Magnetic Optimization Algorithm Research Articles

COST 231-Hata Propagation Model Optimization in 1800 MHz Band Based on Magnetic Optimization Algorithm: Application to the City of Limbé

Network planning is essential for the construction and the development of wireless networks. The network planning cannot be possible without an appropriate propagation model which in fact is its foundation. Initially used mainly for mobile radio networks, the optimization of propagation model is becoming essential for efficient deployment of the network in different types of environment, namely rural, suburban and urban especially with the emergence of concepts such as digital terrestrial television, smart cities, Internet of Things (IoT) with wide deployment for different use cases such as smart grid, smart metering of electricity, gas and water. In this paper we use an optimization algorithm that is inspired by the principles of magnetic field theory namely Magnetic Optimization Algorithm (MOA) to tune COST231-Hata propagation model. The dataset used is the result of drive tests carry out on field in the town of Limbe in Cameroon. We take into account the standard K-factor model and then use the MOA algorithm in order to set up a propagation model adapted to the physical environment of a town. The town of Limbe is used as an implementation case, but the proposed method can be used everywhere. The calculation of the root mean square error (RMSE) between the real data from the radio measurements and the prediction data obtained after the implementation of MOA allows the validation of the results. A comparative study between the value of the RMSE obtained by the new model and those obtained by the optimization using linear regression, by the standard COST231-Hata models, and the free space model is also done, this allows us to conclude that the new model obtained using MOA for the city of Limbe is better and more representative of this local environment than the standard COST231-Hata model. The new model obtained can be used for radio planning in the city of Limbé in Cameroon.

Quantitative study of the defects of ferromagnetic materials using the magnetic charge model and particle swarm optimization algorithm

Local defects in components are an important factor responsible for causing damage to steel structures. Hence, metal magnetic memory (MMM) has been used to investigate this issue in recent years. MMM can detect defects based on variations in the self-magnetic leakage of ferromagnetic materials. However, there have been problems of difficulty in quantifying the theoretical parameters of the magnetic charge model and the single characterization of magnetic feature parameters, when using MMM for quantitative analysis of defects. Therefore, the particle swarm optimization (PSO) algorithm was introduced to quicky and accurately quantify the parameters of the magnetic charge model. Theoretical values were compared with experimental data to verify the accuracy of the proposed method. Then, the defect information (defect width and defect depth) was changed and the variation patterns of the magnetic signal and characteristic parameters were analyzed. Finally, the weight of each characteristic parameter was calculated using the entropy value method. A theoretical formula to comprehensively describe defects using multi-feature parameters was proposed. The results show that the theoretical values calculated based on the parameter identification of the PSO algorithm well agreed with the experimental data. Moreover, the proposed formula well described the relationship between the defect width and characteristic parameters. This study is expected to provide a basis for improving the quantitative analysis of MMM.

Research on Magnetic Field Optimization Algorithm Based on Step Shimming

Research on Magnetic Field Optimization Algorithm Based on Step Shimming

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.

An Intrusion Detection System Based on Hybrid of Artificial Neural Network (ANN) and Magnetic Optimization Algorithm (MOA)

Intrusion Detection System is a type of security application that protects computer and network systems. A variety of techniques have been proposed to increase IDS accuracy. Thisresearch study focuses on improving an IDS detection performance by combiningan Artificial Neural Network (ANN) with a Magnetic Optimization Algorithm (MOA), with the goal of increasing the classification rate and achieving high detection accuracy in IDS. The suggested ANNMOA result demonstrated that it is possible to improve IDS accuracy by up to 98.5 percent

Research on Comprehensive Evaluation of Economic Management Performance Based on Improved Fuzzy Clustering Algorithm

In order to solve the problems of low recall rate and precision rate, high error rate, and long evaluation time in traditional evaluation methods, a comprehensive evaluation of economic management performance based on an improved fuzzy clustering algorithm is designed. The improved magnetic optimization algorithm was used to optimize the fuzzy C-mean algorithm, the improved fuzzy clustering algorithm was completed, and the improved fuzzy clustering algorithm was used to mine the economic management performance data. Using data mining findings and AHP’s weighting formula, a complete method for evaluating economic management effectiveness was developed. The BP neural network was improved using a genetic algorithm based on the index weight calculation findings, and the full-assessment model of economic management performance was constructed. Using this approach, it is possible to accurately and quickly assess the economic management performance of a company with a high rate of recall and accuracy; the error rate of a thorough assessment ranges between −3 percent and 4 percent; the average duration for an assessment is 0.81 seconds.

Tunicate Swarm Magnetic Optimization With Deep Convolution Neural Network For Collaborative Filter Recommendation

Abstract Collaborative filtering (CF) is a well-known and eminent recommendation technique to predict the preference of new users by revealing the structures of historical records of the examined users. Even though CF is effectively adapted in several commercial areas, many limitations still exist, particularly in the sparsity of rating data that raises many issues. This paper devises a novel deep learning strategy for CF to recognize user preferences. Here, black hole entropic fuzzy clustering (BHEFC) is devised for clustering item sequences to form groups with similar item sequences. Moreover, cluster centroids are optimized using the tunicate swarm magnetic optimization algorithm (TSMOA), which is devised by combining tunicate swarm algorithm and magnetic optimization algorithm. After grouping similar items together, the group matching is performed based on a deep convolutional neural network (Deep CNN). Subsequently, the visitor sequence and query sequence are compared using Jaro–Winkler distance, which contributes to the best visitor sequence. From this best visitor sequence, the recommended product is acquired. The proposed TSMOA–BHEFC and Deep CNN outperformed other methods with minimal mean absolute error of 0.200, mean absolute percentage error of 0.198 and root mean square error of 0.447, respectively.

EHMO-Based Deep ResNet for Survival Timeline Prediction of Adenocarcinoma Cancer.

Lung cancer is due to the growth of uncontrolled cells in the lungs, and the death rate is high compared with all types of cancer. It is recognized and treated using images of computed tomography (CT). This paper develops the elephant herding magnetic optimization-based deep residual network (EHMO-based Deep ResNet) for survival timeline prediction in adenocarcinoma. Here, preprocessing is performed using a Gaussian filter for the lung CT image. The preprocessed image is subjected to lung lobe segmentation, which is performed by the active contour model. Nodule identification locates nodules in the segmented image, where the process is carried out using a grid-based scheme. After that, feature extraction is carried out to extract intensity, wavelet, tetrolet transform, local optimal oriented pattern (LOOP), and clinical features. Finally, the extracted features are fed to the prediction module, which is based on the Deep ResNet classifier, which is trained by the proposed EHMO optimization algorithm. Here, the developed EHMO combines elephant herding optimization (EHO) and the magnetic optimization algorithm (MOA). The developed adenocarcinoma survival timeline prediction technique exhibits efficient performance in terms of accuracy, 0.955; maximal sensitivity, 0.962; and high specificity, 0.958.

Improved Magnetic Guidance Approach for Automated Guided Vehicles by Error Analysis and Prior Knowledge

Navigation accuracy and robustness are key performance indexes of automated guided vehicles (AGVs). In our previous study, the magnetic guidance approach based on magnetic dipole model and non-linear optimization algorithm was proposed, which has high positioning accuracy and could estimate the yaw angle of AGV directly. However, the localization accuracy of the magnetic guidance approach will deteriorate if the magnetic nails (MNs) buried in the ground have installation errors or the magnetic moments between the MNs are inconsistent. To overcome this problem, we propose an improved method based on error analysis and prior knowledge for the magnetic guidance approach. Firstly, the factors that affect the localization accuracy are analyzed, and the parameters ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$B_{\mathrm {T}}$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$p$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$c$ </tex-math></inline-formula> ), whose errors will deteriorate the localization accuracy, are combined with MN pose ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$a$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$b$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$m$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula> ) as optimization variables. Then, the prior knowledge regarding ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$B_{\mathbf {T}}$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$p$ </tex-math></inline-formula> , <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$c$ </tex-math></inline-formula> ) is employed to construct the constraint conditions for the magnetic guidance approach. Finally, the global convergence probability and convergence speed of the improved magnetic guidance approach are analyzed. Experimental results demonstrate the adaptability and robustness of the improved magnetic tracking approach, which diminishes the impact of MN installation errors and magnetic moment deviation. The parking accuracy of AGV is improved to 1.42±0.85 mm and 1.10±0.38°.

Color Difference Detection of Polysilicon Wafers Using Optimized Support Vector Machine by Magnetic Bacteria Optimization Algorithm With Elitist Strategy

A support vector machine (SVM) is an important method in the detection and classification of the color difference on a polysilicon wafer. However, the accuracy of a SVM is affected by its feature vector and parameters. Owing to the complex color information and random texture features on the wafer surface, the feature design is extremely complicated. Meanwhile, a SVM optimized using a popular intelligent algorithm easily falls into a local optimum, and the convergence of the algorithm needs to be improved. Therefore, a classification method is proposed for detecting the color difference from multi-scale features in polysilicon wafer images. First, to extract the features, an image segmentation method is devised based on the maximum region contrast, which effectively applies a threshold segmentation of the wafer images. Second, the multi-scale features and color representations in different color spaces are used to construct a nine-dimensional feature vector that sufficiently describes the surface characteristics of the wafer. An approach to optimize the SVM is finally proposed using a magnetic bacteria optimization algorithm based on an elitist strategy for parameter optimization. The optimum individual of each generation is used to adjust the magnetic moment such that the solution approaches the optimal direction and enhances the global search ability. A fitness function is also introduced to improve the diversity of the solutions through a cross-validation method. The experiment results show that the proposed algorithm achieves an accuracy of 98.3% with a better classification performance than the other methods and that the color difference of polysilicon wafers can be effectively detected.

An optimized convolutional neural network for chatter detection in the milling of thin-walled parts

Chatter is a self-excited vibration that frequently occurs in thin-walled parts milling, which has become a major limitation to productivity and quality. Additionally, convolutional neural network (CNN) has been widely used in detection and classification, but the accuracy and convergence are affected by the initial weight and hyperparameters. Therefore, based on CNN, a method of chatter detection for the milling of thin-walled parts is proposed, which is realized by recognizing the image of the machined surface. First, aiming at the challenges of neural networks in which the weight is randomly initialized, a weight initialization method is proposed based on an improved magnetic bacteria optimization algorithm. The optimal magnetosome of each generation is used to adjust the magnetic moment of the next generation so that the population approaches the optimal solution direction to search for the global optimal value. Second, an improved genetic algorithm is proposed to optimize the network structure and improve the optimization efficiency of hyperparameters. The tabu list and the hill climbing algorithm are introduced into the improved genetic algorithm to avoid repeatedly counting the fitness of the same point and solving the oscillation problem near the optimal solution. The experimental results show that the accuracy, the value of the Matthew correlation coefficient, and the F1 Score value of proposed CNN are 98.3%, 95.5%, and 98.8%, respectively. Compared with other algorithms, the proposed method, which has outstanding recognition performance, is competent in contactless chatter detection.

Improved magnetic charged system search optimization algorithm with application to satellite formation flying

This paper is devoted to the implementation and application of an improved version of the metaheuristic algorithm called magnetic charged system search. Some modifications and novelties are introduced and tested. Firstly, the authors’ attempt is to develop a self-adaptive and user-friendly algorithm which can automatically set all the preliminary parameters (such as the numbers of particles, the maximum iterations number) and the internal coefficients. Indeed, some mathematical laws are proposed to set the parameters and many coefficients can dynamically change during the optimization process based on the verification of internal conditions. Secondly, some strategies are suggested to enhance the performances of the proposed algorithm. A chaotic local search is introduced to improve the global best particle of each iteration by exploiting the features of ergodicity and randomness. Moreover, a novel technique is proposed to handle bad-defined boundaries; in fact, the possibility to self-enlarge the boundaries of the optimization variables is considered, allowing to achieve the global optimum even if it is located on the boundaries or outside. The algorithm is tested through some benchmark functions and engineering design problems, showing good results, followed by an application regarding the problem of time-suboptimal manoeuvres for satellite formation flying, where the inverse dynamics technique, together with the B-splines, is employed. This analysis proves the ability of the proposed algorithm to optimize control problems related to space engineering, obtaining better results with respect to more common and used algorithms in literature.

A Hybrid Metaheuristic Method in Training Artificial Neural Network for Bankruptcy Prediction

Corporate bankruptcy prediction is an important task in the determination of corporate solvency, that is, whether a company can meet up to its financial obligations or not. It is widely studied as it has a significant effect on employees, customers, management, stockholders, bank lending assessments, and profitability. In recent years, machine learning techniques, particularly Artificial Neural Network (ANN), have widely been studied for bankruptcy prediction since they have proven to be a good predictor, especially in financial applications. A critical process in learning a network is weight training. Although the ANN is mathematically efficient, it has a complex weight training process, especially in computation time when involving a large training data. Many studies improved ANN’s weight training using metaheuristic algorithms such as Evolutionary Algorithms (EA), and Swarm Intelligence (SI) approaches for bankruptcy prediction. In this study, two metaheuristics algorithms, Magnetic Optimization Algorithm (MOA) and Particle Swarm Optimization (PSO), have been enhanced through hybridization to propose a new method MOA-PSO. Hybrid algorithms have been proven to be capable of solving optimization problems faster, with better accuracy. The MOA-PSO was used in training ANN to improve the performance of the ANN in bankruptcy prediction. The performance of the hybrid MOA-PSO was compared with that of four existing algorithms. The proposed hybrid MOA-PSO algorithm exhibits promising results with a faster and more accurate prediction, with 99.7% accuracy.

Fuzzy magnetic optimization clustering algorithm with its application to health care

Clustering is an important tool for data mining and knowledge discovery that helps in revealing hidden structures and “clusters” found in large data sets. Fuzzy C-means (FCM) is considered to be popular data clustering method due to its capability of clustering the datasets that are uncertain, vague and/or are otherwise difficult to cluster. Although, noted both for its simplicity of implementation and its output validity, performance of FCM usually gets affected in case of poor initialization resulting in the algorithm getting trapped into a local optimum. To overcome this shortcoming, the present study proposes a novel clustering algorithm called fuzzy magnetic optimization clustering (Fuzzy-MOC) which embeds the concept of fuzzy clustering into magnetic optimization algorithm. In Fuzzy-MOC, the data points apply force directly to the magnetic particles due to which the particles change their positions in the feature space. Magnetic particles are attracted by their neighbours assumed to be in a lattice like structure. The proposed algorithm is evaluated on a set of 16 benchmark datasets taken from the UCI Machine Learning Repository including high dimensional gene expression dataset. Experimental results demonstrate that Fuzzy-MOC outperforms the other state-of-the-art algorithms in terms of different performance metrics like F1, accuracy, purity and RI measure.

Magnetic optimization algorithm for data clustering

In this paper, a new clustering algorithm inspired by magnetic force is proposed. This algorithm is not sensitive to the initialization problem of cluster centroids. Centroid particles change their position according to the total magnetic force applied by data points. The position of the particle gets updated by employing magnetic resultant force to find the best position of centroid particle for clustering. To evaluate the performance of the proposed algorithm, numerical experiments are conducted on eleven benchmark data sets taken from UCI repository and are compared with five different clustering algorithms. The results show that the proposed algorithms are more accurate, efficient and robust as compared to the other clustering algorithms.

Automatic identification of epileptic EEG signals through binary magnetic optimization algorithms

Epilepsy is a class of chronic neurological disorders characterized by transient and unexpected electrical disturbances of the brain. The automated analysis of the electroencephalogram (EEG) signal can be instrumental for the proper diagnosis of this mental condition. This work presents a systematic assessment of the performance of different variants of the binary magnetic optimization algorithm (BMOA), two of which are introduced here, while serving as feature selectors for epileptic EEG signal identification. In this context, the optimum-path forest classifier was adopted as a classification model, whereas different wavelet families were considered for EEG feature extraction. In order to compare the performance of the improved BMOA variants against the traditional one, as well as other metaheuristic techniques, namely particle swarm optimization, binary bat algorithm, and genetic algorithm, we employed a well-known EEG benchmark dataset composed of five classes of EEG signals (two of which comprising normal patients with eyes open or closed, and the remaining comprising ill patients with different levels of epilepsy). Overall, the results evidenced the robustness of the proposed BMOA and its variants.

Optimization of Value of Parameters in Ad-hoc on Demand Multipath Distance Vector Routing Using Magnetic Optimization Algorithm

Vehicular Ad-hoc Networks is one of the emerging research areas of Mobile adhoc network. One of the key problems of VANET is changing topology of vehicles which leads to frequent disconnections. Therefore, for communication among the running vehicles, routing of the message becomes a challenging problem. Although, many routing protocols have been proposed in the literatures, but the performance of these protocols, in different scenarios, depends on the value of parameters used in. The objective of our work is to find best fitness function value for Ad-hoc on demand multipath distance vector routing protocol, in real scenario map by obtaining an optimal value of parameters using Magnetic Optimization Algorithm. Therefore, in this paper, we have proposed an algorithm based on Magnetic Optimization Algorithm which finds the optimal value of parameters for Ad-hoc on demand multipath distance vector routing protocol in a given scenario. The fitness function guides Magnetic Optimization Algorithm to achieve the best fitness value. The experimental results, using the optimal value of parameters obtained by Magnetic Optimization Algorithm, show 81.41% drop in average end-to-end delay, 39.24 % drop in Normalized Routing Loads, and slight rise (0.77%) in the packet delivery ratio as compared to using default value of parameters in Ad-hoc on demand multipath distance vector routing protocol.

Support Vector Machine Optimization Based On Magnetic Bacteria Optimization Algorithm

Classification performance of support vector machine (SVM) will be influenced by its model parameters. For this problem, a new method named magnetic bacteria optimization algorithm (MBOA) that optimizes the parameters of SVM is proposed. It is tested by the UCI standard data sets and compared with the other optimization algorithms, such as particle swarm optimization (PSO). Experimental results show that the MBOA can optimize the parameters of SVM well and has better performance than the compared algorithms.

Motor Imagery Electroencephalograph Classification Based on Optimized Support Vector Machine by Magnetic Bacteria Optimization Algorithm

In this paper, an optimized support vector machine (SVM) based on a new bio-inspired method called magnetic bacteria optimization algorithm method is proposed to construct a high performance classifier for motor imagery electroencephalograph based brain---computer interface (BCI). Butterworth band-pass filter and artifact removal technique are combined to extract the feature of frequency band of the ERD/ERS. Common spatial pattern is used to extract the feature vector which are put into the classifier later. The optimization mechanism involves kernel parameters setting in the SVM training procedure, which significantly influences the classification accuracy. Our novel approach aims to optimize the penalty factor parameter C and kernel parameter g of the SVM. The experimental results on the BCI Competition IV dataset II-a clearly present the effectiveness of the proposed method outperforming other competing methods in the literature such as genetic algorithm, particle swarm algorithm, artificial bee colony, biogeography based optimization.

Opposition-based Magnetic Optimization Algorithm with parameter adaptation strategy

Magnetic Optimization Algorithm (MOA) has emerged as a promising optimization algorithm that is inspired by the principles of magnetic field theory. In this paper we improve the performance of the algorithm in two aspects. First an Opposition-Based Learning (OBL) approach is proposed for the algorithm which is applied to the movement operator of the algorithm. Second, by learning from the algorithm׳s past experience, an adaptive parameter control strategy which dynamically sets the parameters of the algorithm during the optimization is proposed. To show the significance of the proposed parameter adaptation strategy, we compare the algorithm with two well-known parameter setting techniques on a number of benchmark problems. The results indicate that although the proposed algorithm with the adaptation strategy does not require to set the parameters of the algorithm prior to the optimization process, it outperforms MOA with other parameter setting strategies in most large-scale optimization problems. We also study the algorithm while employing the OBL by comparing it with the original version of MOA. Furthermore, the proposed algorithm is tested and compared with seven traditional population-based algorithms and eight state-of-the-art optimization algorithms. The comparisons demonstrate that the proposed algorithm outperforms the traditional algorithms in most benchmark problems, and its results is comparative to those obtained by the state-of-the-art algorithms.