检索结果-内蒙古大学图书馆

4th International Conference on Graphic and Image Processing (ICGIP)

作者： Liu, Shuping Cheng, Yanliu North China Elect Power Univ Baoding 071003 Hebei Peoples R China

ISBN: (纸本)9780819495662

In this paper, the MPI master-slave parallel genetic algorithm is implemented by analyzing the basic genetic algorithm and parallel MPI program, and building a Linux cluster. This algorithm is used for the test of maximum value problems (Rosen brocks function). And we acquire the factors influencing the master-slave parallel genetic algorithm by deriving from the analysis of test data. The experimental data shows that the balanced hardware configuration and software design optimization can improve the performance of system in the complexity of the computing environment using the master-slave parallel genetic algorithms.

关键词： MPI Cluster parallel genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

DGA Fault Diagnosis Based on the Counter Propagation Neural Network Optimized by parallel genetic algorithm

DGA Fault Diagnosis Based on the Counter Propagation Neural ...

引用

IEEE International Conference of Region 10 (TENCON)

作者： Zhao, An-Xin Zhang, Cai-Tian Xian Univ Sci & Technol Network Ctr Xian Peoples R China HeNan Econ & Trade Vocat Coll Dept Elect Engn Zhengzhou Peoples R China

ISBN: (纸本)9781479928255;9781479928279

Using the counter propagation artificial neural network (CPANN) to diagnose the DGA fault, network structural parameters should be set, such as the training epochs, network size etc. When user to set, it would be affect by the artificial subjective factors. If we use the traversal search way, it would be the consumption of computing and time. So this article employed parallel genetic algorithm to optimize network structure optimization parameters of counter propagation neural network. genetic algorithm is a simulation Darwin the evolution natural selection and genetic mechanism of biological evolution process calculation model, and a by simulating natural evolution to search the optimal solution. In the GA procedure, the fitness function was defined by the correct ratio combination of the calibration data set and validation data set, as the rules for selecting the optimal network parameters. When selecting the optimal network parameters, the relatively high repeated frequency of chromosome and the optimal fitness function values simultaneously were considered.

关键词： dissolved gas-in-oil analysis (DGA) fault diagnosis Counter-Propagation Artificial Neural Networks (CPANN) parallel genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimal deploying IoT services on the fog computing: A metaheuristic-based multi-objective approach

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第10期34卷 10010-10027页

作者： Wu, Banghua Lv, Xuebin Shamsi, Wameed Deyah Dizicheh, Ebrahim Gholami Sichuan Univ Coll Cybersecur Chengdu 610041 Peoples R China Al Mustaqbal Univ Coll Informat Technol Unit Babylon 51001 Iraq Univ Tehran Sch ECE Tehran Iran Sichuan Univ Sch Comp Sci & Engn Chengdu 610064 PR Peoples R China

This study deals with solving the Internet of Things (IoT) Service Placement Problem (SPP) in fog computing environment using metaheuristic approaches. Basically, SPP is a non-deterministic polynomial-time hard (NP-hard) with huge discrete search spaces that is often processed by heuristic and metaheuristic approaches. We proposed an Improved parallel genetic algorithm (IPGA) to solve SPP and named it IPGA-SPP. Since the genetic algorithm may get stuck in local optima, we configure it in parallel with a shared memory along with several elitist operators. IPGA-SPP considers resource distribution for load balancing and prioritizes service execution to reduce latency. Also, IPGA-SPP solves the problem as a multi-objective problem by maintaining a set of Pareto solutions by making compromises between service latency, service cost, resource utilization and service time. Although many metaheuristic approaches have been developed for SPP, but satisfying the quality of service (QoS) and simultaneously guaranteeing security to overcome the constraints of fog computing has been less considered. In this regard, we equip IPGA-SPP with a two-way trust management mechanism so that clients and service providers can verify each other's trustworthiness. Therefore, the proposed scheme is a latency-aware, cost-aware and trustaware approach to improve the deployment process in fog computing. Through simulation on a synthetic fog environment, IPGA-SPP has shown an average of 8.4% better performance compared to state-of-theart methods such as CSA-FSPP, GA-PSO, EGA and WOA-FSP.

关键词： Internet of Things Fog Computing Services Placement Multi-objective problem parallel genetic algorithm Trust Management Mechanism

来源：评论

学校读者我要写书评

暂无评论

Optimization of RIS Placement for Satellite-to-Ground Coverage Enhancement

Optimization of RIS Placement for Satellite-to-Ground Covera...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Liu, Xingchen Xue, Liuxun Sun, Shu Tao, Meixia Shanghai China

ISBN: (纸本)9798350370218

In satellite-to-ground communication, ensuring re-liable and efficient connectivity poses significant challenges. The reconfigurable intelligent surface (RIS) offers a promising solution due to its ability to manipulate wireless propagation environments and thus enhance communication performance. In this paper, we propose a method for optimizing the placement of RISs on building facets to improve satellite-to-ground commu-nication coverage. We model satellite-to-ground communication with RIS assistance, considering the actual positions of buildings and ground users. The theoretical lower bound on the cover-age enhancement in satellite-to-ground communication through large-scale RIS deployment is derived. Then a novel optimization framework for RIS placement is formulated, and a parallel genetic algorithm is employed to solve the problem. Simulation results demonstrate the superior performance of the proposed RIS deployment strategy in enhancing satellite communication coverage probability for nonline-of-sight users. The proposed framework can be applied to various architectural distributions, such as rural areas, towns, and cities, by adjusting parameter settings. © 2023 IEEE.

关键词： parallel genetic algorithm Reconfigurable intelligent surfaces satellite-to-ground communication

来源：评论

学校读者我要写书评

暂无评论

parallel image encryption with bitplane decomposition and genetic algorithm

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2018年第19期77卷 25799-25819页

作者： Mozaffari, Saeed Semnan Univ Fac Elect & Comp Engn Semnan Iran

Image encryption is an efficient technique to protect image content from unauthorized parties. In this paper a parallel image encryption method based on bitplane decomposition is proposed. The original grayscale image is converted to a set of binary images by local binary pattern (LBP) technique and bitplane decomposition (BPD) methods. Then, permutation and substitution steps are performed by genetic algorithm (GA) using crossover and mutation operations. Finally, these scrambled bitplanes are combined together to obtain encrypted image. Instead of random population selection in GA, a deterministic method with security keys is utilized to improve security level. The proposed encryption method has parallel processing capability for multiple bitplanes encryption. This distributed GA with multiple populations increases encryption speed and makes it suitable for real-time applications. Simulations and security analysis are done to demonstrate efficiency of our algorithm.

关键词： parallel image encryption Bitplain decomposition Local binary pattern Metaheuristic algorithms parallel genetic algorithm GPU programming

来源：评论

学校读者我要写书评

暂无评论

Glubam roof truss with riveted glubam connections adopting thin-walled steel tube: Experiment, modeling, and model-updating

引用

JOURNAL OF BUILDING ENGINEERING 2024年 96卷

作者： Shi, Da Xu, Yongjia Demartino, Cristoforo Lu, Guoshan Li, Zhi Zhejiang Univ Coll Civil Engn & Architecture 866 Yuhangtang Rd Hangzhou 310058 Zhejiang Peoples R China Politecn Torino DISEG Dipartimento Ingn Strutturale Edile & Geotec Corso Duca Degli Abruzzi 24 I-10128 Turin Italy Zhejiang Univ Univ Illinois Urbana Champaign Inst Haining 314400 Zhejiang Peoples R China Univ Illinois Dept Civil & Environm Engn Urbana IL 61801 USA Roma Tre Univ Dept Architecture I-00153 Rome Italy Nanjing Tech Univ Coll Civil Engn Nanjing 211800 Peoples R China

Bio-based laminated structures offer a timely solution to meet the pressing demand for resource-efficient and environmentally responsible construction practices in civil engineering. Riveted connections are a kind of commonly used joint and significantly impact the mechanical behaviors of global structure. However, existing studies on the complex behavior of such joints for bamboo-based structures are insufficient. This study investigated the hysteretic behavior of riveted Glued Laminated Bamboo (glubam) connections using thin-walled steel tube and corresponding planar roof truss with thin-walled steel tube connections by experimental and numerical methods. Firstly, cyclic tests were conducted on the riveted glubam connections with thin-walled steel tube to investigate their hysteretic behavior. The test matrix encompasses four distinct connection configurations, carefully selected to assess the connection behavior of glubam. After the investigation of connection behavior, cyclic tests were further conducted on glubam planar roof truss structures to evaluate their global and local hysteretic behavior. Subsequently, the numerical hysteretic models for joints and hybrid roof trusses were developed within the OpenSeesPy framework. To accurately and efficiently calibrate the model parameters, a novel parallel genetic algorithm (PGA) was proposed to carry out an initial calibration on model parameters. Based on PGA, a more comprehensive model updating framework combining the neural network, prior knowledge and PGA was developed to obtain optimal parameters. Finally, the numerical models were successfully validated against the experimental data, demonstrating the effectiveness of the established numerical model and model-updating framework.

关键词： Glubam riveted connections Thin-walled steel tube Model updating parallel genetic algorithm Neural network and prior knowledge

来源：评论

学校读者我要写书评

暂无评论

Distributed parallel algorithms for online virtual network embedding applications

引用

INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS 2023年第1期36卷 e4325-e4325页

作者： Lu, Qiao Nguyen, Khoa Huang, Changcheng Carleton Univ Dept Syst & Comp Engn Ottawa ON K1S 5B6 Canada

Network virtualization (NV) has ubiquitously emerged as an indispensable attribute to enable the success of the forthcoming virtualized networks (eg, 5G network and smart Internet of Things [IoT]). Virtual network embedding (VNE) is the major challenge in NV that allows multiple heterogeneous virtual networks (VNs) to simultaneously coexist on a shared substrate infrastructure. A great number of VNE algorithms have been proposed, but over the past decades, most of them are only targeting for VNE node mapping. In this paper, we propose two distributed parallel genetic algorithms, which are based on two versions of crossover and mutation schemes, for online VN link embedding problems with low latency and high efficiency. Furthermore, we conduct a time analysis on the executing time of independently distributed parallel computing machines in details. This comprehensive analysis validates the parallel computing scalability on an identical number of predefined parallel machines. Extensive simulations have shown that our proposed algorithms can achieve better performance than integer linear programming (ILP)-based solutions while meeting the stringent time requirements for online VN embedding applications. Our proposed algorithms yield superior performance in running time with 32.78% up to 1727.8% faster than existing popular VNE algorithms. Additionally, the theoretical analysis indicates that the execution time can be reduced to logarithmic times by applying proposed distributed parallel algorithms.

关键词： 5G network distributed parallel algorithm metaheuristic network virtualization parallel genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

The Automated Fault-recovery for Four-legged Robots using parallel genetic algorithm

引用

Procedia Computer Science 2013年 24卷 158-166页

作者： Hyunsoo Park Kyung Joong Kim Department of Computer Engineering Sejong University Seoul Republic of Korea

It is expected that robots could operate autonomously in extreme environments without human intervention. However, it is not a trivial task to design robots robust to all kinds of faults. On the other hand, Biological entities have capability to create new behaviors overcoming unexpected damage on their body. This is also one of desirable properties for industrial robots operating remotely in extreme conditions. In this paper, we propose to use a bio- inspired learning algorithm to generate new behaviors on a four-legged robot against unexpected body damages. Since the learning algorithm can be accelerated using parallelism on multiple machines, it is possible to adapt to changes (damages) quickly using remote computational resources. Experimental results show that the robot could adapt to damages on different part of robot's body successfully.

关键词： fault-tolerant robot parallel genetic algorithm neural network physical-based simulation

来源：评论

学校读者我要写书评

暂无评论

Fast parallel computation of reduced row echelon form to find the minimum distance of linear codes

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期224卷

作者： Cuellar, Manuel P. Lobillo, F. J. Navarro, Gabriel Univ Granada Dept Comp Sci & Artificial Intelligence Calle Periodista Daniel Saucedo Aranda s-n E-18071 Granada Spain Univ Granada Dept Algebra Calle Fuente Nueva S-N E-18071 Granada Spain Univ Granada CITIC Calle Periodista Rafael Gomez Montero 2 E-18071 Granada Spain

Finding the distance of linear codes is a key aspect to build error correcting codes, and also to design attacks in code-based post-quantum cryptography;however, it is a NP-hard problem difficult to be addressed. Metaheuristics, and more specifically genetic algorithms, have proven to be a promising tool to improve the search of an upper bound for the distance of a given linear code. In a previous work, it was demonstrated that the there exists a column permutation of a code matrix whose Reduced Row Echelon Form (RREF) contains a row of minimum weight, i.e. the code distance, although calculating RREF during fitness evaluation increases the time complexity of the algorithm substantially. In this work, we propose parallelization of multiple calculations of Reduced Row Echelon Forms simultaneously, and its integration into a fully parallelized design of a CHC evolutionary algorithm to overcome this limitation. Moreover, we demonstrate empirically a substantial improvement in time complexity for the approach in practical case studies to find the distance of linear codes over different finite fields.

关键词： Linear code Minimum distance genetic algorithm parallel genetic algorithm GPU-based parallel model Post-quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

A hybrid, massively parallel implementation of a genetic algorithm for optimization of the impact performance of a metal/polymer composite plate

引用

INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS 2013年第2期27卷 217-227页

作者： Narayanan, Kiran Mora, Angel Allsopp, Nicholas El Sayed, Tamer King Abdullah Univ Sci & Technol Thuwal 239556900 Saudi Arabia Cray Comp Stuttgart Germany

A hybrid parallelization method composed of a coarse-grained genetic algorithm (GA) and fine-grained objective function evaluations is implemented on a heterogeneous computational resource consisting of 16 IBM Blue Gene/P racks, a single x86 cluster node and a high-performance file system. The GA iterator is coupled with a finite-element (FE) analysis code developed in house to facilitate computational steering in order to calculate the optimal impact velocities of a projectile colliding with a polyurea/structural steel composite plate. The FE code is capable of capturing adiabatic shear bands and strain localization, which are typically observed in high-velocity impact applications, and it includes several constitutive models of plasticity, viscoelasticity and viscoplasticity for metals and soft materials, which allow simulation of ductile fracture by void growth. A strong scaling study of the FE code was conducted to determine the optimum number of processes run in parallel. The relative efficiency of the hybrid, multi-level parallelization method is studied in order to determine the parameters for the parallelization. Optimal impact velocities of the projectile calculated using the proposed approach, are reported.

关键词： parallel genetic algorithm computational steering optimization impact ductile fracture composite

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：