Monitoring network traffic and detecting security threats is a vital task in today's world, and intrusion detection systems (IDS) have become an essential tool for this purpose. However, IDSs have to analyze large...
详细信息
Monitoring network traffic and detecting security threats is a vital task in today's world, and intrusion detection systems (IDS) have become an essential tool for this purpose. However, IDSs have to analyze large volumes of data, which often contain irrelevant and redundant features. This makes the job of IDSs more challenging, as they must sift through all available features to identify attack patterns, leading to longer processing time and reduced detection accuracy. To address this, we propose a new wrapper approach for solving the feature selection (FS) problem. Our proposed approach uses a novel multi-objective binary bat algorithm (MBBA-FS) with a decision tree classifier. The MBBA-FS aims to produce a set of non-dominated solutions that minimize the number of features used while maintaining a high detection accuracy. Then, we use a frequency ranking method to identify a single subset of relevant features from the resulting set of non-dominated solutions. We tested the feasibility and performance of our approach against other leading FS methods using various datasets, including KDD CUP 1999, NLS-KDD, UNSW-NB15, and several synthetic benchmarks. The experimental results show that MBBA-FS outperforms existing FS approaches in terms of classification accuracy and number of selected features.
Federated learning (FL) is an advanced distributed machine learning (ML) framework designed to address issues related to data silos and data privacy. In real-world applications, common problems like non-convex optimiz...
详细信息
Federated learning (FL) is an advanced distributed machine learning (ML) framework designed to address issues related to data silos and data privacy. In real-world applications, common problems like non-convex optimization and nonindependent and identically distributed (Non-IID) client data reduce training efficiency, cause local optima, and degrade performance. Therefore, we propose a FL scheme based on the bat algorithm (Fedbat), which leverages the echolocation mechanism of bats to effectively balance global and local search capabilities, enabling the algorithm to escape local optima with a certain probability. By combining global optimal model weight optimization with dynamically adjusted search strategies, Fedbat guides weaker client models toward the global optimum, thereby accelerating convergence. Additionally, Fedbat allows for adaptive parameter adjustments across various datasets. To mitigate client drift, we extend Fedbat with Jensen-Shannon (JS) divergence to quantify differences between local and global models. Clients decide whether to upload their local models based on this divergence, to enhance the global model's generalization and minimize communication overhead. Experimental results demonstrate that Fedbat converges 5 times faster and enhances test accuracy by more than 40%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\%$$\end{document} compared to FedAvg. The extended Fedbat effectively mitigates the decrease in the generalization performance of the global model and reduces communication costs by approximately 20%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\%$$\end{document}. Compar
The interacting multiple model particle filter (IMM-PF) is a filtering method commonly used for nonlinear non-Gaussian radar systems. Its transfer probabilities are usually fixed and dependent on prior information. Wh...
详细信息
The interacting multiple model particle filter (IMM-PF) is a filtering method commonly used for nonlinear non-Gaussian radar systems. Its transfer probabilities are usually fixed and dependent on prior information. When tracking maneuvering targets, the IMM-PF may cause excessive tracking errors due to the model switching lag. In addition, the particle impoverishment caused by the resampling of the particle filter seriously affects the filtering accuracy. Therefore, the IMM-PF has difficulty meeting the accuracy and speed requirements of modern high-performance radar target tracking systems. To address these problems, an adaptive interacting multiple model particle filter based on the dual-pattern bat algorithm (ADIMM-DPBA-PF) is proposed for tracking maneuvering targets under nonlinear and non-Gaussian conditions. First, the adaptive model switching mechanism is established to adjust the transition probabilities using the model probability posterior information at consecutive times, improving the model switching efficiency. Second, a particle filter based on the dual-pattern bat algorithm (DPBA-PF) is proposed. The filter exploits global search and local search strategies to optimize the particles and intelligently move the particles to the high likelihood region. Finally, a particle filter based on the dual-pattern bat algorithm is used to form the adaptive interacting multiple model method. The experimental results show that the proposed algorithm has better comprehensive performance than the IMM-PF.
With the new round of changes in global manufacturing, cloud manufacturing, a new intelligent manufacturing model that integrates information manufacturing, cloud computing, and other technologies, has been proposed. ...
详细信息
With the new round of changes in global manufacturing, cloud manufacturing, a new intelligent manufacturing model that integrates information manufacturing, cloud computing, and other technologies, has been proposed. It aims to rationalise manufacturing resource utilisation and adapt to complex user requirements. However, current research on service composition in cloud manufacturing mode does not fully consider the evaluation indicators of service quality and users' actual needs and constraints. Therefore, this paper first studies multiple service quality optimisation objectives and constraint problems in practical applications and then proposes a dynamic adaptive bat algorithm based on Gaussian mutation. The algorithm achieves fast convergence and reduces the probability of falling into the local extremum by dynamic random adjustment strategy. The effectiveness of the proposed method is verified by comparative experiments. The experimental results show that the proposed method is superior to other algorithms' solution quality and comprehensive performance.
Technological advancements have resulted in the accumulation of vast amounts of data across various industries, often containing redundant or irrelevant features. As a result, the development of efficient feature sele...
详细信息
Technological advancements have resulted in the accumulation of vast amounts of data across various industries, often containing redundant or irrelevant features. As a result, the development of efficient feature selection methods has become increasingly critical. This paper proposes an Improved Binary bat algorithm (IBBA) to overcome the limitations of the original bat algorithm (BA), particularly its weak exploration ability and tendency to become trapped in local optima. IBBA enhances both exploration and exploitation through a novel Fitness-based Exploitation Strategy (FES) and an improved Harris Hawks Optimization (HHO). Additionally, random perturbations are introduced during iterations to adjust positions that deviate from the search space, thus preventing ineffective searches. Since the original BA is primarily designed for continuous optimization problems, this study also investigates the effect of four V-shaped transfer functions on the algorithm's performance. Experimental results on 28 datasets with varying dimensionalities (ranging from nine to 12,600 features) demonstrate that IBBA outperforms 12 state-of-the-art metaheuristic algorithms in terms of fitness, accuracy, feature selection ratio, and runtime. Moreover, an analysis of exploration and exploitation shows that IBBA effectively balances these two processes, addressing BA's exploration shortcomings. The Wilcoxon signed-rank test, conducted at a significance level of 0.05, validates the algorithm's effectiveness, revealing that IBBA demonstrates significant advantages in 87.5% of the tests. Finally, comparisons with 14 recently proposed feature selection methods highlight IBBA's competitive classification accuracy. Therefore, this study is expected to make a valuable contribution to solving feature selection problems across datasets with diverse dimensionalities.
The increasing demand for high-performance two-stage CMOS Op-Amps in electronic, communications, and biomedical applications necessitates their operation with wide bandwidth, high voltage gain, and low power consumpti...
详细信息
The increasing demand for high-performance two-stage CMOS Op-Amps in electronic, communications, and biomedical applications necessitates their operation with wide bandwidth, high voltage gain, and low power consumption. By leveraging the bat algorithm global search and local exploration capabilities, the study demonstrates a significant improvement in the amplifier's overall performance. This design of a two-stage CMOS Op-Amp using 0.18 mu m TSMC technology, powered by a +/- 1.8 V supply voltage. The simulation outcomes were gathered using the PSPICE software (version 17.4). These design strategies prove highly efficient, achieving high gain, high frequency, and low power consumption. Additionally, the paper showcases the execution and simulation results of a two-stage CMOS Op-Amp based on the bat algorithm, utilising MATLAB for this purpose. The employment of the BA results in substantial enhancements in performance metrics. Specifically, the Unity Gain Bandwidth sees a doubling in its value, the voltage gain rises by 20%, power consumption falls by 39.1%, and the Common Mode Rejection Ratio improves by 20% compared to a two-stage CMOS Op-Amp designed without the BA. The findings underscore the BA potency as a robust optimisation method for boosting the performance of a two-stage CMOS Op-Amp.
In this paper, we propose a three-layered neural network controller (NC) optimized using an improved bat algorithm (BA) for a rotary crane system. In our previous study, the simulation results showed that an NC optimi...
详细信息
In this paper, we propose a three-layered neural network controller (NC) optimized using an improved bat algorithm (BA) for a rotary crane system. In our previous study, the simulation results showed that an NC optimized using the original BA exhibits good control and evolutionary performance. However, the simulation execution time was long. Therefore, to address this problem, we propose an improved BA that reduces the execution time. We show that the NC optimized by the improved BA exhibits the same control performance as that optimized via conventional methods. It is also shown that the time for evolutionary calculations can be reduced.
Phishing websites are a growing threat to internet users, and traditional detection methods like blacklisting or relying on SSL certificates are no longer enough to keep up with the rapidly changing landscape of cyber...
详细信息
Phishing websites are a growing threat to internet users, and traditional detection methods like blacklisting or relying on SSL certificates are no longer enough to keep up with the rapidly changing landscape of cyberattacks. In this study, we propose a new approach that combines the power of XGBoost, a popular machine learning algorithm, with the bat algorithm for adaptive hyperparameter optimization, specifically for detecting phishing websites. The bat algorithm, inspired by how bats use echolocation, helps fine-tune critical hyperparameters like learning rate and maximum tree depth, making XGBoost more accurate and better at learning patterns in the data without overfitting. This approach strikes a balance between exploring new solutions and refining the best ones, leading to improved classification performance. Our experiments show that this method significantly enhances accuracy, achieving 94.27% across multiple datasets. Overall, this integrated approach offers an efficient and reliable solution for detecting phishing websites, providing a valuable tool in the ongoing fight against online threats and improving cybersecurity.
bat algorithm (BA) is a novel population-based evolutionary algorithm inspired by echolocation behavior. Due to its simple concept, BA has been widely applied to various engineering applications. As an optimization ap...
详细信息
bat algorithm (BA) is a novel population-based evolutionary algorithm inspired by echolocation behavior. Due to its simple concept, BA has been widely applied to various engineering applications. As an optimization approach, the global search characteristics determine the optimization performance and convergence speed. In BA, the global search capability is dominated by the velocity updating. How to update the velocity of bats may seriously affect the performance of BA. In this paper, we propose a triangle-flipping strategy to update the velocity of bats. Three different triangle-flipping strategies with five different designs are introduced. The optimization performance is verified by CEC2013 benchmarks in those designs against the standard BA. Simulation results show that the hybrid triangle-flipping strategy is superior to other algorithms.
Optimizing reservoir operation rule is considered as a complex engineering problem which requires an efficient algorithm to solve. During the past decade, several optimization algorithms have been applied to solve com...
详细信息
Optimizing reservoir operation rule is considered as a complex engineering problem which requires an efficient algorithm to solve. During the past decade, several optimization algorithms have been applied to solve complex engineering problems, which water resource decision-makers can employ to optimize reservoir operation. This study investigates one of the new optimization algorithms, namely, bat algorithm (BA). The BA is incorporated with different rule curves, including first-, second-, and third-order rule curves. Two case studies, Aydoughmoush dam and Karoun 4 dam in Iran, are considered to evaluate the performance of the algorithm. The main purpose of the Aydoughmoush dam is to supply water for irrigation. Hence, the objective function for the optimization model is to minimize irrigation deficit. On the other hand, Karoun 4 dam is designed for hydropower generation. Three different evaluation indices, namely, reliability, resilience, and vulnerability were considered to examine the performance of the algorithm. Results showed that the bat algorithm with third-order rule curve converged to the minimum objective function for both case studies and achieved the highest values of reliability index and resiliency index and the lowest value of the vulnerability index. Hence, the bat algorithm with third-order rule curve can be considered as an appropriate optimization model for reservoir operation.
暂无评论