Search

© 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.In this study, we apply multilevel thresholding segmentation to color images of plant disease. Given that thresholding segmentation is just an optimization problem, we use Otsu’s function as the objective function. To solve this optimization problem, we implement five metaheuristic algorithms, namely artificial bee colony (ABC), cuckoo search (CS), teaching–learning-based optimization (TLBO), teaching–learning-based artificial bee colony (TLABC) and a modified version of TLABC proposed in this work, known as MTLABC. This version is a hybridization between TLABC and Levy flight where the search equations of TLABC are changed according to Levy flight equations; this modification, based on the experimental results, yields a significant improvement in TLABC. Various numbers of thresholding levels are tried to compare the performance of the optimization algorithms at multiple dimensions. The performance is measured according to five measures: the objective function, CPU time, peak noise-to-signal ratio, structural similarity index and color feature similarity. These measures indicate that our proposed algorithm, with the best values of the measures in most images and levels, ranks first. Also, Friedman and Wilcoxon signed-rank tests are used to analyze the results statistically. These two tests prove that our proposed algorithm is significantly different from the other four algorithms.

As a relatively new model, the Artificial Bee Colony Algorithm (ABC) has shown impressive success in solving optimization problems. Nevertheless, its efficiency is still not satisfactory for some complex optimization problems. This paper has modified ABC and its other recent variants to improve its performance by modify the scout phase. This modification enhances its exploitation ability by intensifying the regions in the search space, which probably includes reasonable solutions. The experiments were performed on the CEC2014 benchmark suite, CEC2015 benchmark functions, and three real-life problems: pressure vessel design problem, tension and compression spring design problem, and Frequency-Modulated (FM) problem. And the proposed modification was applied to basic ABC, Gbest-Guided ABC, Depth First Search ABC, and Teaching Learning Based ABC, and they were compared with their modified counterparts. The results have shown that our modification can successfully increase the performance of the original versions. Moreover, the proposed modified algorithm was compared with the state-of-the-art optimization algorithms, and it produced competitive results.

Endüstriyel ortamlarda giderek daha fazla kullanılan mobil robotlar için yol planlanması önemli bir problemdir. Bu problem, engelli bir ortamda başlangıç düğümünden hedef düğüme kadar mesafe ve süre gibi bazı kriterler dikkate alınarak engellere çarpmadan uygun bir yolun bulunmasıdır. Alternatif yolların üretilmesinde doğrusal (düz çizgi) veya doğrusal olmayan (eğri) amaç fonksiyonlarının kullanılması performansı önemli ölçüde etkilemektedir. Bu çalışmada, küresel yol planlama için farklı zorluk derecelerine sahip ortamlarda doğrusal ve doğrusal olmayan amaç fonksiyonlarının kullanımı karşılaştırmalı incelenmiştir. Uygun yolların bulunmasında evrimsel algoritmalardan biri olan genetik algoritma (Genetic Algorithm, GA) kullanılmıştır. Simülasyon sonuçları, mobil robotların yol planlamasında doğrusal amaç fonksiyonu kullanılmasının hem mesafe hem de algoritma çalışma süresi açısından avantajlı olduğunu göstermiştir., Path planning is an important problem for mobile robots, which are increasingly used in industrial environments. This problem is to find a suitable path from a starting node to a target node without colliding obstacles, taking into account some criteria such as distance and time. The use of linear (straight line) or nonlinear (curve) objective functions in the generation of alternative paths significantly affects the performance. In this study, the use of linear and nonlinear objective functions for global path planning in environments with different degrees of difficulty has been comparatively examined. Genetic algorithm (GA), one of the evolutionary algorithms, was used to find suitable paths. The simulation results showed that using the linear objective function in path planning of mobile robots is advantageous in terms of both distance and algorithm running time.

© 2021, The Author(s), under exclusive licence to Springer Nature B.V.Deep neural networks (DNNs), which are extensions of artificial neural networks, can learn higher levels of feature hierarchy established by lower level features by transforming the raw feature space to another complex feature space. Although deep networks are successful in a wide range of problems in different fields, there are some issues affecting their overall performance such as selecting appropriate values for model parameters, deciding the optimal architecture and feature representation and determining optimal weight and bias values. Recently, metaheuristic algorithms have been proposed to automate these tasks. This survey gives brief information about common basic DNN architectures including convolutional neural networks, unsupervised pre-trained models, recurrent neural networks and recursive neural networks. We formulate the optimization problems in DNN design such as architecture optimization, hyper-parameter optimization, training and feature representation level optimization. The encoding schemes used in metaheuristics to represent the network architectures are categorized. The evolutionary and selection operators, and also speed-up methods are summarized, and the main approaches to validate the results of networks designed by metaheuristics are provided. Moreover, we group the studies on the metaheuristics for deep neural networks based on the problem type considered and present the datasets mostly used in the studies for the readers. We discuss about the pros and cons of utilizing metaheuristics in deep learning field and give some future directions for connecting the metaheuristics and deep learning. To the best of our knowledge, this is the most comprehensive survey about metaheuristics used in deep learning field.

Monitoring of production lines in real-time and prediction of undesirable situations are critical. In this study, a Modbus-based prototype application is performed to collect and evaluate data such as temperature, voltage, current, and frequency from the production lines' devices.With this design, the system board is simplified by removing the programmable logic controller, relays, analog modules, and cables. Also, the system is provided monitoring and controlling remotely by adding a modem. Furthermore, data collected from the system are used for fuzzy logic-based predictive maintenance. With the developed model, a self-controlling adaptive system is provided. The results show that the new approach applies to collecting and interpreting data from different qualified devices.

It is an essential issue for mobile robots to reach the target points with optimum cost which can be minimum duration or minimum fuel, depending on the problem. In this paper, it was aimed to develop a software for the optimal path planning of mobile robots in user-defined two-dimensional environments with static obstacles and to analyze the performance of some optimization algorithms for this problem using this software. The developed software is designed to create obstacles of different shapes and sizes in the work area and to find the shortest path for the robot using the selected optimization algorithm. Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC) and Genetic Algorithm (GA) were implemented in the software. These algorithms have been tested for optimum path planning in four models with different problem sizes and different difficulty levels. When the results are evaluated, it is observed that the ABC algorithm gives better results than other algorithms in terms of the shortest distance. With this study, the use of optimization algorithms in real-time path planning of land mobile robots or unmanned aerial vehicles can be simulated.

The use of technology for the purpose of improving crop yields, quality and quantity of the harvest, as well as maintaining the quality of the crop against adverse environmental elements (such as rodent or insect infestation, as well as microbial disease agents) is becoming more critical for farming practice worldwide. One of the technology areas that is proving to be most promising in this area is artificial intelligence, or more specifically, machine learning techniques. This chapter aims to give the reader an overview of how machine learning techniques can help solve the problem of monitoring crop quality and disease identification. The fundamental principles are illustrated through two different case studies, one involving the use of artificial neural networks for harvested grain condition monitoring and the other concerning crop disease identification using support vector machines and k-nearest neighbor algorithm.

Günümüzde mobil robotların hedef noktalara optimum maliyetle ulaşma problemi önemli bir çalışma sahası haline gelmiştir. Optimum maliyet çalışmalarda farklılık göstermekle beraber genel olarak, hedefe ulaşmak için geçen süre, mesafe, harcanan enerji veya bunların bir arada değerlendirildiği değişik kombinasyonlar olabilmektedir. Özellikle çok engelli karmaşık ortamlarda problemlerin çözümünün kabul edilebilir sürelerde gerçekleştirilebilmesi büyük önem taşımaktadır. Bu sürelerde çözümlere ulaşabilmek için algoritmaların daha hızlı çalışması gerekebilmektedir. Ancak bunun için genelde algoritma tarafında iyileştirmeler yapılmaktadır. Bu çalışmada ise problem tarafında iyileştirmeye odaklanılmıştır. Bu doğrultuda, statik engelli ve iki boyutlu ortamlarda engellerin kümelenmesiyle ortam karmaşıklığının azaltılması ve bu sayede optimizasyon algoritmalarının çalışma hızının artırılması amacıyla, parçacık sürü optimizasyonu (Particle Swarm Optimization, PSO) ve k-ortalamalar kümeleme algoritmalarının bir arada kullanıldığı yeni bir model önerilmektedir. K-ortalamalar kümeleme algoritması ile orijinal ortamdaki engeller kümelenip yeni bir ortam oluşturulmaktadır. PSO algoritması ile bu yeni ortamda optimum yol planlanmaktadır. Geliştirilen model çeşitli kümeleme oranları ile test edilmiş ve kümeleme yaklaşımının etkisi değerlendirilmiştir. Değerlendirme sonucunda, kümeleme oranı arttıkça en kısa mesafeli yol açısından küçük kayıplar elde edilmiş ancak algoritmanın çalışma hızı bu kayıpları fazlasıyla telafi edebilecek seviyede artmıştır. Ayrıca optimum çalışma hızı için kümeleme oranlarının orta seviyelerde belirlenmesi gerektiği de tespit edilmiştir. Sonuç olarak, rastgele dağılımlı çok sayıda engelin bulunduğu iki boyutlu ortamlar için yol planlama algoritmalarının çalışma hızı geliştirilen model sayesinde artırılabilir.

The term swarm refers to any restrained collection of interacting agents or individuals. For survival, creatures need to live or perform some tasks collectively such as defending against predators, foraging, mating, etc. An intelligent swarm optimizes a goal or task by responding adaptively to the local and/or global environmental changes in a collective manner. Swarm intelligence research field deals with designing algorithms inspired by the collective behavior of social creatures. Task division and self-organization abilities lead swarm intelligence to occur in a colony and the self-organization is characterized by positive-feedback, negative feedback, fluctuation and multiple interactions in order to use the local information to form a global pattern without a supervision. Ants, termites, birds, and fishes are some examples of social animals that have swarm intelligence and inspire researchers to design problem solving techniques. Bees also are a typical example of creatures performing tasks collectively in nest site selection, nest building, mating, and foraging. Among these activities, foraging might be the most crucial one for the survival of a bee colony. The swarm intelligence in foraging of a honey bee colony inspired Karaboga to design an optimization algorithm, Artificial Bee Colony (ABC), in which the search is guided by the bees’ exploration and exploitation mechanisms to maximize the quality of the honey within the hive. In this chapter, first, the foraging behavior of real honey bees is summarized and then, the details of Artificial Bee Colony algorithm about how it mimics the foraging behavior is provided. In the third section, an application of ABC algorithm is carried out on a software engineering problem, software defect prediction.

Although many algorithms have been proposed, no single algorithm is better than others on all types of problems. Therefore, the search characteristics of different algorithms that show complementary behavior can be combined through portfolio structures to improve the performance on a wider set of problems. In this work, a portfolio of the Artificial Bee Colony, Differential Evolution and Particle Swarm Optimization algorithms was constructed and the first parallel implementation of the population-based algorithm portfolio was carried out by means of a Message Passing Interface environment. The parallel implementation of an algorithm or a portfolio can be performed by different models such as master-slave, coarse-grained or a hybrid of both, as used in this study. Hence, the efficiency and running time of various parallel implementations with different parameter values and combinations were investigated on benchmark problems. The performance of the parallel portfolio was compared to those of the single constituent algorithms. The results showed that the proposed models reduced the running time and the portfolio delivered a robust performance compared to each constituent algorithm. It is observed that the speedup gained over the sequential counterpart changed significantly depending on the structure of the portfolio. The portfolio is also applied to a training of neural networks which has been used for time series prediction. Result demonstrate that, portfolio is able to produce good prediction accuracy. (C) 2017 Elsevier B.V. All rights reserved.

The great improvement in the current technology, particularly in the field of artificial intelligence, has effectively contributed to solving many problems, especially in the medical field. More recently, skin cancer (melanoma) has become one of the most dangerous cancers threatening human life, although it can be treated more frequently at early detection. Unfortunately, only highly-trained specialists can diagnose the disease accurately. Therefore, in this paper we have introduced various software technologies to detect and diagnose skin cancer through images, thus saving lives and reducing the spread of the disease, as well as reducing unnecessary traditional eradication of non-carcinogenic areas. Our method combines image processing techniques (image enhancement, hair removal and segmentation using Otsu's thresholding), feature extraction techniques (Gray Level Co-Occurrence Matrix (GLCM) features and color moments features) and commonly used classification methods, such as Weighted KNN, Cubic SVM, Medium Gaussian SVM, and Multi-Layer Perceptron (MLP) trained by some of the common swarm intelligent techniques like Artificial Bee Colony (ABC), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Teaching Learning Based Artificial Bee Colony (TLABC), and Modified Teaching Learning Based Artificial Bee Colony (MTLABC) which is the proposed algorithm in this paper. Experimental results for 996 dermoscopy dataset images, show that the classification accuracy and the convergence of the trained Neural Network (NN) using the proposed MTLABC is better than the other evolutionary algorithms used in this study for the same purpose. At the same time, the experimental results show that the classification accuracy of the trained NN using the proposed MTLABC is better than the results of commonly used classification methods.

Using Wi-Fi signal strengthfor detecting objects in an indoor environment has different types ofapplications, such as, locating perpetrator in finite areas, and detecting thenumber of users on an access point. In this work, we propose a hybridoptimization algorithm to train training Multi-Layer Perceptron Neural Network thatcould be distributed in monitoring and tracking devices used for determiningthe location of users based on the Wi-Fi signal strength which their personaldevices receive. This hybrid algorithm combines Artificial Bee Colony (ABC) andLevy Flight (LF) algorithm, called ABCLF. ABCLF increases the exploration andexploitation capabilities of ABC so that it can be used efficiency for thepurpose of training Multi-Layer Perceptron “MLP” Neural Network. The proposedABCLF algorithm guarantees the enhancing of accuracy with the increasing in iterations because it hasthe powerfull of the frame work of Artificial Bee Colony algorithm “threephases whith different strategies of searching” and the powerfull of the LevyFlight local search algorithm which has been used in both onlooker bee phase with a short step size walk to guarantee the enhancing in theexploitation and in scout bee phase with a long step size walk to guarantee the enhancing inthe exploration. The results of ourstudy show that the classification accuracy of the trained neural network usingABCLF is better than the other evolutionary algorithms used in this study forthe same purpose like ABC, Genetic Algorithm (GA), Biogeography-BasedOptimization (BBO), Probability Based Incremental Learning (PBIL) and ParticleSwarm Optimization (PSO)., Using Wi-Fi signal strength for detecting objects in an indoor environment has different types of applications, such as, locating perpetrator in finite areas, and detecting the number of users on an access point. In this work, we propose a hybrid optimization algorithm to train training Multi-Layer Perceptron Neural Network that could be distributed in monitoring and tracking devices used for determining the location of users based on the Wi-Fi signal strength which their personal devices receive. This hybrid algorithm combines Artificial Bee Colony (ABC) and Levy Flight (LF) algorithm, called ABCLF. ABCLF increases the exploration and exploitation capabilities of ABC so that it can be used efficiency for the purpose of training Multi-Layer Perceptron “MLP” Neural Network. The proposed ABCLF algorithm guarantees the enhancing of accuracy with the increasing in iterations because it has the powerfull of the frame work of Artificial Bee Colony algorithm “three phases whith different strategies of searching” and the powerfull of the Levy Flight local search algorithm which has been used in both onlooker bee phase with a short step size walk to guarantee the enhancing in the exploitation and in scout bee phase with a long step size walk to guarantee the enhancing in the exploration. The results of our study show that the classification accuracy of the trained neural network using ABCLF is better than the other evolutionary algorithms used in this study for the same purpose like ABC, Genetic Algorithm (GA), Biogeography-Based Optimization (BBO), Probability Based Incremental Learning (PBIL) and Particle Swarm Optimization (PSO).

Url:http://sujest.selcuk.edu.tr/sumbtd/article/view/489 DOI: 10.15317/Scitech.2018.127, We consider the problem of accurate in-body ranging for localization of a wireless capsule endoscope utilizing ultra-wide band (UWB) signaling. In this context, we explore the joint use of neural network structures and learning algorithms based on metaheuristics, an example of which is particle swarm optimization (PSO). The contributions of this paper are three-fold. First, we undertake a systematic performance analysis of the PSO technique for UWB-based in-body ranging and propose an improved version of the PSO algorithm. Second, we quantitatively compare the performance of PSO techniques against more traditional learning algorithms, such as Bayesian Regularization, Levenberg-Marquardt and Single Conjugate Gradient. Third, we quantify the impact of activation functions used to define the neural network structure on performance. Our results indicate that PSO-based techniques can outperform traditional techniques by as much as 44%, depending on the activation functions used in the neural network., Bu makalede, ultra geniş bant (UWB) sinyalleri kullanan bir kablosuz kapsül endoskopunun lokalizasyonu için hassas vücut içi mesafe ölçümü problemi ele alınmaktadır. Bu bağlamda, yapay sinir ağları ve metaheuristik temelli öğrenme algoritmalarının (örnek olarak parçacık sürüsü optimizasyonu (PSO) ortak kullanımı irdelenmektedir. Makalenin literatüre katkıları şu şekilde özetlenebilir. İlk olarak, UWB tabanlı vücut içi mesafe ölçümü için PSO algoritmasının sistematik bir performans analizi yapılmış ve söz konusu problemin çözümü için PSO algoritmasının geliştirilmiş bir versiyonu önerilmiştir. İkinci olarak, önerilen PSO algoritmasının performansı Bayesian Regularization, Levenberg-Marquardt ve Single Conjugate Gradient gibi geleneksel öğrenme algoritmaları ile karşılaştırılmıştır. Son olarak, yapay sinir ağlarında kullanılan aktivasyon fonksiyonlarının performans üzerindeki etkileri incelenmiştir. Elde edilen sonuçlar, önerilen PSO algoritması vasıtası ile geleneksel tekniklere nazaran % 44’e varan performans artışları elde edilebileceğini göstermektedir

In this study, we proposed a parallel implementation of the combinatorial type artificial bee colony algorithm which has an efficient neighbor production mechanism. Running time and performance tests of the proposed parallel model were carried on the traveling salesmen problem. Results show that parallel artificial bee colony algorithm decreases the running time due to exploiting the computational power of parallel computing systems. Beside, better quality solutions are obtained compared to the reproduction methods of the genetic algorithm.

Despite the efficiency of evolutionary algorithms is prominent for large scale problems, their running times in terms of CPU time are quite large. Multi processing units served by recent hardware developments can be employed to overcome this drawback reducing the running time and sharing the total workload. However, evolutionary algorithms cannot be directly distributed to processing units due to their cooperative working models. These models need to be modified to be able to run them on distributed environments without causing deterioration in performance. In this study, a detailed performance analysis of a parallel model for the artificial bee colony algorithm, which is one of the recently developed swarm based evolutionary algorithms and a promising numerical optimization tool, is proposed. For this purpose large-scale benchmark problems are solved by the proposed model and also its original sequential counterpart model. The model is also applied to a real-world problem: training of neural networks for classification purposes. Comparative results show that the artificial bee colony algorithm is very suitable to use in parallel architectures since it has the ability to produce high quality solutions with small populations due to its perturbation operator. The proposed model decreases the running time in addition to improving the performance and convergence rate of the algorithm. It can be said that the speedup gained over its sequential counterpart is almost linear. (C) 2013 Elsevier Inc. All rights reserved.

Evolutionary algorithms often need huge running times when solving large-scale optimization problems. One of the solutions for this issue is to introduce parallelization into the algorithm. To benefit from this approach for the artificial bee colony optimization algorithm, we present a new synchronous and parallel version of the algorithm. Performances of the proposed version and the original asynchronous algorithm are compared in terms of efficiency and speedup. Algorithms are competed to solve 20 large-scale global optimization problems. Comparative results show that the proposed parallel algorithm is still efficient as asynchronous version while it requires much less time to solve complex and large problems.

It is known that parallel computing systems have some advantages to solve large scale and hard problems. However, traditional multi-processor parallel architectures are not widely used since they are hard to operate and they have high cost in setting-up .It has been an important point to Graphical Processing Units (GPU) were shown to be used in general-purpose applications because they naturally have hundreds of parallel cores. Studies related with the usage of GPUs in general-purpose are increasing day by day. In this study, Fast Fourier Transform (FFT), Inverse Fast Fourier Transform (IFFT) and Radon Transforms widely used in signal and image processing problems have been implemented on Quadro FX 3800 GPU which is one of the recent graphical cards of NVIDIA. From the results, applications on GPU provided gain in terms of time as compared to the applications implemented on traditional Central Processing Unit (CPU).