检索结果-内蒙古大学图书馆

8th International Conference on Artificial Intelligence and Security (ICAIS)

作者： Bo, Xiong Feng Wenlong Zhang, Jin Hainan Univ Sch Informat & Commun Engn Haikou 570228 Hainan Peoples R China Towson Univ Dept Comp & Informat Sci 8000 York Rd Towson MD 21252 USA

ISBN: (纸本)9783031067884;9783031067877

The traditional whale algorithm has some shortcomings such as low solution accuracy and falling into local optimization easily. Aiming at these, a new whale optimization algorithm (NWOA) based on the artificial fish swarm algorithm is proposed, which combined with the advantages of artificial fish swarm algorithm that the crowding factor is used to limit the cluster size to promote the algorithm to be more optimized widely. The new whale optimization algorithm introduces the concept of crowding in the artificial fish swarm algorithm (AFSA) into the whale algorithm and changes characteristics of whale populations, and it overcomes the shortcoming of the traditional whale algorithm that individual whales perform different foraging behaviors according to the size of the random probability number. By calculating the degree of crowding around the prey, the foraging behavior of individual whales is designed to improve the convergence speed and optimization accuracy of the whale algorithm and enhance the stability of the algorithm. The simulation experiment is conducted by selecting 9 benchmark test functions. The experimental results show that the convergence speed and algorithm stability of the algorithm in this paper are significantly improved compared to the traditional whale algorithm.

关键词： Whale optimization algorithm Artificial fish swarm algorithm algorithm optimization Random probability number Crowdedness

来源：评论

学校读者我要写书评

暂无评论

A Neural Network algorithm of Learning Rate Adaptive optimization and Its Application in Emitter Recognition 13th

A Neural Network Algorithm of Learning Rate Adaptive Optimiz...

引用

13th European-Alliance-for-Innovation (EAI) International Conference on Simulation Tools and Techniques (EAI SIMUtools)

作者： Jiang, Jihong Gou, Yan Zhang, Wei Yang, Jian Gu, Jie Shao, Huaizong Univ Elect Sci & Technol China Chengdu 611731 Sichuan Peoples R China Southwest China Inst Elect Technol Chengdu 610036 Sichuan Peoples R China Sci & Technol Elect Informat Control Lab Chengdu 610036 Sichuan Peoples R China Peng Cheng Lab Shenzhen 519012 Guangdong Peoples R China

ISBN: (纸本)9783030971243;9783030971236

The setting of the learning rate in neural network training is very important. A too low learning rate will reduce the network optimization speed and prolong the training time while a too high learning rate is easy to exceed the optimal value, leading to the difficulty of model convergence. To solve this problem, based on the analysis of two common learning rate strategies, the attenuating learning rate and the adaptive learning rate, combined with the Adam algorithm, this paper proposes an adaptive learning rate algorithm based on the value of the current loss function and the previous one, and verifies the effectiveness of the algorithm by using the actual radiation source signal. The experimental results show that compared with the Adam algorithm, the number of network training iterations is reduced by 45.5% and the recognition accuracy has increased by 3.6%, which effectively improves the learning speed and reduces the training time.

关键词： Neural network Learning rate algorithm optimization Emitter recognition Application

来源：评论

学校读者我要写书评

暂无评论

Parallel multi-join query optimization algorithm for distributed sensor network in the internet of things

Parallel multi-join query optimization algorithm for distrib...

引用

Conference on Smart Sensor Phenomena, Technology, Networks, and Systems Integration

作者： Zheng, Yan Heilongjiang Inst Technol Sch Comp Sci & Technol Harbin 150050 Peoples R China

ISBN: (纸本)9781628415391

Internet of things (IoT), focusing on providing users with information exchange and intelligent control, attracts a lot of attention of researchers from all over the world since the beginning of this century. IoT is consisted of large scale of sensor nodes and data processing units, and the most important features of IoT can be illustrated as energy confinement, efficient communication and high redundancy. With the sensor nodes increment, the communication efficiency and the available communication band width become bottle necks. Many research work is based on the instance which the number of joins is less. However, it is not proper to the increasing multi-join query in whole internet of things. To improve the communication efficiency between parallel units in the distributed sensor network, this paper proposed parallel query optimization algorithm based on distribution attributes cost graph. The storage information relations and the network communication cost are considered in this algorithm, and an optimized information changing rule is established. The experimental result shows that the algorithm has good performance, and it would effectively use the resource of each node in the distributed sensor network. Therefore, executive efficiency of multi-join query between different nodes could be improved.

关键词： Multi-join query algorithm optimization genetic algorithm communication efficiency internet of things

来源：评论

学校读者我要写书评

暂无评论

Multiobjective optimization of the Synchrotron Radiation Source Siberia-2 Lattice Using a Genetic algorithm

引用

PHYSICS OF PARTICLES AND NUCLEI LETTERS 2018年第1期15卷 92-96页

作者： Korchuganov, V. N. Smygacheva, A. S. Fomin, Ye. A. Natl Res Ctr Kurchatov Inst Moscow 123182 Russia

Numerical simulation is one of the most efficient methods of investigating and optimizing nonlinear effects. However, simulating complex processes considering numerous nonlinear effects with the use of classical optimization methods is very difficult. This work deals with the application of a multiobjective genetic algorithm for the optimization of lattices of synchrotron radiation sources. This algorithm allows one to efficiently optimize both the linear and complex strongly nonlinear lattices of accelerators to obtain the required facility parameters.

关键词： algorithm optimization Accelerators crystal lattices optimization methods Synchrotron radiation sources nonlinearity optimization method Genetic algorithm (GA)

来源：评论

学校读者我要写书评

暂无评论

Landscape Garden Planning optimization algorithm Based on Group Intelligent optimization Path Technology 1

Landscape Garden Planning Optimization Algorithm Based on Gr...

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Wang, Xiao Piao, Yushun Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9798350316469

With the continuous development of China's economy and society, the urban population is increasing and the urban area is also expanding. In this context, landscape garden planning and design is particularly important. This article introduces the basic principles, advantages and application of group intelligent optimization path technology in landscape and garden planning optimization. Through the use of this technology, the planning efficiency can be effectively improved. The use of this technology can greatly reduce manual intervention in traditional landscape garden planning, and greatly improve the efficiency of landscape garden planning and design. The experimental results show that the number of iterations of the landscape garden planning optimization algorithm based on the group intelligent optimization path technology can reach at least 332 times. Through swarm intelligence optimization, we can better understand the needs of tourists or users, thereby planning more practical and humane landscape gardens, and improving the user experience. © 2023 IEEE.

关键词： algorithm optimization Group Intelligence optimization Landscape Architecture Path Technology

来源：评论

学校读者我要写书评

暂无评论

The optimization and Implementation of the Auto-Exposure algorithm Based on Image Entropy 8

The Optimization and Implementation of the Auto-Exposure Alg...

引用

8th International Conference on Digital Image Processing (ICDIP)

作者： Ning, Jingyi Lu, Tiejun Liu, Liyan Guo, Liye Jin, Xiaofeng 2 Siyingmen N Rd Beijing 100076 Peoples R China

ISBN: (纸本)9781510605039;9781510605046

To achieve auto-exposure in digital cameras, image brightness is widely used because of its direct relationship with exposure time. Although image entropy which represents information measure of image is widely used in various image processing applications, it has not been used on FPGA in AE system due to its complex calculation. Image with maximum entropy value contains more information. So this paper presents an algorithm based on image entropy. By searching maximum entropy value, the image can get an appreciate exposure. What's more, by using formula manipulation of image entropy and piecewise linearization of the log function, the optimized algorithm grasps the overall change rule in stead of traditional calculation and has been realized on FPGA. The experiment results show that on basis of 10M work frequency of CMOS image sensor ( electronic shutter, 1024 by 1024 pixels, on-chip 12-bit ADC) and 100M clock frequency of FPGA (ALTERA-EP2S60F48414N), this algorithm works well. And at the same time, the algorithm improves the amount of image information and increases the accuracy of auto exposure.

关键词： auto-exposure image-entropy algorithm optimization realize on FPGA

来源：评论

学校读者我要写书评

暂无评论

Research on Logistics Development Level Classification using Enhanced K-Means Clustering algorithm based on AC-PSO optimization 3

Research on Logistics Development Level Classification using...

引用

3rd IEEE International Conference on Electrical Engineering, Big Data and algorithms, EEBDA 2024

作者： Liu, Yiwen Business School Henan University of Science and Technology Luoyang China

ISBN: (纸本)9798350380989

This paper introduces an optimized K-means clustering model based on AC-PSO, aiming to address challenges associated with the selection of initial cluster centers in traditional K-means clustering. Leveraging the potent search capabilities of the Particle Swarm optimization (PSO) algorithm, the AC-PSO algorithm overcomes issues present in traditional PSO, such as a lack of rigorous mathematical foundations and weakened search capabilities in later stages leading to susceptibility to local optima. The proposed algorithm incorporates adaptive update strategies and employs chaotic mapping-based inertia weight selection, providing a more robust optimization process and avoiding the pitfalls of local optima during the optimization journey. Comprehensive tests on benchmark datasets (Iris, Wine, and Breast Cancer) demonstrate the superior performance of the proposed model in terms of precision, fitness values, and convergence speed when compared to traditional K-means and K-means based on PSO. Furthermore, the application of the optimized model to the clustering of logistics development levels across 18 cities in Henan Province for the year 2020 validates its effectiveness in real-world scenarios. This optimized K-means clustering model offers a novel approach to address the challenge of initial cluster center selection, showcasing potential improvements in accuracy and efficiency across various clustering tasks. © 2024 IEEE.

关键词： algorithm optimization Benchmark datasets Factor analysis K-means clustering Particle Swarm optimization Regional logistics development

来源：评论

学校读者我要写书评

暂无评论

Optimizing time-delay estimation for underwater acoustic positioning in tank inspection robots to mitigate reflection interference

引用

APPLIED OCEAN RESEARCH 2025年 154卷

作者： Xu, Zhenyu Chen, Zhangwei Zhejiang Univ State Key Lab Fluid Power & Mechatron Syst Hangzhou Peoples R China

Robot inspection of large storage tanks has become the primary method for addressing hidden risks in the petrochemical industry. Accurate positioning of Tank Inspection Robots (TIR) is crucial in this process. However, the unique characteristics of the liquid medium and tank walls introduce challenges such as noise, reverberations, and multipath effects, which frequently complicate the acoustic positioning of robots. These issues are further complicated by numerous interface reflections. To address the problems caused by reflections, this paper focuses on time-delay estimation for underwater acoustic positioning. It analyzes the impact of reflections on various acoustic positioning methods and simplifies the time-delay estimation process within the Time Difference of Arrival (TDOA) localization algorithm in reverberant environments. To this end, the paper introduces the AMCOCEP algorithm, which integrates Generalized Cross-Correlation, the cepstrum, and the Average Magnitude Difference Function (AMDF). The effectiveness of the proposed positioning model and method is validated by positioning a robot within a storage tank and comparing positioning accuracy before and after algorithm optimization. According to the experimental results, the AMCOCEP algorithm reduces the average error by 1.07 cm and improves the average accuracy by 30.7 %.

关键词： Tank inspection robot Underwater acoustic positioning Time-delay estimation Reflection interference algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

Integrating knowledge-data-driven method to predict load-displacement curve on a trapdoor

引用

COMPUTERS AND GEOTECHNICS 2025年 178卷

作者： Zeng, Hui Lin, Xing-Tao Wang, Deng Chen, Xiangsheng Su, Dong Chen, Ruidi Liu, Wei Shenzhen Univ Key Lab Resilient Infrastruct Coastal Cities MOE Shenzhen 518060 Peoples R China Shenzhen Univ Coll Civil & Transportat Engn Shenzhen 518061 Peoples R China State Key Lab Intelligent Geotech & Tunnelling Shenzhen 518060 Guangdong Peoples R China Shenzhen Univ Underground Polis Acad Shenzhen 518060 Peoples R China

Accurately predicting the overlying earth pressure of underground structures is a key point in the design and construction of underground structures. On the basis of the existing composite function model describing the load-displacement curve (LDC) and experimental data, a intergrating knowledge-data-driven method to predict LDC is proposed in this paper. The buried depth (H), trapdoor width (B), soil weight (gamma) and internal friction angle (phi) are selected as multi-characteristic input variables. The initial modulus of arching a, the minimum soil arching ratio rho min, the minimum soil arching ratio displacement xi min and the ultimate soil arching ratio rho ult are output variables. Two swarm intelligence optimization algorithms (i.e., sparrow search algorithm (SSA) and particle swarm optimization (PSO)) are used to optimize the parameters of the established generalized regression neural network (GRNN), and the knowledge-data cooperatively driven prediction of the LDC is realized. The results show that the GRNN model optimized by swarm intelligence algorithm has better prediction performance than the GRNN model. The LDC obtained from the output parameters of three GRNN models are compared with the results of the trapdoor experiments. The comparison results show that the LDC obtained by the GRNN model optimized by swarm intelligence algorithm are more consistent with the experimental results than that those obtained by GRNN model, and the prediction performance of the SSA-GRNN is slightly better than that of the PSO-GRNN.

关键词： Soil arching effect Load-displacement curve (LDC) Composite function model Generalized regression neural network algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

Exploration on Text Detection optimization algorithm Based on Neural Network Technology 1

引用

13th International Conference on Frontier Computing, FC 2023

作者： Liang, Junxia Qi, Yongjun Faculty of Megadata and Computing Guangdong Baiyun University Guangdong Guangzhou510450 China School of Information and Communication Technology Mongolian University of Science and Technology Bayanzurkh District Ulaanbaatar13341 Mongolia

ISBN: (数字)9789819992997

ISBN: (纸本)9789819992980

In this rapidly changing era of information technology, images have always been the main tool for human communication of information. In daily life, a large number of natural scene images, such as road signs, advertising slogans, etc., often contain important textual information, which is of great help to people’s understanding of image content. Text is a type of linguistic information that exists in various aspects of people’s lives. The textual information in it can help people understand, describe, and analyze natural scenes, and has important social value. Neural network technology is of great help for optimizing text detection. This paper discussed the optimization performance of neural network algorithm for text detection, and verified the progressiveness of the algorithm through experiments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： algorithm optimization Experimental Study Neural Network Technology Text Detection

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：