The artificial algae a*algorithm (AAA) is a recently introduced metaheuristic a*algorithm inspired by the behavior and characteristics of microalgae. Like other metaheuristic a*algorithms, AAA faces challenges such as local...
详细信息
The artificial algae a*algorithm (AAA) is a recently introduced metaheuristic a*algorithm inspired by the behavior and characteristics of microalgae. Like other metaheuristic a*algorithms, AAA faces challenges such as local optima and premature convergence. Various strategies to address these issues and enhance the performance of the a*algorithm have been proposed in the literature. These include levy flight, local search, variable search, intelligent search, multi-agent systems, and quantum behaviors. This paper introduces chaos theory as a strategy to improve AAA's performance. Chaotic maps are utilized to effectively balance exploration and exploitation, prevent premature convergence, and avoid local minima. Ten popular chaotic maps are employed to enhance AAA's performance, resulting in the chaotic artificial algae a*algorithm (CAAA). CAAA's performance is evaluated on thirty benchmark test functions, including unimodal, multimodal, and fixed dimension problems. The a*algorithm is also tested on three classical engineering problems and eight space trajectory design problems at the European Space Agency. A statistical analysis using the Friedman and Wilcoxon tests confirms that CAA demonstrates successful performance in optimization problems.
Artificial electric field a*algorithm (AEFA) is a metaheuristic optimization a*algorithm proposed in recent years, which has been successfully applied to address various optimization problems. However, it is likely to con...
详细信息
Artificial electric field a*algorithm (AEFA) is a metaheuristic optimization a*algorithm proposed in recent years, which has been successfully applied to address various optimization problems. However, it is likely to converge prematurely or fall into local optima when solving complex problems. To overcome these disadvantages, a multi-strategy artificial electric field a*algorithm (MAEFA) is proposed in this paper. For the MAEFA a*algorithm, the global optimal solution information is utilized to improve the diversity of population and global search ability. Then, the adaptive Coulomb's constant is configured to balance the global exploration and local search. Also, a restart strategy is designed to further alleviate the premature convergence. To validate the effectiveness of MAEFA, it is compared with three AEFA a*algorithms and several other evolutionary a*algorithms on 14 test problems presented in CEC 2005 and 13 basic benchmark functions. Furthermore, a wind power prediction model based on MAEFA a*algorithm and back-propagation (BP) neural network is established to investigate its application ability. Experiments show that MAEFA is significantly superior to other a*algorithms in tackling these benchmark functions with different dimensions. Furthermore, in terms of wind power prediction, the BP neural network model optimized by MAEFA a*algorithm also provides higher prediction accuracy.
The traditional synchronization a*algorithms often struggle to meet the stringent requirements of civil aviation communication. This paper proposes an adaptive time synchronization a*algorithm based on Kalman filtering (K...
详细信息
The traditional synchronization a*algorithms often struggle to meet the stringent requirements of civil aviation communication. This paper proposes an adaptive time synchronization a*algorithm based on Kalman filtering (KF) to enhance the synchronization performance of civil aviation communication systems. Firstly, a dynamic clock model is established considering the characteristics of civil aviation communication, with clock offset and drift as state variables. Moreover, a step-by-step detection strategy is employed to adaptively adjust the detection range based on the statistical characteristics of synchronization errors, thereby improving the a*algorithm's robustness and convergence speed. To evaluate the a*algorithm's performance, a civil aviation communication system-level simulation platform is built based on ICAO standards, and various typical scenarios, such as take-off, landing, and cruising, are designed. Simulation results demonstrate that the proposed a*algorithm achieves significant improvements in synchronization accuracy, convergence speed, and robustness compared to classical synchronization a*algorithms based on phase-locked loops (PLL) and early late gates (ELD).
As a critical component of rotating machinery, the operating status of rolling bearings is not only related to significant economic interests but also has a far-reaching impact on social security. Hence, ensuring an e...
详细信息
As a critical component of rotating machinery, the operating status of rolling bearings is not only related to significant economic interests but also has a far-reaching impact on social security. Hence, ensuring an effective diagnosis of faults in rolling bearings is paramount in maintaining operational integrity. This paper proposes an intelligent bearing fault diagnosis method that improves classification accuracy using a stacked denoising autoencoder (SDAE) and adaptive hierarchical hybrid kernel extreme learning machine (AHHKELM). First, a hybrid kernel extreme learning machine (HKELM) is initially constructed, leveraging SDAE's deep network architecture for automatic feature extraction. The hybrid kernel functions address the limitations of single kernel functions by effectively capturing both linear and nonlinear patterns in the data. Subsequently, the hierarchical hybrid kernel extreme learning machine (HHKELM) is refined through an enhanced Aquila Optimizer (AO) a*algorithm, which iteratively optimizes the kernel hyperparameter combination. The AO a*algorithm is further enhanced by incorporating chaos mapping, implementing a refined balanced search strategy, and fine-tuning parameter \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$G_2$$\end{document}, which collectively improve its ability to escape local optima and conduct global searches, thus strengthening the robustness of the model during parameter optimization. Experimental results on the CWRU , MFPT and JNU datasets demonstrate that stacked denoising autoencoder-adaptive hierarchical hybrid kernel extreme learning machine (SDAE-AHHKELM) has better fault classification accuracy, robustness, and generalization than KELM and other methods.
Under the recent condition of information technology, intelligent sports teaching management needs to change the traditional mode to improve the efficiency. At present, modern multimedia technology has fully integrate...
详细信息
Under the recent condition of information technology, intelligent sports teaching management needs to change the traditional mode to improve the efficiency. At present, modern multimedia technology has fully integrated network communication technology, and teaching work is more carried out in the network conditions, which makes the teaching mode completely changed. Because of characteristics of the autonomous and interactive, network teaching mode makes the communication between students, students and teachers easier and closer. The traditional single auxiliary teaching mode can not quickly feedback various information defects are also solved by the network teaching mode. The network teaching mode has own advantages. It can not only fully mobilize students' enthusiasm for learning, but also change the traditional teaching mode. In this paper, we propose the online sports guiding assurance system based on artificial intelligence a*algorithm and intelligent speech semantic extraction. The objectives of the study contains the following aspects: (1) AFSA a*algorithm has the advantages of good global convergence, low initial value requirements, strong robustness and so on. So we consider this as the model for the AI. (2) In B/S multi-layer structure, the hierarchy is divided not based on physical structure but according to its structural logic, so we consider this as the platform structure. The experimental results show that the proposed a*algorithm performs well in error correction, duplication processing and data integration in database text matching. The proposed model performs best on each test set, and its accuracy is generally higher than that of traditional a*algorithms such as SVM, CNN, KNN and FCM. On the test set, the accuracy of the proposed method is 0.9896, while the accuracy of SVM, CNN, KNN and FCM are 0.9175, 0.9235, 0.9389 and 0.9564 respectively.
Recent discoveries indicating that the brain retains its ability to adapt and change throughout life have sparked interest in cognitive training (CT) as a possible means to postpone the development of dementia. Despit...
详细信息
Recent discoveries indicating that the brain retains its ability to adapt and change throughout life have sparked interest in cognitive training (CT) as a possible means to postpone the development of dementia. Despite this, most research has focused on confirming the efficacy of training outcomes, with few studies examining the correlation between performance and results across various stages of training. In particular, the relationship between initial performance and the extent of improvement, the rate of learning, and the asymptotic performance level throughout the learning curve remains ambiguous. In this study, older adults underwent ten days of selective attention training using an adaptive a*algorithm, which enabled a detailed analysis of the learning curve's progression. Cognitive abilities were assessed before and after CT using the Mini-mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA). The findings indicated that: (1) Initial performance is positively correlated with Learning amount and asymptotic performance level, and negatively correlated with learning speed;(2) Age is negatively correlated with learning speed, while it is positively correlated with the other three parameters. (3) Higher pre-training MMSE scores predicted higher post-training MMSE scores but less improvement;(4) Higher pre-training MoCA scores predicted higher post-training MoCA scores and less improvement;(5) The parameters of the learning curve did not correlate with performance on the MMSE or MoCA. These results indicate that: (1)Selective attention training using adaptive a*algorithms is an effective tool for cognitive intervention;(2) Older individuals with poor baseline cognitive abilities require more diversified cognitive training;(3) The study supports the compensation hypothesis.
Network dismantling, which aims at finding the optimal node sequence whose removal will dismantle the whole network effectively, remains as a hot topic in the research area of complex networks and systems. In this stu...
详细信息
Network dismantling, which aims at finding the optimal node sequence whose removal will dismantle the whole network effectively, remains as a hot topic in the research area of complex networks and systems. In this study, an improved network dismantling strategy based on ant-colony optimization a*algorithm is proposed. Through large quantities of numerical simulations, compared with several classical network dismantling methods, the effectiveness of the proposed strategy is verified. Current results can provide a new perspective for us to comprehend the complexity and optimization of complex networked systems.
Predictive maintenance (PdM) is a proactive approach aimed at anticipating the future point of failure for a machine or a component, with the goal of reducing both the frequency and the expenses associated with unplan...
详细信息
Predictive maintenance (PdM) is a proactive approach aimed at anticipating the future point of failure for a machine or a component, with the goal of reducing both the frequency and the expenses associated with unplanned downtime. Recent advances in machine learning (ML) techniques have enabled PdM to be more efficient with diverse and successful applications in various manufacturing industries. The support vector machine (SVM), a fundamental ML a*algorithm, is renowned for its effectiveness in addressing classification and regression tasks. Nevertheless, the successful application of SVM hinges on the careful tuning of its parameters, a process that significantly influences its predictive performance. This research seeks to optimize the selection of the regularization parameter C C and the kernel parameter sigma \sigma using metaheuristic methods. It suggests combining the altruistic dragonfly a*algorithm (ADA) with SVM to enhance the prediction of maintenance failures. The primary motive for integrating altruism into this research is the unprecedented utilization of altruistic principles within this specific area. In addition, ADA-SVM provides a balance between exploration and exploitation. This balance is achieved through the altruistic behavior of dragonflies, where they help each other find better solutions. Therefore, this model is not trapped in the local optimum. The effectiveness of the model ADA-SVM is assessed on aircraft engine sensor data in comparison with other metaheuristic optimization a*algorithms, namely, genetic a*algorithms (GA), particle swarm optimization (PSO), grey wolf optimization (GWO) and dragonfly a*algorithm (DA). The performance of the SVM has been improved significantly by using parameter optimization. Besides, while GA-SVM, PSO-SVM, and DA-SVM models were able to predict engine failures with 95% accuracy, and the GWO-SVM, which demonstrated a good performance in terms of accuracy compared to other metaheuristics a*algorithms, achieves an accura
To improve the efficiency of mobile robot movement, this paper investigates the fusion of the A* a*algorithm with the Dynamic Window Approach (DWA) a*algorithm (IA-DWA) to quickly search for globally optimal collision-fre...
详细信息
To improve the efficiency of mobile robot movement, this paper investigates the fusion of the A* a*algorithm with the Dynamic Window Approach (DWA) a*algorithm (IA-DWA) to quickly search for globally optimal collision-free paths and avoid unknown obstacles in time. First, the data from the odometer and the inertial measurement unit (IMU) are fused using the extended Kalman filter (EKF) to reduce the error caused by wheel slippage on the mobile robot's positioning and improve the mobile robot's positioning accuracy. Second, the prediction function, weight coefficients, search neighborhood, and path smoothing processing of the A* a*algorithm are optimally designed to incorporate the critical point information in the global path into the DWA calculation framework. Then, the length of time and convergence speed of path planning are compared and simulated in raster maps of different complexity. In terms of path planning time, the a*algorithm reduces by 23.3% compared to A*-DWA;in terms of path length, the a*algorithm reduces by 1.8% compared to A*-DWA, and the optimization iterations converge faster. Finally, the reliability of the improved a*algorithm is verified by conducting autonomous navigation experiments using a ROS (Robot Operating System) mobile robot as an experimental platform.
Group key management offers a flexible and reliable security mechanism for secure communication in wireless sensor network by assisting with suitable adjustments of the number of keys per node and the number of re-key...
详细信息
Group key management offers a flexible and reliable security mechanism for secure communication in wireless sensor network by assisting with suitable adjustments of the number of keys per node and the number of re-keying messages. In this article, we obtained a datasets using a projective plane after removing a single element. We employ a stacking ensemble a*algorithm to predict the re-keying value in a projective plane. To improve the performance of the prediction in the stacking model, adaptive boosting and random forest models are chosen as base learners, and for the meta-learner, linear regression is chosen. We observed that the stacking ensemble a*algorithm demonstrated higher accuracy compared to individual models. The accuracy of the stacking ensemble a*algorithm is found to be 0.9999, with MAE, MSE, and RMSE values of 0.0026, 0.0000, and 0.0030 respectively.
暂无评论