In recent years, the increasing energy demand and the depletion of fossil fuels have driven researchers to focus on renewable energy sources. In this context, the efficient control of DC-DC power converters connected to photovoltaic (PV) panels—commonly used for solar energy generation—has become increasingly important. This study employs the recently developed Artificial Hummingbird Algorithm (AHA) and the Cheetah Optimization Algorithm (CO) to optimally control a Buck-Boost converter coupled with a PV panel. Both AHA and COA are applied to enhance control performance based on the Integral of Time-Weighted Squared Error (ITSE) criterion by tracking the maximum power point (MPPT) of the PV panel under varying temperature and irradiance conditions. The algorithm optimizes the parameters of the Proportional–Integral (PI) controller used in the converter, thereby improving the system’s dynamic response. The findings demonstrate that the proposed approach delivers faster, more stable, and more accurate performance.

The Artificial Hummingbird Algorithm (AHA), a meta-heuristic algorithm that mimics hummingbird feeding behaviours and was inspired by nature, was published in 2021 by Liying Wang. This approach uses axial, diagonal, and omnidirectional flight capabilities to carry out migration and foraging processes in a directed manner. The AHA was used in this study to analysed the direct current (DC) motor speed control problem based on proportional-integral-derivative (PID) controllers. The integral of the time-weighted absolute error (ITAE) was employed as an error-based objective function for parameter optimization once the ideal PID parameters (kp, ki, and kd) were identified in the controller design. The AHA was contrasted with other algorithms from the literature at various DC motor operating points in order to increase diversity. The results showed that the AHA that was suggested performed successfully and effectively for the DC motor speed control problem.

Elektromanyetik uyumluluk (EMC), modern elektronik sistemlerin kesintisiz ve güvenilir bir şekilde çalışabilmesi için hayati bir gerekliliktir. EMC, elektronik cihazların hem kendi içlerinde hem de çevredeki diğer cihazlarla uyumlu çalışmasını sağlayarak, elektromanyetik girişimlerin (EMI) oluşturduğu olumsuz etkileri en aza indirir. Günümüzde elektronik cihazlar, çeşitli frekanslarda ve yoğun elektromanyetik gürültü ortamlarında çalışmak zorunda kalmaktadır. Bu durum, cihazların performansını, güvenilirliğini ve uzun vadeli işlevselliğini doğrudan etkileyebilir. Bu çalışmada, LT3845 buck regülatörü kullanılan bir elektronik güç dağıtım kartı için MIL-STD-461G CE102 standardına uygun bir EMI filtresinin tasarım ve optimizasyon süreci ayrıntılı olarak ele alınmıştır. Tasarım sırasında, devre bileşenleri dikkatlice seçilerek performans etkinliği sağlanmıştır. Laboratuvar ortamında gerçekleştirilen testler, tasarlanan EMI filtresinin elektromanyetik gürültüyü başarıyla bastırdığını ve CE102 test sonuçlarının sınırlar dahilinde olduğunu doğrulamıştır. Bu çalışma, güç elektroniği sistemlerinde EMC uyumluluğunu artırmaya yönelik önemli bir adım atmakta ve EMI filtre tasarımına yenilikçi bir yaklaşım sunmaktadır. Ayrıca, tasarım süreci, gelecekte benzer sistemlerin geliştirilmesinde yol gösterici bir kaynak teşkil etmektedir.

Chaotic systems, despite their deterministic structure, are structures that are highly sensitive to initial conditions and therefore exhibit long-term unpredictable dynamics. Because of these properties, chaotic systems are widely used in various engineering and scientific fields such as cryptography, radar technologies, signal processing, biomedical modelling and random number generation. In this study, the Sprott 94 F chaotic system model is investigated in detail in both numerical analyses and analog environments. The time series and phase portraits of the system are analysed through numerical simulations performed in MATLAB, and to better understand its dynamic structure, the system's chaotic behaviour is verified by calculating bifurcation diagrams and Lyapunov exponents spectrums. On the analog side, the realizability of the model is first evaluated on an analog circuit designed using op-amp components. Subsequently, an alternative circuit design is implemented using Second Generation Current Conveyor (CCII) structures, which offer the advantages of higher frequency performance and wide bandwidth, and the chaotic structure of the system is also investigated on these structures. Numerical analyses and analog results are evaluated comparatively, the chaotic behaviours observed in both analog approaches were consistent with numerical simulations.

Metaheuristic techniques are capable of representing optimization frames with their specific theories as well as objective functions owing to their being adjustable and effective in various applications. Through the optimization of deep learning models, metaheuristic algorithms inspired by nature, imitating the behavior of living and non-living beings, have been used for about four decades to solve challenging, complex, and chaotic problems. These algorithms can be categorized as evolution-based, swarm-based, nature-based, human-based, hybrid, or chaos-based. Chaos theory, as a useful approach to understanding neural network optimization, has the basic idea of viewing the neural network optimization as a dynamical system in which the equation schemes are utilized from the space pertaining to learnable parameters, namely optimization trajectory, to itself, which enables the description of the evolution of the system by understanding the training behavior, which is to say the number of iterations over time. The examination of the recent studies reveals the importance of chaos theory, which is sensitive to initial conditions with randomness and dynamical properties that are principally emerging on the complex multimodal landscape. Chaotic optimization, in this regard, accelerates the speed of the algorithm while also enhancing the variety of movement patterns. The significance of hybrid algorithms developed through their applications in different domains concerning real-world phenomena and well-known benchmark problems in the literature is also evident. Metaheuristic optimization algorithms have also been applied to deep learning or deep neural networks (DNNs), a branch of machine learning. In this respect, the basic features of deep learning and DNNs and the extensive use of metaheuristic algorithms are overviewed and explained. Accordingly, the current review aims at providing new insights into the studies that deal with metaheuristic algorithms, hybrid-based metaheuristics, chaos-based metaheuristics as well as deep learning besides presenting recent information on the development of the essence of this branch of science with emerging opportunities, applicability-based optimization aspects and generation of well-informed decisions.

The objective in optimal control problems is to determine the control rule to be applied according to the objective function determined for a given system. Theoretically, different solution methods have been developed starting from calculus of variation such as Pontriagin, Hamilton, or Riccati. In this study, apart from analytical methods, it is proposed to apply algorithms inspired by nature to the same problem. Among these algorithms, genetic algorithm, firefly algorithm, Harris Hawk's optimization algorithm, and differential evolution optimization algorithm have been applied to given optimal control problems and their successes were compared in terms of statistical analysis such as minimum, maximum, average, Wilcoxon, and Friedman analysis. The originality of this study is to control the system with discrete control rule by partitioning the control signal, to be applied to the system which is wanted to be optimally controlled. This will allow the control of different techniques, such as MPC or NMPC, which will contribute to the determination of the global optimum control rule, especially in the solution of nonlinear systems. In addition, three different applications have been performed to demonstrate. As a result of these experiments, it has been shown that these algorithms can be applied successfully to such problems.

Machine learning methods can generally be categorized as supervised, unsupervised and reinforcement learning. One of these methods, Q learning algorithm in reinforcement learning, is an algorithm that can interact with the environment and learn from the environment and produce actions accordingly. In this study, eight different on-line methods have been proposed to determine online the value of the learning parameter in the Q learning algorithm depending on different situations. In order to test the performance of the proposed methods, these algorithms are applied to Frozen Lake and Car Pole systems and the results are compared graphically and statistically. When the obtained results are examined, Method 1 has produced better performance for Frozen Lake, which is a discrete system, while Method 7 has produced better results for the Cart Pole System, which is a continuous system.

In this study, a controller design was carried out for the heat exchanger, which is widely used in the industry. Firstly, Zeigler Nichols step, Zeigler Nichols frequency, AMIGO step and AMIGO frequency methods were used for the PID controller in the control of this system. Then, using the mathematical model of the heat exchanger system, 2%, 5% and 10% overshoot constraints were added to the ISE performance criteria, and controller designs were realized with genetic algorithm. In addition, two different topologies were used for the fuzzy PID controller in the controller design. The results obtained were examined and it was seen that the design realized with fuzzy logic for this study could be improved more. However, topologies designed with fuzzy logic have obtained better results than classical PID controllers and the classical PID designed study in the literature.

Fotovoltaik modül modellerinin parametre doğru tahmini sistemlerin verimliliği üzerinde önemli bir etkisi bulunmaktadır. Fotovoltaik sistemlerde en iyi performansı elde etmek amacıyla parametrelerini tahmin etmede algoritmaların etkinliği kullanılmaktadır. Bu sebepten dolayı bu çalışmada fotovoltaik modül modelinin parametrelerini çıkarmada kaos teorisinin rassallığı ve Balina optimizasyon algoritmasının etkililiği birleştirilerek Henon kaotik tabanlı Balina optimizasyon algoritmaları (HBOA) önerilmiştir. Ayrıca önerilen dört farklı Kaotik Henon tabanlı Balina optimizasyon algoritması, mevcut balina optimizasyon algoritmasına kıyasla doğruluğu ve güvenilirliği arttırdığı görülmüştür. Algoritmaların istatistiksel değerleri göz önünde bulundurularak performansları değerlendirilmiştir. Ayrıca algoritmalardan elde edilen karşılaştırma sonuçlarının güvenirliklerini test etmek amacıyla Wilcoxon ve Friedman testleri kullanılmıştır. Sonuç olarak deneysel sonuçlara göre önerilen algoritmaların literatürdeki algoritmalara göre daha iyi performans gösterdiği belirlenmiştir.

Bu makalede otomatik gerilim regülatör sistemin oransal integral türev denetleyici optimal parametre değerlerini ayarlamak amacıyla yeni bir algoritma olan deniz yırtıcıları algoritması önerilmiştir. Önerilen algoritma ile terminal geriliminin maksimum yüzde aşımı, yerleşme süresi, yükselme süresi ve kararlı durum hatasını en aza indirmek ve optimal oransal integral türev denetleyicisi ile otomatik gerilim regülatör sisteminin geçici durum yanıtının iyileştirilmesi amaçlanmıştır. Denetleyici parametrelerini ayarlamak için karesel hatanın integrali, ağırlıklı karesel hatanın integrali, zaman’ın karesel integrali ve Zwe-Lee Gaing amaç fonksiyonları kullanılmıştır. Deniz yırtıcıları algoritma tabanlı oransal-integral-türev denetleyicinin performansı, literatürde önerilen çeşitli amaç fonksiyonları kullanılarak gerçekleştirilen farklı meta-sezgisel algoritmalar tarafından uyarlanmış oransal integral türev denetleyicileri ile karşılaştırmalı analizler yapılmıştır. Bu analizler geçici tepki analizi, kök konum analizi ve sağlamlık gibi analiz yöntemleri ile gerçekleştirilmiştir. Simülasyon sonuçları, deniz yırtıcıları algoritmasıyla ayarlanan oransal integral türev kontrollü otomatik gerilim regülatör sisteminin yerleşme süresi, tepe aşımı ve kararlılık açısından daha iyi performans gösterdiğini kanıtlamıştır.

In this study, the emerging, novel marine predators algorithm is proposed to adjust the proportional-integral-derivative controller of the automatic voltage regulator system. With the proposed algorithm, this study aimed to minimize the maximum percent excess of the terminal voltage, settling time, rise time, and steady-state error and improve the transient response of the automatic voltage regulator system with an optimal proportional-integral-derivative controller. The integral of squared error, integral of weighted squared error, squared integral of time, and Zwe-Lee Gaing objective functions were used to set the controller parameters. The performance of the proportional-integral-derivative controller based on the marine predators algorithm was compared with those of the proportional-integral-derivative controllers adapted by different metaheuristic algorithms using various objective functions suggested in the literature. These analyses were conducted using analysis methods such as transient response, root locus, and robustness. The simulation results show better performance in terms of the settling time, over-peak, and stability of the proportional-integral-derivative-controlled automatic voltage regulator system tuned with the marine predators algorithm.

Parameter estimation of model of Photovoltaic model has substantial influence on systems performance. Effectiveness of algorithms has been used to estimate parameters to obtain the best performance of Photovoltaic systems. Therefore, in this study, to acquire parameters of photovoltaic systems, Chaotic Henon based Whale optimization algorithm (HWOA) has been proposed such that randomness of Henon map and whale optimization algorithms is combined and hybridized. Furthermore, the proposed four different Chaotic Henon-based Whale optimization algorithms have been shown to increase accuracy and reliability compared to the current whale optimization algorithm. Performances of algorithms have been evaluated by considering statistical values. In addition, Wilcoxon and Friedman tests have been used to test the reliability of the comparison results obtained from the algorithms.Consequently, it has been determined that experimental results of proposed algorithms have better performance than the algorithms in literature.

Optimization of parameters in solar cell modeling allows monitoring the status of the model under different operating conditions of the system and finding possible errors. In order to accurately predict optimal parameters in single and dual diode solar cell models, meta-heuristic algorithms such as Particle Swarm Optimization (PSO), Firefly Algorithm (FA), Cuckoo Search (CS) and Flower Pollination (FPA) were used. In addition, IAE and RMSE objective functions were used to minimize the error between the experimental diode parameter values calculated by these algorithms. In order to evaluate the accuracy and performance of these algorithms, Genetic algorithm (GA), Simulated Annealing (SA), Harmony Search (HS) and Pattern Search (PS) in the literature were compared numerically and graphically with meta-heuristic algorithms. Comparative results showed that FPA had superior performance in terms of accuracy and reliability compared to other methods in the problem of estimating the parameters of solar cells. Consequently, it was determined that solar cell models were improved by using parameters optimized by meta-heuristic algorithms.

Bu çalışmada, 5-fazlı, 10/8 kutup konfigürasyonlu, segmantal rotorlu olarak tasarlanmış ve literatüre girmiş olan yeni bir model anahtarlamalı relüktans motor (SARM)' nin yapısal özelliklerinin bir incelemesi sunulmuştur. SARM’ ın klasik yapıda bir anahtarlamalı relüktans motorla (ARM) farklılıkları açıklanmıştır. Beş fazlı SARM’ ın durum denklemleri temel elektrik motorları modeli kullanılarak farklı bir rotor yapısına sahip SARM ait faz akımları, manyetik akı değişimleri ve faz durumları, görünür endüktansın profilinin hesaplanmasıyla elde edilmiştir. Çalışmanın devamında SARM’ dan elde edilen durum denklemleri kullanılarak dinamik simülasyon sonuçları geliştirilmiştir. Bilgisayar ortamında ilgili yazılım dili ile geliştirilen algoritmada çalıştırılan kod parçaları, SARM’ ın 0°’ den 90°’ ye kadar 1°’lik açı ile döndürülerek ideal akım kaynakları ile uygulanan akımın fonksiyonunun değişimi görülmüştür. SARM’ ın her dönüş açısında bitişik olan iki fazı ortak endüktans oluşturacak şekilde enerjilendirilmiştir. Gerçekleştirilen analizlerde elde edilen akımın değişimleri her bir faz için faz akımlarının simülasyon sonucu değişimleri görselleştirilerek açıklanmıştır.

Güneş pili modellenmesinde parametrelerin optimizasyonu sistemin farklı çalışma koşullarında durumunu izlemek ve modeldeki olası hataları bulmaya imkân sağlar. Güneş pillerinin tek ve çift diyot modellerindeki optimal parametrelerinin doğru ve verimli çıkarılması amacıyla parçacık sürü optimizasyon(PSO), ateş böceği (FA), guguk kuşu (CS) ve çiçek tozlaşma (FPA) meta-heuristik algoritmaları kullanılmıştır. Tekli ve çift diyot modellerinin hesaplanan ve deneysel veriler arasındaki hatayı minimize etmek amacıyla IAE ve RMSE amaç fonksiyonları kullanılmıştır. Geliştirilen algoritmaların performanslarını incelemek amacıyla literatürde bulunan diğer meta-heuristik algoritmalarla sayısal ve grafiksel olarak karşılaştırılmıştır. Karşılaştırmalı analiz verileri FPA’nın diğer yöntemlere göre yakınsama hızının daha hızlı, daha sağlam, verimli ve doğruluk açısından en iyi performansa sahip olduğu gösterilmiştir.

In this study, a memcapacitor-based chaotic oscillator and its engineering applications are discussed. Also nonlinear feedback control method is applied to drive the system to equilibrium and the modeling of the memcapacitor system with Artificial Neural Networks (ANN) as engineering applications. Some dynamical properties such as phase portraits, equilibrium points and bifurcation of the proposed system are investigated. A video of the chaotic memcapacitor circuit was created using phase portraits. The image processing technique was used to determine the object in the video. ANN is trained by both a backpropagation method and the Levenberg–Marquardt method. It is shown that the states of the chaotic memcapacitor oscillator system trained with ANN can be reconstructed and modeled in this way and the results are given.

In this study, the modification of the Deb feasibility method is considered to solve the constrained optimization problems. In the developed modified Deb feasibility constraint method, the third rule in its procedure was revised in order to increase the performance of the Deb feasibility constraint handling method. The innovation in the method is based on generating a new individual by using both possible solutions that violate the constraints in the method used for solving the problem. In detail, discussions were given about the application and usefulness of six constrained handling techniques. Furthermore, genetic algorithm, particle swarm optimization, Harris hawks optimization, whale optimization algorithm, grey wolf optimization and sine cosine algorithms were applied to both various benchmark functions and also different engineering application problems such as pressure vessel design, welded beam design, speed reducer design and active filter design. Overall the experimental results show that modified Deb feasibility constraint handling technique is more robust and efficient than Deb feasibility technique and most of the other constraint handling techniques.

Dorsal hand vein pattern is a physiological feature that can distinguish and define one person from another. Feature extraction from images is considered as the most important step in biometric systems. In this study, a fractal technique, which is both an advanced and a complex method, is proposed for feature extraction from the images of hand vessel pattern. In recent years, this approach has been widely used as an active research area in image processing. Therefore, fractal size based tissue analysis method, which is calculated by box counting method, which is a new technique in determining the tissue properties of the dorsal hand vein, has been applied. Experimental findings on the dorsal vein databases of Bosphorous and SUAS show that our proposed method yields promising and optimistic results compared to other known techniques.

Cell studies play an important role in the basis of studies on cancer diagnosis and treatment. Reliable viability assays on cancer cell studies are essential for the development of effective drugs. Lens-free digital in-line holographic microscopy has become a powerful tool in the characterization and viability analysis of microparticles such as cancer cells due to its advantages such as high efficiency, low cost, and flexibility to integrate with other components. This study is designed to perform viability tests using fractal dimensions of alive and dead cancer cells based on digital holographic microscopy and machine learning. In the in-line holography configuration, a microscopy assembly consisting of inexpensive components was built using an LED source, and the images were reconstructed using computational methods. The standard US Air Force Resolution Target was used to evaluate the capability of our imaging setup then holograms of stained cancer cells were recorded. To characterize individual cells, 19 different rotational invariant fractal dimension values were extracted from the images as features. An artificial neural network technique was employed for the classification of fractal features extracted from cells. The artificial neural network was compared with four other machine learning techniques through five different classification performance measures. The empirical results indicated that artificial neural networks performed better than compared classification techniques with accuracies of 99.65%. The method proposed in this paper provides a new method for the study of cell viability which has the advantages of high accuracy and potential for laboratory application.