Yazar "Sonuc, Emrullah" seçeneğine göre listele
Listeleniyor 1 - 12 / 12
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe An adaptive parallel evolutionary algorithm for solving the uncapacitated facility location problem(Pergamon-Elsevier Science Ltd, 2023) Sonuc, Emrullah; Ozcan, EnderMetaheuristics, providing high level guidelines for heuristic optimisation, have successfully been applied to many complex problems over the past decades. However, their performances often vary depending on the choice of the initial settings for their parameters and operators along with the characteristics of the given problem instance handled. Hence, there is a growing interest into designing adaptive search methods that automate the selection of efficient operators and setting of their parameters during the search process. In this study, an adaptive binary parallel evolutionary algorithm, referred to as ABPEA, is introduced for solving the uncapacitated facility location problem which is proven to be an NP-hard optimisation problem. The approach uses a unary and two other binary operators. A reinforcement learning mechanism is used for assigning credits to operators considering their recent impact on generating improved solutions to the problem instance in hand. An operator is selected adaptively with a greedy policy for perturbing a solution. The performance of the proposed approach is evaluated on a set of well-known benchmark instances using ORLib and M*, and its scaling capacity by running it with different starting points on an increasing number of threads. Parameters are adjusted to derive the best configuration of three different rewarding schemes, which are instant, average and extreme. A performance comparison to the other state-of-the-art algorithms illustrates the superiority of ABPEA. Moreover, ABPEA provides up to a factor of 3.9 times acceleration when compared to the sequential algorithm based on a single-operator.Öğe Binary crow search algorithm for the uncapacitated facility location problem(Springer London Ltd, 2021) Sonuc, EmrullahThe crow search algorithm (CSA) is a recently proposed population-based optimization algorithm for continuous optimization. Since the original CSA searches for a feasible solution in a continuous search space, it cannot handle binary optimization problems directly. A few binary variants of CSA are presented in the literature. However, these variants search for a new solution in the continuous domain and need transfer functions to adapt the solution to the binary domain. This may cause poor exploration, making some regions in the search space impossible to discover. This paper proposes an effective binary CSA (BinCSA) using bitwise operations that directly searches for a feasible solution in the binary search space. For this purpose, the original update mechanism of the CSA is improved using exclusive-OR and AND logical operators in order to provide a good balance between exploration and exploitation in the binary search space. The effectiveness of the proposed BinCSA is evaluated on the uncapacitated facility location problem (UFLP), one of the most widely investigated pure binary optimization problems. The performance of BinCSA is examined using two different UFLP datasets, ORLIB and M*. The experimental results show that BinCSA obtained the optimal solution for 13 out of 15 instances of ORLIB and 12 out of 20 instances of M*. Moreover, BinCSA exhibits superior performance on ORLIB instances when compared to other methods and is very competitive on M* instances in terms of solution quality and robustness. The source code for BinCSA, as used for the UFLP, is available at https://github.com/3mrullah/BinCSA.Öğe A cooperative GPU-based Parallel Multistart Simulated Annealing algorithm for Quadratic Assignment Problem(Elsevier - Division Reed Elsevier India Pvt Ltd, 2018) Sonuc, Emrullah; Sen, Baha; Bayir, SafakGPU hardware and CUDA architecture provide a powerful platform to develop parallel algorithms. Implementation of heuristic and metaheuristic algorithms on GPUs are limited in literature. Nowadays developing parallel algorithms on GPU becomes very important. In this paper, NP-Hard Quadratic Assignment Problem (QAP) that is one of the combinatorial optimization problems is discussed. Parallel Multistart Simulated Annealing (PMSA) method is developed with CUDA architecture to solve QAP. An efficient method is developed by providing multistart technique and cooperation between threads. The cooperation is occurred with threads in both the same and different blocks. This paper focuses on both acceleration and quality of solutions. Computational experiments conducted on many Quadratic Assignment Problem Library (QAPLIB) instances. The experimental results show that PMSA runs up to 29x faster than a single-core CPU and acquires best known solution in a short time in many benchmark datasets. (C) 2018 Karabuk University. Publishing services by Elsevier B.V.Öğe CUDA-based parallel local search for the set-union knapsack problem(Elsevier, 2024) Sonuc, Emrullah; Ozcan, EnderThe Set -Union Knapsack Problem (SUKP) is a complex combinatorial optimisation problem with applications in resource allocation, portfolio selection, and logistics. This paper presents a parallel local search algorithm for solving SUKP on the Compute Unified Device Architecture (CUDA) platform in Graphics Processing Units (GPUs). The proposed method employs a compact algorithm that divides the search space into smaller regions. For diversity, each thread in a GPU block starts the search process from a different location in a region using a different initial solution. Each thread then searches the local optimum by utilising communication between individuals through a crossover operator exploiting the best solution within the GPU block. Through extensive experiments on a set of SUKP benchmark instances ranging in size from small to large, we demonstrate the effectiveness of the proposed algorithm in finding high -quality solutions within comparable time frames. Furthermore, a comparative performance analysis with the current state-of-the-art SUKP algorithms reveals the competitive advantage of the proposed method. The GPU-based parallel local search algorithm using uniform crossover is a valuable addition to the repertoire of algorithms addressing SUKP, highlighting its potential for practical applications in real -world decision -making scenarios.Öğe Deepfake detection using rationale-augmented convolutional neural network(Springer Heidelberg, 2021) Ahmed, Saadaldeen Rashid Ahmed; Sonuc, EmrullahDeepfake network is a prominent topic of research as an application to various systems about security measures. Although there have been many recent advancements in facial reconstruction, the greatest challenge to overcome has been the means of finding an efficient and quick way to compute facial similarities or matches. This work is created utilizing the rationale-augmented convolutional neural network (CNN) on MATLAB R2019a platform using the Kaggle DeepFake Video dataset with an accuracy of 95.77%. Hence, real-time deepfake facial reconstruction for security purposes is difficult to complete concerning limited hardware and efficiency. This research paper looks into rational augmented CNN state-of-the-art technology utilized for deepfake facial reconstruction via hardware such as webcams and security cameras in real time. Additionally, discuss a history of face reconstruction and provide an overview of how it is accomplished.Öğe The Efficiency of Classification Techniques in Predicting Anemia Among Children: A Comparative Study(Springer International Publishing Ag, 2022) Saihood, Qusay; Sonuc, EmrullahAnemia is the most common disease among children under school age, especially in developing countries, due to a lack of understanding about its causes and preventive measures. In most cases, anemia refers to malnutrition and is closely related to demographic and social factors. Previously, statistical methods were used to predict anemia among children and identify associated factors. It was concluded that this is not a good way. Following the success of machine learning (ML) techniques in exploring knowledge from clinical data in healthcare, it was a good chance to explore the knowledge of social factors associated with childhood anemia. In this study, we compared the performance of eight different ML techniques for predicting anemia in children using social factors to find the most appropriate method. ML techniques achieved promising results in predicting and identifying factors associated with childhood anemia. Multilayer perceptron (MLP) has the best accuracy of 81.67% with all features, while Decision Tree (DT) has the best accuracy of 82.50% when we applied feature selection methods. The explored knowledge of the social factors associated with anemia can guide nutritional practices and factors essential to child health. Additionally, identified factors can help prevent anemia outbreaks for appropriate intervention by governments and healthcare organizations.Öğe Evaluating the effectiveness of rationale-augmented convolutional neural networks for deepfake detection(Springer, 2023) Ahmed, Saadaldeen Rashid; Sonuc, EmrullahDeepfake image detection has emerged as an important area of research due to its wide-ranging implications for various security systems. In particular, in the field of deep learning, the task of detecting fake images has traditionally been challenging due to its complicated and abstract nature, especially in the field of computer vision where accurate analysis and understanding of facial landmarks play a crucial role. This study introduces a rational-augmented convolutional neural network (RACNN) for deepfake image detection. The RACNN combines a convolutional neural network (CNN) with a reasoning generator, which generates binary masks to highlight the crucial regions that contribute to the CNN's decision-making process. To improve the accuracy and efficiency of the reasoning generator, a reinforcement learning technique is used to train it to generate accurate and compact masks. Through extensive experiments conducted on a large dataset of deepfake images, the effectiveness of the RACNN method is demonstrated, achieving an impressive accuracy rate of 94.87% on an open-source dataset, namely FaceForensics++. The comparative analysis shows the superiority of the RACNN model over existing approaches, especially in terms of accuracy. This robustly demonstrates the effectiveness of the RACNN in accurately distinguishing between real and fake images. The AUC of 95.69% on the dataset serves as a strong indication of the effectiveness of our proposed method in accurately detecting fake facial images generated by various deepfake techniques. Our model proves to be a promising way to advance the field of deepfake image detection, providing potential improvements to the capabilities of such systems.Öğe A modified crow search algorithm for the weapon-target assignment problem(Ramazan Yaman, 2020) Sonuc, EmrullahThe Weapon-Target Assignment (WTA) problem is one of the most important optimization problems in military operation research. In the WTA problem, assets of defense aim the best assignment of each weapon to target for decreasing expected damage directed by the offense. In this paper, Modified Crow Search Algorithm (MCSA) is proposed to solve the WTA problem. In MCSA, a trial mechanism is used to improve the quality of solutions using parameter LIMIT. If the solution is not improved after a predetermined number of iterations, then MCSA starts with a new position in the search space. Experimental results on the different sizes of the WTA problem instances show that MCSA outperforms CSA in all problem instances. Also, MCSA achieved better results for 11 out of 12 problem instances compared with four state-of-the-art algorithms. The source codes of MCSA for the WTA are publicly available at http://www.3mrullah.com/MCSA.htmlÖğe A Parallel Simulated Annealing Algorithm for Weapon-Target Assignment Problem(Science & Information Sai Organization Ltd, 2017) Sonuc, Emrullah; Sen, Baha; Bayir, SafakWeapon-target assignment (WTA) is a combinatorial optimization problem and is known to be NP-complete. The WTA aims to best assignment of weapons to targets to minimize the total expected value of the surviving targets. Exact methods can solve only small-size problems in a reasonable time. Although many heuristic methods have been studied for the WTA in the literature, a few parallel methods have been proposed. This paper presents parallel simulated algorithm (PSA) to solve the WTA. The PSA runs on GPU using CUDA platform. Multi-start technique is used in PSA to improve quality of solutions. 12 problem instances (up to 200 weapons and 200 targets) generated randomly are used to test the effectiveness of the PSA. Computational experiments show that the PSA outperforms SA on average and runs up to 250x faster than a single-core CPU.Öğe A practical framework for early detection of diabetes using ensemble machine learning models(Tubitak Scientific & Technological Research Council Turkey, 2023) Saihood, Qusay; Sonuc, EmrullahThe diagnosis of diabetes, a prevalent global health condition, is crucial for preventing severe complications. In recent years, there has been a growing effort to develop intelligent diagnostic systems for diabetes utilizing machine learning (ML) algorithms. Despite these efforts, achieving high accuracy rates using such systems remains a significant challenge. Recent advancements in ensemble ML methods offer promising opportunities for early detection of diabetes, as they are known to be faster and more cost-effective than traditional approaches. Therefore, this study proposes a practical framework for diagnosing diabetes that involves three stages. The data preprocessing stage encompasses several crucial tasks, including handling missing values, identifying outliers, balancing the data, normalizing the data, and selecting relevant features. Subsequently, the hyperparameters of the ML algorithms are fine-tuned using grid search to improve their performance. In the final stage, the framework employs ensemble techniques such as bagging, boosting, and stacking to combine multiple ML algorithms and further enhance their predictive capability. Pima Indians Diabetes Database open-access dataset was used to test the performance of the proposed models. The experimental results of this framework indicate the superiority of ensemble methods in diagnosing diabetes compared to individual ML models. The stacking method achieved the best accuracy among the ensemble methods, with the stacked random forest (RF) and support vector machine (SVM) model attaining an accuracy of 97.50%. Among the bagging methods, the RF model yielded the highest accuracy, while among the boosting methods, eXtreme Gradient Boosting (XGB) model achieved the highest accuracy rates of 97.20% and 97.10%, respectively. Moreover, our proposed framework outperforms other ML models as confirmed by the comparison. The study has demonstrated that ensemble methods are crucial for accurate diabetes diagnosis, enabling early detection through efficient preprocessing and calibrated models.Öğe VALIDATION OF DAILY PRECIPITATION ESTIMATES OF THE REGIONAL CLIMATE MODEL REGCM4 OVER THE DOMAINS IN TURKEY WITH NWP VERIFICATION TECHNIQUES(Parlar Scientific Publications (P S P), 2014) Sen, Burak; Kilinc, Recep; Sen, Baha; Sonuc, EmrullahWe present a validation study for a 50-km resolution version of the RegCM4 regional climate model over the East Mediterranean Basin. In this study, the observation and evaluation of the model results against each other as well as graphication, which mostly generates scatter plot graphs of the atmosphere for operational weather forecasting models (NWP, numerical weather prediction), with 11 different statistical verification score values were evaluated by calculating the regional climate model results. As a result of the analysis, it has been estimated that the rainfall is 42% higher than the estimated average amount RegCM4 simulations based on the 50 observation stations. Meteorological Service (TSMS, Turkish State Meteorological Service) observation network monitored 50 stations based on the average of Frequency Bias Index (FBI), Proportion Correct (PC), Probability of Detection (POD), False Alarm Ratio (FAR), False Alarm Rate (F), Hanssen-Kuipers Skill Score (KSS), the Threat Score (TS), Equitable Threat Score (ETS), Heidke Skill Score (HSS), The Odds Ratio (OR), and Odds Ratio Skill Score (ORSS) values which are as follows, respectively: 0.70, 0.70, 0.52, 0.32, 0.38, 0.39, 0.21, 0.34, 5.99, and 0.69. The objective score values calculated for RegCM4 climate model were found to be close to the score values of the NWP models. Given these values, which were found to be successful for RegCM4 model dynamics, the results generated by other models, recovery/adaptation techniques will be used for the application of hydrological studies.Öğe Verifying regional climate model results with web-based expert-system(Elsevier Science Bv, 2012) Sonuc, Emrullah; Sen, Baha; Sen, BurakThe verification system aims at monitoring the forecast quality over time. Verification helps improving the forecast quality by knowing the strengths and weaknesses of the existing forecasting system and by comparing the quality of different forecasting methodologies. Thus, the web-based verification system has been developed for verification of forecast results that is produced by International Center for Theoretical Physics Regional Climate Model v4 for our country. The forecasters and analysts can analyze the data in real-time with this web-based system. In this study, model values obtained from the system provided by ULAKBIM High Performance and Grid Computing Center. Model and station values were compared with each other for verification of model results with observation values. Therefore model grid values are transferred to station by using bi-linear and nearest neighbor (k-NN) (proximal) interpolation methods. This process in meteorological literature is called grid to point technique. Verification methods for forecasts of continuous variables are used to verify forecast values with observation values. Some verification methods; Mean Error, Mean Absolute Error and Root Mean Square Error, are calculated for validation. Verification results are shown as table and graphics on web-based system which is developed by the power of PHP (PHP: Hypertext Preprocessor). (C) 2011 Published by Elsevier Ltd.
