Search

Intrusion Detection System (IDS) can ensure the network security by identifying network intrusions according to the abnormal traffic data. However, the intrusion detection data has the problem of high dimensionality and changes with network and attack environments, which leads to the poor performance and poor portability of intrusion detection algorithms. Therefore, this paper proposes an intrusion detection algorithm based on joint symmetric uncertainty and hyperparameter optimized fusion neural network. Firstly, a feature selection method based on symmetric uncertainty and approximate Markov blanket is proposed, which fully considers the correlation and redundancy of features, and also the correlation between combined features and the class label, so as to reduce the data dimensionality. Secondly, the CNN-LSTM classifier fused with Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is used to extract the spatial features and temporal features to improve the classification performance. Finally, the Particle Swarm Optimization (PSO) algorithm is improved and used to automatically optimize the hyperparameters of the classifier, so that the classifier can be applied to different intrusion detection datasets with better generalization ability and portability. Experiments have verified the effectiveness and superiority of the proposed algorithm on multiple evaluation indicators. • An effective algorithm for intrusion detection is proposed in this paper. • Feature selection is based on symmetric uncertainty and approximate Markov blanket. • A fusion neural network is constructed to extract the spatial and temporal features. • The PSO algorithm is improved to automatically optimize the hyperparameters. [ABSTRACT FROM AUTHOR]

• Distinct DG Output Modes Validation: The simulation validates distinct DG output modes, impacting prediction. • Mode-Based State Estimation: The paper proposes an innovative mode-based state estimation using IPSO-DBSCAN clustering, overcoming k-means limitations. • Enhanced Data Recovery using DBSCAN: Enhanced data recovery employs DBSCAN with improved secondary clustering, guided by similarity and homogeneity, outperforming traditional methods. • BiGRU-PF State Estimation: BiGRU-PF enhances state estimation accuracy and robustness in distribution networks by detecting DG output modes, addressing k-means limitations, and improving data recovery. This paper proposes a new forecasting-aided state estimation (FASE) method for distribution systems that mitigates issues with uncertain distributed generation (DG) and lost measurements. We utilize an Improved Particle Swarm Optimization (IPSO)-optimized Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for examination of historical DG output data. Based on identified DG output modes, it facilitates precise state prediction and data reconstruction,. The proposed method employs a Bidirectional Gated Recurrent Unit (BiGRU) neural network for state prediction and a particle filter (PF) for final state filtering. The method verification is provided through Python simulations of the Distribution Transformer Unit (DTU)7k distribution network system, demonstrating improved accuracy and robustness against sudden load change and bad data in measurements. [ABSTRACT FROM AUTHOR]

• A novel MPPT controller based on yellow saddle goatfishes algorithm (YSGA) for energy optimization of PV systems. • Qualitative and quantitative comparison of YSGA with BAT,GWO,SOA,PSO, and P&O under partial shading condition. • Statistical analysis based on: the average best so far (AB), the median best so far (MB), and standard deviation (SD). • Wilcoxon test with 5% significance level based on the median value is applied to verify the superiority of the algorithm. This paper proposes a novel maximum power point tracking (MPPT) technique based on a new optimization algorithm called yellow saddle goatfish algorithm (YSGA). The photovoltaic system loses a significant amount of power under partial shading conditions (PSC). Because of the presence of bypass diodes, several maximums appear in the Power-Voltage characteristic, making tracking the global maximum power point (GMPP) extremely difficult. A yellow saddle goatfish-based MPPT algorithm is proposed and implemented to address this issue and improve the efficiency of the PV system. This algorithm employs a subgroup research methodology and a very interesting strategy of particle collaboration during GMPP tracking, providing a balance between the exploration and exploitation phases of the research process. To investigate its performance, tests were conducted using six different partial shading patterns and a fast irradiance variation. The simulation was carried out in MATLAB/Simulink using a series of MSX60 solar panels. The results were compared to well-known and efficient algorithms such as the Grey wolf optimization algorithm (GWO), the Bat algorithm (BAT), particle swarm optimization (PSO), the Seagull optimization algorithm (SOA), and the Perturb and observe (P&O) algorithm. The findings demonstrate the proposed method's high robustness, as well as its high dynamic and accuracy in tracking the GMPP. Furthermore, a quantitative and statistical analysis of 100 tests revealed that it outperformed the other algorithms in terms of efficiency, success rate, convergence time, and solution dispersion. [ABSTRACT FROM AUTHOR]

• An advanced shuffled frog leaping algorithm (DSSRLFLA) is developed for model evaluation and feature selection. • A dynamic step size adjustment strategy based on historical information is designed to balance exploration and exploitation. • Specular reflection learning mechanism increases the possibility of searching for valid solutions and enhances the search ability. • An improved simulated annealing strategy is executed for each memetic to improve the efficiency of local exploitation. • DSSRLFLA can obtain higher quality optimal solutions compared to some competitive algorithms. The shuffled frog leaping algorithm is a new optimization algorithm proposed to solve the combinatorial optimization problem, which effectively combines the memetic algorithm based on a memetic algorithm and the particle swarm algorithm based on population behavior. The algorithm is widely used because it is easy to implement and requires few parameters to be adjusted. However, there are still some characteristics of this method that need to be improved because it is easy to fall into local optimization or poor search ability. To alleviate this limitation, a new version of the improved SFLA is proposed in this paper, which incorporates a dynamic step size adjustment strategy based on historical information, a specular reflection learning mechanism, and a simulated annealing mechanism based on chaotic mapping and levy flight. Firstly, the dynamic step size adjustment strategy based on historical information effectively helps to balance local exploration and global exploitation and alleviates the problem of falling into local optimum. Second, the specular reflection learning mechanism increases the possibility of searching for valid solutions in feasible domains and enhances the search ability of individuals in the population. Finally, an improved simulated annealing strategy is executed for each memetic, which improves the efficiency of local exploitation. In order to test the performance of the proposed algorithm, 31 test functions were selected from IEEE CEC2014 and 23 essential benchmark functions, and comparative experiments were carried out from the two dimensions of 30 and 100. Furthermore, a series of competing algorithms are selected, which involve nine classical standard algorithms, including PSO, BA, SSA, FA, SCA, WOA, GWO, MFO, and SFLA, as well as, six well-known improved algorithms, including LSFLA, DDSFLA, GOTLBO, ALCPSO, BLPSO, CLPSO. Furthermore, Wilcoxon signed-rank test and Friedman test are used as testing tools to illustrate the scalability of the proposed algorithm. From the analysis of the results, it can be seen that this proposed method has been effectively improved concerning stability and the quality of the optimal solution obtained from the search, both in low and high dimensions, and the ability to jump out of the local optimum has also been enhanced. In addition, to prove that this method has a reliable performance in discrete problems and continuous problems, DSSRLFLA is mapped into a discrete space, and 24 UCI data sets are also selected to evaluate the performance of the new feature selection method. The experimental results illustrate that this improved method can obtain fewer features and higher classification accuracy than some well-known feature selection methods. [ABSTRACT FROM AUTHOR]

This paper considers the inverse p -median location problem with variable edge lengths and variable vertex weights on general graphs in which the modification costs are the fuzzy random variables. We present a model for the problem in fuzzy random environment in which the objective value is computed by conditional value at risk criterion. Then, we show that the problem is NP-hard under this criterion. Therefore, a new hybrid modified particle swarm optimization algorithm is proposed to obtain the approximate optimal solution of the proposed model. Finally, computational experiments are given to illustrate high efficiency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

PSO (particle swarm optimization), is an intelligent search method for finding the best solution according to population state. Various parallel implementations of this algorithm have been presented for intensive-computing applications. The ALC-PSO algorithm (PSO with an aging leader and challengers) is an improved population-based procedure that increases convergence rapidity, compared to the traditional PSO. In this paper, we propose a low-power heterogeneous parallel implementation of ALC-PSO algorithm using OmpSs and CUDA, for execution on both CPU and GPU cores. This is the first effort to heterogeneous parallel implementing ALC-PSO algorithm with combination of OmpSs and CUDA. This hybrid parallel programming approach increases the performance and efficiency of the intensive-computing applications. The proposed approach of this article is also useful and applicable for heterogeneous parallel execution of the other improved versions of PSO algorithm, on both CPUs and GPUs. The results demonstrate that the proposed approach provides higher performance, in terms of delay and power consumption, than the existence implementations of ALC-PSO algorithm. [ABSTRACT FROM AUTHOR]

• Differential privacy and deep learning are combined to alleviate the problem of model privacy leakage. • Differential evolution is used to optimize the learning rate, accelerate the model convergence, and avoid the privacy loss. • The particle swarm optimization method is used to find the optimal weight that satisfies the privacy. • The algorithm in this paper is verified on three data sets, and the accuracy and efficiency are better. In deep learning differential privacy protection, adding noise based on gradient has become a mainstream algorithm, but excessive gradient perturbation noise causes accuracy degradation. To solve this problem, a differential privacy protection algorithm based on differential evolution and particle swarm optimization is proposed to realize hyperparameter optimization in differential privacy, reduce the impact of noise on the model, and effectively improve the accuracy. On the one hand, the differential evolution scheme performs selection, crossover and mutation on learning rate η , make it approach the global optimal solution, and improve the computational efficiency of the algorithm. On the other hand, the particle swarm optimization scheme is adopted. Without changing the parameters and gradient structure, the parameters are optimized by using the network propagation attributes, which reduces the influence of noise on the accuracy. Experiments are performed on three datasets: Cifar10, Mnist and FashionMnist. Compared with the existing differential privacy algorithms, under the same privacy budget, the proposed algorithm has better accuracy and higher efficiency. [ABSTRACT FROM AUTHOR]

Artificial rabbits optimization (ARO) is a swarm intelligence-based algorithm inspired by the survival strategies of rabbits. Although ARO has a good convergence rate, it is prone to get stuck in the local optima and converge prematurely. To overcome this, the present paper redesigns the exploration operator of the ARO algorithm with the roulette fitness-distance balance (RFDB) and dynamic fitness-distance balance (d FDB) strategies. In this context, three different versions of the fitness-distance balance-based artificial rabbits optimization (FDBARO) algorithm are developed. The performance of the original ARO and FDBARO versions (FDBARO-1, FDBARO-2, and FDBARO-3) are evaluated on CEC 2017 and CEC 2020 benchmark functions. The obtained results are analyzed with the Wilcoxon and Friedman statistical tests. Statistical and convergence analysis results showed that the FDBARO-3 algorithm designed with the d FDB selection method can explore the search space more successfully compared to other algorithms. This version was named the dynamic FDBARO (d FDBARO) algorithm. Moreover, the practicability of the proposed d FDBARO is highlighted by the solution of the optimal power flow (OPF) problem formulated with renewable energy sources (RESs) and flexible alternating current transmission system (FACTS) devices considering fixed and uncertain load demands. Experimental results showed that the proposed d FDBARO is a competitive algorithm for solving global optimization and constrained OPF problems. The source code of the d FDBARO algorithm is available at https://www.mathworks.com/matlabcentral/fileexchange/154845-dfdbaro-an-enhanced-metaheuristic-algorithm. [ABSTRACT FROM AUTHOR]

• In this paper, the optimized GWO-MCSVM assessment model is constructed step by step, and the nonlinear convergence factor is used to replace the conventional convergence factor in the Grey Wolf algorithm and the thought of parameter initialization by tent chaotic mapping, which makes it more suitable for the data analysis of transformers. The improved GWO-MCSVM model ensures the rapidity and reliability of assessment. • The initialization of model parameters based on Tent chaotic map completes the preprocessing of model input data, determines the initial parameter selection of GWO parameter optimization process, and improves the optimization speed of the algorithm. • The parameters of GWO-MCSVM model are optimized through training samples of transformer operation parameters in practical projects, and the GWO-MCSVM model is tested through groups of test samples. Compared with the existing GA-SVM model and PSO-SVM model, it is verified that the model has high accuracy (accuracy rate is more than 90%) in transformer condition assessment, is superior to the existing assessment model, and has bright scalability. The continuous and reliable operation of the transformer is the basis to ensure the normal operation of the power system. Relevant departments collect multi-dimensional and multi-source heterogeneous parameter data during the operation, maintenance and repair of transformers. The effective information contained in the parameter data can directly reflect the current operating status of the transformer. On the basis of support vector machine and grey wolf algorithm, an improved GWO-MCSVM algorithm based on nonlinear convergence factor and Tent chaotic mapping is proposed. The algorithm parameters are optimized through training samples, and the results are evaluated and verified in the algorithm itself, so as to improve the accuracy of the status assessment results. Finally, the accuracy of assessment results of the algorithm proposed in this paper, existing genetic algorithms and particle swarm optimization algorithms are compared by evaluating multiple sets of measured samples. By comparison, the effectiveness of the algorithm proposed in this paper for transformer condition assessment has been verified. [ABSTRACT FROM AUTHOR]

In this paper, a new approach is proposed for the smooth path planning of mobile robot based on a new quartic Bezier transition curve and an improved particle swarm optimization (PSO) algorithm. First, a dedicatedly constructed quartic Bezier transition curve with three overlapped control points is developed to fulfil the G 3 -continuity of the smooth path at the joints of the path segments, so as to guarantee the high-order smoothness of the path for the movement of mobile robot. Then, the smooth path planning of mobile robot is formulated mathematically as an optimization problem under several criteria and constraints of the smooth path, e.g. length, smoothness, safety and robot kinematics. Furthermore, an improved PSO with adaptive weighted delay velocity (PSO-AWDV) algorithm is presented for the optimization problem of smooth path planning, where the parameter relationship to ensure the convergence of PSO-AWDV is derived through the stability analysis of the algorithm. Finally, several simulation experiments are carried out to confirm the effectiveness and superiority of the proposed new approach combined with the new quartic Bezier transition curve and the improved PSO-AWDV algorithm. [ABSTRACT FROM AUTHOR]

This paper proposes a novel hybrid algorithm which is mathematically modelled by amalgamating the superior features of recently developed Grey Wolf Optimizer (GWO), Sine Cosine Algorithm (SCA), and Crow Search Algorithm (CSA). Researchers have already implemented the aforementioned three algorithms and obtained superior quality results for solving diverse optimization problems. The novel hybrid Variegated GWO Algorithm (VGWO) developed in this proposed research work is initially realized and validated for solving IEEE CEC-C06 2019 benchmark functions. Thereafter, the proposed VGWO is utilized as an optimization tool to solve three emerging and complex power system optimization problems which includes energy management of microgrid systems operated in both islanded and grid-connected mode, dynamic economic emission dispatch and reactive power planning (RPP) problem. A comparative analysis of the proposed VGWO approach with other established metaheuristics is undertaken for each optimization problem. Numerical results show that the novel hybrid VGWO algorithm outperformed an ample number of optimization techniques in providing better quality solutions. The proposed hybrid algorithm yielded a 36.93% reduction in active power loss and 36.80% reduction in operating cost with respect to base case condition for RPP problem. Likewise while solving microgrid energy management problems 9–30% savings was realized in the generation cost compared to the ones mentioned in literature. The capability of handling many complex constraints within a minimum amount of computational time to provide consistently best solutions prioritize the proposed hybrid algorithm among its kinds. Statistical analysis validates the authenticity and viability of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper presents an efficient inverse design method of arrayed waveguide grating (AWG) based on BPNN-PSO. Five important structural parameters of AWG are selected as inputs, and the spectral responses of three output channels are used as outputs. A forward network is trained, and the prediction accuracy of the network is improved by optimizing the number of hidden layer neurons. By combining the forward network with the traditional particle swarm optimization (PSO) algorithm, a series of structure designs targeting the desired performance can be generated. This method significantly improves the efficiency and accuracy of the PSO algorithm by introducing neural networks, making it suitable for efficient inverse design and multi-structure analysis of AWG. • Combining BPNN and PSO for AWG inverse design. • Training the forward network to replace the electromagnetic simulation process significantly reduces design time. • The design requirements for AWG allow for both spectral response and desired performance. • This method enables the multi-solution design of AWG according to the desired performance. [ABSTRACT FROM AUTHOR]

Natural frequencies, which are relatively easy parameters to obtain, provide efficient information about the dynamic behavior of structures. Controlling these parameters can help to minimize the destructive effect of dynamic loads on structures. However, the optimal design of the size and shape of truss structures with controlling dynamic constraints is an expensive problem. While frequency constraints are nonlinear and non-convex, handling natural frequencies as constraints is a challenging task, which prevents the phenomenon of resonance, large deformations, and destruction of a structure. Also, reducing the vibration amplitude of a structure would reduce the stress and deflections. In this paper, the Improved Marine Predators Algorithm (IMPA) is proposed and implemented for size and shape optimization of truss structures subject to natural frequency constraints. In this method, a Novel CF (NCF) factor is introduced to control the predator's step size when looking for prey. To evaluate the performance of IMPA, the optimum weight of structures under dynamic constraints was computationally investigated. To demonstrate the efficiency and robustness of IMPA, 37-bar truss bridge, 52-bar dome, 72-bar space truss, 120-bar dome, 200-bar planar truss, and 600-bar dome truss were optimized. Compared to other state-of-the-art algorithms, the results indicate that IMPA performs better in solving these nonlinear structural optimization problems. • Marine Predators Algorithm Improved based on a new strategy. • A novel formula is proposed for CF factor. • engineering problems with dynamic constraints are investigated to prove the capabilities of new swarm algorithm. • The results are compared with state-of-the-art swarm algorithms. [ABSTRACT FROM AUTHOR]

Cloud data center comprises various physical and virtual machines, alongside storage datacenter services provided by cloud providers. Effectively mapping tasks to optimize resource utilization and load balance is essential for efficient task scheduling. This process, referred to as scheduling constraints, can significantly enhance overall efficiency. However, to harness the benefits of this scheduling, one must address the challenges arising during task execution. The interdependencies between tasks and the diverse resources available in the datacenter pose significant hurdles to efficient resource allocation. To address these challenges, this paper introduces the Hybrid HEFT-PSO-GA algorithm (HEPGA), aiming to efficiently allocate tasks to available resources across the datacenter. The HEPGA algorithm builds upon prior research by integrating the strengths of PSO (Particle Swarm Optimization) and GA (Genetic Algorithm) to optimize task scheduling in cloud computing environments. Through the fusion of PSO, GA, and HEFT-based Initialization, the algorithm strives to efficiently allocate tasks to processors, thereby minimizing the makespan. This approach capitalizes on parallel processing capabilities to further enhance resource utilization in the cloud environment. By varying the weights of the fitness function and considering the resources within the datacenter, we meticulously analyze the algorithm's performance concerning both makespan and Resource Utilization (RU). The results of these tests underscore the algorithm's consistent and robust resource utilization across diverse weight configurations, highlighting its adaptability to varying priorities. Moreover, the observed variations in makespan performance based on different weights emphasize the algorithm's potential for excellence when tailored to specific optimization goals. [ABSTRACT FROM AUTHOR]

Trajectory similarity analysis of moving target is the foundation for mining high-value and regular behavioral information such as motion preferences, activity hotspots and frequent paths. Unlike most trajectory similarity analysis methods aimed at discovering correlations of target activities in time, space or spatio-temporal domains, this paper focuses on the shape matching of target trajectories. If some specific shapes frequently appear in historical trajectories, extracting these local shapes would be beneficial for analyzing the target motion templates and behavior modes. Trajectory segments with similar shapes may not have spatio-temporal correlation, and the shapes also have geometric transformation characteristics such as rotation, scaling and translation. Since the existing trajectory similarity analysis methods cannot be directly applied, an algorithm for extracting similar segments based on shape matching is proposed. First, a new shape descriptor based on signed barycenter distance (SBD) is established. It describes a trajectory as a one-dimensional shape feature sequence, which has the advantage of low computational complexity. Then, the distributed nearest neighbor search strategy is used in the particle swarm optimization (PSO) method, which aims to accelerate the retrieval of trajectory segments with similar shapes and improve the matching accuracy. Experiments on MPEG-7, handwritten character and maneuvering target simulation trajectory data sets show that compared with the existing typical shape descriptors, SBD shape descriptor has advantages in accuracy and noise insensitivity, and the improved PSO method can efficiently and accurately obtain the local shape matching results. [ABSTRACT FROM AUTHOR]

Find the global optimal solution of the model is one promising research topic in computational intelligent community. Dependent on analogies to natural processes, the evolutionary swarm intelligent algorithms are widely used for solving global optimization problems which directed by the fitness values. In this paper, we propose one efficient fractional global learning machine (Fragmachine) which includes two stages (descending and ascending) to determine the optimal search path. The neural network model is used to approach the given fitness value. Specifically, for the descending stage, the integer gradient of the network output with respect the current location is employed to find the next descending point, while for the ascending stage, the fractional gradient is implemented to climb and escape from the local optimal point. We further propose one adaptive learning rate during training which relies on both the current gradient (integer or fractional) information and the fitness value. Finally, a series of numerical experiments verify the effectiveness of the proposed algorithm, Fragmachine. [ABSTRACT FROM AUTHOR]

In this paper, the far-distance nonplanar rapid cooperative rendezvous with multiple specific-direction thrusts is investigated. In the optimization process, the indirect method is adopted. The homotopy method is used to smooth the dynamical equations. The solutions of the initial co-state variables of the energy-optimal problem are obtained by the quantum-behaved particle swarm optimization (QPSO) algorithm. Sequential quadratic programming (SQP) algorithm is coupled into the homotopy method to overcome the difficulty in nonsmooth integration when the thrust switches on & off frequently. The solutions of the fuel-optimal problem are obtained by the homotopy-SQP coupled method. The simulation results show the feasibility of the cooperative rendezvous with multiple specific-direction thrusts. The "suitable point" of normal thrust is investigated. [ABSTRACT FROM AUTHOR]

In this paper, a hybrid algorithm was proposed for multi-objective optimization design with high efficiency and low computational cost based on the Gaussian process regression and particle swarm optimization algorithm. For the proposed method, the global performance indices, including regular workspace volume, global transmission index, global stiffness index, and global dynamic index were considered as objective functions. First, the multi-objective optimization problem considering the boundary conditions, objective, and constraint functions was constructed. Second, the Latin hypercube design was regarded as the design of experiment to obtain the computer sample points. Besides, the high-precision objective-function values were obtained by increasing the node density in the workspace at these sample points to provide sufficient information for the mapping model. Third, the Gaussian process regression was proposed to build the mapping model between the objective functions and the design parameters, thus reducing the computational cost of global performance indices. Cross-validation and external validation were adopted to verify the mapping model. Finally, the hybrid algorithm combined with the Gaussian process regression and particle swarm optimization algorithm was proposed for multi-objective optimization design. The 2PRU-UPR parallel manipulator was taken as a case to implement the proposed method (where P was a prismatic joint; R a revolute joint; U a universal joint). The comparison from the back propagation neural network, multivariate regression, and Gaussian process regression mapping models showed that the Gaussian process regression model had higher accuracy and robustness. The proposed hybrid algorithm saved 99.84% of computational cost compared to using the particle swarm optimization algorithm. The Pareto frontier of the multi-objective optimization problem of the 2PRU-UPR parallel manipulator was also obtained. After optimization , the performance indices were significantly improved. • A mapping modeling between objective functions and design parameters based on Gaussian process regression is proposed. • A multi-objective optimization design method combined with the mapping model and particle swarm algorithm is proposed. • The proposed method can significantly reduce the computational cost for the high computation-intensive design problems. • A study on the comparison of the robustness and accuracy among the three mapping models is carried out. • The three mapping models are multivariate regression, BP neural network, and Gaussian process regression models. [ABSTRACT FROM AUTHOR]

In this study, an energy efficiency study has been carried out through the moment values of a quadrotor applied in the position control with the differential evolution algorithm (DE), which is under the evolutionary algorithms among meta-heuristic algorithms particle swarm optimization (PSO) which is among swarm-based algorithms and gravity search algorithm (GSA) among physics-based algorithms and charged system search (CSS) algorithm, which are all well-known in the literature. The efficient use of energy in electrically powered flying mechanisms is important in terms of completing its task. The aim of this study is to obtain proportional–integral–derivative (PID) coefficients that minimize the energy consumption caused by quadrotor moments. First of all, 12 PID coefficients calculated with traditional Ziegler Nicholes, and trying-error methods for the control of the quadrotor have been trained with DE, PSO, GSA and CSS algorithms and their cost values have been found for this problem. In the study, optimum PID coefficients have been found separately with each algorithm and torque data giving energy efficiency have been obtained by applying them to the state equations. Although the cost minimization convergence value obtained from DE does not look good compared to other algorithms, it has been observed that the moment values of the obtained PID coefficients in the control program are lower. In the study, it has been shown that the PID coefficients obtained from DE reach the target with approximately less energy than the maximum-moment value of the PSO, which provides the closest moment value. It can be thought that this value contributes to energy consumption in each orbital movement of the quadrotor. The simulation results show that the coefficients obtained from DE provide better energy efficiency and are superior to other algorithms compared in terms of energy efficiency. • PID coefficients for quadrotor control are optimized with DE,PSO,CSS,GSA algorithms • The torque values to be applied to each motor were adjusted with these coefficients • The total force applied with DEPID in the z direction is smaller than others • DEPID consumes less energy than the other algorithms in the paper [ABSTRACT FROM AUTHOR]

In this study, an energy efficiency study has been carried out through the moment values of a quadrotor applied in the position control with the differential evolution algorithm (DE), which is under the evolutionary algorithms among meta-heuristic algorithms particle swarm optimization (PSO) which is among swarm-based algorithms and gravity search algorithm (GSA) among physics-based algorithms and charged system search (CSS) algorithm, which are all well-known in the literature. The efficient use of energy in electrically powered flying mechanisms is important in terms of completing its task. The aim of this study is to obtain proportional–integral–derivative (PID) coefficients that minimize the energy consumption caused by quadrotor moments. First of all, 12 PID coefficients calculated with traditional Ziegler Nicholes, and trying-error methods for the control of the quadrotor have been trained with DE, PSO, GSA and CSS algorithms and their cost values have been found for this problem. In the study, optimum PID coefficients have been found separately with each algorithm and torque data giving energy efficiency have been obtained by applying them to the state equations. Although the cost minimization convergence value obtained from DE does not look good compared to other algorithms, it has been observed that the moment values of the obtained PID coefficients in the control program are lower. In the study, it has been shown that the PID coefficients obtained from DE reach the target with approximately less energy than the maximum-moment value of the PSO, which provides the closest moment value. It can be thought that this value contributes to energy consumption in each orbital movement of the quadrotor. The simulation results show that the coefficients obtained from DE provide better energy efficiency and are superior to other algorithms compared in terms of energy efficiency. • PID coefficients for quadrotor control are optimized with DE,PSO,CSS,GSA algorithms • The torque values to be applied to each motor were adjusted with these coefficients • The total force applied with DEPID in the z direction is smaller than others • DEPID consumes less energy than the other algorithms in the paper [ABSTRACT FROM AUTHOR]

• Modeling artificial upwelling efficiency under crossflow. • Optimized nozzle layout improves upwelling efficiency. • Discrete particle swarm algorithm enhances carbon sequestration. • Increasing nozzles will improve performance, but raises investment cost. • Reference for engineering design of artificial upwelling. Artificial upwelling (AU) is widely recognized as a geoengineering tool to enhance oceanic fertility and stimulate the earth's capability of self-healing. Several air-lifted AU systems have been established to promote seaweed growth and facilitate carbon sequestration, for instance, in Norway and China. However, few researchers have addressed the critical issue of optimizing the layout of the underwater nozzle array (UNA), a key component of the air-lifted AU system. In this paper, we propose a novel method to optimize the layout of UNA by introducing and improving the discrete particle swarm optimization (DPSO) algorithm to guide the optimal nozzle positions. Furthermore, we develop the nutrient transport efficiency model to evaluate the performance of the AU system and apply it to investigate a typical AU system, namely the one in Aoshan Bay, China. Our results demonstrate that the proposed DPSO algorithm outperforms the conventional particle swarm optimization algorithm and the nutrient transport efficiency under the optimized UNA layouts was improved by an average of 14.5% to 35.0% compared to randomly generated layouts. These findings suggest that our optimization method could serve as a scientific reference for the engineering design of AU. [ABSTRACT FROM AUTHOR]

In this paper, a projection-based distributed algorithm is proposed to solve the economic dispatch problem of power system with communication delays under switching topologies. The algorithm is suitable for economic dispatch problem with strongly convex cost function, and ensures that the output power of each generator is always kept within its output limit. In addition, the topology is only required to be jointly connected. Firstly, the relationship between the equilibrium point and the optimal solution of the algorithm is analyzed, and then a common Lyapunov function is introduced for a set of switching topologies. According to the Lyapunov stability theory and Cauchy convergence criterion, LMIs-based sufficient conditions for the convergence of the algorithm are obtained. Finally, the effectiveness of the algorithm under different cases are verified by MATLAB simulation results. • The economic dispatch under switching topology with communication delay is studied. • A projection-based distributed algorithm with is proposed to solve the problem. • The communication topology is only required to be jointly connected. • The delay-dependent LMI conditions for the convergence of the algorithm are obtained. • The effects of parameters on the delay bound and convergence rate are analyzed. [ABSTRACT FROM AUTHOR]

• The bearingless permanent magnet slice motor control system for artificial hearts. • To improved (SMO) and high frequency injection method was proposed in this paper. • GAPSO algorithm was adopted the critical point of low-speed domain and medium. • High-speed domain to realize smooth switching between different estimation methods. Increase in volume in the bearingless permanent magnet slice motor (BPMSM) control system for artificial hearts is the major problem in the existing works. A sensorless control method of the BPMSM for the artificial heart is proposed in the study based on an improved sliding mode observer (SMO) and improved high-frequency injection method. Also, a full-speed rotor position detection method combining the high-frequency injection (FHI) method and sliding mode observer is designed. In this method, an improved high-frequency injection method was designed in the low-speed domain, and an improved sliding-mode observer was designed in the medium–high-speed domain. Besides, the speed domain switching method based on the genetic particle swarm optimization (GAPSO) algorithm was adopted at the critical point of the low-speed domain and the medium and high-speed domain to realize the smooth switching between different estimation methods, and then realize the sensorless control of the rotor in the full speed domain. Secondly, the simulation study by Simulink was used to compare the detection effects of the BPMSM rotor position and speed of the artificial heart pump under different methods are compared in this work. The results show that the speed estimation value and rotor position estimation value of the new method in this paper were closer to the actual value, the position estimation error is 3%, and the speed estimation error was within 1.5%. Further, the experimental study was carried out on the principal prototype of the sensorless control part of the artificial heart to verify the effectiveness of the proposed method. The method proposed in this paper has certain generality in the field of motor sensorless control technology, and has important reference value for researchers in this field. [ABSTRACT FROM AUTHOR]

This paper aims at the parameter estimation of dual-rate Hammerstein-Volterra (DR-HV) systems. The auxiliary model (AM) method is applied to solve the incomplete identification data caused by the dual-rate sampling. Besides, combining the particle swarm optimization (PSO) and the gradient search principle, this paper proposes an improved algorithm — the hybrid particle swarm-gradient based on the auxiliary model (AM-HPSG) algorithm, which is employed to the DR-HV identification. The AM-HPSG method converts the nonlinear identification issue into the optimization problem in the parameter space. Moreover, the application of the gradient mutation strategy in the AM-HPSG algorithm can not only improve the optimization speed and the identification accuracy, but also solve the premature problem of the basic PSO method. To verify the feasibility of the AM-HPSG algorithm, the second-order DR-HV model and the third-order DR-HV models are considered in simulation. And it can be easy to find that the AM-HPSG performs much better than the PSO and the gradient iterative (GI) methods through algorithm comparison. [ABSTRACT FROM AUTHOR]

Distribution network nodes are numerous and monitoring devices are widely distributed. All monitoring data are uploaded to the cloud master for centralized processing may cause serious problems, such as network congestion, information delay and high computational complexity. The edge computing can provide a good solution, which requires reasonable distribution network partition. This paper proposes a Monte Carlo optimized spectral clustering (MCOSC) distribution network partition method for edge server configuration. Firstly, the objective function of distribution network partition number is constructed with economic and real-time communication indexes, which are more suitable for edge computing than electrical distance and voltage sensitivity indexes. Then the optimal number of partitions is obtained by particle swarm optimization (PSO) with the constraints of communication reliability. Secondly, to solve the problem that the traditional spectral clustering is easy to fall into the local optimal solution, a Monte Carlo optimized spectral clustering method is proposed to make the distribution network partition results more reasonable. Finally, the performance of the proposed method is evaluated by IEEE 33 bus and 69 bus systems distribution network models. The results indicate that the Monte Carlo optimization partition method has better accurate, robustness and convergence speed than traditional spectral clustering method. • The economic and real-time indexes are defined based on edge computing to optimize the number of network partitions. • A Monte Carlo optimized spectral clustering method is proposed to improve the distribution network partition results. • IEEE 33 and 69 bus systems test results indicate the proposed method has better accurate, robustness and convergence speed. [ABSTRACT FROM AUTHOR]

Wind resource is one of the most promising renewable energy, which has become a suitable replacement for fossil fuels. Optimizing the transferring wind energy from a wind turbine is essential to obtain the maximum power output as other variables are uncontrollable. This paper presents four different optimization algorithms, namely ant lion optimization (ALO), whale optimization algorithm (WOA), particle swarm optimization (PSO), and crow search optimization (CSO), considering a hybrid decision-making model to compare the performances of wind energy optimization. In the first phase, the evolutionary algorithms are defined based on several factors to meet the need for wind energy based on volumetric and time reliability, reversibility, and vulnerability as well as evaluate optimized energy to the subscriber from the Gansu region. In the second phase, the ordinal priority approach (OPA) is coupled with VIseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method to rank the evolutionary algorithms. Then, the results are compared with the absolute optimal response based on the nonlinear programming method obtained from GAMS software. The results demonstrate that an ALO outperforms other algorithms. The average accuracy of ALO is 92%. CSO is the least accurate with 55% of the absolute optimal response. ALO is found to be faster, more efficient, and achieved economy and reliability as compared to other optimization algorithms for solving the problem under consideration. It is shown that the applied models are robust, effective, and able to save costs. [ABSTRACT FROM AUTHOR]

This paper develops a robust strategy based on integrating three mutation phases and adapted control parameters into the Adaptive Guided Differential Evolution algorithm called (mAGDE) to improve diversity and exploration of the original AGDE. The mAGDE performance is evaluated using IEEE CEC'2020 test suite. Furthermore, the mAGDE is employed to identify the solid oxide fuel cell (SOFC) model optimal parameters. Two modes of SOFC operation are investigated, steady and transient states. The results obtained from the proposed mAGDE are compared with a number of recent, well-established and reputed meta-heuristics, including Particle swarm optimization, Teaching learning-based optimization, Whale optimization algorithm, Harris hawks optimization, Marine predators algorithm, Archimedes optimization algorithm, Differential evolution, and the original AGDE. Additionally, the statistical parameters that measure the performance of the proposed optimizer and the other competitors are calculated. The main finding demonstrated the preference and robustness of the suggested mAGDE in constructing the SOFC circuit that closely converges to the actual one. During the steady-state operation, the best fitness value obtained via the suggested mAGDE for operation at 1273 K is 2.2995E−06, while in the transient-state operation, the best SMSE is 1.04. The average cost function is decreased by 43.33% compared to the one obtained by the original AGDE. From the aforementioned assessments, it can be concluded that the proposed mAGDE is outstanding and promising. • This paper introduces a modified mAGDE based on the integration of a modified three-phases AGDE with the DE_SPA algorithm. • A modified three-phases AGDE has been introduced to maintain diversity and convergence of the evolutionary process. • The CEC'2020 test suite problems are used to demonstrate the performance mAGDE against other competitors. • Applying for first time mAGDE to identify the optimal parameters of SOFC model. • The robustness of the proposed strategy-based mAGDE is proved. [ABSTRACT FROM AUTHOR]

[Display omitted] • Surrogate model is trained to provide an inexpensive function. • Traditional optimization algorithm has been improved from two aspects. • A novel algorithm provides powerful tool for back analysis of geomechanical parameters. • The parametric investigation for rock mass under complex geological conditions has been implemented. Geomechanical properties of rock mass are of vital importance for design optimization and stability evaluation in geotechnical engineering. Traditionally, they are estimated by laboratory experiments, in situ tests, and empirical classification, which ignore the scale effect, and may be not representative, leading to uncertainties of parameters. Back analysis method based on the monitoring displacement data provides the state-of-the-art tool for the estimation of geomechanical parameters. This paper proposed a novel back analysis method, which combined the optimized particle swarm optimization (OPSO) algorithm with the support vector machine (SVM) algorithm. And then, we cooperate the method with finite element method (FEM) forming the comprehensive method named OPSO-SVM-ABAQUS. This method has developed the standard PSO algorithm from two aspects for more powerful optimization capability and higher optimization precision. The OPSO algorithm is then used for the estimation of the SVM hyperparameters and the optimal values of geomechanical parameters. Furthermore, the performance of the proposed algorithm is compared with other six algorithms. Finally, the geomechanical parameters of the interlayered soft and hard rocks are calculated accurately, with the average error between the back-analyzed and assumed actual parameters to be 0.91 %. And the parametric investigations are implemented with the trained model. It dominates that the proposed algorithm is feasible for reasonable parameters in geotechnical engineering under complex geological conditions. [ABSTRACT FROM AUTHOR]

With the increasing penetration of electric vehicles (EVs), the harmful impact caused by EV's disorderly charging becomes larger. Aiming for mitigating the impact of disorderly charging on the grid and improving the user's satisfaction, this paper firstly performs the Monte Carlo simulation (MCS) to obtain the distribution information of EVs' disorderly charging. Then an improved particle swarm optimization (PSO) algorithm is presented to model the orderly charging strategy. In order to maintain the diversity of the population better, a rotation matrix is utilized to yaw particle's search direction slightly in the improved PSO. And by adjusting the inertia weight index and learning factor, the problems of poor local optimization ability and premature convergence of the original PSO is alleviated. Finally, the proposed approach is verified by a practical engineering case. The outcome demonstrates that the proposed orderly charging strategy can significantly lower the charging cost and peak-valley difference. • The factors affecting the charging of electric vehicles are analyzed. • The load characteristics of electric vehicle disorderly charging are simulated. • The improved PSO algorithm is used to realize the orderly charging of electric vehicles. [ABSTRACT FROM AUTHOR]

• Particle Swarm Optimization to find optimal values for image reconstruction by Phase Retrieval. • Faster convergence and better reconstruction results for 16-bit images. • Image reconstruction process is automated, eliminating the manual search of best values for reconstruction. Imaging through scattering media has become an important aspect in optical imaging. To achieve this, different approaches have been presented to recover the phase of an imaging object from its scattered speckle behind a scattering medium. However, all these algorithms require initial parameters which are obtained based on prior knowledge of the imaging object. This is impractical, as prior knowledge of the imaging object is not always available in real imaging applications. In this paper, we propose using a Particle Swarm Optimization algorithm to find these optimal parameters without requiring prior knowledge of the imaging object. These optimal values are then adopted in the Phase Retrieval algorithm based on object-modulated speckles for object image reconstruction behind a scattering medium in a single-shot imaging system. The obtention of the values for the standard deviation for Gaussian filter and the threshold control allows Phase Retrieval to converge faster and avoids the need for running the algorithm more than once in the search for the best reconstruction. [ABSTRACT FROM AUTHOR]

In order to meet the logistics and distribution requirements with poor actual traffic conditions, this paper considers adding soft time windows and stochastic factors (road traffic congestion, weather changes, etc.) based on classic vehicle routing problem. Firstly, we construct a time-dependent vehicle routing problem (TDVRP) with soft time windows model with the objective function of minimizing the total cost of distribution. A Hybrid Algorithm (HA) combining Sweep Algorithm (SA) and Improved Particle Swarm Optimization (IPSO) is developed to solve this model. Secondly, we compare IPSO with other algorithms through benchmark test functions and traditional vehicle routing problem cases. Finally, By applying HA to the modified Solomon benchmark test set, this paper compares HA with the existing solutions in the number of vehicles used, total transportation distance and total waiting time. Then experimental results manifest the practicability of HA. [ABSTRACT FROM AUTHOR]

• This paper studied the low NO x combustion optimization based on PDOBLPSO. • Opposition-based learning is carried out with some learning probability. • The optimized NO x emissions are lower when the learning probability is in [0.1 0.3]. • Optimized NO x emissions based on PDOBLPSO are lowest among the studied algorithms. • Low NO x combustion optimization based on PDOBLPSO is most stable among the studied algorithms. NO x emissions emitted from coal-fired power plants are threatening human beings. Combustion optimization is an important technology to reduce NO x emissions. However, this technology is troubled with premature when swarm algorithms are employed. This paper studied low NO x combustion optimization based on partial dimension opposition-based learning particle swarm optimization. In this algorithm, opposition-based learning is carried out with some learning probability for each dimension of global best particle. The proposed algorithm was applied to the combustion optimization of some 600 MW boiler. Results show that median optimized NO x emissions and mean optimized NO x emissions are lower when the learning probability is located between 0.1 and 0.3. Median optimized NO x emissions and mean optimized NO x emissions based on partial dimension opposition-based learning particle swarm optimization are lowest among the studied algorithms in most cases with limited iterations. Up to 37.72 mg/Nm3 median NO x emissions can be further reduced by partial dimension opposition-based learning particle swarm optimization compared with the optimized result provided by particle swarm optimization in some case. Besides, low NO x combustion optimization based on partial dimension opposition-based learning particle swarm optimization is most stable among the studied algorithms. [ABSTRACT FROM AUTHOR]

Decision-making is one of the important deals in knowledge transfer and it can be useful for the multi-source domains. Meanwhile, the existing knowledge transfer schemes do not use privacy-preserving techniques for preserving security. This can be a problem for critical domains like financial market forecasting as the misuse of security can lead to legal and financial implications. In recent years, cloud services have revolutionized various technological applications. Cloud computing has become more popular with digital technologies as it provides uninterrupted services like transmission, storage, and intensive computing of data. The architecture of the cloud is also cost-efficient. Besides, various promising services from the cloud, some challenges need to be addressed to secure the privacy of the cloud users as millions of users access its services. Privacy preservation is an important aspect in the field of data mining, and the necessity of securing important data in the cloud from hackers is on the rise. Privacy-preserving data mining algorithms have been analyzed over recent years to provide sufficient solutions for securing the privacy of the data in the cloud. This paper plans to introduce a new hybrid meta-heuristic concept for developing a privacy preservation strategy towards business data under the cloud sector. The main objective of this paper is to design a new hybrid red deer-bird swarm algorithm (RD-BSA) to ensure higher convergence and since the use of control parameters over the solution generation is minimized. The proposed privacy preservation scheme on three financial databases is evaluated with the performance against the existing privacy preservation schemes. Different analyses like statistical, key sensitivity, Known-Plaintext Attack (KPA), and Chosen-Plaintext Attack (CPA) are used for evaluating the efficiency of the algorithm. The comparative analysis of the proposed model over the conventional models demonstrates its effective performance via diverse analysis. [ABSTRACT FROM AUTHOR]

Wave energy technologies have the potential to play a significant role in the supply of renewable energy worldwide. One of the most promising designs for wave energy converters (WECs) are fully submerged buoys. In this paper, we explore the optimisation of WEC arrays consisting of three-tether buoys. Such arrays can be optimised for total energy output by adjusting the relative positions of buoys in a wave farm. As there are complex hydrodynamic interactions among WECs, the evaluation of each parameter setting is computationally expensive and thus limits the feasible number of full model evaluations that can be made. Furthermore, these WEC interactions make up a non-convex, multi-modal (with multiple local-optima), continuous and constrained optimisation problem. This problem is challenging to solve using optimisation methods. To tackle the challenge of optimising the positions of WECs in a wave farm, we propose a novel multi-swarm cooperative co-evolution algorithm which consists of three meta-heuristics: the multi verse optimiser (MVO) algorithm, the equilibrium optimisation (EO) method, and the moth flame optimisation (MFO) approach with a backtracking strategy, we introduce a fast, effective new surrogate model to speed up the process of optimisation. To assess the effectiveness of our proposed approach, 11 state-of-the-art bio-inspired algorithms and three recent hybrid heuristic techniques were compared in six real wave situations located on the coasts of Australia, with two wave farm sizes (four and nine WECs). The experimental study presented in this paper shows that our hybrid cooperative framework exhibited the best performance in terms of the quality of obtained solutions, computational efficiency, and convergence speed compared with other 14 state-of-the-art meta-heuristics. Furthermore, we found that the power output of the best-found 9-buoy arrangements were higher than that of perpendicular layouts at at 4.15 % , 3.29 % , 3.62 % , 9.2 % , 5.74 % , and 2.43 % for the Perth, Adelaide, Sydney, Tasmania, Brisbane, and Darwin wave sites, respectively. Our investigations reveal that the best-found arrangement at the Tasmania wave site was able to absorb the highest level of wave power relative to the other locations. • A new Multi-swarm Cooperative optimisation framework is proposed to optimise wave farms performance. • A new fast surrogate model is developed to speed up expensive optimisation process of wave farm. • To improve the placement of converters, a symmetrical backtracking search algorithm is proposed. • To handle the infeasible wave converters layout during the optimisation, a new and effective repair function is developed. • The proposed optimiser enhances significantly the total power output at six wave farms compared with previous methods. [ABSTRACT FROM AUTHOR]

• A new BP-ANN calculation method for reactor fuel reloading optimization was developed. • The BP-ANNs developed in this paper have higher precision than those in similar paper. • Five different meta-heuristic algorithms were compared when combining with the BP-ANN calculation method for fuel reloading optimization. • The developed BP-ANN calculation method for reactor fuel reloading optimization obviously fasten the calculation time. In order to obtain optimal core configurations, the problems of fuel reloading optimization must be solved in nuclear engineering field. This problem is a combinational optimization problem with an enormous solution space. In the traditional calculation method, the meta-heuristic algorithms (MHAs) are used to search and update optimization solutions continuously, while the core physics calculation programs are used to calculate the optimization parameters. In this research, we developed a new BP-ANN calculation method to solve the problems of fuel reloading optimization for thorium-based block-type high temperature gas-cooled reactors (HTGRs). In this method, the function of core physics calculation programs are replaced by BP-ANNs in order to reduce calculation time. Besides, five different MHAs, which are genetic algorithm (GA), particle swarm optimization (PSO), Teaching-learning based optimization algorithm (TLBO), harmony search (HS) and Rank-based ant system (RAS), are used under this new method to solve the problems of fuel reloading optimization, respectively. The results shows that PSO is the best MHA with a real feasible solution ratio of 0.30 and the best fitness function value of 0.455904. Compared to the traditional calculation method, the calculation time of BP-ANN calculation method is reduced to 0.7% of the former. [ABSTRACT FROM AUTHOR]

• The electrical equipment was divided into time-shifting and non-time-shifting power. • The starting time of time-shifting load was selected as the variable in PSO algorithm. • The battery capacity was selected to meet the demand of the power peak at night. With the continuous expansion of the development scale, photovoltaic integrated greenhouses are becoming an important type of smart grid prosumer. The demand side management (DSM) of energy is becoming increasingly important in terms of satisfying the energy consumption requirements of production and increasing the economic benefits of the same piece of land. By analyzing greenhouse production activities and the operation of electrical equipment, a particle swarm optimization (PSO) scheme is proposed in this paper, which selects the starting time of time-shifting powers as optimization factors and maximizes the income of power generation as the objective function. In addition, this paper analyzes the problem of energy consumption scheduling in greenhouse production. The results show that this scheme helps to optimally schedule the greenhouse energy consumption and achieves maximum profit by ensuring the reasonable operation of the system. The optimization scheme is beneficial to guide the production activities in greenhouses and the construction of photovoltaic integrated greenhouse systems. [ABSTRACT FROM AUTHOR]

Many engineering and scientific problems in the real-world boil down to optimization problems, which are difficult to solve by using traditional methods. Meta-heuristics are appealing algorithms for solving optimization problems while keeping computational costs reasonable. The marine predators algorithm (MPA) is a modern optimization meta-heuristic, inspired by widespread Lévy and Brownian foraging strategies in ocean predators as well as optimal encounter rate strategies in biological interactions between predator and prey. However, MPA is not without its shortcomings. In this paper, a quasi-opposition based learning and Q-learning based marine predators algorithm (QQLMPA) is proposed. This offers multiple improvements over standard MPA. Primely, Q-learning allows MPA to fully use the information generated by previous iterations. And also, quasi-opposition based learning serves to increase population diversity, reducing the risk of convergence to inferior local optima. Numerical experiments demonstrate better performance by QQLMPA on 32 benchmark optimization functions and three engineering problems: designs of pressure vessel, hydro-static thrust bearing, and speed reducer. • Q-learning is introduced to MPA for adaptively choosing search mode. • Quasi-opposition learning is used to enhance the exploration of MPA. • The proposed optimizer can achieve great performance for continuous optimization. [ABSTRACT FROM AUTHOR]

• The paper benefits from Reinforcement Learning in industrial control applications. • TD3 policy gradient is implemented to learn optimal PI controller dynamics. • The actor-network learns the optimal PI dynamics using the reward mechanism. • The performance of the optimal PI dynamics is compared with the other results. To benefit from the advantages of Reinforcement Learning (RL) in industrial control applications, RL methods can be used for optimal tuning of the classical controllers based on the simulation scenarios of operating conditions. In this study, the Twin Delay Deep Deterministic (TD3) policy gradient method, which is an effective actor-critic RL strategy, is implemented to learn optimal Proportional Integral (PI) controller dynamics from a Direct Current (DC) motor speed control simulation environment. For this purpose, the PI controller dynamics are introduced to the actor-network by using the PI-based observer states from the control simulation environment. A suitable Simulink simulation environment is adapted to perform the training process of the TD3 algorithm. The actor-network learns the optimal PI controller dynamics by using the reward mechanism that implements the minimization of the optimal control objective function. A setpoint filter is used to describe the desired setpoint response, and step disturbance signals with random amplitude are incorporated in the simulation environment to improve disturbance rejection control skills with the help of experience based learning in the designed control simulation environment. When the training task is completed, the optimal PI controller coefficients are obtained from the weight coefficients of the actor-network. The performance of the optimal PI dynamics, which were learned by using the TD3 algorithm and Deep Deterministic Policy Gradient algorithm, are compared. Moreover, control performance improvement of this RL based PI controller tuning method (RL-PI) is demonstrated relative to performances of both integer and fractional order PI controllers that were tuned by using several popular metaheuristic optimization algorithms such as Genetic Algorithm, Particle Swarm Optimization, Grey Wolf Optimization and Differential Evolution. [ABSTRACT FROM AUTHOR]

Driver pathways have been acknowledged to play critical roles in the initiation and progression of cancers►hence it is essential for precision medicine related studies to develop accurate and efficient methods to identify them. Although previous approaches have shown promising results by integrating multi-omics data, their preset artificial parameters may decrease the convenience to use and limit the application scalability. In this paper, a novel integration approach is proposed to incorporate four omics data, i.e., construct a weighted non-binary mutation matrix without presetting artificial parameters. A parameter-free identification model is put forward based on it. It takes advantage of the association between genes in the PPI network as well as balances the contribution of coverage and mutual exclusivity with the harmonic mean. Furthermore, a cooperative co-evolution algorithm is proposed for solving this model. In the algorithm, a particle swarm optimization algorithm suitable for solving combinatorial problems is presented. Three cooperative operators are devised to construct the cooperation among the populations and the swarm to increase the population diversity. Both real biological datasets and simulated ones were exerted to perform experimental comparisons among the proposed method and six other state-of-the-art ones. The gene sets identified by the presented method generally contain more genes involved in known signaling pathways than those obtained by the other methods. Simultaneously, both high accuracy and high efficiency of the proposed method were verified in experiments, making it practical in realistic applications and an effective supplementary tool to identify driver pathways. • A non-binary mutation matrix is constructed without artificial adjustable parameters. • The model incorporates gene association and balances coverage and mutual exclusivity. • A PSO algorithm suitable for solving combinatorial problems is presented. • A co-operative co-evolution algorithm is put forward for solving the presented model. • The performance is compared among the proposed method and seven state of the art ones. [ABSTRACT FROM AUTHOR]

Feature selection is an important preprocessing technique in the fields of data mining and machine learning. With the promotion of privacy protection awareness, recently it becomes a very practical and challenging issue to select high-quality feature subsets while ensuring the privacy of all participants. However, there is a lack of research results on this issue, i.e., feature selection under privacy protection. Aiming at the issue, this paper proposes a federated feature selection framework for the first time. In the framework, inspiring by the idea of federated learning, a credible third participant is introduced to process and integrate optimal feature subsets from multiple participants. On the basis of the framework, a federated evolutionary feature selection algorithm based on particle swarm optimization is proposed to effectively solve feature selection problems with multiple participants under privacy protection. Two new operators satisfying the requirement of privacy protection, i.e., the feature assembling strategy with multi-participant cooperation and the swarm initialization strategy guided by assembling solution, are designed to improve the ability of the proposed algorithm. Compared with several typical assembling feature selection algorithms on 15 data sets, experimental results show that the proposed algorithm can significantly improve the classification accuracy of the feature subset selected by each participant, while protecting the privacy of data. [ABSTRACT FROM AUTHOR]