Moth Flame Optimization Research Articles

Moth–Flame-Optimization-Based Parameter Estimation for FCS-MPC-Controlled Grid-Connected Converter With LCL Filter

The ability to model a system with high accuracy plays an important role in finite-control-set model-predictive-control (FCS-MPC)-controlled LCL-interfaced grid-connected converters (LCL-GCCs). However, the effect of aging, unmeasured noise, and temperature change on LCL-GCCs may result in parameter perturbations between the prediction model and the actual system. A model mismatch may occur, which may lead to violations of constraints, worsen the power quality of the grid current, and even threaten the system stability. This article presents a novel nature-inspired optimization paradigm named moth–flame-optimization (MFO), which applies the spiral logarithmic function to simulate the flight of a moth approaching a flame. The method is designed to efficiently identify and update the model parameters, and the fitness function for the state variables is designed and solved iteratively to minimize mismatches with the model. The advantages of the proposed method are its fast convergence and ability to determine parameters with high accuracy. These advantages effectively prevent the algorithm from converging to local optima. To achieve the harmonic rejection capability, a sliding discrete Fourier transform (SDFT) algorithm is also proposed to predict the harmonic at each sampling interval; thus, the harmonics are considered in the cost function. Experimental comparisons under different scenarios validate the effectiveness of the proposed SDFT-based MFO–MPC method.

Güve-Alev Optimizasyon Algoritması Kullanarak Pleurotus cornucopiae var. citrinopileatus Mantarı Ekstraksiyon Koşullarının Optimizasyonu

Bu çalışmanın amacı, Pleurotus cornucopiae var. citrinopileatus mantarı ekstraksiyon koşullarının yapay zekâ metotlarıyla optimize edilmesidir. Bu amaç doğrultusunda %0, 30, 60, 90 etanol oranı kullanılarak, 1, 2 ve 4 mg/mL ekstrakt konsantrasyonunda elde edilen ekstraktların, 1,2, 3, 4,2 ve 6 pH koşullarındaki antioksidan aktiviteleri mevcut bir deneysel çalışmadan elde edilmiştir. Ekstraksiyon koşullarının modellenmesi Yapay Sinir Ağları (YSA) ile yapılmış ve Güve-Alev Optimizasyon (GAO) algoritması kullanılarak optimize edilmiştir. En iyi tahmin modelini elde etmek için farklı gizli nöron sayıları denenmiş ve en uygun gizli nöron sayısı 5 olarak bulunmuştur. Elde edilen bu modelin hata karelerinin ortalaması ve ortalama mutlak yüzde hatası tüm veri seti için sırasıyla 1,79 ve %3,24 olarak bulunmuştur. Optimizasyon süreci sonrasında maksimum antioksidan aktivite %56,76 olarak bulunmuştur ve bu sonucu elde etmek için optimum ekstraksiyon parametreleri %66,34 etanol oranı, 4 mg/mL ekstrakt konsantrasyonu ve 2,36 pH olarak belirlenmiştir. Bu çalışma, YSA ve GAO algoritmasının birlikte kullanılması ile ekstraksiyon koşullarının optimizasyonunda zaman, emek ve maliyetverimliliği sağlandığını ortaya koymuştur.

A composite framework coupling FCRM, LSSVM and improved hybrid IHHOMFO optimization for Takagi–Sugeno fuzzy model identification

This paper proposes a novel Takagi–Sugeno fuzzy model identification method by combining fuzzy c-regression model clustering (FCRM), least squares support vector machine (LSSVM) and intelligent optimization algorithm. Firstly, in order to improve the performance of FCRM for the complex nonlinear dataset, in this paper the method of FCRM based on LSSVM (FCRM-LSSVM) is proposed to discover the data structure and obtain the antecedent parameters. And then, a newly developed intelligent optimization algorithm by hybridizing Harris hawks optimization and moth-flame optimization algorithm (IHHOMFO) is proposed to further optimize the antecedent membership function parameters obtained by the FCRM-LSSVM. Finally, the proposed novel T-S fuzzy model identification combines FCRM, LSSVM and IHHOMFO for solving actual model identification problems. Experiments on five different datasets demonstrate that the proposed method is more efficient than conventional methods, such as T-S model identification based on fuzzy c-means (FCM), FCRM and FCRM-LSSVM, in standard measurement indexes. This study thus demonstrates that the proposed method is a credible and competitive fuzzy model identification method. The novel method contributes not only to the theoretical aspects of fuzzy model, but is also widely applicable in data mining, image recognition and prediction problems.

An effective weather forecasting method using a deep long–short-term memory network based on time-series data with sparse fuzzy c-means clustering

Weather forecasting is the scientific procedure of determining the state of the atmosphere considering both time frames and locations. This article devises a novel magnetic feedback artificial tree algorithm-based deep long–short-term memory (MFATA-based deep LSTM) classifier with time-series data. MFATA is the combination of the magnetic optimization algorithm MOA with the feedback artificial tree FAT algorithm for weather forecasting. Here, the feature selection is processed using a Moth Flame Optimization based Bat (MFO-Bat). Then, based on the clustered result, the forecasting process is accomplished using a deep LSTM classifier. Finally, the Taylor series model is used to generate the final forecast result. The proposed method achieved mean square error, root mean square error, mean absolute scaled error and symmetric mean absolute percentage error values of 4.12, 2.03, 0.602 and 56.376, respectively. The approach developed in this study has the potential to be used as an efficient and reliable weather forecasting method.

COOT OPTIMIZATION ALGORITHM FOR PARAMETER ESTIMATION OF PHOTOVOLTAIC MODEL

Because of the technical and environmental advantages of many solar energy sources, their use has recently been rapidly rising. The extraction of the unknown parameters in photovoltaic models is one of the key challenges in the modeling and simulation of solar energy sources. To satisfy the behavior of the solar photovoltaic (SPV) cells, the Single-Diode Model (SDM) is recommended as a more dependable modeling method. In this study, we applied the recently introduced meta-heuristic optimization method that inspires the behavior of the swarm of birds called Coot. This Coot Algorithm is used to estimate the unknown parameters of an SPV cell/module at 33 ºC. Simulation results of this study were compared with other nine different previous Optimization Algorithms, which are Moth Flame Optimization (MFO), Dragonfly Algorithm (DA), Whale Optimization Algorithm (WOA), Grey Wolf Optimization (GWO), Ant Lion Optimization (ALO), Harris Hawk Optimization (HHO), Hybrid of Particle Swarm Optimization and Grey Wolf Optimization (PSOGWO), Marine Predator Algorithm (MPA), and African Vultures Optimization Algorithm (AVOA). The obtained results of this comparison showed that the Coot algorithm outperformed the previous algorithms in terms of the root mean square error (RMSE) and the degree of convergence between the power versus voltage curve and the current versus voltage curve compared with the measured data. Moreover, the results confirm that the Coot optimization algorithm is favorable in reducing time and improving accuracy.

Human Gait Analysis: A Sequential Framework of Lightweight Deep Learning and Improved Moth-Flame Optimization Algorithm.

Human gait recognition has emerged as a branch of biometric identification in the last decade, focusing on individuals based on several characteristics such as movement, time, and clothing. It is also great for video surveillance applications. The main issue with these techniques is the loss of accuracy and time caused by traditional feature extraction and classification. With advances in deep learning for a variety of applications, particularly video surveillance and biometrics, we proposed a lightweight deep learning method for human gait recognition in this work. The proposed method includes sequential steps–pretrained deep models selection of features classification. Two lightweight pretrained models are initially considered and fine-tuned in terms of additional layers and freezing some middle layers. Following that, models were trained using deep transfer learning, and features were engineered on fully connected and average pooling layers. The fusion is performed using discriminant correlation analysis, which is then optimized using an improved moth-flame optimization algorithm. For final classification, the final optimum features are classified using an extreme learning machine (ELM). The experiments were carried out on two publicly available datasets, CASIA B and TUM GAID, and yielded an average accuracy of 91.20 and 98.60%, respectively. When compared to recent state-of-the-art techniques, the proposed method is found to be more accurate.

A hybrid particle swarm optimization with multi-objective clustering for dermatologic diseases diagnosis

Abstract Effective and personalized treatment relies heavily on skin disease categorization. In the stratification of skin disorders, it is crucial to identify the subtypes of illnesses to provide an efficient therapy. To attain this aim, researchers have focused their attention on cluster algorithms for the stratification of skin disorders in recent decades. But, cluster algorithms have real-world drawbacks, including experimental noises, a large number of dimensions, and a poor ability to comprehend. Cluster algorithms, in particular, determine the quality of clusters using a single internal evaluation operation in the majority of cases. A single internal assessment procedure is difficult to design and robust for all datasets, which is a problem. The multi-objective particle swarm obtained high sensitivity in the existing work, but it is not able to anticipate all kinds of classes. An optimized cluster distance parameter for K-means clustering is determined using a hybrid particle swarm and moth flame optimization. Multi-objective is guided by two cluster value indices, including the K-means clustering misclassification rate and neural network classification rate. Hybrid PSO will solve the multi-objective problem to identify the optimal cluster for clustering. On the dermatological dataset from the UCI repository, MATLAB R2020a will be used to evaluate the proposed method. This will be followed by an evaluation of the proposed method’s performance using the cluster evaluation indices.

Moth-Flame Optimization Algorithm for Efficient Cluster Head Selection in Wireless Sensor Networks

Network lifetime and energy consumption are the important requirement of wireless sensor networks. The sensor network is mainly used for the military and civil applications, habitat monitoring. These tasks consume more energy for the data processing and directly affect the network lifetime. Clustering methodology provides a better solution for prolonging the network lifetime and reducing the energy consumption. In this paper, moth flame optimization algorithm is proposed in LEACH-C algorithm for identifying the suitable cluster head in wireless sensor networks. The proposed methodology uses the navigation method of moths for balancing the exploration and exploitation phases in the optimization process. The residual energy of the node and distance between the cluster head and sensor node are utilized to calculate the fitness function. The proposed methodology is evaluated with the help of performance metrics of network lifetime, energy consumption and number of alive nodes. The proposed methodology prolongs the network lifetime and reduces the energy consumption.

Power System Stability Enhancement Using a Novel Hybrid Algorithm Based on the Water Cycle Moth-Flame Optimization

Poor control of the power grid can lead to a total system collapse, causing significant economic losses and possible damage to security and social peace. Therefore, improving power system stability, particularly transient stability, has become one of the major research topics. This paper proposes a developed modeling approach that provides the optimal stabilizer parameters of the control devices, aiming at improving the electrical network stability by minimizing the angular speed deviation in the presence of a severe disturbance event using a novel hybrid algorithm called Water Cycle-Moth Flame Optimization (WCMFO). The main advantages of the proposed method are the speed of response and its efficient exploration and exploitation ability to attain the best solution quality. This is achieved by imposing a thermodynamic incident (an abrupt change in mechanical torque) on the well-known test model (SMIB), Single Machine Infinite Bus. To test the effectiveness of the proposed method, Power System Stabilizer (PSS), Proportional-Integral-Derivative (PID-based PSS), and Fractional Order-PID (FOPID-based PSS) are implemented to control and ensure the system’s ability to return to a stable state in the presence of this fault. The achieved experimental outcomes have proven the superiority, and efficiency of the developed approach (WCMFO) in terms of damping the oscillations and reducing the overshot, with an improvement of 44% over the Water Cycle Algorithm (WCA), Moth-Flame Optimization (MFO), and Artificial Ecosystem Optimization (AEO). It is envisaged that the proposed method could be very useful in the design of a practical high-performance power system stabilizer.

Structural optimization of a rotary joint by hybrid method of FEM, neural-fuzzy and water cycle–moth flame algorithm for robotics and automation manufacturing

Rotary joint is used in robotic arm for mobility aids and rehabilitation device. The rotary joint often requires a compactness, a lightness, and a large load capacity in robotics as well as automation manufacturing. However, the experience-based design methods take a lot of time, finances, and human resources to achieve the mentioned multiple functions. To overcome the above difficulties, the article proposes a new design technique to solve the structural optimization for the rotary joint. The proposed optimization technique is formed by topology method, analysis of variance, finite element method, adaptive neuro-fuzzy inference system model, and water cycle moth-flame optimization algorithm. A new rotary joint is designed via the topology optimization. The adaptive neuro-fuzzy inference system is optimized by Taguchi technique to enhance the modeling accuracy. The geometry of the joint is optimized by the water cycle moth-flame optimization algorithm. The results found that the rotary joint can stand a torque of 357.46 N.mm with the equivalent stress up to 489.98 MPa. The difference between the optimal prediction results and simulations are 0.27% and 0.58% for the moment reaction and the equivalent stress, respectively. The small error proves the developed hybrid method has a high reliability.

Optimally filtering and matching processing for regional upstrokes to improve ultrasound transit time-based local PWV estimation

Background and objectivePulse wave velocity (PWV) is an important index for quantifying the elasticity of artery. Local PWV estimates based on ultrasonic transit time (TT) methods, however, are affected by the reflected waves and ultrasonic noise, biasing the spatiotemporal propagation of the time fiduciary point (TFP) positioning in the distension waveforms. In this study, an optimally filtering and matching processing for regional upstrokes is proposed to improve the ultrasound TT-based local PWV estimation. Method(i) Smooth the pulse waves (PWs) using the Savitzky–Golay filter with one set of randomly combined parameters. (ii) An arbitrary region at the first beam upstroke of the smoothed PWs is selected as the curve template, and then matched with the upstrokes of other PWs by calculating the sum of square differences (SSD) between the template and matching regions to find its similar regions. (iii) Update the filter parameters and the template using the moth-flame optimization (MFO) feedback for computing the new SSD value. When the new SSD value is smaller than the historical one, the later will be replaced. (iv) Repeat the above steps until the MFO algorithm converges to the minimum SSD value. (v) Output the optimal filter parameters and the locations of regional curves corresponding to the minimum SSD value. Then the time delay of the PWs propagation can be detected by using the starting points of the regional curves as the TFPs. ResultsWe conducted performance comparison with the advanced TT method through both simulation and clinical experiments. The results demonstrate that the proposed work observes considerable reductions on both the normalized root mean square error ± the standard deviation (from 6.73 ± 2.27% to 1.57 ± 0.72%) and the coefficient of variation (from 13.39% to 8.87%). ConclusionsThe results of this study support that the proposed method may facilitate the early diagnosis and prevention of local arterial stiffness .

A Hybrid Moth Flame Optimization Algorithm for Global Optimization

A Hybrid Moth Flame Optimization Algorithm for Global Optimization

Fuzzy Combination of Moth-Flame Optimization and Lightning Search Algorithm with Fuzzy Dynamic Parameter Adjustment

In general, this paper is focused on creating a fuzzy combination of two optimization algorithms. In this case, the algorithms work with populations and allow us to migrate between them every certain number of iterations. On the other hand, fuzzy logic is responsible for the dynamic adjustment of parameters within each of the algorithms since the variables are different in each algorithm. In previous works, a combination between genetic algorithm and particle swarm optimization was developed, which motivated us to create this combination expecting to obtain better results when compared to the previous works. The moth-flame optimization and lightning search algorithm were combined to obtain a powerful hybrid metaheuristic combining the advantages of both individual algorithms.

Enhancement of available transfer capability using TCSC with hybridized model: Combining lion and moth flame algorithms

AbstractThe practical computations of enhancing available transfer capability (ATC) are evolving in the recent times. Most of the presently available techniques for enhancing ATC are being implemented; however, in many cases, they do not consider the impact of communications taking place in between the “power transfers, loop flows, non‐linearities, operating policies, and most importantly voltage collapse blackouts,” respectively. Thus, the current research work aims to introduce a new hybrid method to solve the chaos in ATC in power system. The thyristor‐controlled series compensation (TCSC) that belongs to series flexible alternating current transmission system device is utilized for enhancing ATC. The introduced algorithm is termed as Lion Updated Moth Flame Optimization (LU‐MFO) to select the corresponding line for TCSC device to be connected.

A Novel Metaheuristic Optimization for Throughput Maximization in Energy Harvesting Cognitive Radio Network

In this article, a novel technique is proposed, namely rank-based multi-objective antlion optimization (RMOALO), and applied to optimize the performance of the energy harvesting cognitive radio network (EHCRN). The original selection method in multi-objective antlion optimizer (MOALO) is suitably changed to improve the algorithm, thus reaching the optimal solution for the problem. The proposed technique shows considerable performance improvement over the method used in the multi-objective antlion optimizer (MOALO). The performance of the proposed RMOALO is demonstrated on five benchmark mathematical functions and compared to multi-objective particle swarm optimization (MOPSO), multi-objective moth flame optimization (MOMFO), MOALO-Tournament, and MOALO-Roulette. The simulation results show an improved convergence of RMOALO and find the optimal solution to the throughput maximization problem. We show that RMOALO provides 16.33 % improved average throughput with the optimal value of sensing duration for the varying amount of harvested energy compared to MOPSO, MOMFO, MOALO-Roulette, and MOALO-Tournament.

Statistical analysis based reactive power optimization using improved differential evolutionary algorithm

AbstractThis study presents a novel improved differential evolutionary (IDE) algorithm for optimizing reactive power management (RPM) problems. The effectiveness of IDE algorithm is tested on different unimodal and multimodal benchmark functions. The objective function of the RPM is considered as the minimization of active power losses. Initially, the power flow analysis approach is employed to detect the optimal position of flexible AC transmission system (FACTS) devices. The proposed method is used to determine the optimal value of control variables such as generator's reactive power generation, transformer tap settings, and reactive power sources. Furthermore, the efficacy of the IDE approach is compared with other promising optimization methods such as variants of differential evolution algorithm, moth flame optimization (MFO), brainstorm‐based optimization algorithm (BSOA), and particle swarm optimization (PSO) on various IEEE standard test bus (i.e., IEEE‐30, ‐57, ‐118, and ‐300) systems with active and reactive loading incorporating FACTS devices. A Static VAR compensator (SVC) for shunt compensation and a thyristor‐controlled series compensator (TCSC) for series compensation were used as FACTS devices. The proposed IDE method significantly reduces the active power loss, that is, 55.65% in IEEE 30, 39.68% in IEEE 57, 16.32% in IEEE 118, and 8.56% in IEEE 300 bus system at nominal loading. Finally, the statistical analysis such as Wilcoxon signed‐rank test (WSRT) and ANOVA test were thoroughly analysed to demonstrate the firmness and accuracy of the proposed technique.

Enhanced convolutional neural network based android software maintainability prediction

Advancement in mobile technology, necessitates quality in development of android applications. To improve the quality of android application, evaluation of its maintenance has to be started from the initial stage of development. There are several existing models involved in android application maintenance evaluation, but most of them suffers from the class imbalance problem and its performance depends on the size of the dataset. This paper focuses on overcoming the class imbalance while using convolutional neural network for prediction the android application maintainability. In this work both android metrics and object-oriented metrics are used for evaluating the android application maintainability. The standard convolutional neural network is enhanced by pretraining it using evolutionary algorithm known as moth flame optimization (MFO). The MFO involves in optimizing the learning parameters of convolutional layer and after the training process is completed, with the acquired knowledge it handles the small size dataset very effectively during the testing phase. Thus, the simulation results of maintainability prediction in android application development using proposed enhanced CNN achieves better result while comparing with other standard classification models.

Feature selection using improved multiobjective and opposition-based competitive binary gray wolf optimizer for facial expression recognition

Facial expression recognition (FER) in computer vision is a very daunting computational task because of high-intra class variations. Researchers have developed methods for extracting features from images that apply conventional and deep learning approaches. When conventional approaches are used in FER system, the size of extracted features is very large, which may adversely affect the performance of the classifier. Therefore, in the process of FER, feature selection is an essential phase. We propose an improvement on competitive binary gray wolf optimizer in discrete search space named as Improved MOCBGWO, and it is utilized to perform feature selection within wrapper-based setup. Next, we applied the SVM and K nearest neighbors classifiers to selected features for investigating the performance of the proposed system through two publicly available standard datasets: CK+ and JAFFE. We compared the performance of the proposed improvement with binary gray wolf optimizer, binary moth flame optimizer, binary particle swarm optimizer, and competitive binary GWO for evaluating its efficacy. The experimental results reveal that our proposed improvement boosts the recognition accuracy along with reduction in the size of feature vector in a superior way as compared to other methods.

An improved deep convolutional neural network architecture for chromosome abnormality detection using hybrid optimization model.

Chromosomes are thread-like structures located in the cell nucleus that contains the human body blueprint. Chromosome analysis is also known as karyotyping is the test taken to detect the abnormalities identified in the human chromosome. The two types of widely known chromosome abnormalities are structural and numerical abnormalities. Manual karyotyping is complex, time-consuming, and error-prone. To overcome these complexities, automated chromosome karyotype architecture is proposed using the deep convolutional neural network (DCNN) architecture. Training the DCNN architecture from scratch needs a huge dataset and to overcome this problem a generative adversarial networks is used to create adversarial samples that resemble the images in the actual dataset. The time-consuming hyperparameter tuning in the DCNN architecture is overcome using the hybrid moth-flame optimization integrated with the hill-climbing strategy (HMFOHC). The HMFOHC algorithm is mainly utilized in this article to minimize the huge number of parameters associated with the DCNN architecture. The efficiency of the proposed methodology is evaluated using two datasets namely the BioImLab chromosome dataset and hospital dataset. The proposed HMFOHC optimized DCNN architecture is mainly utilized for multiclass classification where it differentiates five numerical chromosome abnormalities, namely Trisomy 13, Trisomy 18, Trisomy 21, Trisomy XXY syndrome, and Monosomy X. The proposed model offers an accuracy, F1-score, and kappa coefficient value of 98.65%, 98.86%, and 0.9894, respectively. The results obtained show that the proposed model achieves higher classification accuracy when compared with the different state-of-art techniques such as deep learning, random forest, and CNN. The inference time of the proposed methodology is 12.5s which is relatively lower than the state-of-art techniques. The proposed approach can help cytogenetics forensic experts make better decisions and save time by automating manual karyotyping. RESEARCH HIGHLIGHTS: Manual karyotyping is complex, time-consuming, and error-prone. To overcome these complexities, automated chromosome karyotype architecture is proposed using the DCNN architecture The proposed method is mainly applied for multiclass classification where the different types of numerical abnormalities are addressed such as Trisomy 13, Trisomy 18, Trisomy 21, Trisomy XXY syndrome, and Monosomy X.

Optimal placement and sizing of FACTS devices for optimal power flow using metaheuristic optimizers

This paper proposes the implementation of various metaheuristic algorithms in solving the optimal power flow (OPF) with the presence of Flexible AC Transmission System (FACTS) devices in the power system. OPF is one of the well-known problems in power system operations and with the inclusion of the FACTS devices allocation problems into OPF will make the solution more complex. Thus, seven metaheuristic algorithms: Barnacles Mating Optimizer (BMO), Marine Predators Algorithm (MPA), Moth–Flame Optimization (MFO), Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), Teaching–Learning-Based Optimization (TLBO) and Heap-Based Optimizer (HBO) are used to solve two objective functions: power loss and cost minimizations. These algorithms are selected from the different metaheuristics classification groups, where the implementation of these algorithms into the said problems will be tested on the modified IEEE 14-bus system. From the simulation results, it is suggested that TLBO and HBO perform better compared to the rest of algorithms.