检索结果-内蒙古大学图书馆

Improving fusion with optimal weight selection in Face Recognition

INTEGRATED COMPUTER-AIDED ENGINEERING 2012年第3期19卷 229-237页

作者： Quang Duc Tran Kantartzis, Panagiotis Liatsis, Panos City Univ London Informat Engn & Med Imaging Grp Sch Engn & Math Sci London EC1V 0HB England

Face recognition has a large number of applications, including security/counterterrorism, person identification, Internet communications, E-commerce, and computer entertainment. Although research in automatic face recognition has been conducted since the 1960s, there exist research challenges in its practical application in the terms of performance accuracy, which deteriorates significantly with changes in illumination, pose, expression and occlusions. However, these inherent limitations can be potentially alleviated by fusing biometric information based on multiple facial features. Following this vision, the work presented here offers three contributions. Firstly, we present a Face Recognition System, where diverse biometrics features such as total face, eyes, nose, mouth, etc are extracted from the face image. Secondly, we analyse a number of approaches for combining the aforementioned information at matching score level. Thirdly, we proposed a new approach, based on a recently proposed optimisation technique, the bees algorithm, to determine the optimal weight parameters to enhance the performance of the fusion system. Experiments on the CASIA and ORL face databases indicate that the proposed method achieves consistently high recognition rates, compared to traditional FR approaches, such as the Eigenfaces, Fisherfaces, and D-LDA methods.

关键词： Face recognition multibiometric system Linear Discriminant Analysis density based score fusion bees algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of Nature Inspired algorithms to Multi-objective Optimization of New Generation Network Problem 22

Application of Nature Inspired Algorithms to Multi-objective...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Kozdrowski, Stanislaw Wnuk, Kacper Warsaw Univ Technol Warsaw Poland

ISBN: (纸本)9781450392686

The subject of the paper is the application of metaheuristic algorithms inspired by nature for multi-criteria optimization in new generation optical networks. In the considered optical network, criteria related to the structure and topology of the network and the equipment used were taken into account. Network criteria include the length of optical channels, optical fiber attenuation, and dispersion. On the other hand, the hardware criteria include the cost of transponders and a finite range of frequency slides in the optical spectrum of the optical fiber. Several nature-inspired metaheuristics were used for the multi-criteria optical network optimization problem. The proposed algorithm, based on the bee algorithm was compared with others taken from the literature. Simulation results of all algorithms were implemented and carried out using test networks with topology typical for telecommunication networks. The proposed and improved algorithm obtained good results that encourage further work and research.

关键词： multi-objective optimization metaheuristics evolutionary algorithm bees algorithm combinatorial optimization optical network design

来源：评论

学校读者我要写书评

暂无评论

Artificial Bee Colony Optimization for Multi Objective Economic Load Dispatch of a Modern Power system

Artificial Bee Colony Optimization for Multi Objective Econo...

引用

International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)

作者： Rao, R. Kameswara Srinivas, P. Divakar, M. S. M. Venkatesh, G. S. N. M. Raghu Engn Coll Dept EEE Visakhapatnam Andhra Pradesh India Raghu Inst technol Dept EEE Visakhapatnam Andhra Pradesh India

ISBN: (纸本)9781467399395

This paper presents using the bees algorithm approach to multi-objective optimal economic dispatch of electrical power systems. The generation of electricity from the fossil fuel releases several contaminants, such as sulfur oxides, nitrogen oxides and carbon dioxide, into the atmosphere. Genetic algorithmic approach to power system optimization, as reported here for a case of economic power dispatch, consists essentially of minimizing the objective function while gradually satisfying the constraint relations. In the Multi-objective problem formulation, four important non-commensurable objectives in an electrical thermal power system are considered. These are economy and environmental impacts because of NOx, SO2, CO2 emissions. The suitability of the proposed approach is described to multiobjective optimal economic dispatch of electrical power systems.

关键词： optimization genetic algorithms economic dispatch bees algorithm

来源：评论

学校读者我要写书评

暂无评论

Achieving CO2 Emission Targets for Energy Consumption at Canadian Manufacturing and beyond;using Hybrid Optimization Model

Achieving CO2 Emission Targets for Energy Consumption at Can...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Marzi, Arash Marzi, Elham Marzi, Hosein Dr John Hugh Gillis Reg High Sch Antigonish NS B2G 2W5 Canada St Francis Xavier Univ Dept Informat Syst Antigonish NS B2G 2W5 Canada

ISBN: (纸本)9781467361293;9781467361286

Due to sporadic climate change and global warming, world have signed international protocols promising to reduce their nation's emissions. This study focuses on the application of the bees algorithm, embedded with an artificial neural network, to determine practical yearly reductions for minimizing oil, natural gas, and coal emissions as by-products of energy consumption in Canada's manufacturing sector based on the Copenhagen Targets for Canada for 2020.

关键词： bees algorithm Artificial Neural Networks Optimization Emission reduction Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Optimal Design and Performance Evaluation of A Grid Independent Hybrid Micro Hydro-Solar-Wind-Fuel Cell Energy System Using Meta-Heuristic Techniques

Optimal Design and Performance Evaluation of A Grid Independ...

引用

1st International Conference on Non Conventional Energy (ICONCE)

作者： Tudu, B. Mandal, K. K. Chakraborty, N. Jadavpur Univ Dept Power Engn Kolkata India

ISBN: (纸本)9781479933396

This paper presents the design and optimal sizing of a grid independent hybrid energy system consisting of micro hydro, solar, wind and fuel cell for catering a specific load. The optimal sizing is obtained using a comparatively new optimization technique called bees algorithm (BA) and the performance of the algorithm is compared with an established meta-heuristic techniques called particle swarm optimization (PSO) and also the system performance is evaluated in terms of the cost of the system. For obtaining the optimal sizing, net present cost (NPC) of the system has been considered. The system is designed such a way that the maximum utilization of the resources and carbon free electricity can be achieved. Keeping in mind this aspect, apart from renewable resources, electrolyser is introduced for production of hydrogen utilizing the excess power. It is observed that the system is quite feasible in meeting the load and in terms of cost of energy and also observed that though both the algorithms are capable of giving global solution, but Particle swarm optimization is fast in reaching optimal solution and takes less CPU time as compared to bees algorithm.

关键词： Hybrid energy system Unit sizing Micro-hydro plant Wind turbine Particle swarm optimization bees algorithm

来源：评论

学校读者我要写书评

暂无评论

Vehicle Safety Monitoring System Based on Internet of Things and Identification with Physiological Characteristics 1

Vehicle Safety Monitoring System Based on Internet of Things...

引用

1st IEEE International Conference on Knowledge Innovation and Invention (ICKII)

作者： Wang, Zhi-Hao Hendrick Wang, Chih-Min Jong, Gwo-Jia Natl Kaohsiung Univ Sci & Technol 415 Jiangong Rd Kaohsiung 80778 Taiwan

ISBN: (纸本)9781538652671

In general, it is a Very dangerous condition for a driver driving a car while his mental state is not clear. In this paper, a vehicle safety monitoring system is designed based on the Internet of Things and physiological characteristics identification. This system is divided into two parts, the first part is the network-coordinator and router which were installed on the road, and the second part is the network-end device that installed on the vehicle.

关键词： Internet of Things Vehicle Safety Monitoring System Identification of physiological characteristics Zigbee Networking bees algorithm

来源：评论

学校读者我要写书评

暂无评论

BPEL - Business Process Execution Language Process Creation and Fault Localization Framework 5

BPEL - Business Process Execution Language Process Creation ...

引用

5th International Conference on Confluence - The Next Generation Information Technology Summit (Confluence)

作者： Kaur, Usvir Singh, Dheerendra Sri Guru Granth Sahib World Univ Dept Comp Sci & Engn Fatehgarh Sahib India SUS Coll Engn & Technol Dept Comp Sci & Engn Tangori India

ISBN: (纸本)9781479942367

Context: WS-BPEL has been recognized as service composition language which is both executable and process-oriented. Customers are benefited from the collaboration of various providers of web services. An XML format based language known as BPEL different from syntax and semantics from traditional program language. Objective: In this paper, we create a BPEL process creation example and framework for fault localization by implementing bees algorithm. Method: Based on the example of BPEL process creation we create an environment for local fault localization and uses bees optimization algorithm to generate combinations of different base roots that result in lower fault occurrence. Result: bees optimization algorithm is used to calculate number of faults occurrence. Results show that different combinations of different base tags result in lower fault occurrence. Conclusion: We conclude that our proposed framework of BPEL process creation and fault localization is effective in locating faults by generating test cases in BPEL programs.

关键词： Web Services- Business Process Execution Language(WSBPEL) Fault Localization Framework bees algorithm

来源：评论

学校读者我要写书评

暂无评论

Building synthetic networks of the budding yeast cell-cycle using swarm intelligence

Building synthetic networks of the budding yeast cell-cycle ...

引用

11th IEEE International Conference on Machine Learning and Applications (ICMLA)

作者： Ruz, Gonzalo A. Timmermann, Tania Goles, Eric Univ Adolfo Ibanez Fac Ingn & Ciencias Av Diagonal Las Torres 2640 Santiago Chile

ISBN: (纸本)9780769549132;9781467346511

A swarm intelligence technique called the bees algorithm is formulated to build synthetic networks of the budding yeast cell-cycle. The resulting networks contain the original fixed points of the budding yeast cell-cycle network plus additional fixed points to reduce the basin size of the fixed point associated to the G1 phase of the cell-cycle, with the purpose of promoting cell proliferation for biotechnological applications. One thousand synthetic networks were found using the bees algorithm, 84.5% had basins size for the G1 fixed point less or equal to 10, whereas the original model has a basin size for that fixed point of 1764. One of the synthetic networks was analyzed by a biologist concluding that the resulting model was quite consistent from a biological point of view, supporting the proposed method as a tool for biologist to construct synthetic networks with desired characteristics.

关键词： Boolean networks bees algorithm cell-cycle gene regulatory networks computational biology

来源：评论

学校读者我要写书评

暂无评论

Biological System Behaviours and Natural-inspired Methods and Their Applications to Supply Chain Management

Biological System Behaviours and Natural-inspired Methods an...

引用

4th International Conference of Bionic Engineering (ICBE 2013)

作者： Fan, Xuemei Zhang, Shujun Hapeshi, Kevin Yang, Yinsheng Jilin Univ Coll Quartermaster Technol Changchun 130023 Jilin Peoples R China Univ Gloucestershire Sch Comp & Technol Cheltenham Glos England Jilin Univ Coll Biol & Agr Engn Changchun Kagawa Peoples R China

ISBN: (纸本)9783037859322

People have learnt from biological system behaviours and structures to design and develop a number of different kinds of optimisation algorithms that have been widely used in both theoretical study and practical applications in engineering and business management. An efficient supply chain is very important for companies to survive in global competitive market. An effective SCM (supply chain management) is the key for implement an efficient supply chain. Though there have been considerable amount of study of SCM, there have been very limited publications of applying the findings from the biological system study into SCM. In this paper, through systematic literature review, various SCM issues and requirements are discussed and some typical biological system behaviours and natural-inspired algorithms are evaluated for the purpose of SCM. Then the principle and possibility are presented on how to learn the biological systems' behaviours and natural-inspired algorithms for SCM and a framework is proposed as a guide line for users to apply the knowledge learnt from the biological systems for SCM. In the framework, a number of the procedures have been presented for using XML to represent both SCM requirement and bioinspiration data. To demonstrate the proposed framework, a case study has been presented for users to find the bio-inspirations for some particular SCM problems in automotive industry.

关键词： learn from nature biological system behaviours supply chain management ACO bees algorithm Genetic algorithm Firefly algorithm

来源：评论

学校读者我要写书评

暂无评论

Review on Feature Selection algorithms for Anomaly-Based Intrusion Detection System 3rd

Review on Feature Selection Algorithms for Anomaly-Based Int...

引用

3rd International Conference of Reliable Information and Communication Technology (IRICT)

作者： Alamiedy, Taief Alaa Anbar, Mohammed Al-Ani, Ahmed K. Al-Tamimi, Bassam Naji Faleh, Nameer Univ Sains Malaysia Natl Adv IPv6 Ctr Usm 11800 Penang Malaysia Taibah Univ Coll Comp Sci & Engn Medina Saudi Arabia USM Sch Elect & Elect Engn Nibong Tebal 14300 Penang Malaysia

ISBN: (纸本)9783319990071;9783319990064

As Internet networks expand, the amount of network threats and intrusions increased, the demand for an efficient and reliable defense system is required to detect network security vulnerabilities. Intrusion Detection Systems (IDS) are a vital constituent of security of a network to avert data illegal usage and misappropriation. IDS deal with massive amount of data movement that comprises repetitive and inappropriate features. The detection rate implementation is frequently affected by these inappropriate features which also munch up intrusion detection system resources. A significant portion in the removal of dissimilar and not used features in IDS is done by the feature selection method. Methods included are data mining techniques, machine learning, statistical analysis, support vector machine models and neural networks. In this paper, we provide review of several algorithms used for anomaly-based intrusion detection systems to improve performance of machine learning classifiers. This paper first summarizes the theoretical basis of IDS, and then discusses the feature selection techniques and their types.

关键词： Intrusion detection system Feature selection Genetic algorithm bees algorithm Support vector machine Principle components analysis Artificial bee colony

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：