Opposition-based moth-flame optimization improved by differential evolution for feature selection

Moth flame optimization (MFO) algorithm proves to be an excellent choice for numerical optimization. However, for some complex objectives, MFO may get trapped in local optima or suffer from premature convergence. In order to overcome these issues, an improved MFO-based algorithm, called opposition-based moth flame optimization with Cauchy mutation and evolutionary boundary constraint handling (OMFO), is presented. The proposed method integrates opposition-based learning (OBL) with Cauchy mutation (CM) and evolution boundary constraint handling (EBCH) technique with MFO to improve its performance. OBL and EBCH improve the convergence of MFO, while CM helps MFO to escape local optima. The effect of each method (OBL, CM, EBCH) on MFO is validated using 18 benchmark functions and two constrained real-world problems. Simulation results indicate that opposition-based MFO integrated with Cauchy mutation and EBCH has the best performance among the MFO variants. The OMFO algorithm is also compared with various algorithms in the literature and provides competitive results in terms of increased exploitation and exploration capability, improved convergence and local optima avoidance.

In this research we study the optimization problem of path planning in an oceanic ecosystem with a Static current in the presences of various obstacles with the autonomy of Autonomous underwater vehicles (AUV). We introduce an improved Moth flame optimization algorithm called refraction principle and opposite-based-learning Moth flame optimization (ROBL-MFO) in a Static current environment. This algorithm addresses the differences between the traditional Moth flame optimization (MFO) algorithm. First, it adjusts the moth position update formula we deal with the term of the historically optimal flame average, and improves the convergence velocity of the algorithm. Secondly, it uses a random inverse learning strategy to narrow down the algorithm search. Finally, the principle of refraction provides the algorithm with the ability to jump from the local optima and help the algorithm avoid premature convergence. The numerical results show that the ROBL-MFO improves the classical MFO, in terms of optimization criteria.KeywordsAutonomous underwater vehiclesPath planningStatic currentRefraction principle and opposite-based learning - Moth flame optimization

Due to adverse effects of hostile deployment environment(s), sensors nodes (SNs) deployed in the network may drain or get damaged. This attributes for loss of connectivity between the sensors and the sink node. Hence it is necessary to design the wireless sensor network (WSN) in a manner that the network is capable of coping up with the failure of few nodes/links. Using single hop data communication model reduces the lifetime of the network as the SNs are resource constrained (in terms of battery). Relay nodes (RNs) facilitate in improving network lifetime, fault tolerance and/or connectivity. Finding minimum number of relay nodes for a fault tolerant, fully connected network is a NP Hard problem. In this paper, we follow two phase relay node placement procedure to achieve the objective. In the first phase, we cluster the SNs using mean shift algorithm and place RNs as the cluster heads. In the second phase, we use metaheuristic algorithms like Moth Flame Optimization (MFO), Differential Evolution (DE), Bat algorithm (BA) and Biogeography Based Optimization algorithm (BBO) to place the RNs such that the required fault tolerance is achieved along with fully connected network. Extensive simulation results prove that MFO algorithm performs better for fault tolerant relay node placement problem.

Cross-correlation stacking-based microseismic source location using three metaheuristic optimization algorithms

Cardiovascular Disease (CVD) is one of the primary diseases that causes death every year. An approximation of roughly about 17.5 million people dies due to CVD, signifying about 31% of global deaths. Based on the statistics, every 34 seconds, a person dies due to heart disease. Various classification algorithms have been developed and utilized as classifiers to support doctors who are ineffectually diagnosed with heart disease. The main aim of this work is to improve the performance of the heart disease approach using image processing algorithm. To improve the effectiveness and efficiency of classification performance for heart disease diagnosis, an optimized neural network was proposed based on the feature extraction and selection approach for handling features. The objective of this investigation is to diagnose heart diseases using feature extraction, reduction based classification and image processing methods. The proposed model comprises of two subsets: Feature extraction using gray scale properties and Moth flame optimization (MFO) for effectual feature selection, followed by a classification technique using Generalized Regression Neural Network. The first system includes three stages: (i) Pre-processing of the dataset (ii) feature extraction (iii) performing MFO for efficient selection. In the second method, GRNN is proposed. The heart data set obtained from ACDC Challenge, was utilized for performing the computation. The image obtained from the MRI-scanner is in the NIfTI image format. The pre-process step used in this is to convert the image type from INT16 to uint8 to improve the quality of image viewing and for feature extraction process. In this phase, the texture properties from the pre-processed image are calculated and the value is in the numeric format. These values are the feature attributes of the dataset. The feature attributes of the image are given as input for the moth flame optimization process and output is the feature selected from the optimization process. The whole process is performed on the feature attributes of the image by determining the optimal feature for the classifier by reducing its error rate. The optimal feature from the moth flame optimization is used for training and testing the network. The classifier used in this approach is a single neural network classifier with a regression nature. Due to the regression property, the network is well trained with the feature. The Generalized regression neural network is used for classifying heart diseases. The proposed method achieves the accuracy of 96.23%, sensitivity of 95.41% and specificity of 96.75%. These values are calculated based on the confusion matrix of the classifier. In this, the feature extraction using the gray scale properties plays an important role to determine the feature attributes from the MRI heart images. The Moth flame optimization able to produce an accuracy of 97.23% using GRNN for classification with minimum single attribute mean of the image. It also outperformed the other methods, either the feature extraction based classification or the feature reduction based classification.

Snake Optimizer: A novel meta-heuristic optimization algorithm

Due to the unexpected breakdowns that can happen in various components of a production system, failure to reach production targets and interruptions in the process of production are not surprising. Since this issue remains for manufactured products, this halting results in the loss of profitability or demand. In this study, to address a number of challenges associated with the management of crucial spare parts inventory, a mathematical model is suggested for the determination of the optimal quantity of orders, in the case of an unpredicted supplier failure. Hence, a production system that has various types of equipment with crucial components is assumed, in which the crucial components are substituted with spare parts in the event of a breakdown. This study’s inventory model was developed for crucial spare parts based on the Markov chain process model for the case of supplier disruption. Moreover, for optimum ordering policies, re-ordering points, and cost values of the system, four metaheuristic algorithms were utilized that include Grey Wolf Optimizer (GWO), Genetic Algorithm (GA), Moth–Flame Optimization (MFO) Algorithm, and Differential Evolution (DE) Algorithm. Based on the results, reliable suppliers cannot meet all of the demands; therefore, we should sometimes count on unreliable suppliers to reduce unmet demand.

Moth-Flame Optimization (MFO) algorithm is a widely used nature-inspired optimization algorithm. However, for some complex optimization problems, such as high dimensional and multimodal problems, the MFO may fall into the local optimal solution. Hence, in this paper an ameliorated Moth-Flame Optimization (AMFO) algorithm is presented to improve the solution quality and global optimization capability. The key features of the proposed algorithm are the Gaussian mutation produce flames and the modified position updating mechanism of moths, which can improve the ability of MFO to jump out of local optimum solutions. In addition, opposition-based learning is adopted to initialize the population. The AMFO algorithm is compared with 9 state-of-the-art algorithms (such as Lévy Moth-Flame Optimization (LMFO), Grey Wolf Optimization (GWO), Sine Cosine Algorithm (SCA), Heterogeneous Comprehensive Learning Particle Swarm Optimization (HCLPSO)) on 23 classical benchmark functions. The comparative results show that the AMFO is effective and has good performance in terms of jumping out of local optimum, balancing exploitation ability and exploration ability. Furthermore, the AMFO is adopted to optimize the parameters of fast learning network (FLN) to build the prediction model of silicon content in liquid iron for blast furnace, and simulation experiment results from field data show that the root mean square error of the AMFO-FLN model is 0.0542, hit ratio is 91 and the relative error is relatively stable, the main fluctuation is between -0.1 and 0.1; compared with other ten silicon content in liquid iron models, the AMFO-FLN model has better predictive performance.

Feature selection is the process of choosing, or removing, features to obtain the most informative feature subset of minimal size. Such subsets are used to improve performance of machine learning algorithms and enable human understanding of the results. Approaches to feature selection in literature exploit several optimization algorithms. Multi-objective methods also have been proposed, minimizing at the same time the number of features and the error. While most approaches assess error resorting to the average of a stochastic K-fold cross-validation, comparing averages might be misleading. In this paper, we show how feature subsets with different average error might in fact be non-separable when compared using a statistical test. Following this idea, clusters of non-separable optimal feature subsets are identified. The performance in feature selection can thus be evaluated by verifying how many of these optimal feature subsets an algorithm is able to identify. We thus propose a multi-objective optimization approach to feature selection, EvoFS, with the objectives to i. minimize feature subset size, ii. minimize test error on a 10-fold cross-validation using a specific classifier, iii. maximize the analysis of variance value of the lowest-performing feature in the set. Experiments on classification datasets whose feature subsets can be exhaustively evaluated show that our approach is able to always find the best feature subsets. Further experiments on a high-dimensional classification dataset, that cannot be exhaustively analyzed, show that our approach is able to find more optimal feature subsets than state-of-the-art feature selection algorithms.

Extreme Learning Machine (ELM) algorithm assigns the input weights and biases in a “one-time stamp” fashion, this method makes the algorithm to be ill-conditioned and reduces its classification accuracy. The contribution of this work is the enhancement of the performance of ELM with the Moth-Flame Optimization (MFO) algorithm to improve classification accuracy. A hybrid of the Moth-Flame Optimization and Extreme Learning Machine (MFO-ELM) algorithm is implemented in MATLAB. MFO ensures a concurrent simulation of exploration and exploitation of the search space to select an optimum candidate solution. The candidate solution is reshaped into input weights and biases for ELM classification. The hybrid algorithm is validated on five life-selected datasets. The performance improvement of MFO-ELM is compared with ELM-optimized Particle Swarm Optimization (PSO-ELM) and Competitive Swarm Optimization (CSO-ELM) algorithms. The improvement rates are qualitatively and quantitatively evaluated to show the improvement of MFO-ELM on ELM and the other meta-heuristic algorithms. MFO-ELM improved the accuracies of the basic ELM in all 100% of the simulations and performed better than the other meta-heuristic algorithms in 80% of the simulations. The performance of MFO-ELM is more competitive, and it is recommended for solving classification problems.

This paper proposes a fast restoration strategy of distribution systems using an enhanced differential evolution (EDE) approach. Service restoration of distribution systems is an emergent task that must be performed rapidly by the system operators. Basically, it is a complicated combinatorial optimization problem, often having many candidate solutions to be evaluated by the operators. To improve the efficiency of restoration and reduce the burden on the operators, this paper proposes an EDE method combining variable scaling differential evolution (VSDE) algorithm and ant system (AS) to solve the combinatorial optimization problem. To verify the effectiveness of the proposed method, a typical distribution system of the Taiwan Power Company (TPC) was tested and compared with the existing methods. The results show the proposed method was superior to the existing methods in terms of convergence time and the obtained restoration plan.

Multi-layer competitive-cooperative framework for performance enhancement of differential evolution

Introduction. The assessment of the reliability and cost of complex systems, such as Complex Bridge Systems (CBS) and Life Support Systems in Space Capsules (LSSSC), is fascinating. To achieve the ideal system design through diverse constraints and increase overall system reliability, researchers have extensively explored system reliability and cost optimization problems. Hence, the significant advancement in metaheuristic methods is the primary source of further system reliability and cost optimization process refinement.
 Aim and tasks. This research attempts to enhance the reliability and cost of complex systems named CBC and LSSSC has been presented. 
 Results. The structure is based on few recent metaheuristic techniques, such as Moth Flame Optimization (MFO), Whale Optimization Algorithm (WOA), Gazelle Optimization Algorithm (GOA), Dragonfly Algorithm (DA), and Coati Optimization Algorithm (COA). Comparing the acquired findings to those found in other proposed techniques demonstrates the usefulness of a methodology based on COA. The proposed COA algorithm exhibits enhanced efficiency by offering superior solutions to reliability and cost-optimization problems. In addition, a non-parametric Friedman ranking was performed for validation. The results of this research are based on improving the reliability of the parameters and decreasing complex systems’ costs used by the five metaheuristic methods. Observing the convergence graph, Friedman ranking, statistical results test, and tables determined that COA is the most effective algorithm for a complex system’s cost and reliability parameters compared to other existing approaches, and also provided a faster solution.
 Conclusions. This study proposes unique ways to reduce costs while increasing parameter reliability in complex systems. After analysing the comparative solution, the authors found that when comparing these approaches (GOA, DA, MFO, WOA, and COA), the COA provided the best minimum solution for the cost and reliability of complex systems. Hence, the suggested COA procedure was more successful than that described in this study.

A new intrusion detection system based on Moth–Flame Optimizer algorithm

In machine learning, feature selection is a crucial and important operation. The basic goal of the feature selection problem is to lower the size of the feature set while preserving performance accuracy. To classify the datasets, many approaches have been devised. Metaheuristic algorithms, on the other hand, have received a lot of interest for handling a variety of optimization problems. As a result, this paper gives a comprehensive assessment of the literature on employing metaheuristic algorithms to solve feature selection problems. Furthermore, based on their behavior, metaheuristic algorithms have been divided into four types. A classified list of over a hundred metaheuristic algorithms is also provided. Only binary variations of metaheuristic algorithms have been evaluated and categorized in order to address the feature selection problem, and a comprehensive explanation of each has been provided. The binary classification, name of the classifier used, datasets, and evaluation metrics for metaheuristic algorithms used to solve feature selection problems are all included. After analyzing the articles, problems and issues in getting the optimal feature subset using various metaheuristic methods are identified. Finally, several research needs are identified for researchers who want to continue their work on building or refining metaheuristic categorization algorithms. A case study is presented for an application in which UCI datasets are adopted and a number of metaheuristic algorithms are used to achieve the optimum functionality.KeywordsMachine learningMetaheuristic algorithmsFeature selectionClassificationBinary variations