Particle Swarm Research Articles

Comparison of hybrid binary GWO-PSO algorithm with feature selection methods by using machine learning classifiers

In the field of machine learning, feature selection methods used in the pre-processing of data for the classifier have become very popular. Instead of the whole dataset, it is important to create a new sub-dataset by discarding the irrelevant and redundant variables in the dataset to make the data ready for analysis. In this way, both the performance of the learning classifier will increase, and cost and time savings will be achieved. In this study, the performance of the hybrid binary grey wolf optimization - particle swarm optimization (BHGWOPSO) algorithm with machine learning methods is investigated. In addition, a comparison was made between BHGWOPSO and other feature selection methods such as principial component analysis and filter methods in contrast to literature. Thus, it is aimed to show which of the different feature selection methods will work better. For this purpose, five different benchmark datasets with different number of features were selected. Both feature selection methods and machine learning classifiers were compared with each other using the accuracy metric. As a result of the comparisons, it was observed that a different feature selection method and a different classifier had higher accuracy values for each data set.

Dynamic Foraging in Swarm Robotics: A Hybrid Approach with Modular Design and Deep Reinforcement Learning Intelligence

This paper proposes a hybrid approach that combines intelligent algorithms and modular design to solve a foraging problem within the context of swarm robotics. Deep reinforcement learning (RL) and particle swarm optimization (PSO) are deployed in the proposed modular architecture. They are utilized to search for many resources that vary in size and exhibit a dynamic nature with unpredictable movements. Additionally, they transport the collected resources to the nest. The swarm comprises 8 E-Puck mobile robots, each equipped with light sensors. The proposed system is built on a 3D environment using the Webots simulator. Through a modular approach, we address complex foraging challenges characterized by a non-static environment and objectives. This architecture enhances manageability, reduces computational demands, and facilitates debugging processes. Our simulations reveal that the RL-based model outperforms PSO in terms of task completion time, efficiency in collecting resources, and adaptability to dynamic environments, including moving targets. Notably, robots equipped with RL demonstrate enhanced individual learning and decision-making abilities, enabling a level of autonomy that fosters collective swarm intelligence. In PSO, the individual behavior of the robots is more heavily influenced by the collective knowledge of the swarm. The findings highlight the effectiveness of a modular design and deep RL for advancing autonomous robotic systems in complex and unpredictable environments.

Adaptive Particle Swarm Optimization with Landscape Learning for Global Optimization and Feature Selection

Particle swarm optimization (PSO), an important solving method in the field of swarm intelligence, is recognized as one of the most effective metaheuristics for addressing optimization problems. Many adaptive strategies have been developed to improve the performance of PSO. Despite these advances, a key problem lies in defining the configuration criteria of the adaptive algorithm. This study presents an adaptive variant of PSO that relies on fitness landscape analysis, particularly via ruggedness factor estimation. Our approach involves adaptively updating the cognitive and acceleration factors based on the estimation of the ruggedness factor using a machine learning-based method and a deterministic way. We tested them on global optimization functions and the feature selection problem. The proposed method gives encouraging results, outperforming native PSO in almost all instances and remaining competitive with state-of-the-art methods.

Research on Cross-Border e-Commerce Supply Chain Prediction and Optimization Model Based on Convolutional Neural Network Algorithm

Enhancing the precision of supply chain management and reducing operational costs are crucial for the development of the cross-border e-commerce market. However, existing research often overlooks the demand uncertainty caused by seasonal variations and the challenges of handling returns in logistics. Therefore, this paper proposes a SARIMA-CNN-BiLSTM prediction model that effectively captures both the seasonal and nonlinear characteristics of cross-border e-commerce supply chains. Additionally, by incorporating the returns process, a supply chain distribution optimization model is developed with the objective of minimizing total operational costs. The model is solved using an improved whale optimization algorithm. In validation with real-world data, the SARIMA-CNN-BiLSTM model achieved a mean absolute percentage error reduction of 6.479 and 7.703 compared to convolutional neural network (CNN) and BiLSTM models, respectively. Moreover, the chosen optimization algorithm reduced the cost by 231,310 CNY, 62,564 CNY, and 131,632 CNY compared to the whale optimization algorithm, genetic algorithm, and particle swarm optimization, respectively. The proposed approach provides robust support for cross-border e-commerce enterprises in reducing costs and enhancing efficiency in their operations.

Forecasting Renewable energy and electricity consumption using evolutionary hyperheuristic algorithm

This research utilizes time series models to forecast electricity generation from renewable energy sources and electricity consumption. The configuration of optimal parameters for these models typically requires optimization algorithms, but conventional algorithms may struggle with fixed search patterns and limited robustness. To address this, we propose an auto-evolution hyper-heuristic algorithm named AE-GAPB. AE-GAPB integrates a genetic algorithm (GA) at the high-level component and employs particle swarm optimization (PSO) and the bat algorithm (BA) at the low-level component. The GA continuously finds the best hyperparameters for PSO and BA based on prediction accuracy, which significantly accelerates the optimization and improves the accuracy. Additionally, the crossover and mutation rates of GA evolve over iteration time and fitness value space, further enhancing its adaptability. We validated AE-GAPB on six time series forecasting models and compared it with five well-known optimization algorithms as well as GAPB without auto-evolution at the high-level component. As a result, AE-GAPB achieved excellent results on renewable energy generation and electricity consumption datasets from the Hokkaido, Kyushu, and Tohoku regions of Japan.

Multi-objective optimization of hybrid energy systems using gravitational search algorithm

The depletion of fossil fuel reserves, increasing environmental concerns, and energy demands of remote communities have increased the acceptance of using hybrid renewable energy systems (HRES). However, choosing an optimal HRES from economic, environmental, reliability, and sustainability aspects is still challenging. To solve this challenge, this study introduces a novel multi-objective optimization approach using the Gravitational Search Algorithm (GSA) and non-dominated sorting techniques. The proposed framework addresses four objectives: minimizing the loss of power supply probability, reducing total costs, increasing renewable energy fraction, and lowering CO2 emissions. A carbon tax sensitivity analysis evaluates the system’s economic performance under varying scenarios. Also, the amount of damage caused by the release of carbon dioxide on human health and the ecosystem is examined. In this way, an optimal configuration consisting of wind turbines, photovoltaic panels, and diesel generators is introduced to satisfy the above objectives. Results demonstrate that the GSA outperforms established methods, such as multi-objective particle swarm optimization and non-dominated sorting genetic algorithm II in Pareto front diversity and convergence. In this work, the optimal system achieves an 18.4% increase in renewable energy share, reducing ecosystem and human health damage by 14.2%. Notably, with a 20% increase in the carbon tax, system costs increased by 3%. These findings underscore the potential of multi-objective optimization combined with carbon tax policies to enhance energy system sustainability and affordability.

Advanced Efficient Feature Selection Integrating Augmented Extreme Learning Machine and Particle Swarm Optimization for Predicting Nitrogen Use Efficiency and Yield in Corn

Advanced Efficient Feature Selection Integrating Augmented Extreme Learning Machine and Particle Swarm Optimization for Predicting Nitrogen Use Efficiency and Yield in Corn

Optimization and Analysis of Gear Set Structure for Continuous Loading and Unloading Hydraulic Power Tongs

Optimizes and analyzes the gear set structure of hydraulic power pliers used in continuous loading and unloading operations. The optimization design process of gear set structure was elaborated in detail, including the selection of independent variables, determination of constraint conditions, and establishment of optimization objectives and fitness functions. The simulated annealing particle swarm optimization algorithm (SAPSO) was used for optimization design, and the optimization results showed that the total volume of the gear set was reduced by 17.1%. Finally, the strength of the optimized gear set was verified through finite element analysis, and the results showed that the strength of the optimized gear set met the actual working requirements.

Particle Swarm Optimization of a Single Server Retrial Queue with Delayed Repair Under Working Vacation From Optional Service to ReService

Queueing systems (QS) play a critical role in modeling and optimizing various real-world processes by managing the flow of entities within systems involving queues. To address this, the proposed QS integrates features such as single arrivals, a retrial mechanism, optional re-service, working vacations, and delay repair scenarios. The system’s dynamics are comprehensively analyzed using the supplementary variable technique, which provides deeper insights into its behavior and performance metrics. Furthermore, to enhance operational efficiency, an advanced cost optimization technique is employed to identify the optimal cost structure for the system. This holistic approach not only sheds light on the operational intricacies of the QS but also offers practical strategies for cost reduction and validation of analytical findings, thereby advancing queueing theory and broadening its practical applications across multiple domains.

Automatic Vertical Root Fracture Detection on Intraoral Periapical Radiographs With Artificial Intelligence-Based Image Enhancement.

To explore transfer learning (TL) techniques for enhancing vertical root fracture (VRF) diagnosis accuracy and to assess the impact of artificial intelligence (AI) on image enhancement for VRF detection on both extracted teeth images and intraoral images taken from patients. A dataset of 378 intraoral periapical radiographs comprising 195 teeth with fractures and 183 teeth without fractures serving as controls was included. DenseNet, ConvNext, Inception121, and MobileNetV2 were employed with model fusion. Prior to evaluation, Particle Swarm Optimization (PSO) and Deep Learning (DL) image enhancement were applied. Performance assessment included accuracy rate, precision, recall, F1-score, AUC, and kappa values. Intra- and inter-observer agreement, according to the Gold Standard (GS), were assessed using ICC and t-tests. Statistical significance was set at p < 0.05. The DenseNet + Inception fusion model achieved the highest accuracy rate of 0.80, with commendable recall, F1-score, and AUC values, supported by precision (0.81) and kappa (0.60) values. Molar tooth examination yielded an accuracy rate, precision, recall, and F1-score of 0.80, with an AUC of 0.84 and kappa of 0.60. For premolar teeth, the fusion network showed an accuracy rate of 0.78, an AUC of 0.78, and notable metrics, including F1-score (0.80), recall (0.85), precision (0.71), and kappa (0.55). ICC results demonstrated acceptable agreement (≥ 0.57 for molars, ≥ 0.52 for premolars). TL methods have demonstrated significant potential in enhancing diagnostic accuracy for VRFs in radiographic imaging. TL is emerging as a valuable tool in the development of robust, automated diagnostic systems for VRF identification, ultimately supporting clinicians in delivering more accurate diagnoses.

Investigation into Shaped Wide-Beam Reflectarray Surfaces Reflectors as Passive Repeaters in Wireless Networks

This paper investigates the use of a Reflectarray Surface (RAS) to provide a shaped beam for use as a passive repeater in a wireless network. A shaped beam can be desirable as it may provide coverage over a dead-spot region. Examples of a flat-topped and sloping top shaped beams having a nominal beamwidth of 30◦ and a steering angle of 40◦ at 10 GHz are investigated, designed using the particle swarm optimizer in MATLAB. Measurement and simulation from CST show reasonable agreement to the 'array factor' synthesis patterns but display practical detuning effects that may limit this approach. Additionally, it was noted element factor has a more significant impact on such beam shaping.

Research on Fire Detection of Cotton Picker Based on Improved Algorithm.

According to the physical characteristics of cotton and the work characteristics of cotton pickers in the field, during the picking process, there is a risk of cotton combustion. The cotton picker working environment is complex, cotton ignition can be hidden, and fire is difficult to detect. Therefore, in this study, we designed an improved algorithm for multi-sensor data fusion; built a cotton picker fire detection system by using infrared temperature sensors, CO sensors, and the upper computer; and proposed a BP neural network model based on improved mutation operator hybrid gray wolf optimizer and particle swarm optimization (MGWO-PSO) algorithm based on the BP neural network model. This algorithm includes the introduction of a mutation operator in the gray wolf algorithm to improve the search ability of the algorithm, and, at the same time, we introduce the PSO algorithm idea. The improved fusion algorithm is used as a learning algorithm to optimize the BP neural network, and the optimized network is used to process and predict the data collected from temperature and gas sensors, which effectively improves the accuracy of fire prediction. The sensor measurements were compared with the actual values to verify the effectiveness of the GWO-PSO-optimized BP neural network model. Once experimentally verified, the improved GWO-PSO algorithm achieves a correlation coefficient R of 0.96929, a prediction accuracy rate of 96.10%, and a prediction error rate of only 3.9%, while the system monitors an accurate early warning rate of 96.07%, and the false alarm and omission rates are both less than 5%. This study can detect cotton picker fires in real time and provide timely warnings, which provides a new method for the accurate detection of fires during the field operation of cotton pickers.

Early Prediction of Cardio Vascular Disease (CVD) from Diabetic Retinopathy using improvised deep Belief Network (I-DBN) with Optimum feature selection technique

Cardio Vascular Disease (CVD) is one of the leading causes of mortality and it is estimated that 1 in 4 deaths happens due to it. The disease prevalence rate becomes higher since there is an inadequate system/model for predicting CVD at an earliest. Diabetic Retinopathy (DR) is a kind of eye disease was associated with increasing risk factors for all-causes of CVD events. The early diagnosis of DR plays a significant role in preventing CVD. However, there are many works have been carried out on classification of the disease but they focused less on feature selection and increasing the accuracy of the model. The proposed work introduces Improvised Deep Belief Network named I-DBN to resolve the above mentioned problems and mainly to concentrate on improving the entire performance of the model leading to the unbiased output. We used Principal Component Analysis (PCA) and Particle Swarm Optimization (PSO) algorithm for feature extraction and selection respectively. Five performance metrics have been used to assess the proposed model. The results of I-DBN outperform other state-of-the-art methods. The result validation ensures that I-DBN can deliver trustworthy recommendations to doctors to treat the patients by enhancing the accuracy of CVD prediction up to 98.95%.

Adaptive hybrid ANFIS-PSO and ANFIS-GA approach for occupational risk prediction

This study attempted to optimize the adaptive neuro-fuzzy inference system (ANFIS) using particle swarm optimization (PSO) and a genetic algorithm (GA) for calculating occupational risk. Numerous studies have shown that the ANFIS is a good approach for predicting engineering problems. However, it is not well investigated in the area of risk assessment. The proposed techniques were evaluated using various statistical indices, i.e., mean absolute error (MAE) and root mean square error (rmse), to characterize their performance. To test the prediction performance of the proposed technique, a comparison with three well-known machine learning approaches, i.e., artificial neural network (ANN), logistic regression (LR) and support vector machine (SVM), was conducted. The obtained results indicate that ANFIS-PSO achieved better prediction performance for both the training and testing phases. Furthermore, the comparative analysis showed that the proposed model is competitive and suitable for occupational risk prediction.

Research on the Prediction Model of Coal Spontaneous Combustion Hazard Level Based on IGWO-GRNN

ABSTRACT To accurately predict the risk level of spontaneous coal combustion, we introduce an improved grey wolf optimization strategy (IGWO) to optimize the generalized regression neural network (GRNN), thereby establishing the IGWO-GRNN coal spontaneous combustion risk level prediction model. The superiority of the IGWO algorithm over the grey wolf optimization algorithm (GWO), whale optimization algorithm (WOA) and particle swarm optimization algorithm (PSO) was verified. Fifty sets of sample data of spontaneous coal combustion in the mining area were selected as the research object, and the data were randomly divided into the training set and the test set according to the ratio of 8:2. The prediction results of the IGWO-GRNN prediction model were obtained and compared with those of the GWO-GRNN, GRNN, BP (Backpropagation), and GRU (Gated Recurrent Unit) models, and the absolute value of the relative error was introduced as an evaluation index of the model prediction accuracy. The results demonstrate that IGWO outperforms GWO, WOA, and PSO in terms of optimization efficiency, with the IGWO-GRNN prediction model yielding the most accurate results. Specifically, the maximum absolute value of the relative error does not exceed 4.27%, and the average relative error is only 3.29%, indicating a substantial improvement over the other models. Therefore, this study achieves high-precision prediction under small-sample data, which provides an important reference value for the small-sample prediction problem in the mining field.

Federated Learning for Extreme Label Noise: Enhanced Knowledge Distillation and Particle Swarm Optimization

Federated learning, with its unique privacy protection mechanisms and distributed model training capabilities, provides an effective solution for data security by addressing the challenges associated with the inability to directly share private data due to privacy concerns. It exhibits broad application potential across various fields, particularly in scenarios such as autonomous vehicular networks, where collaborative learning is required from data sources distributed across different clients, thus optimizing and enhancing model performance. Nevertheless, in complex real-world environments, challenges such as data poisoning and labeling errors may cause some clients to introduce label noise that significantly exceeds ordinary levels, severely impacting model performance. The following conclusions are drawn from research on extreme label noise: highly polluted data severely affect the generalization capability of the global model and the stability of the training process, while the reweighting strategy can improve model performance. Based on these research conclusions, we propose a method named Enhanced Knowledge Distillation and Particle Swarm Optimization for Federated Learning (FedDPSO) to deal with extreme label noise. In FedDPSO, the server dynamically identifies extremely noisy clients based on uncertainty. It then uses the particle swarm optimization algorithm to determine client model weights for global model aggregation. In subsequent rounds, the identified extremely noisy clients construct an interpolation loss combining pseudo-label loss and knowledge distillation loss, effectively mitigating the negative impact of label noise overfitting on the local model. We carried out experiments on the CIFAR10/100 datasets to validate the effectiveness of FedDPSO. At the highest noise ratio under Beta = (0.1, 0.1), experiments show that FedDPSO improves the average accuracy on CIFAR10 by 15% compared to FedAvg and by 11% compared to the more powerful FOCUS. On CIFAR100, it outperforms FedAvg by 8% and FOCUS by 5%.

Research on Sensitivity Improvement Methods for RTD Fluxgates Based on Feedback-Driven Stochastic Resonance with PSO.

With the wide application of Residence Time Difference (RTD) fluxgate sensors in Unmanned Aerial Vehicle (UAV) aeromagnetic measurements, the requirements for their measurement accuracy are increasing. The core characteristics of the RTD fluxgate sensor limit its sensitivity; the high-permeability soft magnetic core is especially easily interfered with by the input noise. In this paper, based on the study of the excitation signal and input noise characteristics, the stochastic resonance is proposed to be realized by adding feedback by taking advantage of the high hysteresis loop rectangular ratio, low coercivity and bistability characteristics of the soft magnetic material core. Simulink is used to construct the sensor model of odd polynomial feedback control, and the Particle Swarm Optimization (PSO) algorithm is used to optimize the coefficients of the feedback function so that the sensor reaches a resonance state, thus reducing the noise interference and improving the sensitivity of the sensor. The simulation results show that optimizing the odd polynomial feedback coefficients with PSO enables the sensor to reach a resonance state, improving sensitivity by at least 23.5%, effectively enhancing sensor performance and laying a foundation for advancements in UAV aeromagnetic measurement technology.

Recursive hierarchical parametric identification of Wiener-Hammerstein systems based on initial value optimization.

In this paper, a novel recursive hierarchical parametric identification method based on initial value optimization is proposed for Wiener-Hammerstein systems subject to stochastic measurement noise. By transforming the traditional Wiener-Hammerstein system model into a generalized form, the system model parameters are uniquely expressed for estimation. To avoid cross-coupling between estimating block-oriented model parameters, a hierarchical identification algorithm is presented by dividing the parameter vector into two subvectors containing the coupled and uncoupled terms for estimation, respectively. To guarantee consistent estimation on these parameters, an auxiliary block model is designed to predict the inner unmeasurable variables of the Wiener-Hammerstein system for computational iteration. Furthermore, two adaptive forgetting factors are designed to accelerate the convergence rates on estimating both coupled and uncoupled parameters. To overcome the issue of initial value sensitivity involved with the traditional recursive least-squares based algorithms for parameter estimation, a particle swarm optimization (PSO) algorithm based on two different excitation signals is given for initial value optimization of the proposed recursive identification algorithm. Meanwhile, the convergence property of the proposed algorithm is clarified with a proof. Finally, an illustrative example and experiments on a micro-positioning stage are performed to validate the merit of the proposed method.

Automatic positioning of cutting planes for bone tumor resection surgery.

In bone tumor resection surgery, patient-specific cutting guides aid the surgeon in the resection of a precise part of the bone. Despite the use of automation methodologies in surgical guide modeling, to date, the placement of cutting planes is a manual task. This work presents an algorithm for the automatic positioning of cutting planes to reduce healthy bone resected and thus improve post-operative outcomes. The algorithm uses particle swarm optimization to search for the optimal positioning of points defining a cutting surface composed of planes parallel to a surgical approach direction. The quality of a cutting surface is evaluated by an objective function that considers two key variables: the volumes of healthy bone resected and tumor removed. The algorithm was tested on three tumor cases in long bone epiphyses (two tibial, one humeral) with varying plane numbers. Optimal optimization parameters were determined, with varying parameters through iterations providing lower mean and standard deviation of the objective function. Initializing particle swarm optimization with a plausible cutting surface configuration further improved stability and minimized healthy bone resection. Future work is required to reach 3D optimization of the planes positioning, further improving the solution.

Designing artificial intelligence computing techniques to study heat transfer of a ternary hybrid nanofluid flow: Application of particle swarm optimization and artificial neural network

Designing artificial intelligence computing techniques to study heat transfer of a ternary hybrid nanofluid flow: Application of particle swarm optimization and artificial neural network