Global Particle Swarm Optimization Research Articles

Embedded Feature Selection Approach Using Penalized Logistic Regression for Universal Steganalysis

For universal steganalysis, the Spatial Rich Model (SRM) provides a robust feature set in the form of 106 feature submodels (34671-dimensional) to attack highly secure steganography methods. Nonetheless, the curse of dimensionality emerges as a drawback, prompting researchers to explore feature selection methods to achieve optimal performance for steganalyzers. In previous work, a wrapper feature selection method using global and local best particle swarm optimization (GLBPSO) has been used to select 28 submodels of SRM out of 106 submodels. The 28 submodels contain a total of 9152 features and an ensemble classifier has been used for the classification results. In this study, an embedded feature selection and classification approach using logistic regression (LR) with an elastic net penalty has been proposed and applied to the 9152 features. The proposed approach efficiently selects an informative subset of 9152 features while training the LR classifier. This not only reduces the number of features by a significant 75% but also boosts the classification performance when contrasted with the ensemble classifier. The proposed approach achieves an accuracy of 87.41%, surpassing the current state-of-the-art steganalysis methods based on deep learning by a substantial margin of 3-7%. It also outperforms a recent machine learning-based steganalysis method by 13%.

A swarming neural network computing approach to solve the Zika virus model

In this work, a swarming computational procedure is presented for the numerical treatment of the dynamical model of the susceptible, exposed, infected, and recovered (SEIR) classes that portrayed the spreading of Zika virus. The artificial neural network procedures (ANNPs) have been applied to solve the SEIR mathematical model for spreading of the Zika virus together with the hybridization efficiency of global swarming and local search schemes. The global particle swarm optimization (PSO) and local search active-set algorithm (ASA) have been proposed to solve the model. An error based objective function is presented for the SEIR differential model and then optimized by the hybrid computing efficiency of PSO-ASA. Five neurons, fifteen variables of each class and ten numbers of trials have been used to solve the SEIR mathematical model for spreading of the Zika virus. The correctness of the proposed computing ANNPs-PSO-ASA is observed by using the comparison of the obtained and reference solutions along with the performances of the absolute error, ranges around 10−06 to 10−08. The reliability of the designed computing ANNPs-PSO-ASA technique is observed by using the statistical operator performances on single/multiple trials for the SEIR system for spreading of the Zika virus dynamics.

MalAnalyser: An effective and efficient Windows malware detection method based on API call sequences

Continuously evolving malware and their variants pose severe threats to information systems. API call sequence based methodologies perform well in malware detection but often suffer from high-dimensional feature sets or loss of information. Malware developers take advantage of this situation and use sophisticated coding/ obfuscation techniques to add, remove, and replace redundant API calls in malware and evade existing detection mechanisms. To address these concerns, we propose a novel and lightweight API call sequence-based Windows malware detection system, MalAnalyser. Specifically, it first extracts frequent API call subsequences (patterns) from API call sequences because frequent patterns filter superfluous API calls and highlight useful information about malware samples. Thereafter, it applies Global Local Best Particle Swarm Optimization (GLBPSO) algorithm on frequent patterns and identifies a small set of significant features that contribute to malware detection. Finally, MalAnalyser enriches frequent malware patterns using Genetic Algorithm (GA) to unveil unseen malware behavior. Extensive experimentation was conducted to evaluate the performance of MalAnalyser on different datasets and scenarios. GLBPSO considered two feature sets as input during experimentation: (i) the entire feature set and (ii) 60% randomly selected features from the entire set. Experimentation results prove that MalAnalyser attains up to 99.7% accuracy using approximately 30% features of the entire feature set. It is important to note that MalAnalyser achieves up to 100% accuracy on GA enriched feature set. Further, we evaluate the performance of MalAnalyser on a benchmark dataset, and the results proved that MalAnalyser outperforms similar approaches by achieving 99.72% accuracy. Additionally, we determined the suitability of MalAnalyser against a specific type of malware i.e. ransomware, and results showed that MalAnalyser performed remarkably well on ransomware dataset as well.

Nonlinear inversion of electrical resistivity sounding data for multi-layered 1-D earth model using global particle swarm optimization (GPSO)

Interpreting geophysical data requires solving nonlinear optimization problem(s) in inversion. Analytical methods such as least-square have some intrinsic limitations, which include slow convergence and dimensionality, making heuristic-based swarm intelligence a better alternative. Large-scale nonlinear optimization problems in inversion can be solved effectively using a technique within the swarm intelligence family called Particle Swarm Optimization (PSO). This study evaluates the inversion of geoelectrical resistivity data with global particle swarm optimization (GPSO). We attempted to invert field vertical electrical sounding data for a multi-layered 1-D earth model using the developed particle swarm optimization algorithm. The result of the PSO-interpreted VES data was compared with that of the least square inversion result from Winresist 1.0. According to the PSO-interpreted VES results, satisfactory solutions may be attained with a swarm of 200 or fewer particles, and convergence can be reached in fewer than 100 iterations. The GPSO inversion approach has a maximum capacity of 100 iterations, more than the least square inversion algorithm of the Winresist, which has a maximum capacity of 30 iterations. The misfit error of GPSO inversion is 6.14×10−7, much lower than that of the least square inversion of 4.0. The GPSO inversion model has lower and upper limit values of the geoelectric layer parameters model to fit the true model better. The limitations of the developed PSO inversion scheme include a slower execution time of the inversion procedures than the least-square inversion. There is a need for a priori knowledge of the number of layers from borehole reports in the study area. The PSO inversion scheme, however, estimates inverted models closer to the true solutions with greater accuracy than the least-square inversion scheme.

An improved variable forgetting factor recursive least square-double extend Kalman filtering based on global mean particle swarm optimization algorithm for collaborative state of energy and state of health estimation of lithium-ion batteries

An improved variable forgetting factor recursive least square-double extend Kalman filtering based on global mean particle swarm optimization algorithm for collaborative state of energy and state of health estimation of lithium-ion batteries

Parallel Global Best-Worst Particle Swarm Optimization Algorithm for solving optimization problems

The range of applications of swarm optimization algorithms is very vast. However, high dimensions and more number of decision variables make these optimization problems more complex. Particle Swarm Optimization (PSO) is the most popular optimizer for performing such types of optimization. PSO is motivated from the movement and intelligence of swarms. However, the primary constraint with the PSO and other swarm algorithms is enormous computational time (CT) due to more number of decision variables in complex problem. The number of steps inside Swarm Intelligence Algorithms (SIAs) also increase the complexity of computation in the process of optimization. Many iterations of the procedure of SIA need more CT since these algorithms are iterative in nature. In this study, a new Global Best-Worst Particle Swarm Optimization (GBWPSO) algorithm has been proposed so as to provide a fully version of parallel algorithm. GBWPSO algorithm is the combination of PSO and Jaya algorithm that provides a refined version of parallel algorithm having more parallelism. The proposed algorithm is executed on three different computational hardware with various combinations of population size and maximum number of iteration on five different standard benchmark functions. The evaluation is done on the basis of performance metrics such as speedup (S), real speedup (RS), maximum speedup (MS), efficiency (E), and scalability. The proposed parallel algorithm (P-GBWPSO) outperforms both parallel version of PSO and Jaya algorithm in terms of less CT and better optimal solution. Based on the results, we found that system 03 (S3) is best on proposed GBWPSO algorithm with an efficiency of 1.2518 compare with system 01 (S1) and system 02 (S2).

Multi-objective global and local Surrogate-Assisted optimization on polymer flooding

Oil production and polymer injection are two performance indicators of polymer flooding and are usually conflicting objectives. In order to obtain optimal trade-off solutions, this paper proposes a multi-objective global and local surrogate-assisted particle swarm optimization (MO-GLSPSO) method, which consists of alternative steps: global population prescreen and local population search.The global steps use generalized regression neural network (GRNN) to prescreen a better population, and the local steps use radial basis function (RBF) as proxy to search for the next generation. The global steps aim to reduce the chance of generations being trapped in local minima, and the local steps obtain the optimal solutions with a fast convergence rate. The rates (liquid production rate and water injection rate) and polymer injection concentration of wells are tuned to obtain a Pareto-front that maximizes cumulative oil production and minimizes cumulative polymer injection.The MO-GLSPSO method is tested using both synthetic and Brugge benchmark cases. The iterations generally improve the oil production or reduce polymer injection and are stabilized at a Pareto-front of the two objectives. Improved sweep efficiency and polymer utility are also observed in the optimal results. The proposed method is also compared with other two methods, multi-objective genetic algorithm (MOGA) and multi-objective particle swarm optimization (MOPSO), to examine the pros and cons. The results indicate that MO-GLSPSO has a better pareto-front than others.

A jerk-limited heuristic feedrate scheduling method based on particle swarm optimization for a 5-DOF hybrid robot

Compared with machine tools, five degrees-of-freedom (DOFs) hybrid robots have been widely concerned in the manufacturing of large complex surface parts due to their characteristics of high flexibility and large workspace. It is of great significance to schedule the time-optimal feedrate that satisfies the high-order constraints (e.g., jerk or jounce) in the toolpath and joint systems to achieve the high-precision and high-efficiency machining of the robot. To overcome the complexity of five-axis feedrate scheduling and improve the optimality of machining time, this paper proposes a jerk-limited heuristic feedrate scheduling (HFS) method with near-optimal time. Firstly, the analytical equations between all constraints and the parametric feedrate are derived, and the mathematical model for control points optimization of the parametric feedrate profile expressed by a B-spline curve is established. Then, combined with the global search particle swarm optimization (GSPSO) algorithm, a proposed moving window planning method optimizes a small number of control points so that the feedrate curve has enough rising space. Subsequently, to obtain the near time-optimal feedrate, the local search PSO (LSPSO) algorithm within the moving window is developed to locally adjust the non-uniformly inserted control points. Compared with the existing methods, the HFS method is beneficial to further optimize the machining time with a faster computation speed, and ensure the stability of the robot machining. Finally, simulations and experiments on the developed TriMule-800 hybrid robot verify the effectiveness of this method.

A stochastic numerical approach for a class of singular singularly perturbed system.

In the present study, a neuro-evolutionary scheme is presented for solving a class of singular singularly perturbed boundary value problems (SSP-BVPs) by manipulating the strength of feed-forward artificial neural networks (ANNs), global search particle swarm optimization (PSO) and local search interior-point algorithm (IPA), i.e., ANNs-PSO-IPA. An error-based fitness function is designed using the differential form of the SSP-BVPs and its boundary conditions. The optimization of this fitness function is performed by using the computing capabilities of ANNs-PSO-IPA. Four cases of two SSP systems are tested to confirm the performance of the suggested ANNs-PSO-IPA. The correctness of the scheme is observed by using the comparison of the proposed and the exact solutions. The performance indices through different statistical operators are also provided to solve the SSP-BVPs using the proposed ANNs-PSO-IPA. Moreover, the reliability of the scheme is observed by taking hundred independent executions and different statistical performances have been provided for solving the SSP-BVPs to check the convergence, robustness and accuracy.

Multivariate and Global Particle Swarm Algorithm Optimization in mmWave Massive MIMO for Angle Domain Channel Estimation

Exploitation of massive Multiple-Input Multiple-Output gains for downlink transmission in Millimetre Wave Systems comes at the expense of obtaining accurate channel estimation and computing complexity. Moreover, the fundamental task of massive Multiple-Input Multiple-Output channel estimation is to exploit the characteristics of the channel and sparsity of these multi-antennas systems to simplify complicated spatial structures. We tackle the channel estimation problem in constructing angle domain channel model with multivariate optimization. In the proposed global particle swarm optimization for angle domain aided scheme, the channel estimation design is decoupled into two parts The simulation results are provided to demonstrate the superior performance of the proposed algorithm over the traditional CS-based channel estimation methods.

Magnetic field analysis using the improved global particle swarm optimization algorithm to estimate the depth and approximate shape of the buried mass

In this paper, the optimization algorithm based on the population as improved global particle swarm optimization is described and used for inverse modelling of two-dimensional magnetic field data. This algorithm is able to estimate the parameters of depth, shape factor, amplitude coefficient, magnetic inclination angle and origin point coordinates. To evaluate the efficiency of this method, the magnetic field of an artificial model was analysed, with and without added random noise. The results suggest that the proposed algorithm is capable of model parameter estimation with high accuracy. Accordingly, the improved global particle swarm optimization algorithm was used to analyse the magnetic field of the study area in the Ileh region in Iran located in Taybad city. The study area is very rich in terms of iron resources. The estimate for the study area is that the depth of the buried mass centre is about 114.9 m and its approximate shape is similar to a horizontal cylinder based on the calculated shape factor value which is 1.76. The calculated depth is an acceptable match with the average depth of drillings.

Numerical treatment for the nonlinear fifth kind of multi-singular differential model: a neuro-swarming approach

In this study, a numerical scheme is proposed for the fifth order (FO) singular differential model (SDM), FO-SDM. The solutions of the singular form of the differential models are always considered difficult to solve and huge important in astrophysics. A neural network study together with the hybrid combination of global particle swarm optimization and local sequential quadratic programming schemes is provided to find the numerical simulations of the FO-SDM. An objective function is constructed using the differential FO-SDM along with the boundary conditions. The correctness of the scheme is observed by providing the comparison of the obtained and exact solutions. The justification of the proposed scheme is authenticated in terms of absolute error (AE), which is calculated in good measures for solving the FO-SDM. The efficiency and reliability of the stochastic approach are observed using the statistical performances to solve the FO-SDM.

A combined experimental and numerical approach that eliminates the non-uniqueness associated with the Johnson-Cook parameters obtained using inverse methods

Johnson-Cook constitutive model is a commonly used material model for machining simulations. The model includes five parameters that capture the initial yield stress, strain-hardening, strain-rate hardening, and thermal softening behavior of the material. These parameters are difficult to determine using experiments since the conditions observed during machining (such as high strain-rates of the order of 10^5/sec - 10^6/sec) are challenging to recreate in the laboratory. To address this problem, several researchers have recently proposed inverse approaches where a combination of experiments and analytical models are used to predict the Johnson-Cook parameters. The errors between the measured cutting forces, chip thicknesses and temperatures and those predicted by analytical models are minimized and the parameters are determined. In this work, it is shown that only two of the five Johnson-Cook parameters can be determined uniquely using inverse approaches. Two different algorithms, namely, Adaptive Memory Programming for Global Optimization (AMPGO) and Particle Swarm Optimization (PSO), are used for this purpose. The extended Oxley’s model is used as the analytical tool for optimization. For determining a parameter’s value, a large range for each parameter is provided as an input to the algorithms. The algorithms converge to several different sets of values for the five Johnson-Cook parameters when all the five parameters are considered as unknown in the optimization algorithm. All of these sets, however, yield the same chip shape and cutting forces in FEM simulations. Further analyses show that only the strain-rate and thermal softening parameters can be determined uniquely and the three parameters present in the strain-hardening term of the Johnson-Cook model cannot be determined uniquely using the inverse method. A combined experimental and numerical approach is proposed to eliminate this determine all parameters uniquely.

Joint optimization of constrained well placement and control parameters with a quantum-inspired cell-based quality gate function

Well placement and parameter optimization (WPPO) is an essential step in hydrocarbon, geothermal and water resources development which has complexities and difficulties. In fact, high computational cost can be the most important obstacle in WPPO problems. Population-based metaheuristics algorithms (PBMAs) are the most widely utilized ones for WPPO problems. However, these methods suffer from the issue that at each iteration, the minimum number of simulation run is at least equal to the population size. Knowing this, in order to enhance the efficiency of these methods, in this study, we introduced a cell-based quality gate function (CBQGF) which is inspired from quantum gates in quantum computing. The CBQGF is incorporated in our previously introduced inter-distance algorithm (IDC) which we called CBQG-IDC. Since, CBQG sets a condition for each location during the optimization process, locations with poor cell properties will be filtered out to increase the rate of convergence considerably. We applied the CBQG-IDC to two universally popular global optimization methods, genetic algorithm (GA) and particle swarm optimization (PSO) and compared the results to the IDC limited algorithm. In all scenarios, net present value (NPV) was considered as the fitness value and all joint optimization of locations and well associated parameters were conducted simultaneously. The results showed CBQG-IDC with a much higher rate of convergence compared to IDC, while its performance is highly dependent on constant parameters. Ultimately, the proposed CBQG-IDC can be applied to any optimization algorithm for any placement optimization problem in Euclidian geometry to save the computational cost. • A cell-based quality gate function (CBQGF) has been introduced to optimization process. • The proposed CBQGF can be coupled with any arbitrary optimization and applied to any placement optimization problem. • The CBQGF has increased the rate of convergence significantly with substantial computation cost saving. • The threshold value of the cell property and its associated constant have great influence on the search flexibility.

Many-Objective Adaptive Fuzzy With Sliding Mode Control for a Class of Switching Power Converters Using Global Optimization

Control of the power converters in renewable energy systems for stability and efficiency poses a technical challenge due to the intermittency of energy produced and inherent nonlinear dynamics. This paper presents a parametric optimization framework amid the synthesis of an adaptive fuzzy with sliding mode controller for a class of switching power converters suited for renewable energy systems. Four performance metrics essential to the practical needs are suggested. The potential design parameters of the controller are determined, and their influences on the performance metrics are studied and validated. A many-objective optimization problem is formulated accordingly, and a computational platform based on MATLAB/Simulink environment is established to solve the problem. Two multi-objective global search algorithms, i.e., particle swarm and bat optimization, are employed to obtain a set of Pareto optimal controllers, which noticeably enhance the performance metrics of the control system. An experimental platform with dSPACE controller board is utilized to further justify the simulation results. With those optimal controllers, the experimental results also demonstrate improvement of the performance.

Feature reduction of rich features for universal steganalysis using a metaheuristic approach

The development of content adaptive steganographies has become a challenge for steganalysis. This led researchers towards extraction of a rich space of features. The detection of stego images based on spatial rich model (SRM) features and its variants is a promising research area in the field of universal steganalysis. SRM features are extracted as 106 sub-models which collectively provide 34,671 features. So, one of the most significant challenges in universal steganalysis is feature selection. In this paper an improved binary particle swarm optimisation, global and local best particle swarm optimisation (GLBPSO) with Fisher linear discriminant classifier is used to identify relevant feature sub-models which improve the efficiency of a steganalyser. The significant reduction rate of more than 70% is achieved by the proposed approach. This further helps in reducing computational complexity without much affecting the detection capability. The proposed methodology gives superior results when compared with state-of-the-art algorithms.

Swarming Computational Efficiency to Solve a Novel Third-Order Delay Differential Emden-Fowler System

The purpose of this research is to construct an integrated neuro swarming scheme using the procedures of the artificial neural networks (ANNs) with the use of global search particle swarm optimization (PSO) along with the competent local search interior-point programming (IPP) called as ANN-PSOIPP. The proposed computational scheme is implemented for the numerical simulations of the third order nonlinear delay differential Emden-Fowler model (TON-DD-EFM). The TON-DD-EFM is based on two types along with the particulars of shape factor, delayed terms, and singular points. A merit function is performed using the optimization of PSOIPP to find the solutions to the TON-DD-EFM. The effectiveness of the ANN-PSOIPP is certified through the comparison with the exact results for solving four examples of the TON-DD-EFM. The scheme’s efficiency is observed by performing the absolute error in suitable measures found around 10−04 to 10−07. Furthermore, the statistical-based assessments for 100 trials are provided to compute the accuracy, stability, and constancy of the ANN-PSOIPP for solving the TON-DD-EFM.

Particle Swarm Optimization Video Streaming Service in Vehicular Ad-Hoc Networks

Owing to the increasing capabilities of mobile devices and the development of mobile communication techniques in vehicular ad hoc networks (VANETs), mobile multimedia services have focused on supporting high Quality of Service (QoS) and Quality of Experience (QoE) for the subscribers in video streaming services. In VANETs, high-quality video streaming services aim to provide safety, as well as various infotainment applications to the subscribers. Owing to the dynamic topology and frequent connectivity changes in moving vehicles, video streaming services require elastic and continuous updates of vehicle information to present interactive real-time views of nontrivial scenarios on roads. To achieve high QoS and QoE of video streaming services in VANETs, this paper proposes a novel protocol named PSOstreaming that is based on a particle swarm optimization (PSO) which is one one of the mainstream and nature-inspired algorithms for swarm intelligence (SI). PSOstreaming calculates the PSQ score, which is the scoring method of the node in the topology in terms of the data communication capability measurement to analyze and optimize topology information in real-road circumstances. In addition, PSOstreaming utilizes a 3D vector mobility prediction algorithm for the mobility prediction method for the vehicles to address the characteristics of VANETs. In the topology, PSOstreaming defines Global PSO members and Local PSO members to disseminate video packets for video-streaming services to the service requester by computational equations. Experimental results indicate that PSOstreaming achieves high-quality video streaming services with a flexible response to dynamic topology changes and a high frame delivery ratio in terms of QoS and QoE.

B2S3 monolayer: a two-dimensional direct-gap semiconductor with tunable band-gap and high carrier mobility

Atomically two-dimensional materials with direct band-gap and high carrier mobility are highly desirable due to their promising applications in electronic devices. Here, on the basis of ab initio calculations and global particle-swarm optimization method, we predict the B2S3 monolayer as a new semiconductor with favorable functional properties. The B2S3 monolayer possesses a high electron mobility of 553 cm2 V−1 s−1 and a direct band-gap of 1.85 eV. The direct band-gap can be manipulated under biaxial strain. Furthermore, B2S3 monolayer can absorb sunlight efficiently in the entire range of the visible light spectrum. Besides, this monolayer holds good dynamical, thermal, and mechanical stabilities. All the desired properties render B2S3 monolayer a promising candidate for future applications in high-speed (opto)electronic devices.

Application of Surrogate Optimization Routine with Clustering Technique for Optimal Design of an Induction Motor

This paper proposes a new surrogate optimization routine for optimal design of a direct on line (DOL) squirrel cage induction motor. The geometry of the motor is optimized to maximize its electromagnetic efficiency while respecting the constraints, such as output power and power factor. The routine uses the methodologies of Latin-hypercube sampling, a clustering technique and a Box–Behnken design for improving the accuracy of the surrogate model while efficiently utilizing the computational resources. The global search-based particle swarm optimization (PSO) algorithm is used for optimizing the surrogate model and the pattern search algorithm is used for fine-tuning the surrogate optimal solution. The proposed surrogate optimization routine achieved an optimal design with an electromagnetic efficiency of 93.90%, for a 7.5 kW motor. To benchmark the performance of the surrogate optimization routine, a comparative analysis was carried out with a direct optimization routine that uses a finite element method (FEM)-based machine model as a cost function.