A novel randomised particle swarm optimizer

A Random Particle Swarm Optimization Based on Cosine Similarity for Global Optimization and Classification Problems

In today's fast-paced and ever-changing environment, the need for algorithms with enhanced global optimization capability has become increasingly crucial due to the emergence of a wide range of optimization problems. To tackle this issue, we present a new algorithm called Random Particle Swarm Optimization (RPSO) based on cosine similarity. RPSO is evaluated using both the IEEE Congress on Evolutionary Computation (CEC) 2022 test dataset and Convolutional Neural Network (CNN) classification experiments. The RPSO algorithm builds upon the traditional PSO algorithm by incorporating several key enhancements. Firstly, the parameter selection is adapted and a mechanism called Random Contrastive Interaction (RCI) is introduced. This mechanism fosters information exchange among particles, thereby improving the ability of the algorithm to explore the search space more effectively. Secondly, quadratic interpolation (QI) is incorporated to boost the local search efficiency of the algorithm. RPSO utilizes cosine similarity for the selection of both QI and RCI, dynamically updating population information to steer the algorithm towards optimal solutions. In the evaluation using the CEC 2022 test dataset, RPSO is compared with recent variations of Particle Swarm Optimization (PSO) and top algorithms in the CEC community. The results highlight the strong competitiveness and advantages of RPSO, validating its effectiveness in tackling global optimization tasks. Additionally, in the classification experiments with optimizing CNNs for medical images, RPSO demonstrated stability and accuracy comparable to other algorithms and variants. This further confirms the value and utility of RPSO in improving the performance of CNN classification tasks.

A Two-Stage Distributed Task Assignment Algorithm Based on Contract Net Protocol for Multi-UAV Cooperative Reconnaissance Task Reassignment in Dynamic Environments

Multi-UAV systems have been widely used in reconnaissance, disaster relief, communication, and other fields. However, many dynamic events can cause a partial failure of the original mission during the mission execution process, in which case task reassignment should be carried out. How to reassign resources and tasks in multi-dynamic, multi-target, and multi-constraint events becomes a core issue in the enhancement of combat efficiency. This paper establishes a model of multi-UAV cooperative reconnaissance task reassignment that comprehensively considers various dynamic factors such as UAV performance differences, size of target areas, and time window constraints. Then, a two-stage distributed task assignment algorithm (TS-DTA) is presented to achieve multi-task reassignment in dynamic environments. Finally, this paper verifies the effectiveness of the TS-DTA algorithm through simulation experiments and analyzes its performance through comparative experiments. The experimental results show that the TS-DTA algorithm can efficiently solve the task reassignment problem in dynamic environments while effectively reducing the communication burden of UAV formations.

A Stock Price Forecasting Model Integrating Complementary Ensemble Empirical Mode Decomposition and Independent Component Analysis

In recent years, due to the non-stationary behavior of data samples, modeling and forecasting the stock price has been challenging for the business community and researchers. In order to address these mentioned issues, enhanced machine learning algorithms can be employed to establish stock forecasting algorithms. Accordingly, introducing the idea of “decomposition and ensemble” and the theory of “granular computing”, a hybrid model in this paper is established by incorporating the complementary ensemble empirical mode decomposition (CEEMD), sample entropy (SE), independent component analysis (ICA), particle swarm optimization (PSO), and long short-term memory (LSTM). First, aiming at reducing the complexity of the original data of stock price, the CEEMD approach decomposes the data into different intrinsic mode functions (IMFs). To alleviate the cumulative error of IMFs, SE is performed to restructure the IMFs. Second, the ICA technique separates IMFs, describing the internal foundation structure. Finally, the LSTM model is adopted for forecasting the stock price results, in which the LSTM hyperparameters are optimized by synchronously utilizing the PSO algorithm. The experimental results on four stock prices from China stock market reveal the accuracy and robustness of the established model from the aspect of statistical efficiency measures. In theory, a useful attempt is made by integrating the idea of “granular computing” with “decomposition and ensemble” to construct the forecasting model of non-stationary data. In practice, the research results will provide scientific reference for the business community and researchers.

Fog-Edge Collaborative Task Offloading Strategy Based on Chaotic Teaching and Learning Particle Swarm Optimization

To improve the contradiction between the surge of business demand and the limited resources of MEC, firstly, the “cloud, fog, edge, and end” collaborative architecture is constructed with the scenario of smart campus, and the optimization model of joint computation offloading and resource allocation is proposed with the objective of minimizing the weighted sum of delay and energy consumption. Second, to improve the convergence of the algorithm and the ability to jump out of the bureau of excellence, chaos theory and adaptive mechanism are introduced, and the update method of teaching and learning optimization (TLBO) algorithm is integrated, and the chaos teaching particle swarm optimization (CTLPSO) algorithm is proposed, and its advantages are verified by comparing with existing improved algorithms. Finally, the offloading success rate advantage is significant when the number of tasks in the model exceeds 50, the system optimization effect is significant when the number of tasks exceeds 60, the model iterates about 100 times to converge to the optimal solution, the proposed architecture can effectively alleviate the problem of limited MEC resources, the proposed algorithm has obvious advantages in convergence, stability, and complexity, and the optimization strategy can improve the offloading success rate and reduce the total system overhead.

A Transfer Learning-Based Method for Personalized State of Health Estimation of Lithium-Ion Batteries

State of health (SOH) estimation of lithium-ion batteries (LIBs) is of critical importance for battery management systems (BMSs) of electronic devices. An accurate SOH estimation is still a challenging problem limited by diverse usage conditions between training and testing LIBs. To tackle this problem, this article proposes a transfer learning-based method for personalized SOH estimation of a new battery. More specifically, a convolutional neural network (CNN) combined with an improved domain adaptation method is used to construct an SOH estimation model, where the CNN is used to automatically extract features from raw charging voltage trajectories, while the domain adaptation method named maximum mean discrepancy (MMD) is adopted to reduce the distribution difference between training and testing battery data. This article extends MMD from classification tasks to regression tasks, which can therefore be used for SOH estimation. Three different datasets with different charging policies, discharging policies, and ambient temperatures are used to validate the effectiveness and generalizability of the proposed method. The superiority of the proposed SOH estimation method is demonstrated through the comparison with direct model training using state-of-the-art machine learning methods and several other domain adaptation approaches. The results show that the proposed transfer learning-based method has wide generalizability as well as a positive precision improvement.

Dynamic Population Cooperative

Particle swarm optimization (PSO) has attracted wide attention in the recent decade. Although PSO is an efficient and simple evolutionary algorithm and has been successfully applied to solve optimization problems in many real-world fields, premature maturation and poor local search capability remain two critical issues for PSO. Therefore, to alleviate these disadvantages, a dynamic population cooperative particle swarm optimization for global optimization problems (DPCPSO) is proposed. Firstly, to enhance local search capability, an elite neighborhood learning strategy is constructed by leveraging information from elite particles. Meanwhile, to make the particle easily jump out of the local optimum, a crossover-mutation mechanism is utilized. Finally, a dynamic population partitioning mechanism is designed to balance exploration and exploitation capabilities. 16 classic benchmark functions and 1 real-world optimization problem are used to test the proposed algorithm against with 6 typical PSO algorithms. The experimental results show that DPCPSO is statistically and significantly better than the compared algorithms for most of the test problems. Moreover, the convergence speed and convergence accuracy of DPCPSO are also significantly improved. Therefore, the algorithm is highly competitive in solving global optimization problems.

A New GAN-Based Approach to Data Augmentation and Image Segmentation for Crack Detection in Thermal Imaging Tests

As a popular nondestructive testing (NDT) technique, thermal imaging test demonstrates competitive performance in crack detection, especially for detecting subsurface cracks. In thermal imaging test, the temperature of the crack area is higher than that of the non-crack area during the NDT process. By extracting the features of the thermal image sequences, the temperature curve of each spatial point is employed for crack detection. Nevertheless, the quality of thermal images is influenced by the noises due to the complex thermal environment in NDT. In this paper, a modified generative adversarial network (GAN) is employed to improve the image segmentation performance. To improve the feature extraction ability and alleviate the influence of noises, a penalty term is put forward in the loss function of the conventional GAN. A data preprocessing method is developed where the principle component analysis algorithm is adopted for feature extraction. The data argumentation technique is utilized to guarantee the quantity of the training samples. To validate its effectiveness in thermal imaging NDT, the modified GAN is applied to detect the cracks on the eddy current pulsed thermography NDT dataset.

Multi-task Pruning via Filter Index Sharing: A Many-Objective Optimization Approach

State-of-the-art deep neural network plays an increasingly important role in artificial intelligence, while the huge number of parameters in networks brings high memory cost and computational complexity. To solve this problem, filter pruning is widely used for neural network compression and acceleration. However, existing algorithms focus mainly on pruning single model, and few results are available to multi-task pruning that is capable of pruning multi-model and promoting the learning performance. By utilizing the filter sharing technique, this paper aimed to establish a multi-task pruning framework for simultaneously pruning and merging filters in multi-task networks. An optimization problem of selecting the important filters is solved by developing a many-objective optimization algorithm where three criteria are adopted as objectives for the many-objective optimization problem. With the purpose of keeping the network structure, an index matrix is introduced to regulate the information sharing during multi-task training. The proposed multi-task pruning algorithm is quite flexible that can be performed with either adaptive or pre-specified pruning rates. Extensive experiments are performed to verify the applicability and superiority of the proposed method on both single-task and multi-task pruning.

Wavelength selection of terahertz time-domain spectroscopy based on a partial least squares model for quantitative analysis

Terahertz spectroscopy, combined with chemometric methods, has proved to be an effective tool in the quantitative analysis of many substances. However, current research has mainly focused on comparing different algorithms under the full spectrum. In fact, the full spectrum is not only composed of characteristic features of the samples, but also many types of noises. Hence, the accuracy of the quantitative analysis may be unsatisfactory if the full spectrum is selected. In this paper, a wavelength selection method based on partial least squares and absorption peak was proposed and an efficient frequency band was determined in the quantitative analysis of three types of pesticides, i.e., 6-benzylaminopurine, 2, 6-dichlorobenzonitrile, and imidacloprid. By introducing two parameters, the sum of peak intervals (Si) and peak width, the most efficient peak was selected from multiple peaks and the specific peak width was given with the aid of particle swarm optimization. We concluded that the most efficient absorption peak for quantitative analysis corresponding to the largest Si and full width near one-half maximum could characterize full spectrum information precisely. Comparing before and after wavelength selection, the correlation coefficient (R) of the three pesticides have increased from 0.9671, 0.9705, 0.9884 to 0.9921, 0.9934, and 0.9957. In conclusion, the proposed wavelength selection method was demonstrated to be very efficient for the quantitative analysis of the pesticide mixtures, which also could be helpful in the analysis of other multicomponent mixtures with absorption peaks.