检索结果-内蒙古大学图书馆

Congress on Evolutionary Computation

作者： Rogério C. B. L. Póvoa Adriano S. Koshiyama Douglas M. Dias Patrícia L. Souza Bruno A.C. Horta Department of Electrical Engineering PUC-Rio Rio de Janeiro Brazil Department of Computer Science UCL London United Kingdom Dep. of Electronics and Telecommunications UERJ Rio de Janeiro Brazil PUC-Rio LabSem/CETUC Rio de Janeiro Brazil UFRJ Institute of Chemistry Rio de Janeiro Brazil

Genetic programming techniques allow flexibility in the optimization process, making it possible to use them in different areas of knowledge and providing new ways for specialists to advance in their areas more quickly and more accurately. This work presents a preliminary analysis of a new method using multi-gene genetic programming to multimodal numerical optimization. The new algorithm uses some niching techniques based on the clear procedure to maintain the population diversity, in order to perform a multivariate mapping among initial guesses to optimal parameters for a system. We used a multi-modal benchmark set with different characteristics and difficulty levels to evaluate this new algorithm. Statistical analysis suggested that this new multi-modal method using multi-gene genetic programming can be used for problems that requires more than a single solution.

关键词： Optimization Benchmark testing Linear programming Genetic programming Sociology Statistics Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A fully recursive perceptron network architecture

A fully recursive perceptron network architecture

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Markus Hagenbuchner Ah Chung Tsoi Franco Scarselli Shu Jia Zhang School of Computing and IT University of Wollongong Wollongong Australia Dep. of Computer Science University of Wollongong Tuen Mun Wollongong Australia Dep. of Information Engineering University of Siena Siena Italy

This paper introduces a fully recursive perceptron network (FRPN) architecture as an alternative to multilayer perceptron (MLP) with multiple hidden layers networks, popularly known as deep neural networks. The FRPN consists of an input layer, an output layer, and only one hidden layer in which the hidden layer neurons are fully connected with algebraic (instantaneous) connections, and not delayed connections. The FRPN is particularly attractive as an alternative to deep MLP since the FRPN eliminates the need of obtaining the number of hidden layers and the number of neurons per hidden layer. Some insight into the operational mechanisms of the FRPN is obtained through an application to a practical learning problem, viz., the handwritten digit recognition problem.

关键词： Neurons Biological neural networks Training Recurrent neural networks computer architecture Australia Learning systems

来源：评论

学校读者我要写书评

暂无评论

Wavelet transform based technique for text image localization

引用

Karbala International Journal of Modern science 2016年第2期2卷 138-144页

作者： Ali, Suhad A. Hashim, Ashwaq T. Babylon University Science College for Women Computer Science Dep. Babylon Iraq Technology University Control and Systems Engineering Dep. Baghdad Iraq

In this paper, a robust technique based on discrete wavelet transform, edge detection, and morphology operation for scene text detection is proposed. There are several stages in the proposed method. In the first stage, a single wavelet decomposition LH, HL and HH subbands are applied for detecting edges in original scene text image. The projection technique is applied in the second stage to preliminary detect text and non-text pixels. In third stage, 4-connected components are applied, and then area geometric feature is used as threshold to remove non-text region. At last stage, morphological operations are applied to connect isolated text components and to remove non-text regions. The proposed method is applied on a various images such as images of low contrast, complex background images and images of different fonts and size of text. The experimental results show that the proposed method can detect regions of the text perfectly. © 2016 The Authors

关键词： Connected components DWT Image projection Morphological operator

来源：评论

学校读者我要写书评

暂无评论

Recent architectural developments for reducing power consumption and increasing performance

引用

Recent Patents on computer science 2016年第1期9卷 89-98页

作者： Ozkul, Tarik Tuffaha, Mohammed A. Elhiny, Lamees Computer Science and Engineering Dep. American University of Sharjah P.O. Box 26666 Sharjah United Arab Emirates

Background: Power consumption has become one of the most serious obstacles ahead of performance increase. Due to increased power consumption, increasing number of transistors does not seem to be viable anymore. We are being forced to consider other ways of increasing performance without increasing power consumption. To find solution to the problem, the power consumption issue is being looked at more and more carefully at architectural level. Methods: Recent publications and patent databases are reviewed to find extraordinary and innovative architectural techniques developed for reducing power consumption and increasing performance. Results: In most of the cases the focus was specifically on memory area because of the studies that indicated that memory is the biggest power consumer in a typical processor system. The focus of the most methods was also on the cache memory part of the processor system since cache memory is a part that is used with every instruction execution. Any reduction in power cost of the cache memory results in sizable power reduction. Among the methods suggested were techniques of linking cache memory cells to reduce number of operations, reducing size of the cache memory by using multiple small cache memories activated one at a time. Conclusion: Based on the study it can be concluded that future innovative developments to reduce power consumption should concentrate on: a) Main memory part: to reduce the power consumption of main memory by turning on/off unused blocks of memory without effecting performance, b) Cache memory part: use of cache memory efficiently without decreasing performance, c) Efficient multiprocessing architectures. By integrating above mentioned methods to multiprocessors it may be possible to reduce the power consumption further. © 2016 Bentham science Publishers.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic system modeling and simulation

Photovoltaic system modeling and simulation

引用

2017 IEEE International Conference on Industrial Technology, ICIT 2017

作者： Mendalek, N. Al-Haddad, K. Notre Dame University Dep. of Electrical Computer and Communication Engineering Zouk Mosbeh Lebanon Canada Research Department in Energy Conversion and Power Electronics CRC-ECPE École de Technologie Supérieure 1100 Notre-Dame Ouest MontréalQCH3C 1K3 Canada

ISBN: (纸本)9781509053209

This paper presents the modeling and simulation of a photovoltaic (PV) system. The equations governing the operation of the one-diode equivalent model are developed and the identification of the model parameters is performed through MATLAB script. The system studied encompasses a commercial PV panel, a dc-dc boost power converter, a battery and a dc load. The boost converter is controlled using voltage error PID compensator which has an input reference voltage computed by perturb-and-observe (P&O) maximum power point tracking (MPPT) technique. The system is simulated in MATLAB/Simulink environment for different irradiation levels and PV module temperature values. The control strategy is also validated in presence of rapidly varying irradiation conditions. © 2017 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic System Modeling and Simulation

Photovoltaic System Modeling and Simulation

引用

International Conference on Industrial Technology

作者： N. Mendalek K. Al-Haddad Notre Dame University Dep. of Electrical Computer & Communication Engineering Canada Research Chair in Energy Conversion and Power Electronics CRC-ECPE Ecole de Technologie Superieure

ISBN: (纸本)9781509053216

关键词： photovoltaic (PV) systems dc-dc boost converter MPPT perturb-and-observe (P&O) algorithm MATLAB

来源：评论

学校读者我要写书评

暂无评论

A new predictive approach to variables selection through Genetic Algorithm and Fuzzy Adaptive Resonance Theory Using medical diagnosis as a case

引用

Procedia computer science 2017年 109卷 448-457页

作者： Choukri Djellali Mehdi Adda Mathematics Computer Science and Engineering Dep. University of Quebec At Rimouski 300 Allée des Ursulines Rimouski QC G5L 3A1 Canada

Variables selection is challenging task due mainly to huge search space. This study addresses the increasingly encountered chal- lenge of variables selection. It addresses the application of machine learning techniques to the problem of variables selection. We detailed the various models of the variables selection and examined the basic steps that are used to select the cost-effective predictors. We also walked through the initial settings and all variables selection stages, including architecture configuration, strat- egy generation, learning, model induction, and scoring. Results from this study show that the cost and generalization were seen to improve significantly in terms of computing time and recognition accuracy when the proposed system is applied for medical diagnosis. Good comparisons with an experimental study demonstrate the multidisciplinary applications of our approach.

关键词： Data Mining Pattern Recognition Machine Learning Clustering Variables Selection Genetic Algorithm

来源：评论

学校读者我要写书评

暂无评论

A new scalable aggregation scheme for fuzzy clustering taking unstructured textual resources as a case 16

A new scalable aggregation scheme for fuzzy clustering takin...

引用

20th International Database engineering and Applications Symposium, IDEAS 2016

作者： Djellali, Choukri Adda, Mehdi Mathematics Computer Science and Engineering Dep. University of Quebec at Rimouski Rimouski Canada

ISBN: (纸本)9781450341189

The performance of clustering is a crucial challenge, especially for pattern recognition. The models aggregation has a positive impact on the efficiency of Data clustering. This technique is used to obtain more cluttered decision boundaries by aggregating the resulting clustering models. In this paper, we study an aggregation scheme to improve the stability and accuracy of clustering, which allows to find a reliable and robust clustering model. We demonstrate the advantages of our aggregation method by running Fuzzy C-Means (FCM) clustering on Reuters-21578 corpus. Experimental studies showed that our scheme optimized the bias-variance on the selected model and achieved enhanced clustering for unstructured textual resources. © ACM 2016.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

Joining of non-weldable AA7075 and weldable AA6082 aluminium alloy sheets by Friction Stir Welding

引用

IOP Conference Series: Materials science and engineering 2018年第1期448卷

作者： Zsolt Kovács Ferenc Hareancz John von Neumann University GAMF Faculty of Engineering and Computer Science Dep. of Vehicle Technology Kecskemét H-6000 Hungary

In this work, an attempt has been made to join the AA6082-T651 and AA7075-T651 aluminium alloys by friction stir welding (FSW). The FSW is a solid-state joining process which primarily used on aluminium because the metal is not melted during the process so the base material can not soften. For the welding were using cylindrical pin tool, marble table to avoid the harmful heat conduction, two rotation rate of 500 and1000 rpm and different traverse speeds of 15, 20, 25 and 30 mm/min to weld butt joints. The aim of present study were to experimentally explore the dissimilar bounds. For evaluations, hardness testing were using to create hardness profiles across the joint in through thickness direction and optical microscope to classify the microstructures and crystallographic textures of base materials (BM). Based on the results obtained it can be stated that the FSW suitable for AA7075 and AA6082 welding by further optimization of the process parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

General Quantized Innovation Kalman Filter for Stochastic Uncertain Systems with Random Packet Dropouts

General Quantized Innovation Kalman Filter for Stochastic Un...

引用

Youth Academic Conference of Chinese Association of Automation

作者： Huai min Li Qiang Ling School of Computer and Information Engineering Fuyang Normal University Fuyang 236037 China Dep. of Automation University of Science and Technology of China Hefei 230027 China

ISBN: (纸本)9781538629024

Due to of the bandwidth constraint, sensors may only be able to transmit a finite number of bits to save the energy, and the measurement data may have to be quantized before transmission especially in wireless sensor networks (WSNs). This paper studies the problem of the general quantized innovation filtering with random packet dropouts for linear stochastic uncertain systems. The multiplicative uncertainty of system parameters is first converted into additive noises. Then under the Gaussian assumption on the predicted density, the Lloyd-Max quantizer, a general quantized innovation filter with random packet dropouts in the linear minimum mean square error (LMMSE) sense is derived based on the projection theory and Bayes Rule. Furthermore a sufficient condition is provided, under which a general quantized innovation filter with random packet dropouts can be reduced into a standard Kalman filter. An example is simulated to illustrate the effectiveness and correctness of the designed filter.

关键词： General Quantized Innovation Filter Stochastic Uncertain System Packet Dropouts

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：