Improved Salp Swarm Algorithm Research Articles

Dynamic Emergency Vehicle Path Planning and Traffic Evacuation Based on Salp Swarm Algorithm

In view of the rescue delay due to traffic congestion in the urban road network, this paper implemented real-time traffic control with congestion index constraints in emergency vehicle dispatching and proposed a two-stage optimization model and algorithm. In the first stage, salp swarm algorithm (SSA) was combined with Dijkstra algorithm, and a novel hybrid algorithm with new updating rules was designed to get the multiple alternative paths. In the second stage, an improved salp swarm algorithm (ISSA) with a population grouping strategy was proposed to obtain the best evacuation schemes and the optimal rescue paths of emergency vehicles. Results of the illustrative examples show that, after evacuation, the average travel time of all alternative paths is reduced by 24.22%, while traffic congestion indexes of the adjacent road sections almost unchanged. The computation time of the hybrid algorithm for obtaining the set number of alternative paths is 56.62% and 50.47% shorter than that of bat algorithm (BA) and SSA. For the solution of the evacuation model, the computation time of the ISSA is 33.51%, 30.15%, and 30.60% shorter than that of particle swarm optimization (PSO), BA, and SSA, and the optimal solution of the ISSA is 25.92%, 10.06%, and 0.97% better than that of PSO, BA, and SSA. That is, we shorten the emergency response time and control the adverse impact of traffic evacuation on background traffic. The improved algorithm has excellent performance. This study provides a new idea and method for emergency rescue of traffic accidents.

Performance optimization of annealing salp swarm algorithm: frameworks and applications for engineering design

AbstractSwarm salp algorithm is a swarm intelligence optimization algorithm enlightened by the movement and foraging behaviors of the salp population. The salp swarm algorithm (SSA) has a simple structure and fast processing speed and can gain significant results on objective functions with fewer local optima. However, it has poor exploration ability and is easy to suffer from the local optimal solutions, so it performs poorly on multimodal objective functions. Besides, its unfair balance of exploration and exploitation is another notable shortcoming. To ameliorate these shortcomings and enhance the algorithm’s performance on multimodal functions, this research proposes simulated annealing (SA) improved salp swarm algorithm (SASSA). SASSA embeds the SA strategy into the followers’ position updating method of SSA, performs a certain number of iterations of the SA strategy, and uses Lévy flight to realize the random walk in the SA strategy. SASSA and 23 original and improved competitive algorithms are compared on 30 IEEE CEC2017 benchmark functions. SASSA ranked first in the Friedman test. Compared with SSA, SASSA can obtain better solutions on 27 benchmark functions. The balance and diversity experiment and analysis of SSA and SASSA are carried out. SASSA’s practicability is verified by solving five engineering problems and the fertilizer effect function problem. Experimental and statistical results reveal that the proposed SASSA has strong competitiveness and outperforms all the competitors. SASSA has excellent exploration ability, suitable for solving composition functions with multiple peaks. Meanwhile, SASSA brings about a good balance of exploration and exploitation and dramatically improves the quality of the solutions.

Improved Salp swarm algorithm for solving single-objective continuous optimization problems

Improved Salp swarm algorithm for solving single-objective continuous optimization problems

An internet traffic classification method based on echo state network and improved salp swarm algorithm.

Internet traffic classification is fundamental to network monitoring, service quality and security. In this paper, we propose an internet traffic classification method based on the Echo State Network (ESN). To enhance the identification performance, we improve the Salp Swarm Algorithm (SSA) to optimize the ESN. At first, Tent mapping with reversal learning, polynomial operator and dynamic mutation strategy are introduced to improve the SSA, which enhances its optimization performance. Then, the advanced SSA are utilized to optimize the hyperparameters of the ESN, including the size of the reservoir, sparse degree, spectral radius and input scale. Finally, the optimized ESN is adopted to classify Internet traffic. The simulation results show that the proposed ESN-based method performs much better than other traditional machine learning algorithms in terms of per-class metrics and overall accuracy.

Novel Improved Salp Swarm Algorithm: An Application for Feature Selection.

We live in a period when smart devices gather a large amount of data from a variety of sensors and it is often the case that decisions are taken based on them in a more or less autonomous manner. Still, many of the inputs do not prove to be essential in the decision-making process; hence, it is of utmost importance to find the means of eliminating the noise and concentrating on the most influential attributes. In this sense, we put forward a method based on the swarm intelligence paradigm for extracting the most important features from several datasets. The thematic of this paper is a novel implementation of an algorithm from the swarm intelligence branch of the machine learning domain for improving feature selection. The combination of machine learning with the metaheuristic approaches has recently created a new branch of artificial intelligence called learnheuristics. This approach benefits both from the capability of feature selection to find the solutions that most impact on accuracy and performance, as well as the well known characteristic of swarm intelligence algorithms to efficiently comb through a large search space of solutions. The latter is used as a wrapper method in feature selection and the improvements are significant. In this paper, a modified version of the salp swarm algorithm for feature selection is proposed. This solution is verified by 21 datasets with the classification model of K-nearest neighborhoods. Furthermore, the performance of the algorithm is compared to the best algorithms with the same test setup resulting in better number of features and classification accuracy for the proposed solution. Therefore, the proposed method tackles feature selection and demonstrates its success with many benchmark datasets.

Improved salp swarm algorithm based on particle swarm optimization for maximum power point tracking of optimal photovoltaic systems

Improved salp swarm algorithm based on particle swarm optimization for maximum power point tracking of optimal photovoltaic systems

Improved Salp Swarm Optimization Algorithm for Damping Controller Design for Multimachine Power System

This paper proposes an improved salp swarm algorithm (ISSA) as an effective metaheuristic method for tackling global optimization issues and damping power system oscillations. In the suggested ISSA, new equations are introduced to update the location of the leader and followers. This modification improves the method’s exploration possibilities while also preventing it from converging prematurely. Benchmark test functions are used to confirm the proposed algorithm’s performance, and the results are compared to SSA and other effective optimization algorithms. According to the extensive comparisons, the enhanced ISSA algorithm has higher convergence accuracy and stability than the original SSA and other researched algorithms. Furthermore, the feasibility and efficiency of the proposed method were demonstrated by the simultaneous coordinated design of UPFC based damping controllers. For the two-area, four-machine system, the experimental findings are provided. Simulation experiments reveal that ISSA designed controllers outperform those created using other methods.

Orthogonal Waveform Design for MIMO Radar Based on Improved Salp Swarm Algorithm

Orthogonal Waveform Design for MIMO Radar Based on Improved Salp Swarm Algorithm

Two-stage feature selection for classification of gene expression data based on an improved Salp Swarm Algorithm.

Microarray technology has developed rapidly in recent years, producing a large number of ultra-high dimensional gene expression data. However, due to the huge sample size and dimension proportion of gene expression data, it is very challenging work to screen important genes from gene expression data. For small samples of high-dimensional biomedical data, this paper proposes a two-stage feature selection framework combining Wrapper, embedding and filtering to avoid the curse of dimensionality. The proposed framework uses weighted gene co-expression network (WGCNA), random forest and minimal redundancy maximal relevance (mRMR) for first stage feature selection. In the second stage, a new gene selection method based on the improved binary Salp Swarm Algorithm is proposed, which combines machine learning methods to adaptively select feature subsets suitable for classification algorithms. Finally, the classification accuracy is evaluated using six methods: lightGBM, RF, SVM, XGBoost, MLP and KNN. To verify the performance of the framework and the effectiveness of the proposed algorithm, the number of genes selected and the classification accuracy was compared with the other five intelligent optimization algorithms. The results show that the proposed framework achieves an accuracy equal to or higher than other advanced intelligent algorithms on 10 datasets, and achieves an accuracy of over 97.6% on all 10 datasets. This shows that the method proposed in this paper can solve the feature selection problem related to high-dimensional data, and the proposed framework has no data set limitation, and it can be applied to other fields involving feature selection.

Improved salp swarm algorithm based on gravitational search and multi-leader search strategies

<abstract> <p>The salp swarm algorithm (SSA) will converge prematurely and fall into local optimum when solving complex high-dimensional multimodal optimization tasks. This paper proposes an improved SSA (GMLSSA) based on gravitational search and multi-swarm search strategies. In the gravitational search strategy, using multiple salp individuals to guide the location update of search agents can get rid of the limitation of individual guidance and improve the exploration ability of the algorithm. In the multi-swarm leader strategy, the original population is divided into several independent subgroups to increase population diversity and avoid falling into local optimization. In the experiment, 20 benchmark functions (including the well-known CEC 2014 function) were used to test the performance of the proposed GMLSSA in different dimensions, and the results were compared with the most advanced search algorithm and SSA variants. The experimental results are evaluated through four different analysis methods: numerical, stability, high-dimensional performance, and statistics. These results conclude that GMLSSA has better solution quality, convergence accuracy, and stability. In addition, GMLSSA is used to solve the tension/compression spring design problem (TCSD). The proposed GMLSSA is superior to other competitors in terms of solution quality, convergence accuracy, and stability.</p> </abstract>

Multi-strategy improved salp swarm algorithm and its application in reliability optimization.

To improve the convergence speed and solution precision of the standard Salp Swarm Algorithm (SSA), a hybrid Salp Swarm Algorithm based on Dimension-by-dimension Centroid Opposition-based learning strategy, Random factor and Particle Swarm Optimization's social learning strategy (DCORSSA-PSO) is proposed. Firstly, a dimension-by-dimension centroid opposition-based learning strategy is added in the food source update stage of SSA to increase the population diversity and reduce the inter-dimensional interference. Secondly, in the followers' position update equation of SSA, constant 1 is replaced by a random number between 0 and 1 to increase the randomness of the search and the ability to jump out of local optima. Finally, the social learning strategy of PSO is also added to the followers' position update equation to accelerate the population convergence. The statistical results on ten classical benchmark functions by the Wilcoxon test and Friedman test show that compared with SSA and other well-known optimization algorithms, the proposed DCORSSA-PSO has significantly improved the precision of the solution and the convergence speed, as well as its robustness. The DCORSSA-PSO is applied to system reliability optimization design based on the T-S fault tree. The simulation results show that the failure probability of the designed system under the cost constraint is less than other algorithms, which illustrates that the application of DCORSSA-PSO can effectively improve the design level of reliability optimization.

Optimization of magnetic field assisted finishing process during nanofinishing of titanium alloy (grade-5) implant using soft computing approaches

ABSTRACT The present study explores the potential of magnetic field assisted finishing (MFAF) in precise finishing of femoral knee implant made of bio-titanium alloy at the nanometric level. The process parameters, viz. rotational speed of tool, feed rate and carbonyl iron particle (CIP) concentration of MFAF have significant influence on the final surface topography of implants and thus selection of optimal set of their values is a difficult but an important task. In the present work, central composite rotatable design of response surface methodology is considered for nanofinishing of titanium alloy based femoral knee implants. Based on the experimental results, a polynomial regression prediction model for surface roughness is established in terms of MFAF process parameters. The fuzzy logic model with the help of ANOVA analysis is employed to analyze the effect of individual and interaction of parameters on surface roughness of implants. Finally, for further optimizing the final surface roughness of knee implant and determining the best settings of MFAF parameters, an improved salp swarm algorithm (ISSA) is proposed by introducing two important enhancements in basic SSA. The results reveal that SSA and ISSA metaheuristics achieved an improvement in final surface finish of knee implant by 4.04% and 14.24%, respectively, in comparison to default experimental trials during finishing.

A novel mutual aid Salp Swarm Algorithm for global optimization

AbstractSalp Swarm Algorithm is a new intelligent optimization algorithm. Because of it is fewer control parameters and convenient operation, it has attracted the attention of researchers from all circles. However, due to the lack of complex iterative process, it has some disadvantages, such as low optimization precision and poor population diversity in the late iteration. To solve these problems of Salp Swarm Algorithm, we proposed a Salp Swarm Algorithm based on mutual learning mechanism. In this article, the improved Salp Swarm Algorithm uses the iteration factor of tangent change to update the population position, which balances the global exploration and local development ability of the algorithm. At the same time, the introduction of mutual learning mechanism in the local development stage solves the problem of poor population diversity in the later iteration of Salp Swarm Algorithm, and improves the convergence accuracy of the algorithm. Finally, 23 classical and CEC2014 benchmark functions are used to evaluate the effectiveness of the proposed algorithm. The experimental results show that the improved Salp Swarm Algorithm has better optimization accuracy and stability compared with the algorithm of Salp Swarm, Moth Flame Optimization, Grasshopper Optimization, and Ant Lion Optimization.

Short-term wind power prediction based on hybrid variational mode decomposition and least squares support vector machine optimized by improved salp swarm algorithm model

To improve the accuracy of wind power prediction, a short-term wind power prediction model based on variational mode decomposition (VMD) and improved salp swarm algorithm (ISSA) optimized least squares support vector machine (LSSVM) is proposed. In the model, the variational modal decomposition is used to decompose the wind power sequence into multiple eigenmode components with limited bandwidth. The improved salp swarm algorithm is employed to tune the regularization parameter and kernel parameter in LSSVM. The proposed wind power prediction strategy using mean one-hour historical wind power data collected from a wind farm located in zhejiang, China. Compared with other prediction models illustrate the better prediction performance of VMD-ISSA-LSSVM.

Autism Spectrum Disorder Risk Gene Prediction Using Improved Salp Swarm Algorithm and Enhanced Convolution Neural Network Algorithm

A group of Neuro developmental disorders is Autism Spectrum Disorder (ASD) which is characterized by communication skills and social interaction difficulties. In past few years, there is a rapid increase in ASD and its root symptom’s cause is not yet determined. Comparatively large effort is needed in the existing system using Bayes network and there is no universally accepted technique to construct a network from data. An Enhanced Convolution Neural Network (ECNN) and Improved Salp Swarm Algorithm (ISSA) is proposed to solve these issues and for effective ASD classification. The task corresponds to classifying a long non-coding RNA (lncRNA) gene would cause a disease or not. After class balancing, discretization is applied for converting continuous values into discrete values and for optimal gene selection, ISSA algorithm is used. From genomic data, candidate gene biomarkers are identified using this gene selection. Every possible feature subset is computed for minimizing irrelevant features and error rate in gene data. It is focused to enhance ASD classification model’s accuracy. The Enhanced Convolutional Neural Network algorithm is used for ASD classification. The autism microarray dataset from the benchmark public repository, Gene Expression Omnibus (GEO) (National Center for Biotechnology Information (NCBI) is used for analysis. The proposed work using ISSA and ECNN exhibits better performance in terms of precision, accuracy, specificity, sensitivity and time complexity as indicated in the results.

Slap swarm algorithm with memory mechanism and boundary collision processing

Aiming at the problem of that the standard salp swarm algorithm has low result precision and slow convergence velocity in the evolutionary process, an improved salp swarm algorithm optimization based on memory mechanism and boundary collision processing is proposed. Firstly, a Chebyshev chaotic map was used to initialize the salps to make them distribute more evenly in search space. Secondly, adding the memory mechanism introduces the individual history optimum of salps into the optimizing strategy of individual salps, which accelerates the convergence speed of the algorithm. Finally, the boundary collision rebound mechanism is introduced to ensure the effectiveness and diversity of the population. The improved algorithm is simulated on 12 types of benchmark test functions in this paper, and compared with other intelligent optimization algorithms under the same conditions. The results show that the improved algorithm has not only a obvious improvement in convergence speed and convergence accuracy, but also has better optimization performance.

Uncertain Interval Forecasting for Combined Electricity-Heat-Cooling-Gas Loads in the Integrated Energy System Based on Multi-Task Learning and Multi-Kernel Extreme Learning Machine

The accurate prediction of electricity-heat-cooling-gas loads on the demand side in the integrated energy system (IES) can provide significant reference for multiple energy planning and stable operation of the IES. This paper combines the multi-task learning (MTL) method, the Bootstrap method, the improved Salp Swarm Algorithm (ISSA) and the multi-kernel extreme learning machine (MKELM) method to establish the uncertain interval prediction model of electricity-heat-cooling-gas loads. The ISSA introduces the dynamic inertia weight and chaotic local searching mechanism into the basic SSA to improve the searching speed and avoid falling into local optimum. The MKELM model is established by combining the RBF kernel function and the Poly kernel function to integrate the superior learning ability and generalization ability of the two functions. Based on the established model, weather, calendar information, social–economic factors, and historical load are selected as the input variables. Through empirical analysis and comparison discussion, we can obtain: (1) the prediction results of workday are better than those on holiday. (2) The Bootstrap-ISSA-MKELM based on the MTL method has superior performance than that based on the STL method. (3) Through comparing discussion, we discover the established uncertain interval prediction model has the superior performance in combined electricity-heat-cooling-gas loads prediction.

Objective rating of fabric wrinkles via random vector functional link based on the improved salp swarm algorithm

To solve the problem of inefficiency and inaccuracy associated with the classification of fabric wrinkles by human eyes, as well as improve current deficiencies in the application of neural networks for the classification of fabric wrinkles, we propose a model based on the salp swarm algorithm improved by ant lion optimization to optimize the random vector functional link to objectively evaluate the fabric wrinkle level. First, to improve the global searchability of the salp swarm algorithm and avoid the local optima problem, the use of ant lion optimization to improve the salp swarm algorithm is proposed in this study. Afterward, the improved salp swarm algorithm is used to optimize the input weight and hidden layer bias of the random vector functional link to avoid the inaccuracy and instability of random vector functional link classification owing to the randomness of the parameters. Finally, the performance of the proposed algorithm is verified using a fabric wrinkle dataset. Comparative experiments show that the classification accuracy of the proposed ant lion optimization - salp swarm algorithm - random vector functional link algorithm were 8.46%, 2.05%, 10.28%, 3.50%, and 4.42% higher than those of random vector functional link, improved random vector functional link based on salp swarm algorithm, extreme learning machine, improved extreme learning machine based on whale optimization algorithm, and improved backpropagation based on the Levenberg-Marquardt algorithm. Furthermore, the classification accuracy of the wrinkle level was effectively improved. All the fabrics used in this study were monochromatic, and multi-color printed fabrics have a significant impact on the difficulty of image processing and classification results. The next research step is to evaluate the wrinkle level of multi-color printed fabrics.

Improved Salp Swarm Algorithm with Simulated Annealing for Solving Engineering Optimization Problems

Swarm-based algorithm can successfully avoid the local optimal constraints, thus achieving a smooth balance between exploration and exploitation. Salp swarm algorithm (SSA), as a swarm-based algorithm on account of the predation behavior of the salp, can solve complex daily life optimization problems in nature. SSA also has the problems of local stagnation and slow convergence rate. This paper introduces an improved salp swarm algorithm, which improve the SSA by using the chaotic sequence initialization strategy and symmetric adaptive population division. Moreover, a simulated annealing mechanism based on symmetric perturbation is introduced to enhance the local jumping ability of the algorithm. The improved algorithm is referred to SASSA. The CEC standard benchmark functions are used to evaluate the efficiency of the SASSA and the results demonstrate that the SASSA has better global search capability. SASSA is also applied to solve engineering optimization problems. The experimental results demonstrate that the exploratory and exploitative proclivities of the proposed algorithm and its convergence patterns are vividly improved.

Load frequency control of a microgrid employing a 2D Sine Logistic map based chaotic sine cosine algorithm

This paper proposes a maiden application of a two dimensional Sine Logistic map based chaotic sine cosine algorithm (2D-SLCSCA) optimized classical PID controller for load frequency control (LFC) of an islanded microgrid (MG). In comparison to random variables and 1D chaotic sequences, the 2D chaotic sequences are more ergodic and possess a wider chaotic range, thereby enhancing the global convergence speed and search capability of an algorithm. Initially, the proposed 2D-SLCSCA is tested on eight classical benchmark test functions and its performance is compared with 1D Logistic map based chaotic SCA (1D-LCSCA), 1D Sine map based chaotic SCA (1D-SCSCA), and the SCA incorporating random variables. Test results reveal that the proposed algorithm exhibits better convergence characteristics, statistics, and execution time. Finally, the proposed 2D-SLCSCA is implemented for the LFC analysis of the islanded MG. To establish the competence of the proposed algorithm in this regard, its performance is compared with 2D Hénon map based chaotic SCA, 2D Lozi map based chaotic SCA, improved salp swarm algorithm (ISSA), SCA, grey wolf optimizer (GWO), and particle swarm optimization (PSO) algorithm considering diverse load disturbance patterns in the MG. Simulation results affirm that the proposed control scheme augments the frequency response of the MG exhibiting a maximum percentage improvement of 78.89%, 78.86%, and 96.51% in peak overshoot (OSpeak), peak undershoot (USpeak) and objective function (OFITSE) value, respectively as compared to the other algorithms. Furthermore, sensitivity of the proposed 2D-SLCSCA is validated considering ± 30% variation in the MG parameters.