. The Wilcoxon signed-rank test has applied to the experimental results of variations of binary SSA. Compared to well-known evolutionary and recently developed methods in the literature, the variations of binary SSA performance is quite good. In particular, binary SSA-Tanh and binary SSA-Arctan variations of binary SSA showed superior performance.
Citation - WoS: 11
Citation - Scopus: 13
Boosting Galactic Swarm Optimization With Abc
(SPRINGER HEIDELBERG, 2019) Kaya, Ersin; Uymaz, Sait Ali; Koçer, Barış
Galactic swarm optimization (GSO) is a new global metaheuristic optimization algorithm. It manages multiple sub-populations to explore search space efficiently. Then superswarm is recruited from the best-found solutions. Actually, GSO is a framework. In this framework, search method in both sub-population and superswarm can be selected differently. In the original work, particle swarm optimization is used as the search method in both phases. In this work, performance of the state of the art and well known methods are tested under GSO framework. Experiments show that performance of artificial bee colony algorithm under the GSO framework is the best among the other algorithms both under GSO framework and original algorithms.
Citation - WoS: 25
Citation - Scopus: 31
Clustering Analysis Through Artificial Algae Algorithm
(Springer Heidelberg, 2022) Türkoğlu, Bahaeddin; Uymaz, Sait Ali; Kaya, Ersin
Clustering analysis is widely used in many areas such as document grouping, image recognition, web search, business intelligence, bio information, and medicine. Many algorithms with different clustering approaches have been proposed in the literature. As they are easy and straightforward, partitioning methods such as K-means and K-medoids are the most commonly used algorithms. These are greedy methods that gradually improve clustering quality, highly dependent on initial parameters, and stuck a local optima. For this reason, in recent years, heuristic optimization methods have also been used in clustering. These heuristic methods can provide successful results because they have some mechanism to escape local optimums. In this study, for the first time, Artificial Algae Algorithm was used for clustering and compared with ten well-known bio-inspired metaheuristic clustering approaches. The proposed AAA clustering efficiency is evaluated using statistical analysis, convergence rate analysis, Wilcoxon's test, and different cluster evaluating measures ranking on 25 well-known public datasets with different difficulty levels (features and instances). The results demonstrate that the AAA clustering method provides more accurate solutions with a high convergence rate than other existing heuristic clustering techniques.
Citation - WoS: 3
Citation - Scopus: 4
Comparing the Performances of Six Nature-Inspired Algorithms on a Real-World Discrete Optimization Problem
(Springer, 2022) Haklı, Hüseyin; Uguz, Harun; Ortacay, Zeynep
Many new, nature-inspired optimization algorithms are proposed these days, and these algorithms are gaining popularity day by day. These algorithms are frequently preferred for these real-world problems as they need less information, are reliable and robust, and have a structure that can easily be applied to discrete problems. Too many algorithms result in difficulty choosing the correct technique for the problem, and selecting an unwise method affects the solution quality. In addition, some algorithms cannot be reliable for some specific real-world problems but very successful for others. In order to guide and give insight into the practitioners and researchers about this problem, studies involving the comparison and evaluation of the performance of algorithms are needed. In this study, the performances of six nature-inspired methods, which included five new implementations of differential evolutionary algorithms (DE), scatter search (SS), equilibrium optimizer (EO), marine predators algorithm (MPA), and honey badger algorithm (HBA) applied to land redistribution problem and genetic algorithms (GA), were compared. In order to compare the algorithms in detail, various performance indicators were used as problem based and algorithm based. Experimental results showed that DE and SS algorithms have a more successful performance than the other methods by solution quality, robustness, and many problem-based indicators.
Continuous Time Threshold Selection for Binary Classification on Polarized Data
(2019) Sağlam, Ali; Baykan, Nurdan Akhan
Binary classification is used to distinguish some of the data elements from others in a meaningful way according to certain characteristics. Supervised classification techniques often use the ground-truth data, which assists to determine the distinctive characteristics of the elements to be extracted from the data. These techniques also generate new features for all of the data using the current features in accordance with the ground-truth data. One of the purposes of generating new features is to polarize the data elements (to be extracted and others) toward the separate pools on a coordinate axis for binary classification. In this way, the binary classification process is easy using only a threshold value on the axis. In this work, the Linear Discriminant Analysis (LDA) is used to polarize the data and a threshold selection algorithm is proposed, which use the harmonic mean F-score values of the binary classification outputs resulting from some specific threshold values. The key condition in the proposed method is that the most suitable threshold must give the best classification score (F-score value) and other threshold values must give lower classification scores as they become distant from the best threshold value (move away toward the ends of the axis). The proposed method is experimented for binary classifications of some meaningful elements on a remote sensing image taken from a 2D semantic labelling dataset that has the ground-truth images. The proposed method convergences the best threshold value continuously in logarithmic time.
Citation - WoS: 3
Citation - Scopus: 3
Diagnosis of Covid-19 From Blood Parameters Using Convolutional Neural Network
(Springer, 2023) Doğan, Gizemnur Erol; Uzbaş, Betül
Asymptomatically presenting COVID-19 complicates the detection of infected individuals. Additionally, the virus changes too many genomic variants, which increases the virus's ability to spread. Because there isn't a specific treatment for COVID-19 in a short time, the essential goal is to reduce the virulence of the disease. Blood parameters, which contain essential clinical information about infectious diseases and are easy to access, have an important place in COVID-19 detection. The convolutional neural network (CNN) architecture, which is popular in image processing, produces highly successful results for COVID-19 detection models. When the literature is examined, it is seen that COVID-19 studies with CNN are generally done using lung images. In this study, one-dimensional (1D) blood parameters data were converted into two-dimensional (2D) image data after preprocessing, and COVID-19 detection was made with CNN. The t-distributed stochastic neighbor embedding method was applied to transfer the feature vectors to the 2D plane. All data were framed with convex hull and minimum bounding rectangle algorithms to obtain image data. The image data obtained by pixel mapping was presented to the developed 3-line CNN architecture. This study proposes an effective and successful model by providing a combination of low-cost and rapidly-accessible blood parameters and CNN architecture making image data processing highly successful for COVID-19 detection. Ultimately, COVID-19 detection was made with a success rate of 94.85%. This study has brought a new perspective to COVID-19 detection studies by obtaining 2D image data from 1D COVID-19 blood parameters and using CNN.
Citation - WoS: 14
Citation - Scopus: 27
Enhanced Coati Optimization Algorithm for Big Data Optimization Problem
(Springer, 2023) Baş, Emine; Yıldızdan, Gülnur
The recently proposed Coati Optimization Algorithm (COA) is one of the swarm-based intelligence algorithms. In this study, the current COA algorithm is developed and Enhanced COA (ECOA) is proposed. There is an imbalance between the exploitation and exploration capabilities of the COA. To balance the exploration and exploitation capabilities of COA in the search space, the algorithm has been improved with two modifications. These modifications are those that preserve population diversity for a longer period of time during local and global searches. Thus, some of the drawbacks of COA in search strategies are eliminated. The achievements of COA and ECOA were tested in four different test groups. COA and ECOA were first compared on twenty-three classic CEC functions in three different dimensions (10, 20, and 30). Later, ECOA was tested on CEC-2017 with twenty-nine functions and on CEC-2020 with ten functions, and its success was demonstrated in different dimensions (5, 10, and 30). Finally, ECOA has been shown to be successful in different cycles (300, 500, and 1000) on Big Data Optimization Problems (BOP), which have high dimensions. Friedman and Wilcoxon tests were performed on the results, and the obtained results were analyzed in detail. According to the results, ECOA outperformed COA in all comparisons performed. In order to prove the success of ECOA, seven newly proposed algorithms (EMA, FHO, SHO, HBA, SMA, SOA, and JAYA) were selected from the literature in the last few years and compared with ECOA and COA. In the classical test functions, ECOA achieved the best results, surpassing all other algorithms when compared. It achieved the second-best results in CEC-2020 test functions and entered the top four in CEC-2017 and BOP test functions. According to the results, ECOA can be used as an alternative algorithm for solving small, medium, and large-scale continuous optimization problems.
Citation - WoS: 4
Citation - Scopus: 5
Evaluating the Attributes of Remote Sensing Image Pixels for Fast K-Means Clustering
(2019) Sağlam, Ali; Baykan, Nurdan Akhan
Clustering process is an important stage for many data mining applications. In this process, data elements are grouped according to their similarities. One of the most known clustering algorithms is the k-means algorithm. The algorithm initially requires the number of clusters as a parameter and runs iteratively. Many remote sensing image processing applications usually need the clustering stage like many image processing applications. Remote sensing images provide more information about the environments with the development of the multispectral sensor and laser technologies. In the dataset used in this paper, the infrared (IR) and the digital surface maps (DSM) are also supplied besides the red (R), the green (G), and the blue (B) color values of the pixels. However, remote sensing images come with very large sizes (6000 × 6000 pixels for each image in the dataset used). Clustering these large-size images using their multiattributes consumes too much time if it is used directly. In the literature, some studies are available to accelerate the k-means algorithm. One of them is the normalized distance value (NDV)-based fast k-means algorithm that benefits from the speed of the histogram-based approach and uses the multiattributes of the pixels. In this paper, we evaluated the effects of these attributes on the correctness of the clustering process with different color space transformations and distance measurements. We give the success results as peak signal-to-noise ratio and structural similarity index values using two different types of reference data (the source images and the ground-truth images) separately. Finally, we give the results based on accuracy measurement for evaluating both the success of the clustering outputs and the reliability of the NDV-based measurement methods presented in this paper.
Citation - WoS: 2
Citation - Scopus: 3
Fusion and Cnn Based Classification of Liver Focal Lesions Using Magnetic Resonance Imaging Phases
(Yildiz Technical University, 2023) Ci̇han, M.; Uzbaş, B.; Ceylan, M.
The diagnosis and follow-up of focal liver lesions have an important place in radiology practice and in planning the treatment of patients. Lesions detected in the liver can be benign or malign. While benign lesions do not require any treatment, some treatments and surgical operations may be required for malign lesions. Magnetic resonance imaging provides some advantages over other imaging modalities in the detection and characterization of focal liver lesions with its superior soft tissue contrast. Additionally, different phases help make a clear diagnosis of different contrast agent retention properties in magnetic resonance imaging. This study aims to classify focal liver lesions based on convolutional neural networks by fusing magnetic resonance liver images obtained in pre-contrast, venous, arterial, and delayed phases. Magnetic resonance imaging data were obtained from Selcuk University, Faculty of Medicine, Department of Radiology in Turkey. The experiments were performed using 460 magnetic resonance images in four phases of 115 patients. Two experiments were conducted. Two-dimensional discrete wavelet transform was used to fuse the phases in both experiments. In the first experiment, the best model was determined using the original data, different number of convolution layers and different activation functions. In the second experiment, the best-found model was used. Additionally, the number of data was increased using data augmentation methods in this experiment. The results were compared with other state-of-the art methods and the superiority of the proposed method was proved. As a result of the classification, 96.66% accuracy, 86.67% sensitivity and 98.76% specificity rates were obtained. When the results are examined, CNN efficiency increases by fusing MR liver images taken in different phases. © 2021, Yıldız Technical University.
Citation - WoS: 2
Citation - Scopus: 4
FUZZY ADAPTIVE WHALE OPTIMIZATION ALGORITHM FOR NUMERIC OPTIMIZATION
(UNIV MALAYA, FAC COMPUTER SCIENCE & INFORMATION TECH, 2021) Kaya, Ersin; Kılıç, Alper; Babaoğlu, İsmail; Babalık, Ahmet
Meta-heuristic approaches are used as a powerful tool for solving numeric optimization problems. Since these problems are deeply concerned with their diversified characteristics, investigation of the utilization of algorithms is significant for the researchers. Whale optimization algorithm (WOA) is one of the novel meta-heuristic algorithms employed for solving numeric optimization problems. WOA deals with exploitation and exploration of the search space in three stages, and in every stage, all dimensions of the candidate solutions are updated. The drawback of this update scheme is to lead the convergence of the algorithm to stack. Some known meta-heuristic approaches treat this issue by updating one or a predetermined number of dimensions in their update scheme. To improve the exploitation behavior of WOA, a fuzzy logic controller (FLC) based adaptive WOA (FAWOA) is suggested in this study. An FLC realizes the update scheme of WOA, and the proposed FLC determines the rate of the change in terms of dimension. The suggested FAWOA is evaluated using 23 well-known benchmark problems and compared with some other meta-heuristic approaches. Considering the benchmark problems, FAWOA achieves best results on 11 problem and only differential evaluation algorithm achieve best results on 10 problems. The rest of the algorithms couldn't achieve the best results on not more than 5 problems. Besides, according to the Friedman and average ranking tests, FAWOA is the first ranked algorithm for solving the benchmark problems. Evaluation results show that the suggested FAWOA approach outperforms the other algorithms as well as the WOA in most of the benchmark problems.
Citation - WoS: 1
Citation - Scopus: 1
Histological Tissue Classification With a Novel Statistical Filter-Based Convolutional Neural Network
(Wiley, 2024) Ünlükal, Nejat; Ülker, Erkan; Solmaz, Merve; Uyar, Kübra; Tasdemir, Sakir
Deep networks have been of considerable interest in literature and have enabled the solution of recent real-world applications. Due to filters that offer feature extraction, Convolutional Neural Network (CNN) is recognized as an accurate, efficient and trustworthy deep learning technique for the solution of image-based challenges. The high-performing CNNs are computationally demanding even if they produce good results in a variety of applications. This is because a large number of parameters limit their ability to be reused on central processing units with low performance. To address these limitations, we suggest a novel statistical filter-based CNN (HistStatCNN) for image classification. The convolution kernels of the designed CNN model were initialized by continuous statistical methods. The performance of the proposed filter initialization approach was evaluated on a novel histological dataset and various histopathological benchmark datasets. To prove the efficiency of statistical filters, three unique parameter sets and a mixed parameter set of statistical filters were applied to the designed CNN model for the classification task. According to the results, the accuracy of GoogleNet, ResNet18, ResNet50 and ResNet101 models were 85.56%, 85.24%, 83.59% and 83.79%, respectively. The accuracy was improved by 87.13% by HistStatCNN for the histological data classification task. Moreover, the performance of the proposed filter generation approach was proved by testing on various histopathological benchmark datasets, increasing average accuracy rates. Experimental results validate that the proposed statistical filters enhance the performance of the network with more simple CNN models.
Citation - WoS: 39
Citation - Scopus: 51
An Improved Artificial Bee Colony Algorithm for Balancing Local and Global Search Behaviors in Continuous Optimization
(SPRINGER HEIDELBERG, 2020) Haklı, Hüseyin; Kıran, Mustafa Servet
The artificial bee colony, ABC for short, algorithm is population-based iterative optimization algorithm proposed for solving the optimization problems with continuously-structured solution space. Although ABC has been equipped with powerful global search capability, this capability can cause poor intensification on found solutions and slow convergence problem. The occurrence of these issues is originated from the search equations proposed for employed and onlooker bees, which only updates one decision variable at each trial. In order to address these drawbacks of the basic ABC algorithm, we introduce six search equations for the algorithm and three of them are used by employed bees and the rest of equations are used by onlooker bees. Moreover, each onlooker agent can modify three dimensions or decision variables of a food source at each attempt, which represents a possible solution for the optimization problems. The proposed variant of ABC algorithm is applied to solve basic, CEC2005, CEC2014 and CEC2015 benchmark functions. The obtained results are compared with results of the state-of-art variants of the basic ABC algorithm, artificial algae algorithm, particle swarm optimization algorithm and its variants, gravitation search algorithm and its variants and etc. Comparisons are conducted for measurement of the solution quality, robustness and convergence characteristics of the algorithms. The obtained results and comparisons show the experimentally validation of the proposed ABC variant and success in solving the continuous optimization problems dealt with the study.
Citation - WoS: 20
Citation - Scopus: 28
Integration Search Strategies in Tree Seed Algorithm for High Dimensional Function Optimization
(SPRINGER HEIDELBERG, 2020) Güngör, İmral; Emiroğlu, Bülent Gürsel; Çınar, Ahmet Cevahir; Kıran, Mustafa Servet
The tree-seed algorithm, TSA for short, is a new population-based intelligent optimization algorithm developed for solving continuous optimization problems by inspiring the relationship between trees and their seeds. The locations of trees and seeds correspond to the possible solutions of the optimization problem on the search space. By using this model, the continuous optimization problems with lower dimensions are solved effectively, but its performance dramatically decreases on solving higher dimensional optimization problems. In order to address this issue in the basic TSA, an integration of different solution update rules are proposed in this study for solving high dimensional continuous optimization problems. Based on the search tendency parameter, which is a peculiar control parameter of TSA, five update rules and a withering process are utilized for obtaining seeds for the trees. The performance of the proposed method is investigated on basic 30-dimensional twelve numerical benchmark functions and CEC (congress on evolutionary computation) 2015 test suite. The performance of the proposed approach is also compared with the artificial bee colony algorithm, particle swarm optimization algorithm, genetic algorithm, pure random search algorithm and differential evolution variants. Experimental comparisons show that the proposed method is better than the basic method in terms of solution quality, robustness and convergence characteristics.
Citation - WoS: 10
Citation - Scopus: 7
A Jaya-Based Approach To Wind Turbine Placement Problem
(TAYLOR & FRANCIS INC, 2023) Aslan, Murat; Gündüz, Mesut; Kıran, Mustafa Servet
Renewable energy resources are natural, clean, economical, and never-ending energy resources. Wind energy is an important clean, cheap, and easy applicable energy sources. On account of this, generation of the energy from wind technology has been raised day by day because of the competition with fossil-fuel power production methods. By depending on increases the number of turbines located in the wind farm, the average power obtains from each wind turbine appreciable reduces due to the existence of wake effects within the wind farm. Therefore, the optimal placement of turbines in a wind farm provides to get optimum wind energy from the wind farm. When the place where the wind turbines are located is considered as NxN grid, a wind turbine can be established to each cell of this grid. Whether a wind turbine is replaced to each cell of the grid or not can be modeled as a binary-based optimization problem. In this study, a Jaya-based binary optimization algorithm is proposed to determine which cells are used for wind turbine replacement. In order to justify the efficiency of the proposed approach, two different test cases are considered, and the solutions produced by the proposed approach are compared with the solutions of the swarm intelligence or evolutionary computation methods. According to the experiments and comparisons the Jaya-based binary approach shows a superior performance than compared approaches in terms of cost and power effectiveness. While the efficiency of the Jaya-based approach is 92.2% with 30 turbines replacement on 10 x 10 grid, the efficiency of the Jaya-based binary method is 95.7% with 43 turbines replacement on 20 x 20 grid.
Citation - Scopus: 1
A K-Elm Approach To the Prediction of Number of Students Taking Make-Up Exams
(Gazi Univ, Fac Engineering Architecture, 2022) Kıran, Mustafa Servet; Sıramkaya, Eyup; Esme, Engin
Purpose: The main objective of this study is to present a novel problem, and novel methodology to solve this problem. The problem is to predict the number of students who fail the course and will join the make-up exams. Theory and Methods: The number of students who fail the course should take a make-up exam, but some of them do not join these exams due to internal or external motivations, and this causes waste of resources. Majority of voting-based extreme learning machines have been proposed to solve the problem, and the ELM parameters have been optimized by artificial bee colony algorithm. Results: The proposed approach shows better performance than the extreme learning machines in terms of classification accuracy. Conclusion: Before the scheduling make-up exams, the number of students who will join the exams should be predicted by the proposed or similar approaches in order to use resources efficiently.
Citation - WoS: 7
Citation - Scopus: 4
A Literature Review on Deep Learning Algorithms for Analysis of X-Ray Images
(SPRINGER HEIDELBERG, 2023) Seyfi, Gökhan; Esme, Engin; Yılmaz, Merve; Kıran, Mustafa Servet
Since the invention of the X-ray beam, it has been used for useful applications in various fields, such as medical diagnosis, fluoroscopy, radiation therapy, and computed tomography. In addition, it is also widely used to identify prohibited or illegal materials using X-ray imaging in the security field. However, these procedures are generally dependent on the human factor. An operator detects prohibited objects by projecting pseudo-color images onto a computer screen. Because these processes are prone to error, much work has gone into automating the processes involved. Initial research on this topic consisted mainly of machine learning and methods using hand-crafted features. The newly developed deep learning methods have subsequently been more successful. For this reason, deep learning algorithms are a trend in recent studies and the number of publications has increased in areas such as X-ray imaging. Therefore, we surveyed the studies published in the literature on Deep Learning-based X-ray imaging to attract new readers and provide new perspectives.

Browse

Browsing Bilgisayar ve Bilişim Fakültesi Koleksiyonu by WoS Q "Q3"