检索结果-内蒙古大学图书馆

adaptive genetic algorithm-optimized temporal convolutional networks for high-precision ship traffic flow prediction

引用

EVOLVING SYSTEMS 2025年第1期16卷 1-17页

作者： Li, Yunfan Wang, Qian Kaifeng Univ Sch Finance & Econ Kaifeng 475004 Peoples R China

Timely prediction of Ship Traffic Flow (STF) is essential for managing maritime traffic and preventing congestion. However, existing deep neural network-based STF models often face challenges with hyperparameter selection and limited accuracy improvements. This study introduces a Temporal Convolutional Network (TCN) model optimized by an adaptive genetic algorithm (AGA) to address these issues. The methodology begins with comprehensive data preprocessing, using gate-line-based rules to analyze ship traffic entering and leaving ports, leveraging Automatic Identification System (AIS) data. The AGA-TCN model then employs causally dilated convolutions to capture long-term dependencies and extract frequency domain features, with the AGA dynamically optimizing TCN hyperparameters for specific prediction tasks, resulting in an end-to-end STF prediction framework. AIS data from San Francisco waters, covering the period from June 1, 2022, to December 14, 2022, was used to evaluate the model. The performance of the AGA-TCN model was compared against Particle Swarm Optimization (PSO)-TCN, standard TCN, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models. These models were chosen for comparison due to their widespread use in time-series prediction tasks, representing a variety of approaches in deep learning and optimization. The experiments demonstrate that the AGA-TCN model outperformed all these models, with improvements in RMSE, MSE, and MAPE of 54.37%, 79.18%, and 27.43%, respectively, over the standard TCN. These results underscore the robustness and high accuracy of the AGA-TCN model in STF prediction, establishing it as a superior approach for this application.

关键词： Temporal convolutional networks adaptive genetic algorithm Ship traffic flow Prediction

来源：评论

学校读者我要写书评

暂无评论

adaptive genetic algorithm for Reducing Average Waiting Time for Road Traffic Signals 5

Adaptive Genetic Algorithm for Reducing Average Waiting Time...

引用

5th International Conference on Innovative Trends in Information Technology (ICITIIT)

作者： Sankaranarayanan, Manipriya Yerramsetty, Sudhasree Kakkera, Santosh Kumar, Nitant Indian Inst Informat Technol Sri City Dept Comp Sci & Engn Chittoor Andhra Pradesh India

ISBN: (纸本)9798350386813;9798350386820

Addressing the important need to reduce average waiting times at road traffic signals is crucial, this research offers an optimal strategy targeted at improving the traffic flow efficiency. However, despite its success in lowering wait times, the suggested system has difficulties in dealing with unanticipated traffic spikes. The work proposes an adaptive genetic algorithm (AGA) to reduce traffic waiting time and incorporates complex algorithms and modules along with heuristic algorithms and various sorts of crossovers to achieve notable outcomes to minimize traffic congestion. The performance of AGA was evaluated using the Simulation for Urban MObility (SUMO). The simulation included a four-way junction in which a network with default traffic signal information was simulated and their modified phase time using AGA in network waiting time was also simulated and analysed. The analysis revealed improved results in optimization, with considerable gains produced by combining either of the crossover approaches that have been utilized.

关键词： Traffic Optimization Traffic Light Control SUMO software genetic algorithm adaptive genetic algorithm Waiting Time

来源：评论

学校读者我要写书评

暂无评论

adaptive genetic algorithm Based on Individual Similarity to Solve Multi-Objective Flexible Job-Shop Scheduling Problem

引用

IEEE ACCESS 2022年 10卷 45748-45758页

作者： Liang, Xu Liu, Yifan Gu, Xiaolin Huang, Ming Guo, Fajun Beijing Informat Sci & Technol Univ Comp Sch Beijing 100192 Peoples R China Dalian Jiaotong Univ Software Technol Inst Dalian 116021 Peoples R China Dalian Jiaotong Univ Sch Comp & Commun Engn Dalian 116021 Peoples R China

Aiming at the coupling of energy consumption and completion time in flexible job-shop scheduling, this paper took makespan and energy consumption as the optimization objectives, established a scheduling model, and proposed a scheduling strategy based on improved genetic algorithm. Firstly, a hybrid initialization method based on global minimum completion time selection and global minimum workload selection is introduced to generate the initial population, and the scale of the initial population is expanded to increase the diversity of the population;Secondly, the generation method of offspring individuals is improved, grouped according to the non-dominated ranking level and crowding degree of individuals in the population, and the self-contained individuals are generated by performing crossover and mutation, neighborhood search simulated annealing and reverse learning crossover mutation operations respectively. Finally, an improved adaptive crossover and mutation operation based on individual similarity is proposed, which is applied to the algorithm to improve the search ability of the algorithm. Relevant experimental results show that the proposed adaptive genetic algorithm based on individual similarity is feasible and effective in flexible job-shop scheduling.

关键词： Statistics Sociology genetic algorithms Energy consumption Search problems Optimization Codes Hybrid initialization adaptive genetic algorithm opposition-based learning adaptive crossover-mutation

来源：评论

学校读者我要写书评

暂无评论

Optimization design of the modified SST based on adaptive genetic algorithm

引用

INTERNATIONAL JOURNAL OF APPLIED ELECTROMAGNETICS AND MECHANICS 2024年第4期75卷 479-495页

作者： Zhao, Hanyu Zhang, Yueyue Tu, Jianjian Zheng, Fan Li, Jiale Tianjin Univ Technol Sch Elect Engn & Automat Tianjin Peoples R China Tianjin Univ Technol Tianjin Key Lab New Energy Power Convers Transmiss & Intelligent Control Tianjin Peoples R China

The coupling of magnetic, thermal and structural force fields exists in the design, manufacture and operation of the magnetic core of transformer and motor, which makes the experimental data obtained from the standard magnetic properties measurement inconsistent with the actual problem. In order to obtain the magnetic properties measurement data of soft magnetic materials such as electrical steel sheet under multiple physical factors, the magnetic circuit structure was improved on the basis of the standard single sheet tester. At the same time, anti-bending clips made of polyether ether ketone were installed in order to prevent the bending deformation of the sample sheet during the application of tensile stress which would lead to uneven force. Then0 this basic structure of the tester under the coupling of temperature and stress is designed. In order to further improve the excitation performance of the tester and the magnetization uniformity of the sample, combined with COMSOL and MATLAB co-simulation, adaptive genetic algorithm was used to optimize the size of the yoke and excitation coil, thereby ensuring the uniformity of the magnetic field distribution in the measurement area of the sample. Finally, by combining simulation and specific experiments, the loss measurement results of a single sheet tester under different ambient temperatures and different stresses are studied, which proves that the tester is feasible and accurate, and the variation law of complex magnetic characteristics of electrical steel sheets under multiple physical fields is summarized.

关键词： Single sheet tester multiple physical factors adaptive genetic algorithm COMSOL MATLAB

来源：评论

学校读者我要写书评

暂无评论

Improving camera parameter estimation using an adaptive genetic algorithm

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第1期19卷 1-15页

作者： Khrouch, Hafsa Mahdaoui, Abdelaaziz Hsaini, Abdellah Marhraoui Merras, Mostafa Chana, Idriss Bouazi, Aziz Moulay Ismail Univ Meknes IMAGE Lab IEVIA Team ESTM BP 3103 Toulal Morocco Moulay Ismail Univ Meknes IMAGE Lab SCIAM Team ESTM BP 3103 Toulal Morocco

In this paper, we propose an adaptive genetic algorithm designed to address the camera calibration problem. This approach facilitates the resolution of a complex optimization challenge. Our objective is to refine the camera calibration results estimated by the analytical method. For this purpose, a study was conducted on the type and probability of crossover, the probability of mutation and on the adaptation of the initialization intervals. This adaptation consists of adjusting the length of the initialization intervals. The main objective is to find an optimal solution for the camera calibration parameters by minimizing the cost function. This function is reformulated from the relationship between the points of the 3D target and their 2D projection in the image. Experimental tests and evaluations were conducted to validate the proposed approach. The results indicate that our algorithm is robust and can achieve very satisfactory calibration results.

关键词： Camera calibration adaptive genetic algorithm Cost function Non-linear optimization

来源：评论

学校读者我要写书评

暂无评论

Underwater polarization de-scattering method with dynamic contrast constraint and adaptive genetic algorithm

引用

OPTICS AND LASER TECHNOLOGY 2025年 183卷

作者： Li, Yafeng Sun, Xudong Zhang, Jiqing Chen, Yuehan Li, Yudong Fu, Xianping Dalian Maritime Univ Sch Informat Sci & Technol Dalian 116026 Peoples R China

Polarization imaging effectively suppresses backscattering and has attracted widespread attention. However, existing methods struggle to capture the brightest and darkest polarization images and rely on manual selection of background regions to estimate degree of polarization (DoP) of backscattering. To address these challenges, this study proposes an underwater polarization de-scattering method with dynamic contrast constraint and adaptive genetic algorithm. First, we propose an automatic method to compute the brightest and darkest polarization images by taking derivatives of polarization intensity based on the Stokes vector and finding the extreme values to obtain the results directly. Second, we designed dynamic contrast constraint conditions based on image enhancement characteristics and employed an adaptive genetic algorithm to estimate the DoP of backscattering without relying on background regions. Finally, qualitative and quantitative results demonstrate that our method exhibits superior image quality and higher robustness in various turbid water environments, making it suitable not only for underwater targets of different materials but also for underwater media of different turbidity.

关键词： Polarization imaging Underwater polarization de-scattering Dynamic contrast constraint adaptive genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

adaptive genetic algorithm-based design of gamma-graphyne nanoribbon incorporating diamond-shaped segment with high thermoelectric conversion efficiency

引用

中国物理B（英文版） 2023年第4期32卷 124-132页

作者： Jingyuan Lu Chunfeng Cui Tao Ouyang Jin Li Chaoyu He Chao Tang Jianxin Zhong School of Physics and Optoelectronics Xiangtan UniversityXiangtan 411105China Hunan Key Laboratory for Micro-Nano Energy Materials and Device Xiangtan UniversityXiangtan 411105China

The gamma-graphyne nanoribbons(γ-GYNRs)incorporating diamond-shaped segment(DSSs)with excellent ther-moelectric properties are systematically investigated by combining nonequilibrium Green's functions with adaptive genetic *** calculations show that the adaptive genetic algorithm is efficient and accurate in the process of identifying structures with excellent thermoelectric *** multiple rounds,an average of 476 candidates(only 2.88％of all 16512 candidate structures)are calculated to obtain the structures with extremely high thermoelectric conversion *** room temperature thermoelectric figure of merit(ZT)of the optimal γ-GYNR incorporating DSSs is 1.622,which is about 5.4 times higher than that of pristine γ-GYNR(length 23.693 nm and width 2.660 nm).The significant improvement of thermoelectric performance of the optimal γ-GYNR is mainly attributed to the maximum balance of inhibition of thermal conductance(proactive effect)and reduction of thermal power factor(side effect).Moreover,through exploration of the main variables affecting the genetic algorithm,it is revealed that the efficiency of the genetic algorithm can be improved by optimizing the initial population gene pool,selecting a higher individual retention rate and a lower mutation *** re-sults presented in this paper validate the effectiveness of genetic algorithm in accelerating the exploration of γ-GYNRs with high thermoelectric conversion efficiency,and could provide a new development solution for carbon-based thermoelectric materials.

关键词： adaptive genetic algorithm thermoelectric material diamond-like quantum dots gamma-graphyne nanoribbon

来源：评论

学校读者我要写书评

暂无评论

A novel inverse method for Advanced monitoring of lubrication conditions in sliding bearings through adaptive genetic algorithm

引用

AIN SHAMS ENGINEERING JOURNAL 2025年第2期16卷

作者： Wu, Zhenpeng Dong, Bowen Nie, Liangyi Kefal, Adnan Hubei Polytech Univ Sch Mech & Elect Engn Huangshi 435003 Peoples R China Hubei Polytech Univ Hubei Key Lab Intelligent Conveying Technol & Devi Huangshi 435003 Peoples R China Dalian Univ Technol Key Lab Solidificat Control & Digital Preparat Tec Dalian 116024 Peoples R China Sabanci Univ Fac Engn & Nat Sci TR-34956 Istanbul Turkiye

This study introduces an inverse lubrication analysis (ILA) method, a novel approach for simulating the lubrication state of sliding bearings under various load conditions. By integrating experimental pressure data from sliding bearings with an adaptive genetic optimization algorithm, this method precisely calculates the eccentricity, attitude angle, and global pressure distribution of the lubrication film. Unlike traditional forward lubrication analysis (FLA) methods, which indirectly estimate the lubrication film status through loads, the ILA method utilizes direct pressure measurements, ensuring accurate and timely raw data for inverse calculations. This approach rapidly and accurately converts measured data into key parameters, closely aligning simulation results with experimental data. The lubrication states of the experimental sliding bearing under loads of 100 N, 200 N, 300 N, and 400 N were successfully predicted, highlighting the method's reliability in real-world applications. This study provides a new approach and perspective for health monitoring and fault diagnosis of sliding bearings, especially under extreme conditions.

关键词： Inverse lubrication analysis Sliding bearings Hydrodynamic lubrication adaptive genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Calibration on timing skew mismatch of time-interleaved ADC based on optimized adaptive genetic algorithm back-propagation neural network

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 2025年第5期53卷 3023-3038页

作者： Liu, Cheng Zhao, Jiaqing Zhang, Yang Xi, Zhennan Deng, Jiawei Luo, Xiangdong Nantong Univ Sch Microelect Nantong 226019 Jiangsu Peoples R China Nantong Univ Sch Integrated Circuits Prov Key Lab Semicond Devices & Integrated Circuit Nantong 226019 Jiangsu Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong Jiangsu Peoples R China Nantong Univ Jiangsu Key Lab Semicond Device & IC Design Packaging & Testing Nantong Jiangsu Peoples R China

Aiming to address the timing skew mismatch in the time-interleaved analog-to-digital converter (TIADC) system, this paper presents a timing skew mismatch calibration method based on a back propagation (BP) neural network optimized by an adaptive genetic algorithm (AGA). In this paper, a trained BP neural network is used to detect the timing skew mismatch in the TIADC system, and the variable delay line is used to calibrate it. In this paper, AGA is used to optimize the BP neural network, accelerating its training speed and improving the detection accuracy of timing skew mismatch in the system. The proposed approach boasts superior detection speed and accuracy compared to other methods. In this paper, an 18-bit 1GS/S 4-channel TIADC system is simulated and the timing skew mismatch in the system is corrected. Simulation results show that the proposed calibration method has fast detection speed, high detection accuracy, and calibration accuracy. After completing the timing skew mismatch correction, the performance of the TIADC system is dramatically improved. The effective number of bits (ENOB) of the system increases by 9.5 bits, and the spurious-free dynamic range (SFDR) increases by 59.9 dB. This paper presents a timing skew mismatch calibration method based on a back propagation (BP) neural network optimized by an adaptive genetic algorithm (AGA). The optimized BP neural network is trained to detect the timing skew mismatch in the TIADC system. A variable delay line is used to correct timing skew mismatch within the TIADC system. The effective number of bits of the system increases by 9.5 bits, and the spurious-free dynamic range increases by 59.9 dB. image

关键词： adaptive genetic algorithm BP neural network TIADC timing skew mismatch

来源：评论

学校读者我要写书评

暂无评论

Using adaptive genetic algorithm optimize to realize the extended depth-of-field wavefront coding mask for a large field-of-view microscopy system

引用

OPTICS AND LASERS IN ENGINEERING 2025年 185卷

作者： Zhang, Qinghan Jing, Xudong Sun, Liujie Wei, Xiaoxiao Wan, Xinjun Zheng, Jihong Univ Shanghai Sci & Technol Lab Modern Opt Syst Shanghai 200093 Peoples R China

Wavefront coding technology (WFC) is a computational photography technique that significantly extends a system's depth of field (DOF) while mitigating the impact of aberrations and the environment. A freely inserted wavefront coding microscopy system that realizes high-resolution imaging with large DOF in a wide field of view (FOV) is proposed. On the basis of a designed large DOF microscopy system, an adaptive genetic algorithm is developed to interactively analyze, design, and optimize the phase mask and its effects on the system. The algorithm adaptively adjusts the parameters for selection, crossover, and mutation. Furthermore, it reconstructs the optimization function while considering processability, thereby efficiently and accurately selecting phase mask parameters. The phase mask is prepared and integrated into the system with a freely inserted fixture, which provides flexibility and ease of operation. Wavefront encoding/decoding experiments demonstrate that the system can extend the DOF by approximately +/- 13 times in a large FOV, while slightly decreasing the resolution from 6.20 mu m to 7.81 mu m, and mitigating aberrations and FOV effects. The integrated phase mask does not influence the design of the optical system, is universal, and simplifies the system's structure. This provides advantages in applications such as biological microscopes, endoscopes, and drones, which have strict sample and environmental requirements.

关键词： Wavefront coding Extended depth of field adaptive genetic algorithm Large field of view Microscopy system

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：