检索结果-内蒙古大学图书馆

IEEE International Conference on Granular Computing

作者： Feng Jiali Xu Guanglin Wang Xiaofeng Shanghai Maritime Univ Informat Engn Coll Shanghai 200135 Peoples R China

ISBN: (纸本)9781424425129

An attribute computing network induced by qualitative mapping is presented in this paper and the feedback adjustment mechanism for qualitative criterion and the learning algorithm are given. After that, the pattern recognition method based on the attribute computing network is brought forward. An actual application using such method is given in the end.

关键词： pattern recognition method learning algorithms FEEDBACK REGULATION

来源：评论

学校读者我要写书评

暂无评论

Partial discharge pattern recognition method based on variable predictive model-based class discriminate and partial least squares regression

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2016年第7期10卷 737-744页

作者： Zhu, Yongli Jia, Yafei Wang, Liuwang North China Elect Power Univ State Key Lab Alternate Elect Power Syst Renewabl Baoding 071003 Peoples R China

Both the feature extraction method and pattern recognition method are of great importance to assess the health condition of a power transformer. Since the partial discharge (PD) signals of the transformer are non-stationary and non-linear, and the existing pattern recognition methods fail to capitalise on the inter-relations between the extracted features of the signals, a novel pattern recognition method, namely variable predictive model based class discrimination (VPMCD) is introduced for the PD pattern recognition in this research. However, the parameters of VPMCD are estimated by using least squares (LS) regression which is sensitive to multiple correlations between independent variables. Fortunately, partial LS (PLS) regression is usable even if features are highly correlated or the number of trained samples is very small. It is novelly adopted to overcome the defects of LS regression. Therefore, an automatic PD source classifier based on PLS and VPMCD, i.e. PLS-VPMCD, is put forward in this study. PD signal features from either pulse shape characterisations or phase-resolved PD are extracted. Then, the features are used as the input vectors of PLS-VPMCD classifier. PD signals sampled from four artificial defect models are adopted for the algorithms testing. Compared with the original VPMCD and back propagation recognition methods, PLS-VPMCD has much higher recognition accuracy.

关键词： partial discharges least squares approximations regression analysis feature extraction power transformers prediction theory vectors signal sampling partial discharge pattern recognition method partial least square regression variable predictive model-based class discriminate feature extraction method pattern recognition method power transformer PD signal feature extraction VPMCD PLS regression automatic PD source classifier pulse shape characterisation phase-resolved PD extraction artificial defect model backpropagation recognition method

来源：评论

学校读者我要写书评

暂无评论

Investigation of CoPd alloys by XPS and EPES using the pattern recognition method

引用

JOURNAL OF ALLOYS AND COMPOUNDS 2007年第1-2期428卷 190-196页

作者： Lesiak, B. Zemek, J. Jiricek, P. Jozwik, A. Polish Acad Sci Inst Phys Chem PL-01224 Warsaw Poland Acad Sci Czech Republ Inst Phys Prague 16253 6 Czech Republic Polish Acad Sci Inst Biocybernet & Biomed Engn PL-02109 Warsaw Poland Tech Univ Lodz Comp Engn Dept PL-90924 Lodz Poland

The electrons elastically backscattered from a solid surface are visualised in the elastic peak electron spectroscopy (EPES) spectra, which intensity recorded at certain geometry and energy of primary electrons, is a measure of electron backscattering probability. The theoretical description of electron interaction with a solid surface reflected in the EPES spectrum and its vicinity is of a complex character. In the present work the EPES method was applied for quantification of the in-depth composition in sputter-cleaned CoPd alloys and annealed Co50Pd50 at different measurement geometries and electron energies. The present approach applies the pattern recognition method called the fuzzy k-nearest neighbour (fkNN) rule to the line shape analysis of the EPES spectra recorded at Co, Pd and CoPd alloys. The proposed method was successful for distinguishing qualitatively the effect of the surface roughness, the texture and the grain size, and for identifying quantitatively the surface composition. Discrepancies between the results are discussed, within the limitations and sensitivity of the applied method, and the accuracy of the electron elastic cross-sections. (c) 2006 Elsevier B.V. All rights reserved.

关键词： CoPd alloys X-ray photoelectron spectroscopy (XPS) elastic peak electron spectroscopy (EPES) pattern recognition method fuzzy k-nearest neighbour rule (fkNN) quantitative analysis surface segregation

来源：评论

学校读者我要写书评

暂无评论

pattern recognition method from hydrochemical parameters to predict uranium concentrations in groundwater

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2022年 222卷

作者： Khurelbaatar, Luvsanbat Batdelger, Ankhnybayar Khinayat, Tsookhuu Oyuntsetseg, Bolormaa Natl Univ Mongolia Sch Arts & Sci Dept Chem Ulaanbaatar 14201 Mongolia Cent Geol Lab Ulaanbaatar 18080 Mongolia Natl Univ Mongolia Sch Arts & Sci Dept Phys Ulaanbaatar 14201 Mongolia

Traditional methods for determining uranium in groundwater are spectroscopic methods that require time, money, and experienced chemists. A prediction method for predicting uranium concentration using a few hydrochemical parameters that are related to uranium was developed within this study. In this study, uranium, hydrochemical parameters, and trace elements of groundwater around Ulaanbaatar in Mongolia were measured. Inductively coupled plasma mass spectrometry was used to determine the uranium concentration in 135 samples. The relationship between uranium concentration and hydrochemical parameters was studied to determine whether the concentration in groundwater could be predicted using chemometric methods based on some hydrochemical parameters. Chemometric methods were performed using a Python programming language. A pattern recognition method for classifying groundwater samples by specific threshold uranium concentration uses a principal component analysis (PCA) and support vector machine (SVM). The average accuracy of the classifi-cation models was 88.21%. PCA is used to visualize the classification by uranium concentration and show which hydrochemical parameters are crucial to predicting uranium concentration. In this study, a regression model was developed to predict uranium concentration in groundwater using hydrochemical parameters selected by the PCA-SVM combination method. The regression method uses a combination of polynomial regression and multiple linear regression. This combined regression method has shown good results for predicting uranium concentrations based on selected hydrochemical parameters.

关键词： pattern recognition method Uranium prediction Hydrochemical parameters Multivariate regression Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Emission efficiency optimization of RE₂O₃ doped molybdenum thermionic cathode by application of pattern recognition method

引用

APPLIED SURFACE SCIENCE 2005年第1-4期251卷 89-96页

作者： Wang, JS Liu, W Liu, YQ Zhou, ML Beijing Univ Technol Sch Mat Sci & Engn Beijing 100022 Peoples R China

As an alternative for thoriated tungsten thermionic cathodes, molybdenum doped with either a single rare earth oxide such as La2O3, Y2O3 and Sc2O3 or a mixture thereof has been produced by powder metallurgy. It is shown that carbonization can greatly improve the emission properties (i.e. emission capability and stability) of RE2O3 doped molybdenum due to the formation of a (metallic) rare earth atomic layer on the surface of the cathode by the reduction reaction of molybdenum carbide and rare earth oxide. Among all the carbonized samples, La2O3 and Y2O3 co-doped molybdenum cathode showed the best performance in emission. In addition, computer pattern recognition technique has been used to optimize the composition of the material and of the cathode preparation technique. We derive the equation of the emission efficiency as a function of cathode composition and carbonization degree. Based on the projecting coordinates obtained from the equation, the optimum projection region was identified, which can serve as guide for the composition and carbonization degree design. (c) 2005 Elsevier B.V. All rights reserved.

关键词： thermionic emission thoriated tungsten rare earth oxide (RE2O3) molybdenum carbonized cathode pattern recognition method

来源：评论

学校读者我要写书评

暂无评论

A pattern recognition method for Stage Classification of Parkinson's Disease Utilizing Voice Features 3

A Pattern Recognition Method for Stage Classification of Par...

引用

IEEE INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING AND SCIENCES

作者： Caesarendra, Wahyu Ariyanto, Mochammad Setiawan, Joga D. Arozi, Moh. Chang, Cindy R. Diponegoro Univ Dept Mech Engn Fac Engn Semarang 50275 Indonesia Univ Wollongong Sch Nursing & Midwifery Fac Sci Wollongong NSW 2500 Australia

ISBN: (纸本)9781479940844

This paper presents a pattern recognition method for multi-class classification of Parkinson's disease based on PCA, LDA and SVM. 22 voice features which are extracted and reduced using PCA and LDA. SVM is then used during the classification step. The classification accuracy between single features and PCA and LDA features are presented and the results show that the PCA features have greater accuracy than LDA features and the single features.

关键词： diseases feature extraction medical computing pattern classification principal component analysis support vector machines Parkinson's disease stage classification feature classification accuracy linear discriminant analysis pattern recognition method utilizing voice features Accuracy Feature extraction pattern recognition Principal component analysis Support vector machines Testing Training

来源：评论

学校读者我要写书评

暂无评论

Emission efficiency optimization of RE₂O₃ doped molybdenum thermionic cathode by application of pattern recognition method

Emission efficiency optimization of RE<sub>2</sub>O<sub>3</s...

引用

5th Internatioal Vacuum Electron Sources Conference

作者： Wang, JS Liu, W Liu, YQ Zhou, ML Beijing Univ Technol Sch Mat Sci & Engn Beijing 100022 Peoples R China

关键词： thermionic emission thoriated tungsten rare earth oxide (RE2O3) molybdenum carbonized cathode pattern recognition method

来源：评论

学校读者我要写书评

暂无评论

X-ray photoelectron spectroscopy and the pattern recognition method -: their application to surface studies in CoPd alloys

引用

SURFACE AND INTERFACE ANALYSIS 2005年第13期37卷 1143-1150页

作者： Lesiak, B Bilinski, A Józwik, A Polish Acad Sci Inst Phys Chem PL-01224 Warsaw Poland Polish Acad Sci Inst Biocybernet & Biomed Engn PL-02109 Warsaw Poland Tech Univ Lodz Dept Comp Engn PL-90924 Lodz Poland

In the present work, polycrystalline CoPd alloys in varying range of bulk atomic percent composition (Co30Pd70, Co50Pd50 and Co70Pd30) are investigated by means of X-ray photoelectron spectroscopy (XPS). The results of conventional XPS quantitative multiline (ML) approach are compared to the results obtained on the basis of XPS lines shape analysis, where the selected XPS or X-ray induced Auger electron (XAES) transitions, are processed using the pattern recognition method known as the frizzy k-nearest neighbour (fkNN) rule. The fkNN rule is applied to the following spectra line shapes: I'd MNV, Co 2p, Co LMM, I'd 3d and valence band, analysing electrons in a varying range of selected kinetic energies. Both methods showed the surface segregation of I'd in Co30Pd70 and Co50Pd50 alloys. The results of the ML, the binding energy shift (Delta BE) analysis and the fkNN rule remained in agreement. Discrepancies in quantitative results obtained using different approaches are discussed within the accuracy of the applied methods, differences due to mean escape depth (MED) of electrons in considered transitions, their depth distribution function, the sensitivity of electron transition line shape on the environmental change (weaker effect for the inner shell transitions, and stronger effect for the outer shell transitions and Auger electron spectroscopy (AES) electrons transitions) and the non-uniform depth profile concentrations. Copyright (C) 2005 John Wiley & Sons, Ltd.

关键词： CoPd alloys X-ray photoelectron spectroscopy (XPS) X-ray induced Auger electron spectroscopy (XAES) pattern recognition method fuzzy k-nearest neighbour rule (fkNN) surface segregation

来源：评论

学校读者我要写书评

暂无评论

Studies of AuNi alloys by electron spectroscopies with the aid of the line shape analysis by the pattern recognition method

引用

SURFACE AND INTERFACE ANALYSIS 2006年第8期38卷 1204-1210页

作者： Lesiak, B. Zemek, J. Jiricek, P. Jozwik, A. Polish Acad Sci Inst Phys Chem Warsaw Poland Acad Sci Czech Republ Inst Phys Prague 16253 Czech Republic Polish Acad Sci Inst Biocybernet & Biomed Engn PL-02109 Warsaw Poland Tech Univ Lodz Dept Comp Engn PL-90924 Lodz Poland

The spectrum of electrons elastically backscattered from the surface and within its vicinity reflects the probability of electron elastic backscattering on the surface atoms, quasi-elastic scattering and the inelastic scattering visible in the low energy side of the elastic peak. The method for investigating the processes of electron elastic backscattering on the surface atom is called the elastic peak electron spectroscopy (EPES). In the present work, AuNi alloys of different compositions are investigated using X-ray photoelectron spectroscopy (XPS) and the EPES method with the aid of the line shape analysis called the fuzzy k-nearest neighbour (fkNN) rule. The line shape analysis was found to be applicable for EPES spectroscopy. It allows distinguishing the surfaces exhibiting various surface roughness, texture and grain size, and quantifying the selected information depths. The quantitative results obtained from the XPS analysis and the EPES spectra line shape analysis indicated Au surface segregation with Au surface enriched profile. Quantitative discrepancies are discussed within the non-uniform concentration profiles of constituents due to sputter cleaning and annealing, different diffusion coefficients for Au and Ni, differences in the information depths sampled by XPS and EPES methods and differences in electron elastic backscattering cross-sections for Ni and Au. Copyright (C) 2006 John Wiley & Sons, Ltd.

关键词： elastic peak electron spectroscopy EPES X-ray photoelectron spectroscopy XPS line shape analysis pattern recognition method fuzzy k-nearest neighbour rule fkNN rule AuNi alloys Au surface segregation

来源：评论

学校读者我要写书评

暂无评论

EEG based pattern recognition method for Classification of Different Mental Tasking: Preliminary study for stroke survivors in Indonesia

EEG based Pattern Recognition Method for Classification of D...

引用

International Conference on Automation, Cognitive Science, Optics, Micro Electro-Mechanical System, and Information Technology

作者： Wahyu Caesarendra Mochammad Ariyanto Syahara U. Lexon Elta D. Pasmanasari Cindy R. Chang Joga D. Setiawan Department of Mechanical Engineering Universitas Diponegoro Department of Neurology Universitas Diponegoro School of Nursing and Midwifery University Of Wollongong Department of Mechanical Engineering Universiti Teknologi Petronas

ISBN: (纸本)9781467374095

This paper presents a result of pattern recognition method for different mental tasking of 8 volunteers. The EEG data used in this paper were acquired from 8 Indonesian volunteer using Emotiv EEG device with 16 channels. 24 feature extraction methods including time-domain and statistical features are applied to the EEG signal. An artificial neural network (ANN) is employed for classification. This is the preliminary study in developing a pattern recognition method for body prosthetic and wheelchair to disability person. The paper aims to investigate the reliable EEG signal from 14 channels. The results show that among 14 EEG channels, channel F7 and F8 are better in classification than other channels. The test classification of channel F7 and F8 is 66.7%.

关键词： Artificial neural network Classification EEG signal Feature extraction pattern recognition method Feature extraction Electroencephalography Artificial neural networks Taxonomy Indonesia Wheelchair

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：