检索结果-内蒙古大学图书馆

Parallel 1D and 2D vector quantizers using a Kohonen neural network

NEURAL COMPUTING & APPLICATIONS 1996年第2期4卷 64-71页

作者： Mohamed, AS Attia, EN The American University in Cairo

The process of reconstructing an original image from a compressed one is a difficult problem, since a large number of original images lead to the same compressed image and solutions to the inverse problem cannot be uniquely determined. Vector quantization is a compression technique that maps an input set of k-dimensional vectors into an output set of k-dimensional vectors, such that the selected output vector is closest to the input vector according to a selected distortion measure. In this paper, we show that adaptive 2D vector quantization of a fast discrete cosine transform of images using Kohonen neural networks outperforms other Kohonen vector quantizers in terms of quality (i.e. less distortion). A parallel implementation of the quantizer on a network of SUN Sparcstations is also presented.

关键词： neural networks vector quantizers fast discrete cosine transform adaptation algorithm loosely coupled architecture parallel processing

来源：评论

学校读者我要写书评

暂无评论

Peri-implant bone adaptations to overloading in rat tibiae: experimental investigations and numerical predictions

引用

CLINICAL ORAL IMPLANTS RESEARCH 2016年第11期27卷 1444-1453页

作者： Piccinini, Marco Cugnoni, Joel Botsis, John Ammann, Patrick Wiskott, Anselm Ecole Polytech Fed Lausanne Lab Appl Mech & Reliabil Anal Lausanne Switzerland Univ Hosp Geneva Dept Internal Med Special Div Bone Dis Geneva Switzerland Fac Med Geneva Switzerland Univ Geneva Div Fixed Prosthodont & Biomat Univ Clin Dent Med CH-1205 Geneva Switzerland

Objectives(i) To assess the effects of mechanical overloading on implant integration in rat tibiae, and (ii) to numerically predict peri-implant bone adaptation. Materials and methodsTranscutaneous titanium implants were simultaneously placed into both tibiae of rats (n=40). After 2weeks of integration, the implants of the right tibiae were stimulated daily for 4weeks with loads up to 5N (corresponding to peak equivalent strains of 3300500 epsilon). The effects of stimulation were assessed by exvivo mechanical tests and quantification of bone mineral density (BMD) in selected regions of interests (ROIs). Specimen-specific finite element models were generated and processed through an iterative algorithm to mimic bone adaptation. ResultsBilateral implantation provoked an unstable integration that worsened when mild (2-4N) external loads were applied. In contrast, a stimulation at 5N tended to counterbalance the harmful effects of daily activity and, if applied to well-integrated specimens, significantly augmented the implants' resistance to failure (force: +73% P<0.01, displacement: +50% P<0.01 and energy: +153% P<0.01). Specimen-specific numerical predictions were in close agreement with the experimental findings. Both local and overall BMD variations, as well as the implants' lateral stability, were predicted with small errors (0.14gHA/cm(3) and 0.64%, respectively). ConclusionsThe rats' daily activity detrimentally affects implant integration. Conversely, external stimulations of large magnitudes counterbalance this effect and definitively improve integration. These changes can be predicted using the proposed numerical approach.

关键词： adaptation algorithm bone augmentation finite element implant integration invivo stimulation specimen-specific

来源：评论

学校读者我要写书评

暂无评论

Adaptive symbol-by-symbol reception of MPSK on the Gaussian channel with unknown carrier phase characteristics

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 1998年第10期46卷 1275-1279页

作者： Kam, PY Chua, KH Yu, XF Natl Univ Singapore Dept Elect Engn Singapore 119260 Singapore

An adaptive version of the optimum, decision-aided, symbol-by-symbol receiver obtained in our previous works for M-ary phase shift keying over the Gaussian channel with unknown carrier phase characteristics is considered, It uses a first-order adaptive filter for carrier reference tracking, and the filter gain is adapted on-line based on the observed signal samples using a least-mean-square-error criterion. The phase tracking performance of the filter in the steady-state tracking mode is analyzed using a linearized model. The phase tracking error variance is minimized due to the risk function used in designing the filter gain adaptation algorithm. The bit-error probability for quadrature phase shift-keying is obtained, both analytically and via computer simulations.

关键词： adaptation algorithm adaptive receiver coherent detection phase noise phase shift keying

来源：评论

学校读者我要写书评

暂无评论

Mathematical forecasting methods for predicting lead contents in animal organs on the basis of the environmental conditions

引用

ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY 2014年 110卷 232-238页

作者： Czech, Tomasz Gambus, Florian Wieczorek, Jerzy Agr Univ Krakow Fac Agr & Econ Dept Agr & Environm Chem PL-31120 Krakow Poland

The main objective of this study was to determine and describe the lead transfer in the soil-plant-animal system in areas polluted with this metal at varying degrees, with the use of mathematical forecasting methods and data mining tools contained in the Statistica 9.0 software programme. The starting point for the forecasting models comprised results derived from an analysis of different features of soil and plants, collected from 139 locations in an area covering 100 km(2) around a lead-zinc ore mining and processing plant ('Boleslaw'), at Bukowno in southern Poland. In addition, the lead content was determined in the tissues and organs of 110 small rodents (mainly mice) caught in the same area. The prediction models, elaborated with the use of classification algorithms, forecasted with high probability the class (range) of pollution in animal tissues and organs with lead, based on various soil and plant properties of the study area. However, prediction models which use multilayer neural networks made it possible to calculate the content of lead (predicted versus measured) in animal tissues and organs with an excellent correlation coefficient. (C) 2014 Elsevier Inc. All rights reserved.

关键词： Pollution with heavy metals Lead transfer Interpolation methods adaptation algorithm Multi layer neural networks

来源：评论

学校读者我要写书评

暂无评论

MATRIX APPROACH TO CHARACTER RECOGNITION

引用

PATTERN RECOGNITION 1979年第3期11卷 165-168页

作者： FRITZSCH, K Academy of Sciences of the GDR Central Institute of Cybernetics and Information Processes Rudower Chaussee 5 Berlin DDR-1199

The problem of separating two relatively compact classes of matrices by a linear function is investigated. The modality properties of the corresponding optimality criteria are considered. It is recommended that this sort of classifier is used for separating matrix descriptions of characters. The classifier is easy to implement and the sample size is smaller than in the case of a common vector classifier. Some simulation results show that it is possible to utilize the theory of matrix classification in solving a special character recognition problem.

关键词： Matrix classification Feature extraction Linear classificator adaptation algorithm Modality properties Cyrillic letters

来源：评论

学校读者我要写书评

暂无评论

A 5 Gb/s CMOS adaptive equalizer for serial link

引用

Journal of Semiconductors 2018年第4期39卷 66-71页

作者： Hongbing Wu Jingyu Wang Hongxia Liu School of Microelectronics Xidian University Xi'an 710071 China

A 5 Gb/s adaptive equalizer with a new adaptation scheme is presented here by using 0.13μm CMOS process. The circuit consists of the combination of equalizer amplifier, limiter amplifier and adaptation loop. The adaptive algorithm exploits both the low frequency gain loop and the equalizer loop to minimize the inter-symbol interference （ISI） for a variety of cable characteristics. In addition, an offset cancellation loop is used to alleviate the offset influence of the signal path. The adaptive equalizer core occupies an area of 0.3567 mm2 and consumes a power consumption of 81.7 mW with 1.8 V power supply. Experiment results demonstrate that the equalizer could compensate for a designed cable loss with 0.23 UI peak-to-peak jitter.

关键词： adaptation algorithm equalizer amplifier variable gain amplifier limiter amplifier

来源：评论

学校读者我要写书评

暂无评论

Multicriteria Approaches for Predictive Model Generation: A Comparative Experimental Study

Multicriteria Approaches for Predictive Model Generation: A ...

引用

2014 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making (MCDM)

作者： Al-Jubouri, Bassma Gabrys, Bogdan Bournemouth Univ Fac Sci & Technol Smart Technol Res Ctr Poole BH12 5BB Dorset England

ISBN: (纸本)9781479944675

This study investigates the evaluation of machine learning models based on multiple criteria. The criteria included are: predictive model accuracy, model complexity, and algorithmic complexity (related to the learning/adaptation algorithm and prediction delivery) captured by monitoring the execution time. Furthermore, it compares the models generated from optimising the criteria using two approaches. The first approach is a scalarized multi objective optimisation, where the models are generated from optimising a single cost function that combines the criteria. On the other hand the second approach uses a Pareto-based multi objective optimisation to trade-off the three criteria and to generate a set of non-dominated models. This study shows that defining universal measures for the three criteria is not always feasible. Furthermore, it was shown that, the models generated from Pareto-based multi objective optimisation approach can be more accurate and more diverse than the models generated from scalarized multi objective optimisation approach.

关键词： Pareto optimisation computational complexity learning (artificial intelligence) prediction theory Pareto-based multiobjective optimisation adaptation algorithm algorithmic complexity learning algorithm machine learning models model complexity multicriteria approaches multiple criteria nondominated models prediction delivery predictive model accuracy predictive model generation scalarized multiobjective optimisation Accuracy Artificial neural networks Complexity theory Mathematical model Optimization Prediction algorithms Predictive models Pareto optimisation algorithmic complexity Prediction theory Prediction algorithms Complexity theory learning algorithms Prediction models Artificial neural networks complexity classes Mathematical Model machine model Multiple objective

来源：评论

学校读者我要写书评

暂无评论

Expert system with an adaptive fuzzy inference module

Expert system with an adaptive fuzzy inference module

引用

1st International Conference on Knowledge-Based Intelligent Electronic Systems (KES 97)

作者： Kosinski, W Weigl, M Polish Acad of Sciences Warsaw Poland

An adaptive fuzzy expert system (AFES) is constructed as a hybrid in which an adaptive fuzzy inference module is combined with a neural network and equipped with a preprocessor of input data, user interface and the knowledge equisiation and modification unit. The adaptive fuzzy inference module (AFIM) is based on generalized Takagi-Sugeno fuzzy ''If-Then'' rules, forms of which have fuzzy sets involved only in premise parts, while consequent pacts (i.e. output of each rule) are functions of input variables. The final output of the module is the weighted sum of all rule's output. The basic idea of AFIM is to realize a process of fuzzy reasoning and to express parameters of fuzzy reasoning by connection weights of a neural network and by forms of 4-parameter membership functions of fuzzy sets. The system is constructed for the needs of an opto-computer system of diagnostic of surface imperfections of technological elements. Similar system can be useful in other situations, for example in the case of experimental results in which the data are imprecise and unique functional relation between inputs and outputs is not reachable by means of classical methods.

关键词： expert system fuzzy inference module adaptation algorithm neural network

来源：评论

学校读者我要写书评

暂无评论

An Efficient Speed Control Method for Two Mass Drive Systems using ADALINE 3

An Efficient Speed Control Method for Two Mass Drive Systems...

引用

International Conference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials (ICSTM)

作者： Nandana, J. Anas, A. S. TKM Inst Technol Dept Elect & Commun Engn Kollam India

ISBN: (纸本)9781479998555

An industrial two mass system is composed of a motor which is connected to the load machine through a shaft. Sometimes the shaft may be stiff, but in applications such as rolling mill drives, robotic arms, conveyor belts etc., the shaft is elastic. These elastic joints are susceptible to angular vibrations called torsional vibrations that limit the performance of industrial drives. Due to this the motor speed may be different from the load speed. To solve this problem speed controllers are used which will adjust the load speed and the motor speed with that of the reference speed. Fuzzy logic controllers and PI controllers were used earlier. The limitation of these controllers is the lack of analytical tuning. In recent years, neural network have been applied for the control of two mass systems. Adaptive Linear Neuron (ADALINE) based speed controller with an efficient adaptation algorithm can be used to stabilize the two mass drive systems. The control signal to be applied to the two mass system is generated by the ADALINE controller which updates its weight value on demand. The design of modules can be done in Xilinx System Generator. System generator enables the use of MATLAB/Simulink for simulating the designed modules. It also enables the user to create user defined blocks. The modules that are designed in System Generator can be implemented in FPGA. The work is further extended by modifying the linear activation function present in the ADALINE module by non linear activation function.

关键词： ADALINE two mass systems Matlab/Simulink Xilinx system generator activation function adaptation algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of Iterative Procedures for Signal Processing

Application of Iterative Procedures for Signal Processing

引用

IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (ElConRus)

作者： Klionskiy, Dmitry M. Geppener, Vladimir V. St Petersburg Electrotech Univ LETI Fac Comp Sci & Technol St Petersburg Russia

ISBN: (纸本)9781538643402

the paper discusses iterative algorithms of adaptive processing used in different applications. The adaptation algorithms are based on using an adaptive antenna array and a processor and adaptation is followed by computing weight coefficients. We consider the example of an iterative adaptation algorithm using the wanted signal from the target and directional interferences. The paper also discusses the developed software package for studying adaptation algorithms, finding their characteristics and consuming resources.

关键词： iterative procedure adaptation algorithm antenna array software package

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：