检索结果-内蒙古大学图书馆

IEEE International Conference on Industrial Technology (ICIT)

作者： T. Engwirda A. Engwirda L. Vlacic G. Dromey Intelligent Control Systems Laboratory School of Microelectronic Engineering Griffith University QLD Australia School of Computing and Information Technology Griffith University QLD Australia

Using technologies such as Web browser-based programming languages and multimedia tools, the authors are developing a sophisticated control environment for use as a World Wide Web front-end to intelligent control systems. Cooperative behaviour will be remotely facilitated through a two-way transferral of data-status information from the vehicles to the operator, and commands/parameters from the operator to the vehicles. This paper describes the background and context, the proposed solution at the concept level, and issues concerned with implementation.

关键词： Mobile robots Internet World Wide Web Control systems intelligent control Remotely operated vehicles Laboratories Microelectronics Computer languages Multimedia systems

来源：评论

学校读者我要写书评

暂无评论

Cooperative autonomous robot colonies

Cooperative autonomous robot colonies

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： A. Engwirda T. Engwirda L. Vlacic A. Sattar Intelligent Control Systems Laboratory School of Microelectronic Engineering Griffith University Brisbane QLD Australia School of Computing and Information Technology Griffith University Brisbane QLD Australia

A concept for implementation of a colony of cooperative autonomous agents is under development. This concept enables useful and productive work to be accomplished by adaptable and dynamic autonomous agents in real-time and real-world environments. Three primary issues of cooperative autonomous mobile agents are addressed being interaction, management and sustainability. The focus of this paper is the issue of interaction within a colony of cooperative agents while the issues of management and sustainability are scheduled for future research. The view of the agents as a colony is due to their number and the use of agent support structures. A colony of agents has a defined base of operations consisting of relatively static agents while also containing a number of mobile agents.

关键词： Robot sensing systems Navigation Path planning Autonomous agents Australia Mobile agents Large-scale systems Computer errors intelligent control Laboratories

来源：评论

学校读者我要写书评

暂无评论

State assignment techniques in multiple-valued logic

State assignment techniques in multiple-valued logic

引用

International Symposium on Multiple-Valued Logic

作者： K.J. Adams J.G. Campbell L.P. Maguire J.A.C. Webb School of Computing and Mathematical Sciences Magee College University of Ulster Londonderry UK Intelligent Systems Engineering Lab Faculty of Engineering University of Ulster Londonderry UK School of Electrical and Mechanical Engineering University of Ulster Jordanstown UK

Multiple-Valued Logic (MVL) functions are implemented via Boolean multiple-wire arrangements where a careful state assignment methodology is used to ensure efficient implementation regimes. A 'power of N' module is proposed for GF (2/sup 3/). The method avoids the need to factorize the polynomial and circuits can be realised using a combination of NOT AND and XOR functions. In addition, a novel transform over GF (2/sup 2/) is proposed which shows promise when compared to the Reed-Muller-Fourier transform, in its capacity to produce zero coefficients. A possible implementation strategy, using Field Programmable Gate Arrays (FPGAs) is briefly discussed.

关键词： Educational institutions Switches Fourier transforms systems engineering and theory Mechanical engineering Argon Field programmable gate arrays Logic functions Boolean algebra Automata

来源：评论

学校读者我要写书评

暂无评论

Population of Cooperative Autonomous Agents:Preliminary Consideration

引用

IFAC Proceedings Volumes 1998年第20期31卷 1091-1096页

作者： Anthony Engwirda Mark Hitchings Ljubo Vlacic Abdul Sattar Intelligent Control Systems Laboratory School of Microelectronic Engineering School of Computing and Information Technology Griffith University Queensland 4111

A management strategy for a population of cooperative autonomous agents has been developed. This strategy enables activity behaviour management of a large and dynamically changing population. To make large populations of agents manageable it is necessary to make them autonomous. One of the key criteria for such autonomy is that agent behaviour must be adaptable to a dynamic environment. If the goal is to establish a large scale population of agents away from immediate human contact such that the population is autonomous, then it needs to be adaptable and self-sustaining. Management of an autonomous population is seen as one of the key factors for realisation of this goal. System requirements have been identified and application areas suggested.

关键词： Cooperative Autonomous Agents Autonomous Mobile Robots Distributed Control Event Driven Decision Making Large Scale systems

来源：评论

学校读者我要写书评

暂无评论

Further improvements in the generalization capability of the BRAINNE technique for extracting symbolic knowledge from neural networks

Further improvements in the generalization capability of the...

引用

International Conference on Knowledge-Based intelligent Electronic systems (KES)

作者： T. Hossain T.S. Dillon Expert and Intelligent Systems Laboratory Applied Computing Research Institute and School of Computer Science & Computer Engineering La Trobe University Bundoora Australia

The paper examines several methods for improving the generalization capability of the BRAINNE technique. These methods deal with proper training of neural networks and improvements in defining bounds for continuous data.

关键词： Biological neural networks Multi-layer neural network Neural networks intelligent networks intelligent systems Computer networks Noise measurement Particle measurements Laboratories Computer science

来源：评论

学校读者我要写书评

暂无评论

Hybrid BRAINNE: a method for developing symbolic disjunctive rules from a hybrid neural network

Hybrid BRAINNE: a method for developing symbolic disjunctive...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： W.F. Bloomer T.S. Dillon M. Witten Expert and Intelligent Systems Laboratory Applied Computing Research Institute and School of Computer Science and Computer Engineering La Trobe University Bundoora Australia

A method for learning disjunctive rules using a combination of two existing neural network schemes is proposed. The hybrid network consists of two layers; the first is an unsupervised network while the second is a supervised network. The first layer is used for ordering the inputs of training instances into clusters. Initial rules are extracted from this layer using an existing technique called Unsupervised BRAINNE. These rules are then fed into the second layer which is trained using the delta rule. The second layer is then examined to determine which clusters define the output nodes. This method is able to identify disjunctive rules directly rather than utilising a generate and test paradigm as was used in previous supervised versions of BRAINNE.

关键词： Biological neural networks Unsupervised learning Computer networks Supervised learning Hybrid intelligent systems intelligent networks Laboratories Computer science Testing Humans

来源：评论

学校读者我要写书评

暂无评论

Convergence of genetic evolution algorithms for optimization

引用

Parallel Algorithms and Applications 1995年第1-2期5卷 37-56页

作者： He, Jun Kang, Li-Shan Chen, Yong-Jun National Research Center for Intelligent Computing Systems Software Engineering State Key Laboratory Beijing 100080 P.O. Box 2704 China Software Engineering State Key Laboratory China School of Management Wuhan University Wuhan 430072 China

Genetic algorithms are highly parallel, adaptive search method based on the processes of Darwinian evolution. This paper combines genetic algorithms with simulated annealing algorithms to a new kind of random search algorithms which is called genetic evolution algorithms. We give some conditions which guarantee random search algorithms to converge to the global optima set with probability 1 for solving optimization problems and analyze the convergence of genetic evolution algorithms by using Markov chain theory. © 1995, Taylor & Francis Group, LLC. All rights reserved.

关键词： Genetic algorithms Markov chain Optimization problems Simulated annealing algorithms

来源：评论

学校读者我要写书评

暂无评论

Transactions on Rough Sets XII 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： James F. Peters Andrzej Skowron Roman Słowiński Pawan Lingras Duoqian Miao Shusaku Tsumoto

来源：评论

学校读者我要写书评

暂无评论

Efficient Training Approaches for Performance Anomaly Detection Models in Edge computing Environments

引用

ACM Transactions on Autonomous and Adaptive systems 1000年

作者： Duneesha Fernando Maria Rodriguez Patricia Arroba Leila Ismail Rajkumar Buyya Quantum Cloud Computing and Distributed Systems (qCLOUDS) Laboratory School of Computing and Information Systems The University of Melbourne Australia CCS–Center for Computational Simulation Universidad Politécnica de Madrid Spain Intelligent Distributed Computing and Systems Research (INDUCE) Lab Department of Computer Science and Software Engineering United Arab Emirates University United Arab Emirates

Microservice architectures are increasingly used to modularize IoT applications and deploy them in distributed and heterogeneous edge computing environments. Over time, these microservice-based IoT applications are susceptible to performance anomalies caused by resource hogging (e.g., CPU or memory), resource contention, etc., which can negatively impact their Quality of Service and violate their Service Level Agreements. Existing research on performance anomaly detection for edge computing environments focuses on model training approaches that either achieve high accuracy at the expense of a time-consuming and resource-intensive training process or prioritize training efficiency at the cost of lower accuracy. To address this gap, while considering the resource constraints and the large number of devices in modern edge platforms, we propose two clustering-based model training approaches: (1) intra-cluster parameter transfer learning-based model training (ICPTL) and (2) cluster-level model training (CM). These approaches aim to find a trade-off between the training efficiency of anomaly detection models and their accuracy. We compared the models trained under ICPTL and CM to models trained for specific devices (most accurate, least efficient) and a single general model trained for all devices (least accurate, most efficient). Our findings show that ICPTL’s model accuracy is comparable to that of the model per device approach while requiring only 40% of the training time. In addition, CM further improves training efficiency by requiring 23% less training time and reducing the number of trained models by approximately 66% compared to ICPTL, yet achieving a higher accuracy than a single general model.

关键词： Edge computing Microservices IoT Performance anomaly detection Machine learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

Advanced intelligent computing Theories and Applications 1

引用

丛书名： Communications in Computer and Information Science

1000年

作者： De-Shuang Huang Martin McGinnity Laurent Heutte Xiao-Ping Zhang

ISBN: (数字)9783642148316

ISBN: (纸本)9783642148309

The International Conference on intelligent computing (ICIC) was formed to provide an annual forum dedicated to the emerging and challenging topics in artificial intel- gence, machine learning, pattern recognition, image processing, bioinformatics, and computational biology. It aims to bring together researchers and practitioners from both academia and industry to share ideas, problems, and solutions related to the m- tifaceted aspects of intelligent computing. ICIC 2010, held in Changsha, China, August 18-21, 2010, constituted the 6th - ternational Conference on intelligent computing. It built upon the success of ICIC 2009, ICIC 2008, ICIC 2007, ICIC 2006, and ICIC 2005, that were held in Ulsan, Korea, Shanghai, Qingdao, Kunming and Hefei, China, respectively. This year, the conference concentrated mainly on the theories and methodologies as well as the emerging applications of intelligent computing. Its aim was to unify the picture of contemporary intelligent computing techniques as an integral concept that highlights the trends in advanced computational intelligence and bridges theoretical research with applications. Therefore, the theme for this conference was “Advanced intelligent computing Technology and Applications.” Papers focusing on this theme were solicited, addressing theories, methodologies, and applications in science and technology.

关键词： Artificial Intelligence Programming Techniques Computer engineering Pattern Recognition Computation by Abstract Devices Image Processing and Computer Vision

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：