检索结果-内蒙古大学图书馆

Finite-time sliding mode synchronisation of a fractional-order hyperchaotic system optimised using a differential evolution algorithm with dual neural networks

引用

IET NETWORKS 2023年第3期12卷 87-97页

作者： Shao, Keyong Feng, Ao Wang, Tingting Li, Wenju Jiang, Jilu Northeast Petr Univ Sch Elect Informat & Engn Daqing Peoples R China

To solve the synchronisation problem associated with fractional-order hyperchaotic systems, in this study, a new dual-neural network finite-time sliding mode control method was developed, and a differential evolution algorithm was used to optimise the switching gain, control parameters, and sliding mode surface parameters, greatly reducing chattering problems in sliding mode controllers. By using the developed method, the complete synchronisation of the drive system and the response system of a fractional-order hyperchaotic system was realised in a finite time;moreover, the stability of the error system under this method was proved by using Lyapunov stability theorem. Numerical simulation results verified the feasibility and superiority of the method.

关键词： differential evolution algorithm finite-time sliding mode controller fractional hyperchaotic system radial basis function neural network (RBFNN) recurrent neural network (RNN)

来源：评论

学校读者我要写书评

暂无评论

Generating Black-box Audio Adversarial CAPTCHAs based on differential evolution algorithm 27

Generating Black-box Audio Adversarial CAPTCHAs based on Dif...

引用

27th International Conference on Computer Supported Cooperative Work in Design (CSCWD)

作者： Liu, Xinhao Yang, Hao Yan, Qiao Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen Peoples R China

ISBN: (纸本)9798350349184;9798350349191

Audio adversarial CAPTCHAs are commonly used on various websites and applications to distinguish human users from automated programs. However, recent advances in deep learning have given rise to several audio recognition methods that pose a challenge to the security of audio CAPTCHAs. In this paper, we propose DE ES, a novel approach based on the differential evolution algorithm, for generating audio adversarial CAPTCHAs. Our method utilizes a momentum probability update technique to add random noise to the examples and combines differential evolution with gradient estimation to enhance the success rate of attacks. We evaluate the similarity between the adversarial examples and the original examples using audio data visualization techniques. Moreover, we apply our method to generate adversarial CAPTCHAs for two usage scenarios of audio CAPTCHAs: input-based and selection-based, respectively, to demonstrate the feasibility of the proposed algorithm. Our experimental results demonstrate that DE ES outperforms other heuristic-based generation methods in terms of the success rate of generating audio adversarial examples, while maintaining a lower average editing distance. Thus, our method provides an effective solution for generating robust audio adversarial CAPTCHAs that can, to a certain extent, withstand the attacks of deep learning models, thereby improving the security of voice-based authentication systems.

关键词： deep learning adversarial examples CAPTCHA differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

A limited-memory BFGS-based differential evolution algorithm for optimal control of nonlinear systems with mixed control variables and probability constraints

引用

NUMERICAL algorithmS 2023年第2期93卷 493-542页

作者： Wu, Xiang Zhang, Kanjian Guizhou Normal Univ Sch Math Sci Guiyang 550001 Peoples R China Southeast Univ Sch Elect Engn Nanjing 210096 Peoples R China Southeast Univ Sch Automat Nanjing 210096 Peoples R China Southeast Univ Key Lab Measurement & Control CSE Minist Educ Nanjing 210096 Peoples R China

In this paper, we consider an optimal control problem of nonlinear systems with mixed control variables and probability constraints. To obtain a numerical solution of this optimal control problem, our target is to formulate this problem as a constrained nonlinear parameter optimization problem (CNPOP), which can be solved by using any gradient-based numerical computation method. Firstly, some binary functions are introduced for each value of the discrete-valued control variable (DCV). Following that, we relax these binary functions and impose a penalty term on the relaxation such that the solution of the resulting relaxed problem (RP) can converge to the solution of the original problem as the penalty parameter increases. Secondly, we introduce a simple initial transformation for the probability constraints. Following that, an adaptive sample approximation method (ASAM) and a novel smooth approximation technique (NSAT) are adopted to formulate the probability constraints as some deterministic constraints. Thirdly, a control parameterization approach (CPA) is used to transform the deterministic problem (i.e., an infinite dimensional problem) into a finite dimensional CNPOP. Fourthly, in order to combine the advantages of limited memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithms and differential evolution (DE) algorithms, a L-BFGS-based DE (L-BFGS-DE) algorithm is proposed for solving the resulting approximation problem based on an improvied L-BFGS (IL-BFGS) method and an improved DE (IDE) algorithm. Following that, we establish the convergence result of the L-BFGS-DE algorithm. The L-BFGS-DE algorithm consists of two stages. The objectives of the first and second stages are to obtain a probable position of the global solution and to accelerate the convergence rate, respectively. In the IL-BFGS method, we propose a novel updating rule (NUR), which uses not only the gradient information of the objective function but also the value of the objective function. T

关键词： Optimal control Nonlinear systems Mixed control variables Probability constraints Limited memory BFGS method differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Flow Control in Network Media Information Transmission Based on differential evolution algorithm

引用

WIRELESS PERSONAL COMMUNICATIONS 2022年第2期127卷 1265-1282页

作者： Liu, Libin Sun, Zhiyuan Shaanxi Radio & Televis Univ Sch Publ Adm Xian 710068 Peoples R China Xian Univ Architecture & Technol Sch Management Xian 710055 Peoples R China

In order to solve the problems of transmission delay and data loss caused by network congestion and strengthen the quality of service of transmission delay and throughput, a method of flow control in network media information transmission based on differential evolution algorithm was presented. By analyzing the delay effect of buffer on network instability, the problems of flow control at the receiving end were clarified. Moreover, the jitter between packet and end-to-end time delay parameters in dynamic caching mechanism were analyzed. The maximum and minimum values were set to calculate the balance point of real-time communication and smooth network information transmission flow. In addition, the differential evolution algorithm based on adaptive quadratic mutation of population fitness variance was used to improve the adaptive global optimization structure, organize the minimum evolution and input the minimum sample. Through reasonable selection of controller parameters and adaptive calculation, the poles of the closed-loop control system were obtained. Finally, the transmission performance index could be optimized. Thus, the stable control of transmission flow was completed. Simulation results show that the proposed algorithm can effectively improve the transmission performance of heterogeneous networks. Meanwhile, it has obvious advantages when the asymmetric parameters are high.

关键词： differential evolution algorithm Flow control Transmission delay Short-wave data

来源：评论

学校读者我要写书评

暂无评论

Application of Improved differential evolution algorithm In the Flatness Assessment of Exposure Machine Substrates 29

Application of Improved Differential Evolution Algorithm In ...

引用

29th International Conference on Automation and Computing (ICAC)

作者： Xi, Jian Pu Nie, Zi Kai Deng, Li Juan Zhang, Tong Tong Liu, Shi Cong Zhongyuan Univ Technol Key Lab Opt Sensing & Testing Technol Mech Ind Zhengzhou Peoples R China Zhongyuan Univ Technol Sch Mechatron Engn Zhengzhou Peoples R China

ISBN: (纸本)9798350360882;9798350360899

To enhance calculation accuracy and irradiation resolution, an optimization algorithm is utilized to improve the precision and speed of the flatness error assessment of the exposure machine's substrate. This substrate suffers from deviation in parallelism of light path irradiation and large flatness matching errors. The goal is to improve calculation accuracy and irradiation resolution in the production of high-precision and high-resolution products. The proposed approach for assessing the flatness error of the substrate involves using the differential evolution (DE) algorithm. To improve the accuracy and convergence speed of the flatness error assessment, the minimum zone method and the principal component analysis method are integrated into the computational logic of the DE algorithm. The DE algorithm, which uses the minimum zone method, is employed to calculate the flatness error of the exposure machine substrate. The accuracy of the algorithm is verified by assessing the flatness error of the substrate using dot matrix data from the exposure machine substrate as an example. The results indicate that the DE algorithm achieves faster convergence in evaluating substrate flatness error. Compared to the least squares method, it improves evaluation accuracy by 56.7% and accuracy by 23% compared to the genetic algorithm. Additionally, it improves convergence speed by 34.2%. The DE algorithm demonstrates superior evaluation accuracy and calculation speed in substrate flatness error evaluation.

关键词： Exposure machine substrate flatness error differential evolution algorithm hybrid optimization

来源：评论

学校读者我要写书评

暂无评论

Economic-effectiveness analysis of micro-fins helically coiled tube heat exchanger and optimization based on multi-objective differential evolution algorithm

引用

APPLIED THERMAL ENGINEERING 2022年第PartB期201卷 117764-117764页

作者： Yuan, Yuyang Cao, Jiaming Wang, Xuesheng Zhang, Zhao Liu, Yanbin East China Univ Sci & Technol Key Lab Pressure Syst & Safety Minist Educ Shanghai 200237 Peoples R China

In this study, the heat transfer characteristics and hydrodynamics of a new type of micro-fin helically coiled tube (MF-HCT) are modelled and compared with those of typical smooth helically coiled tubes (HCTs). Calculation models are developed and compared for both helically coiled tube heat exchangers (HCTHEXs) and micro-fin helically coiled tube heat exchangers (MF-HCTHEXs). The total cost and effectiveness are selected as the objective functions, and five independent structural parameters are selected for each type of HCTHEX. Subsequently, an adaptive multi-objective optimization differential evolution algorithm is implemented for both of them, and the results are compared. The results indicate that, for Reynolds numbers smaller than 22,000, the MFHCT performs better than the HCT, and the total cost of the MF-HCTHEX is lower than that of the HCTHEX under the same effectiveness. The difference between their total cost increases with their effectiveness and can be up to 79,000 euro. For both the HCTHEX and MF-HCTHEX, when the effectiveness is less than 0.9, it is more appropriate to select a larger winding angle, layer spacing, and tube spacing.

关键词： Helically coiled tube heat exchanger Multi-objective optimization Economic analysis Effectiveness differential evolution algorithm Heat transfer

来源：评论

学校读者我要写书评

暂无评论

L∞ Metric based Multi-Objective differential evolution algorithm and its Industrial Application

引用

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2022年第3期38卷 645-663页

作者： Guo, Zhan Ersoy, Okan K. Yan, Xuefeng East China Univ Sci & Technol Key Lab Adv Control & Optimizat Chem Proc Minist Educ Shanghai 200237 Peoples R China Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 200237 Peoples R China

In multi-objective optimization problems, the objective space of fitness functions has a close relationship with the solution space. Extracting the optimal direction and optimal parameter information are very useful for the optimization process. This paper proposes multi-objective differential evolution algorithm with a clustering based objective space division and parameter adaptation (MODECD). L. metric matrix based optimal strategy is used to split the objective space into sub-spaces and to extract the optimal directions. A fitness value based parameter adaptation and mutation strategy are used to extract the optimal strategy information. The results with 20 benchmark tests show the competitiveness of the MODECD algorithm in both convergence speed and diversity of solution approximating the Pareto front. In addition, MODECD is used to optimize the fermentation process of sodium gluconate as an example of its superior performance in solving real-world problems.

关键词： differential evolution algorithm L-infinity metric parameter adaptation multi-objective optimization sodium gluconate production

来源：评论

学校读者我要写书评

暂无评论

Design Automation for Microwave Branch-line Couplers Using Artificial Neural Networks with Self-Adaptive differential evolution algorithm 6

Design Automation for Microwave Branch-line Couplers Using A...

引用

6th Australian Microwave Symposium, AMS 2025

作者： Chen, Tianqi Wu, Qiang Zhu, Xi University of Technology Sydney School of Electrical and Data Engineering Faculty of Engineering and IT Sydney Australia

ISBN: (纸本)9798350379969

The traditional method for designing branch-line couplers relies on a time-consuming labor-intensive trial-And-error process with multiple EM simulation iterations. This paper introduces a novel framework combining artificial neural networks with a self-Adaptive differential evolution algorithm (ANNs-SaDE) for automatic design. The effectiveness of this framework is demonstrated through the design of wideband three-stage couplers. © 2025 IEEE.

关键词： Artificial neural network branch-line coupler differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

App interaction design in the pop music singing teaching system based on differential evolution algorithm

引用

SOFT COMPUTING 2023年第13期27卷 9065-9075页

作者： Wu, Qinke Nanning Normal Univ Coll Mus & Dance Nanning Peoples R China

The dynamic spectrum management of cognitive technology can greatly increase the utilization of network spectrum, but while bringing convenience to our daily lives, this new technology will also greatly increase the consumption of nodes. At present, the short video industry is growing rapidly with the development of smart phones. Among them, the emergence of online popular music singing teaching platforms (mainly software for shooting short videos with music as the background) has brought significant changes to people's lifestyles. We can learn from the three-stage theory of flow experience to design and explore the method of plan implementation, and propose a targeted interaction design strategy for each flow characteristic, so that the overall design strategy becomes more practical and practical. In the design of this paper, the principle of cognitive wireless sensor network is applied in the technical aspect and the principle of interactive design is applied in the product design. When a user reaches a state of flow while using the online popular music singing teaching platform, it can be evaluated that the user experience of the app is the best. The research on the interaction design of the online pop music singing teaching platform under the flow experience is intended to propose an interactive design strategy that can guide the online pop music singing teaching platform to better create a flow experience for users.

关键词： Wireless sensor Interactive design differential evolution algorithm Platform design

来源：评论

学校读者我要写书评

暂无评论

Quantum Entanglement inspired differential evolution algorithm

Quantum Entanglement inspired Differential Evolution algorit...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Dixit, Abhishek Mani, Ashish Chongqing Univ Educ 1 Sch Artificial Intelligence Chongjiao RdNanshan St Chongqing 400065 Peoples R China Amity Sch Engn & Technol Amity Innovat & Design Ctr Dept EEE Noida India

ISBN: (纸本)9798400701207

The differential evolution (DE) algorithm is an efficient algorithm with strong search capability. This algorithm is easy to implement and used for solving large-scale optimization problems. However, DE also has drawbacks of insufficient diversity in the later search stage, while solving optimization problems, slow convergence speed, and a high search stagnation possibility. Quantum Entanglement inspired differential evolution algorithm (QE-DE) has been proposed in this paper to solve the drawbacks of DE. For solving high-dependency optimization problems, QE-DE integrates entangled states in its Qubits (or quantum bit). The optimization process is further accelerated by utilizing the quantum local search. The proposed QE-DE algorithm is evaluated on the IEEE Congress of evolutionary Computing (CEC 2017) benchmark set for 10 and 30-dimensions. QE-DE is also compared with existing variants of DE and some other popular algorithms. QE-DE outperforms the performance comparison results.

关键词： Quantum Entanglement differential evolution algorithm Metaheuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：