A Multi-robot Pattern Formation Algorithm Based on Distributed Swarm Intelligence

Particle swarm optimization (PSO) can be interpreted physically as a particular discretization of a stochastic damped mass-spring system. Knowledge of this analogy has been crucial to derive the PSO continuous model and to introduce different PSO family members including the generalized PSO (GPSO) algorithm, which is the generalization of PSO for any time discretization step. In this paper, we present the stochastic analysis of the linear continuous and generalized PSO models for the case of a stochastic center of attraction. Analysis of the GPSO second order trajectories is performed and clarifies the roles of the PSO parameters and that of the cost function through the algorithm execution: while the PSO parameters mainly control the eigenvalues of the dynamical systems involved, the mean trajectory of the center of attraction and its covariance functions with the trajectories and their derivatives (or the trajectories in the near past) act as forcing terms to update first and second order trajectories. The similarity between the oscillation center dynamics observed for different kinds of benchmark functions might explain the PSO success for a broad range of optimization problems. Finally, a comparison between real simulations and the linear continuous PSO and GPSO models is shown. As expected, the GPSO tends to the continuous PSO when time step approaches zero. Both models account fairly well for the dynamics (first and second order moments) observed in real runs. This analysis constitutes so far the most realistic attempt to better understand and approach the real PSO dynamics from a stochastic point of view.

In this work, artificial neural network (ANN) models and particle swarm optimization (PSO) models based on machine learning were built to predict the HHVs of MSW quickly. Four kinds of BP ANN models and two PSO models were built using proximate analysis and ultimate analysis of 33 MSW samples as input variables. As a comparison, three classical linear empirical models employed from publications were also used. The modeling results show that the input variables had significant influence on the prediction accuracy. The ANN model based on proximate analysis had lower precision for HHV estimation. The ultimate analysis had better prediction performance while the combination of ultimate analysis and proximate analysis (ANN-4 model) had the best accuracy. With regard to ANN-4 model, the largest relative deviation for all samples was lower than 10%. Due to the complex composition of MSW, the linear empirical model was not suitable for accurate prediction of the calorific value of MSW. Nonlinear empirical formulas obtained by PSO models improved the prediction performance for most samples. In general, the ANN modeling method could predict the thermochemical properties of MSW and provide rapid and effective guidance for the operation of MSW incineration process.

Networked synchronization control has very high technology level, which includes network technology and synchronization control technology, etc. Fault diagnosis of the devices in networked synchronization control system has a great importance for ensuring the normal operation. The radial basis function neural network with particle swarm optimization algorithm is developed. The combination method of RBF neural network and particle swarm optimization is applied to fault diagnosis of networked synchronization control system. The test results indicate that the combination model of RBF neural network and particle swarm optimization can almost entirely recognize each state of the device in networked synchronization control system. The diagnostic accuracy of the combination model of RBF neural network and particle swarm optimization is greater than that of normal RBF neural network.

Water quality planning relies on Biochemical Oxygen Demand BOD. BOD testing takes five days. The Particle Swarm Optimization (PSO) is increasingly used for water resource forecasting. This work designed a PSO technique for estimating everyday BOD at Al-Rustumiya wastewater treatment facility inlet. Al-Rustumiya wastewater treatment plant provided 702 plant-scale data sets during 2012-2022. The PSO model uses the daily data of the water quality parameters, including chemical oxygen demand (COD), chloride (Cl-), suspended solid (SS), total dissolved solids (TDS), and pH, to determine how each variable affects the daily incoming BOD. PSO and multiple linear regression (MLR) findings are compared, and their performance is evaluated using mean square error, relative absolute mistake, and coefficient of determination. PSO utilised COD, TDS, SS, pH, and Cl- as inputs, generating a mean square error of 1029.10, an average absolute relative error of 9.41%, and a coefficient of determination of 0.89. Comparisons demonstrated that the PSO model could accurately calculate the daily BOD at Al-Rustumiya wastewater treatment plant's inlet.

Injecting CO2 into the reservoir can not only improve crude oil recovery but also achieve the goal of CO2 geological storage. It can not only reduce the greenhouse effect but also obtain additional economic benefits. From the perspective of minimum miscible pressure, carbon dioxide flooding can be divided into miscible flooding and immiscible flooding, and miscible flooding is widely used in the oil field. The most important condition for miscible flooding is to achieve the minimum miscible pressure (MMP). In the study, combining the particle swarm optimization (PSO) with Gaussian process regression (GPR), a novel intelligent GPR and particle swarm optimization (GPR-PSO) method was proposed to establish the model of predicting the MMP of the CO2 and oil system. The model uses the database with more data than in the previous literature, with 365 data points, and the value range of the data is also wider. Moreover, the accuracy of GPR-PSO model was evaluated by statistical error and graph error and compared with the prediction results of existing models. The results show that compared with other models, the GPR-PSO model has higher accuracy and wider application range, the mean absolute relative error is only 1.66%. Meanwhile, the reliability of the model is verified by the sensitivity analysis of parameters. The results show that the most influential parameter on the prediction results is the reservoir temperature, and the least influential parameter is the critical temperature of injected gas. The GPR-PSO model can be used not only to predict the MMP of CO2 and oil system but also to predict the MMP of other gases and crude oil system.

Support Vector Machine (SVM) has become a popular method in machine learning in recent years. SVM is widely used as a tool in many classifiction areas. The selection optimum values of the parameters (model selection) for SVM is an important step in SVM design. This paper presents the results of research and testing method Particle Swarm Optimization (PSO) in selecting the parameters for SVM. Here we focus on the selection parameter γ of the RBF function and soft margin parameter C of SVM for classification problems. In this paper we propose a Particle Swarm Optimization variation model which combine the cognition-only model with the social-only model and use randomised low discrepancy sequences for initialising particle swarms. We then evaluate the suggested strategies with a series of experiments on 6 benchmark datasets. Experimental results demonstrate the model we proposed better than grid search and full PSO-SVM model.

Timetable rescheduling of metro network during the last train period

Particle swarm optimization (PSO) is a kind of population-based search methods, that is inspired by social behavior observed in nature, such as flocks of irds and schools of fish. PSO has been receiving attentions, since it has a powerful search ability in function optimization problems, and several improvement has been studied to apply PSO to the multimodal function optimization and optimization in the dynamic environments. The purpose of this paper is to improve PSO performance deteriorated by the degeneracy of particle velocities, in case of high-dimensional optimization problems. We propose a novel PSO model, called the Rotated Particle Swarm (RPS), by introducing the coordinate conversion. The numerical simulation results show that the proposed RPS is effective in optimizing high-dimensional functions.

In many real-world optimization problems, multimodal function optimization is considered, in fact, we are faced with a multimodal optimization problem. Particle swarm optimization (PSO) and continuous ant colony optimization (ACOR) are two population-based optimization techniques that work based on probability laws. The main problem of PSO and ACOR algorithms is premature convergence and falling into local optima. One way to solve the problems is to use combinational methods. This paper presents a combinational method including PSO and ACOR in order to improve the search process. The proposed algorithm tries to solve the problem. Standard benchmark functions are used in order to evaluate the proposed algorithm, proposed method was compared with ACOR, PSO and sequential approach with the enlarged pheromone-particle table of the composition of PSO and ACOR Introduced in [8]. Results show that the proposed method is superior.

Gene controls biological character by various proteins that are formed by isoforms. Through alternative splicing, gene can express multiple isoforms. The next generation of high-throughput RNA sequencing has provided facilitation for quantifying isoform expression level. Extensive efforts have been made in stimulating isoform abundance from RNA-Seq data, but the accuracy still needs to be improved. In this article, we propose a statistical method combined with Particle Swarm Optimization to estimate isoform abundance from RNA-Seq data. After a series of statistical analysis and experiments, we decided on the forms and values of coefficients in Particle Swarm Optimization model. We analyzed the performance of our approach on both simulated and real datasets. Experiment results showed that comparing to Cufflinks our approach makes acceptable improvement on accuracy and is more sensitive to condition changes in most cases.

In order to overcome the poor anti-noise performance of traditional fuzzy C-Means (FCM) algorithm in image segmentation, a novel improved FCM algorithm was proposed in this paper based on Particle Swarm Optimization (PSO) algorithm and Markov Random Field (MRF) model, which can make full use of the global searching ability of PSO and the spatial information integrating ability of MRF for image segmentation. In this algorithm, the image segmentation is converted to a PSO optimization problem, in which the fitness function is set up to containing the spatial information based on the spectral value and the neighboring pixels modeled by MRFs. And segmentation results can be iteratively obtained during the PSO iterations according to the newly designed membership function of FCM in which the spatial information is integrated. The experiments herein reported in this paper illustrate the better performance of this algorithm than the traditional FCM algorithm and the PSO algorithm for image segmentation.

BMUDF: Hybrid Bio-inspired Model for fault-aware UAV routing using Destination-aware Fan shaped clustering

Considering that the global navigation satellite system (GNSS) has the influence of positioning and atmospheric signals from time to time in meteorology, errors caused by moisture, and so on in the effect of the propagation path, these factors have led to the influence of various indexes of meteorological factors. In this study, a meteorological prediction algorithm based on the CNSS and particle swarm optimization is proposed. Aiming at the phenomenon that the particle swarm optimization (PSO) algorithm is prone to slow convergence speed and low optimization accuracy and there is a local optimal but cannot achieve the global optimal, an adaptive Kent chaotic map PSO algorithm is proposed. Through the comprehensive analysis of the meteorological input indicators in the GNSS, a noncurrent weight evaluation system is proposed. Under different evaluation systems, the PSO algorithm is applied, and PCA weight can obtain the best prediction effect. Then, the GA model, PSO model, and ADPSO model are used to predict PM2.5 index in meteorology. The results show that the proposed ADPSO algorithm has a good performance in RMSE, MAE, and R2 model evaluation.

Particle Swarm Optimization (PSO) has become a popular method of feature selection in classification problems, due to its powerful search capability and computational simplicity. Classification problems, such as facial emotion recognition, often involve data sets containing high volumes of features, not all of which are useful for classification. Redundant and irrelevant features have the potential to negatively impact the performance and accuracy of facial emotion recognition systems. The feature selection process identifies the most relevant features to achieve improved classification performance. While the use of PSO as a feature selection method in facial emotion recognition systems has seen some successes, it is still susceptible to the issue of premature convergence. This work presents seven PSO variants which mitigate against the premature convergence problem through the incorporation of three random probability distributions (Cauchy, Gaussian and Levy). At each iteration of the proposed PSO models, probability distributions are used to increase search diversity and reduce the number of redundant features used for classification. The seven PSO variants presented in this study have demonstrated positive results when tested on real world data sets, outperforming the standard PSO model and other related work within the field.

In this paper, we propose an automatic image annotation approach for region labeling that takes advantage of both context and semantics present in segmented images. The proposed approach is based on multi-class K-nearest neighbor, k-means and particle swarm optimization (PSO) algorithms for feature weighting, in conjunction with normalized cuts-based image segmentation technique. This hybrid approach refines the output of multi-class classification that is based on the usage of K-nearest neighbor classifier for automatically labeling images regions from different classes. Each input image is segmented using the normalized cuts segmentation algorithm then a descriptor created for each segment. The PSO algorithm is employed as a search strategy for identifying an optimal feature subset. Extensive experimental results demonstrate that the proposed approach provides an increase in accuracy of annotation performance by about 40%, via applying PSO models, compared to having no PSO models applied, for the used dataset.