Ship predictive collision avoidance method based on an improved beetle antennae search algorithm

Beetle Antennae Search (BAS) is an intelligent algorithm that mimics the beetle preying process. In BAS, there is a beetle which has a left and a right antennae sensing the intensity of the odor emitted by the food. The beetle learns the different sense of two antennas to determine the flight and finally finds the food. The BAS algorithm has been proved to have good optimizing speed and precision when it is applied for low-dimensional optimization problems. However, when solving high-dimensional problems, the algorithm is easily trapped into local optimum. In order to improve the optimization ability of BAS, we have combined particle swarm optimization (PSO) algorithm and proposed a new hybrid BAS and PSO algorithm (BAS-PSO). In BAS-PSO, firstly, the standard PSO is used for particle velocity and position updating. Particles learn ontology information and group optimal information for evolution. Then each particle in the swarm is taken as a beetle independently applying a local search with BAS algorithm. To verify the performance of BAS-PSO, four benchmark functions have been selected in our simulation experiments. The results show that the performance of BAS-PSO is better than BAS and PSO.

In this paper, we focuses on the theoretical analysis on the convergence of the beetle antennae search (BAS) algorithm. For the first time, we prove that the BAS algorithm is convergent with probability 1, which provides some insights about why the BAS algorithm works and also brings us some ideas about how to improve the BAS algorithm in the future. We also test the performance of the BAS algorithm via some representative benchmark functions. Meanwhile, some applications of the BAS algorithm are also presented, showing the advantages of the algorithm over other algorithms.

Beetle antennae search (BAS) algorithm is a newly proposed single-solution based metaheuristic technique inspired by the beetle preying process. Although BAS algorithm has shown good search abilities, it can be easily trapped into local optimum when it is used to solve hard optimization problems. With the intention to overcome this drawback, this paper presents a population-based beetle antennae search (PBAS) algorithm for solving integer programming problems. This method employs the population's capability to search diverse regions of the search space to provide better guarantee for finding the optimal solution. The PBAS method was tested on nine integer programming problems and one mechanical design problem. The proposed algorithm was compared to other state-of-the-art metaheuristic techniques. The comparisons show that the proposed PBAS algorithm produces better results for majority of tested problems.

<title>Abstract</title> Image enhancement is a crucial process in various fields, including medical imaging, remote sensing, and digital photography. This study explores the application of the Beetle Antennae Search (BAS) algorithm for optimizing image enhancement parameters. The BAS algorithm is compared with the Particle Swarm Optimization (PSO) algorithm to evaluate its effectiveness in improving image quality. The objective is to enhance grayscale images by adjusting parameters such as A, B, C, and K to maximize a fitness function that incorporates edge information and entropy. Experimental results demonstrate that BAS consistently outperforms PSO in terms of convergence speed and image quality metrics, including Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). BAS-enhanced images exhibit significant improvements in contrast, brightness, and sharpness, making it a promising tool for image enhancement tasks.

Image will be polluted by different kinds of noise in the process of acquisition, compression, and transmission, resulting in interference to subsequent image segmentation, feature extraction and other processing. With the development of deep convolutional neural network (DCNN), quite a few effective DCNNs have been designed and have made remarkable progress in image denoising. Gradient descent algorithm is generally used for DCNN training. However, due to the complex mathematical properties of the high-dimensional and non-convex loss optimization surface, there are often many local optimal points, saddle points or large range of gradient gentle regions, which affects training effect of the gradient descent algorithm. Although intelligent algorithms such as evolutionary algorithm have global optimization capability, they often have large computing resource requirements and slow convergence speed, which limit its application in DCNN training which is a high-dimensional optimization problem. Beetle antennae search (BAS) algorithm is a simple and efficient bionic intelligent optimization algorithm, which has global search ability. In this paper, the gradient descent method and BAS method are combined as a hybrid method for deep auto-encoder (DAE) denoising network training. Experimental results show that the proposed method accelerates the training speed of the DAE denoising network, reduces the blurring of edge details and improves the visual effect of the restored image.KeywordsBeetle Antennae Search AlgorithmConvolutional neural networkImage denoising

Dual Beetle Antennae Search system for optimal planning and robust control of 5-link biped robots

With the emergence of various online trading technologies, fraudulent cases begin to occur frequently. The problem of fraud in public trading companies is a hot topic in financial field. This paper proposes a fraud detection model for public trading companies using datasets collected from SEC’s Accounting and Auditing Enforcement Releases (AAERs). At the same time, this computational finance model is solved with a nonlinear activated Beetle Antennae Search (NABAS) algorithm, which is a variant of the meta-heuristic optimization algorithm named Beetle Antennae Search (BAS) algorithm. Firstly, the fraud detection model is transformed into an optimization problem of minimizing loss function and using the NABAS algorithm to find the optimal solution. NABAS has only one search particle and explores the space under a given gradient estimation until it is less than an “Activated Threshold” and the algorithm is efficient in computation. Then, the random under-sampling with AdaBoost (RUSBoost) algorithm is employed to comprehensively evaluate the performance of NABAS. In addition, to reflect the superiority of NABAS in the fraud detection problem, it is compared with some popular methods in recent years, such as the logistic regression model and Support Vector Machine with Financial Kernel (SVM-FK) algorithm. Finally, the experimental results show that the NABAS algorithm has higher accuracy and efficiency than other methods in the fraud detection of public datasets.

This manuscript presents ABSAS-CS-GSA, an improved iteration of the beetle antennae search (BAS) algorithm, tailored to address the shortcoming of the BAS with low convergence accuracy and easily falling into local optima. The improvements are structured into three principal components: first, dynamic step-size adjustment predicated on initial population to bolster solution accuracy and expedite convergence; second, position update mechanism integrating golden sine algorithm to diversify search patterns and expedite convergence; and third, population disturbance based on vertical and horizontal cross strategy to avoid falling into local optima. Experimental results on 12 benchmark functions demonstrate ABSAS-CS-GSA's superiority over the standard BAS and its four variants, as well as over two classic swarm intelligence algorithms. The simulation results of the algorithm applied to coverage optimization of wireless sensor networks with 30 nodes and 50 nodes reveal a marked improvement in both optimal and average coverage metrics relative to seven alternative algorithms. The refined algorithm exhibits excellent performance and is well-suited for tackling the coverage issue within wireless sensor networks.

A real-time multi-ship collision avoidance decision-making system for autonomous ships considering ship motion uncertainty

Huber Loss function is a regression type loss function, mainly used for optimization problems.In order to make the predicted value close to the true value and minimize the distance between them, the traditional loss function generally uses the gradient descent method to find the minimum value. However, the gradient descent method takes too long and consumes a lot of memory. It may not necessarily find the global optimal value, and it is easy to fall into the problem of local optimization. The data of the unconstrained function is complicated and huge, and the Huber Loss function sets the hyper-parameter δ to optimize MSE and MAE, we must iterate continuously to train the hyper-parameters to obtain more accurate parameter values, which will cause a problem of large amount of calculations. The beetle antennae search algorithm is a simple biological intelligence optimization algorithm that can provide the best solution based on huge data, with fast convergence speed, small amount of calculation, simple operation, and no need to know the specific function. In order to improve the accuracy of finding the global optimal value, this paper changed the traditional fixed-step antennae search algorithm to variable-step beetle antennae search algorithm. This article will discuss the application of the gradient descent method in the regression loss function, and then use the variable step size beetle antennae search algorithm to optimize Huber Loss function.

High-speed motorized spindle heating will produce thermal error, which is an important factor affecting the machining accuracy of machine tools. The thermal error model of high-speed motorized spindles can compensate for thermal error and improve machining accuracy effectively. In order to confirm the high precision thermal error model, Beetle antennae search algorithm (BAS) is proposed to optimize the thermal error prediction model of motorized spindle based on BP neural network. Through the thermal characteristic experiment, the A02 motorized spindle is used as the research object to obtain the temperature and axial thermal drift data of the motorized spindle at different speeds. Using fuzzy clustering and grey relational analysis to screen temperature-sensitive points. Beetle antennae search algorithm (BAS) is used to optimize the weights and thresholds of the BP neural network. Finally, the BAS-BP thermal error prediction model is established. Compared with BP and GA-BP models, the results show that BAS-BP has higher prediction accuracy than BP and GA-BP models at different speeds. Therefore, the BAS-BP model is suitable for prediction and compensation of spindle thermal error.

• A structured-light stereo vision seeding depth monitoring method was proposed. • A PID control for the downward pressure was designed. • A soil covering and compaction wheel was designed. • A control system for seeding depth adjustment was designed. Precision corn seeding plays a crucial role in modern agriculture, and consistent seeding depth is a key factor in improving seeding quality. Appropriate seeding depth not only promotes seed germination and root development but also influences subsequent plant growth. However, conventional seeding operations typically rely on adjusting the overall downward pressure, making it difficult to precisely control the soil cover amount for each seed and thereby hindering consistent seeding depth. In this study, a novel intelligent soil − covering and compaction device was developed. Furrowing depth and compaction pressure were monitored in real − time using a structured − light binocular camera and a strain gauge, respectively. The soil cover amount and compaction pressure were regulated via a servo motor to ensure seeding depth stability. In addition, a fuzzy PID control system optimized by the Beetle Antennae Search (BAS) algorithm was designed for closed-loop control of compaction pressure. Simulation results indicate that, relative to conventional fuzzy PID control, BAS − PID improves dynamic response. With an acceptance criterion of ± 6 mm for measurement error, the furrowing depth monitoring device achieved a qualification rate of 83.3%. With an acceptance criterion of ± 10 mm for the deviation between post-operation seeding depth and the target depth, the seeding depth qualification rate reached 88%. The coefficient of variation of compaction pressure was 7.49%. Overall, the proposed intelligent soil–covering and compaction device enables accurate furrowing depth monitoring and real-time regulation of soil cover amount and compaction pressure, thereby significantly improving seeding depth consistency.

The multi-objective portfolio optimization is regarded as an multi-objective optimization problem which is complicated and hard to find a satisfactory solution in a limited time. It is more complex and difficult to use the conventional method to solve this problem. In this paper, we first establish a mean-CVaR-entropy model with transaction costs and investment weight restrictions, and then propose a Multi-objective Optimization Algorithm for BeetleSearch(MOBSO), a meta-heuristic optimization algorithm, and a variant of Beetle Antennae Search (BAS) algorithm, which is applied into portfolio optimization to solve this constraint multi-objective optimization problem. Finally, we use the 20 stocksfrom January 2017 to December 2021 in the US stock market to do case studyand compare the results with other meta-heuristic optimization algorithms. It shows that the MOBSO outperforms swarm algorithms such as the particle swarm optimization (PSO) and the genetic algorithm(GA). KeywordsMulti-objective portfolio optimizationBeetle Antennae Search (BAS)Particle Swarm Optimization (PSO)Meta-heuristic optimizationFinance problem

In order to optimize the performance of the transmission network (TN), this paper introduces the random fractal search algorithm based on the beetle antenna search algorithm, thus proposing the random fractal beetle antenna algorithm (SFBA). The main work of this research is as follows: (1) in the beetle antenna search algorithm, this study used a population of beetles and introduced elite members of the population in order to make the algorithm more stable and to some extent improve the accuracy of its answers. (2) Utilizing the elite reverse learning method and the leader’s multilearning strategy for elites helps to strike a balance between the global exploration and local development of the algorithm. This strategy also further improves the ability of the algorithm to find the optimal solution. (3) Experiments on real experimental data show that the SFBA algorithm proposed in this paper is effective in improving TN performance. In summary, the research content of this paper provides a good reference value for the performance optimization of TN in actual production.

Beetle antennae search algorithm (BAS) is based on the searching behavior of longhorn beetles. This newly proposed metaheuristic algorithm is used in the path and function synthesis of multi-bar mechanism. The optimization results are compared with that of other metaheuristic algorithms like genetic algorithm (GA), particle swarm optimization (PSO) and differential evolution (DE) et al. While BAS uses only one group of initial parameters to search the best result, the convergence and efficiency are tested with eight case studies results. Newly added parameter q increases the possibility to find better results during iterations and deals with a higher number of independent parameters efficiently. Revised BAS exhibits good performance both in path synthesis of four-bar mechanism with or without prescribed timing, while optimized parameters increases from 6 to 34, and extends to path and function combined synthesis of Stephenson III six-bar double dwell mechanism with 14 parameters.