Bilgisayar ve Bilişim Fakültesi Koleksiyonu

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

Browse

Now showing 1 - 7 of 7

Citation - WoS: 8
Citation - Scopus: 9
A Comparative Study of Swarm Intelligence and Evolutionary Algorithms on Urban Land Readjustment Problem
(ELSEVIER, 2021) Koç, İsmail; Babaoğlu, İsmail
Land Readjustment and redistribution (LR) is a land management tool that helps regular urban development with the contribution of landowners. The main purpose of LR is to transform irregularly developed land parcels into suitable forms. Since it is necessary to handle many criteria simultaneously to solve LR problems, classical mathematical methods can be insufficient due to time limitation. Since LR problems are similar to traveling salesman problems and typical scheduling problems in terms of structure, they are kinds of NP-hard problems in combinatorial optimization. Therefore, metaheuristic algorithms are used in order to solve NP-hard problems instead of classical methods. At first, in this study, an effective problem-specific objective function is proposed to address the main criteria of the problem. In addition, a map-based crossover operator and three different mutation operators are proposed for the LR, and then a hybrid approach is implemented by utilizing those operators together. Furthermore, since the optimal value of the problem handled in real world cannot be exactly estimated, a synthetic dataset is proposed as a benchmarking set in LR which makes the success of algorithms can be objectively evaluated. This dataset consists of 5 different problems according to number of parcel which are 20, 40, 60, 80 and 100. Each problem set consists of 4 sub-problems in terms of number of landowners per-parcel which are 1, 2, 3 and 4. Therefore, the dataset consists of 20 kinds of problems. In this study, artificial bee colony, particle swarm optimization, differential evolution, genetic and tree seed algorithm are used. In the experimental studies, five algorithms are set to run under equal conditions using the proposed synthetic dataset. When the acquired experimental results are examined, genetic algorithm seems to be the most effective algorithm in terms of both speed and performance. Although artificial bee colony has better results from genetic algorithm in a few problems, artificial bee colony is the second most successful algorithm after genetic algorithm in terms of performance. However, in terms of time, artificial bee colony is an algorithm nearly as successful as genetic algorithm. On the other hand, the results of differential evolution, particle swarm optimization and tree seed algorithms are similar to each other in terms of solution quality. In conclusion, the statistical tests clearly show that genetic algorithm is the most effective technique in solving LR problems in terms of speed, performance and robustness. (C) 2020 Elsevier B.V. All rights reserved.
Citation - WoS: 67
Citation - Scopus: 79
Djaya: a Discrete Jaya Algorithm for Solving Traveling Salesman Problem
(ELSEVIER, 2021) Gündüz, Mesut; Aslan, Murat
Jaya algorithm is a newly proposed stochastic population-based metaheuristic optimization algorithm to solve constrained and unconstrained continuous optimization problems. The main difference of this algorithm from the similar approaches, it uses best and worst solution in the population in order improve the intensification and diversification of the population, and this provides discovering potential solutions on the search space of the optimization problem. In this study, we propose discrete versions of the Jaya by using two major modifications in the algorithm. First is to generate initial solutions by using random permutations and nearest neighborhood approach to create population. Second is the update rule of the basic Jaya algorithm rearranged to solve discrete optimization problems. Due to characteristics of the discrete optimization problem, eight transformation operators are used for the discrete variants of the proposed algorithm. Based on these modifications, the discrete Jaya algorithm, called DJAYA, has been applied to solve fourteen different symmetric traveling salesman problem, which is one of the famous discrete problems in the discrete optimization. In order to improve the obtained best solution from DJAYA, 2-opt heuristic is also applied to the best solution of DJAYA. Once population size, search tendency and the other parameters of the proposed algorithm have been analyzed, it has been compared with the state-of-art algorithms and their variants, such as Simulated Annealing (SA), Tree-Seed Algorithm (TSA), State Transition Algorithm (STA) Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Artificial Bee Colony (ABC), Genetic Algorithm (GA) and Black Hole (BH). The experimental results and comparisons show that the proposed DJAYA is highly competitive and robust optimizer for the problem dealt with the study. (C) 2021 Elsevier B.V. All rights reserved.
Citation - WoS: 173
Citation - Scopus: 237
Human Action Recognition Using Attention Based Lstm Network With Dilated Cnn Features
(ELSEVIER, 2021) Muhammad, Khan; Mustaqeem; Ullah, Amin; Imran, Ali Shariq; Sajjad, Muhammad; Kıran, Mustafa Servet; de Albuquerque, Victor Hugo C.
Human action recognition in videos is an active area of research in computer vision and pattern recognition. Nowadays, artificial intelligence (AI) based systems are needed for human-behavior assessment and security purposes. The existing action recognition techniques are mainly using pre-trained weights of different AI architectures for the visual representation of video frames in the training stage, which affect the features' discrepancy determination, such as the distinction between the visual and temporal signs. To address this issue, we propose a bi-directional long short-term memory (BiLSTM) based attention mechanism with a dilated convolutional neural network (DCNN) that selectively focuses on effective features in the input frame to recognize the different human actions in the videos. In this diverse network, we use the DCNN layers to extract the salient discriminative features by using the residual blocks to upgrade the features that keep more information than a shallow layer. Furthermore, we feed these features into a BiLSTM to learn the long-term dependencies, which is followed by the attention mechanism to boost the performance and extract the additional high-level selective action related patterns and cues. We further use the center loss with Softmax to improve the loss function that achieves a higher performance in the video-based action classification. The proposed system is evaluated on three benchmarks, i.e., UCF11, UCF sports, and J-HMDB datasets for which it achieved a recognition rate of 98.3%, 99.1%, and 80.2%, respectively, showing 1%-3% improvement compared to the state-of-the-art (SOTA) methods. (C) 2021 Elsevier B.V. All rights reserved.
Citation - WoS: 89
Citation - Scopus: 97
Jayax: Jaya Algorithm With Xor Operator for Binary Optimization
(ELSEVIER, 2019) Aslan, Murat; Gündüz, Mesut; Kıran, Mustafa Servet
Jaya is a population-based heuristic optimization algorithm proposed for solving constrained and unconstrained optimization problems. The peculiar distinct feature of Jaya from the other population-based algorithms is that it updates the positions of artificial agent in the population by considering the best and worst individuals. This is an important property for the algorithm to balance exploration and exploitation on the solution space. However, the basic Jaya cannot be applied to binary optimization problems because the solution space is discretely structured for this type of optimization problems and the decision variables of the binary optimization problems can be element of set [0,1]. In this study, we first focus on discretization of Jaya by using a logic operator, exclusive or - xor. The proposed idea is simple but effective because the solution update rule of Jaya is replaced with the xor operator, and when the obtained results are compared with the state-of-art algorithms, it is seen that the Jaya-based binary optimization algorithm, JayaX for short, produces better quality results for the binary optimization problems dealt with the study. The benchmark problems in this study are uncapacitated facility location problems and CEC2015 numeric functions, and the performance of the algorithms is compared on these problems. In order to improve the performance of the proposed algorithm, a local search module is also integrated with the JayaX. The obtained results show that the proposed algorithm is better than the compared algorithms in terms of solution quality and robustness. (C) 2019 Elsevier B.V. All rights reserved.
Citation - WoS: 17
Citation - Scopus: 29
Mode-Cnn: a Fast Converging Multi-Objective Optimization Algorithm for Cnn-Based Models
(ELSEVIER, 2021) İnik, Özkan; Altıok, Mustafa; Ülker, Erkan; Koçer, Barış
Convolutional neural networks (CNNs) have been used to solve many problems in computer science with a high level of success, and have been applied in many fields in recent years. However, most of the designs of these models are still tuned manually; obtaining the highest performing CNN model is therefore very time-consuming, and is sometimes not achievable. Recently, researchers have started using optimization algorithms for the automatic adjustment of the hyper-parameters of CNNs. In particular, single-objective optimization algorithms have been used to achieve the highest network accuracy for the design of a CNN. When these studies are examined, it can be seen that the most significant problem in the optimization of the parameters of a CNN is that a great deal of time is required for tuning. Hence, optimization algorithms with high convergence rates are needed for the parameter optimization of deep networks. In this study, we first develop an algorithm called MODE-CNN, based on the multi-objective differential evolution (MODE) algorithm for parameter optimization of CNN or CNN-based methods. MODE-CNN is then compared with four different multi-objective optimization algorithms. This comparison is carried out using 16 benchmark functions and four different metrics, with 100 independent runs. It is observed that the algorithm is robust and competitive compared to alternative approaches, in terms of its accuracy and convergence. Secondly, the MODE-CNN algorithm is used in the parameter optimization of a CNN-based method, developed previously by the authors, for the segmentation and classification of medical images. In this method, there are three parameters that influence the test time and accuracy: the general stride (GS), neighbour distance (ND), and patch accuracy (PA). These parameters need to be optimized to give the highest possible accuracy and lowest possible test time. With the MODE-CNN algorithm, the most appropriate GS, ND, and PA values are obtained for the test time and accuracy. As a result, it is observed that the MODE-CNN algorithm is successful, both in comparison with multi-objective algorithms and in the parameter optimization of a CNN-based method. (C) 2021 Elsevier B.V. All rights reserved.
Citation - WoS: 49
Citation - Scopus: 54
A New Algorithm Based on Gray Wolf Optimizer and Shuffled Frog Leaping Algorithm To Solve the Multi-Objective Optimization Problems
(ELSEVIER, 2020) Karakoyun, Murat; Özkış, Ahmet; Kodaz, Halife
Multi-objective optimization is many important since most of the real world problems are in multiobjective category. Looking at the literature, the algorithms proposed for the solution of multi-objective problems have increased in recent years, but there is no a convenient approach for all kind of problems. Therefore, researchers aim to contribute to the literature by offering new approaches. In this study, an algorithm based on gray wolf optimizer (GWO) with memeplex structure of the shuffled frog leaping algorithm (SFLA), which is named as multi-objective shuffled GWO (MOSG), is proposed to solve the multi-objective optimization problems. Additionally, some modifications are applied on the proposed algorithm to improve the performance from different angles. The performance of the proposed algorithm is compared with the performance of six multi-objective algorithms on a benchmark set consist of 36 problems. The experimental results are presented with four different comparison metrics and statistical tests. According to the results, it can easily be said that the proposed algorithm is generally successful to solve the multi-objective problems and has better or competitive results. (C) 2020 Elsevier B.V. All rights reserved.
Citation - WoS: 26
Citation - Scopus: 30
A Tree-Seed Algorithm Based on Intelligent Search Mechanisms for Continuous Optimization
(ELSEVIER, 2021) Kıran, Mustafa Servet; Haklı, Hüseyin
One of the recently proposed metaheuristic algorithms is tree-seed algorithm, TSA for short. TSA is developed by inspiring the relation between trees and their seeds in order to solve continuous optimization problems, and it has a simple but effective algorithmic structure. The algorithm uses two different solution generating mechanisms in order to improve balance local and global search abilities. However, when the algorithm is analyzed in detail, it is seen that there are some issues in the basic algorithm. These are (i) when trees in the stand approaches to each other, the diversification in the stand is lost, (ii) there is no mechanism to get rid of local minima for a tree, (iii) some of the fitness calculation goes to waste due to seed generation mechanism of basic TSA. In order to address these issues, four different approaches (withering process, sequential seed generation, best-based solution update rule and dimensional selection for the solution update rule) have been proposed for the basic TSA, and all these approaches have been also integrated within algorithmic framework of TSA, named new tree-seed algorithm briefly NTSA, and each of them has been used to solve 28 CEC2013 benchmark functions. In the experimental comparisons, the variants of TSA have been compared with each other, and the better algorithm, NTSA, has been compared with 17 state-of-art algorithms such as artificial bee colony, particle swarm optimization, differential evolution, genetic algorithm, covariance matrix adaptation evolutionary strategy etc. The experimental analysis and comparisons show that the NTSA shows better or similar performance than/with the compared algorithms in terms of solution quality and robustness. (C) 2020 Elsevier B.V. All rights reserved.

Browse

Browsing Bilgisayar ve Bilişim Fakültesi Koleksiyonu by Publisher "ELSEVIER"