检索结果-内蒙古大学图书馆

Building selective ensembles of Randomization Based Neural Networks with the successive projections algorithm

APPLIED SOFT COMPUTING 2018年 70卷 1135-1145页

作者： Mesquita, Dieggo P. P. Gomes, Joao Paulo P. Rodrigues, Leonardo R. Oliveira, Saulo A. F. Galvao, Roberto K. H. Univ Fed Ceara Dept Comp Sci Fortaleza CE Brazil Inst Aeronaut & Space Div Elect Sao Jose Dos Campos SP Brazil Inst Tecnol Aeronotut Dept Elect Engn Sao Jose Dos Campos SP Brazil

Randomization based methods for training neural networks have gained increasing attention in recent years and achieved remarkable performances on a wide variety of tasks. The interest in such methods relies on the fact that standard gradient based learning algorithms may often converge to local minima and are usually time consuming. Despite the good performance achieved by Randomization Based Neural Networks (RNNs), the random feature mapping procedure may generate redundant information, leading to suboptimal solutions. To overcome this problem, some strategies have been used such as feature selection, hidden neuron pruning and ensemble methods. Feature selection methods discard redundant information from the original dataset. Pruning methods eliminate hidden nodes with redundant information. Ensemble methods combine multiple models to generate a single one. Selective ensemble methods select a subset of all available models to generate the final model. In this paper, we propose a selective ensemble of RNNs based on the successive projections algorithm (SPA), for regression problems. The proposed method, named Selective Ensemble of RNNs using the successive projections algorithm (SERS), employs the SPA for three distinct tasks: feature selection, pruning and ensemble selection. SPA was originally developed as a feature selection technique and has been recently employed for RNN pruning. Herein, we show that it can also be employed for ensemble selection. The proposed framework was used to develop three selective ensemble models based on the three RNNs: Extreme Learning Machines (ELM), Feedforward Neural Network with Random Weights (FNNRW) and Random Vector Functional Link (RVFL). The performances of SERS-ELM, SERS-FNNRW and SERS-RVFL were assessed in terms of model accuracy and model complexity in several real world benchmark problems. Comparisons to related methods showed that SERS variants achieved similar accuracies with significant model complexity reduction. Amon

关键词： Selective ensemble successive projections algorithm Feedforward neural network with random weights Extreme learning machines Random vector functional link

来源：评论

学校读者我要写书评

暂无评论

Application of successive projections algorithm for variable selection to determine organic acids of plum vinegar

引用

FOOD CHEMISTRY 2009年第4期115卷 1430-1436页

作者： Liu, Fei He, Yong Zhejiang Univ Coll Biosyst Engn & Food Sci Hangzhou 310029 Zhejiang Peoples R China

Visible and near infrared (Vis/NIR) spectroscopy was investigated to determine the acetic, tartaric and lactic acids of plum vinegar based on a newly proposed combination of successive projections algorithm-least squares-support vector machine (SPA-LS-SVM). SPA, compared with regression coefficients (RC), was applied to select effective wavelengths (EWs) with least collinearity and redundancies. Five concentration levels (100%, 80%. 60%, 40% and 20%) of plum vinegar were studied. Multiple linear regression (MLR) and partial least squares (PLS) models were developed for comparison. The results indicated that SPA-LS-SVM achieved the optimal performance for three acids comparing with full-spectrum PLS, SPA-MLR, SPA-PLS, RC-PLS and RC-LS-SVM. The root mean square error of prediction (RMSEP) was 0.3581, 0.0714 and 0.0201 for acetic, tartaric and lactic acids, respectively. The overall results indicated that Vis/NIR spectroscopy incorporated to SPA-LS-SVM could be applied as an alternative fast and accurate method for the determination of organic acids of plum vinegars. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Visible and near infrared spectroscopy successive projections algorithm Variable selection Least squares-support vector machine Plum vinegar Organic acids

来源：评论

学校读者我要写书评

暂无评论

Screening analysis of biodiesel feedstock using UV-vis, NIR and synchronous fluorescence spectrometries and the successive projections algorithm

引用

TALANTA 2012年 97卷 579-583页

作者： Insausti, Matias Gomes, Adriano A. Cruz, Fernanda V. Pistonesi, Marcelo F. Araujo, Mario C. U. Galvao, Roberto K. H. Pereira, Claudete F. Band, Beatriz S. F. Univ Fed Paraiba Dept Quim Lab Automacao & Instrumentacao Quim Analit Quimio BR-58051970 Joao Pessoa Paraiba Brazil Univ Nacl Sur Sect Quim Analit INQUISUR CONICET FIA Lab RA-8000 Bahia Blanca Buenos Aires Argentina Inst Tecnol Aeronaut Div Engn Eletron Sao Jose Dos Campos SP Brazil Univ Fed Rural Pernambuco Dept Quim BR-52171900 Recife PE Brazil

This paper investigates the use of UV-vis, near infrared (NIR) and synchronous fluorescence (SF) spectrometries coupled with multivariate classification methods to discriminate biodiesel samples with respect to the base oil employed in their production. More specifically, the present work extends previous studies by investigating the discrimination of corn-based biodiesel from two other biodiesel types (sunflower and soybean). Two classification methods are compared, namely full-spectrum SIMCA (soft independent modelling of class analogies) and SPA-LDA (linear discriminant analysis with variables selected by the successive projections algorithm). Regardless of the spectrometric technique employed, full-spectrum SIMCA did not provide an appropriate discrimination of the three biodiesel types. In contrast, all samples were correctly classified on the basis of a reduced number of wavelengths selected by SPA-LDA. It can be concluded that UV-vis, NIR and SF spectrometries can be successfully employed to discriminate corn-based biodiesel from the two other biodiesel types, but wavelength selection by SPA-LDA is key to the proper separation of the classes. (C) 2012 Elsevier B.V. All rights reserved.

关键词： Biodiesel UV-vis Near infrared and synchronous Fluorescence spectrometry Wavelength selection SIMCA successive projections algorithm Linear discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Near infrared reflectance spectrometry classification of cigarettes using the successive projections algorithm for variable selection

引用

TALANTA 2009年第5期79卷 1260-1264页

作者： Moreira, Edilene Dantas Teles Coelho Pontes, Marcio Jose Harrop Galvao, Roberto Kawakami Ugulino Araujo, Mario Cesar Univ Fed Paraiba Dept Quim Lab Automacao & Instrumentacao Quim Analit Quimio BR-58051970 Joao Pessoa Paraiba Brazil Inst Tecnol Aeronaut Div Engn Eletron Sao Jose Dos Campos SP Brazil

This paper proposes a methodology for cigarette classification employing Near Infrared Reflectance spectrometry and variable selection. For this purpose, the successive projections algorithm (SPA) is employed to choose an appropriate subset of wavenumbers for a Linear Discriminant Analysis (LDA) model. The proposed methodology is applied to a set of 210 cigarettes of four different brands. For comparison, Soft Independent Modelling of Class Analogy (SIMCA) is also employed for full-spectrum classification. The resulting SPA-LDA model successfully classified all test samples with respect to their brands using only two wavenumbers (5058 and 4903 cm(-1)). In contrast, the SIMCA models were not able to achieve 100% of classification accuracy, regardless of the significance level adopted for the F-test. The results obtained in this investigation suggest that the proposed methodology is a promising alternative for assessment of cigarette authenticity. (C) 2009 Elsevier B.V. All rights reserved.

关键词： Cigarettes Near infrared reflectance spectroscopy Classification successive projections algorithm Linear discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Thermogravimetric determination of L-ascorbic acid in non-effervescent formulations using multiple linear regression with temperature selection by the successive projections algorithm

引用

THERMOCHIMICA ACTA 2011年第1-2期526卷 200-204页

作者： Simencio Otero, Rosa Lucia Harrop Galvao, Roberto Kawakami Ugulino Araujo, Mario Cesar Gomes Cavalheiro, Eder Tadeu Univ Sao Paulo Inst Quim Sao Carlos BR-13566590 Sao Carlos SP Brazil CCDM UFSCar Sao Carlos SP Brazil Inst Tecnol Aeronaut Div Engn Eletron BR-12228900 Sao Jose Dos Campos SP Brazil Univ Fed Paraiba Dept Quim BR-58051970 Joao Pessoa PB Brazil

Changing experimental thermogravimetric conditions, such as heating rate and sample mass, may not be sufficient to eliminate the effect of interactions in pharmaceutical analysis. This motivates the investigation of a chemometric approach to determine active drugs in pharmaceutical formulations. The use of multiple linear regression (MLR) with temperatures selected by the successive projections algorithm (SPA) for determination of L-ascorbic acid (AA) in simulated non-effervescent formulations using microcrystalline cellulose as excipient is evaluated. For comparison, two other multivariate calibration methods, MLR with temperatures selected by genetic algorithm (GA) and partial least squares (PLS) using the entire range of temperatures were chosen. MLR-SPA provided the best predictions, in agreement with the expected AA concentration (correlation of 0.991 and root-mean-square error of 0.8%, m/m in the range 61.3-74.9%, m/m). No significant differences were found between the MLR-SPA values and those from iodimetric titration, according to t-test at 95% confidence level. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Thermogravimetry Multivariate calibration Temperature selection successive projections algorithm Analysis of pharmaceutical formulations

来源：评论

学校读者我要写书评

暂无评论

Determination of Chlorophyll and Hardness in Cucumbers by Raman Spectroscopy with successive projections algorithm (SPA) - Extreme Learning Machine (ELM)

引用

ANALYTICAL LETTERS 2023年第8期56卷 1216-1228页

作者： Ding, Daining Yu, Huichun Yin, Yong Yuan, Yunxia Li, Zhaozhou Li, Fang Henan Univ Sci & Technol Coll Food & Bioengn Luoyang 471023 Peoples R China

The chlorophyll content and hardness are critical indicators for evaluating vegetable quality. To overcome the drawbacks of traditional detection methods, Raman spectroscopy was investigated for the determination of chlorophyll content and hardness in cucumbers. Cucumbers at different storage periods were analyzed and a successive projections algorithm - extreme learning machine (SPA-ELM) method was employed to establish a model for chlorophyll content and hardness. The Raman spectra were preprocessed to reduce noise and minimize the background fluorescence. Subsequently, SPA was used to select characteristic wavelengths for chlorophyll content and hardness using 19 and 26 characteristic wavelengths, respectively. ELM was employed to establish a model based on the selected characteristic wavelengths. The predicted results by ELM were compared with those obtained using partial least squares (PLS) and support vector machine (SVM). The results showed that the best accuracy was obtained using the SPA-ELM algorithm. The coefficients of determination (R-2) of SPA-ELM model for chlorophyll content and hardness were 0.9569 and 0.9659. The root mean square error (RMSE) values were 0.0038 and 0.3570, respectively. A good correlation coefficient and small RMSE value were obtained, indicating the results to be highly accurate and reliable. Raman spectroscopy combined with SPA-ELM method was shown to rapidly and accurately evaluate the chlorophyll content and hardness of cucumbers.

关键词： chlorophyll content cucumber hardness Raman spectroscopy successive projections algorithm extreme learning machine (SPA-ELM)

来源：评论

学校读者我要写书评

暂无评论

The successive projections algorithm for interval selection in PLS

引用

MICROCHEMICAL JOURNAL 2013年 110卷 202-208页

作者： Gomes, Adriano de Araujo Harrop Galvao, Roberto Kawakami Ugulino de Araujo, Mario Cesar Veras, Germano da Silva, Edvan Cirino Univ Fed Paraiba CCEN Dept Quim BR-58051970 Joao Pessoa Paraiba Brazil Inst Tecnol Aeronaut Div Engn Eletron BR-12228900 Sao Jose Dos Campos SP Brazil Univ Estadual Paraiba CCT Dept Quim BR-58429500 Campina Grande PB Brazil

The successive projections algorithm (SPA) is aimed at selecting a subset of variables with small multicollinearity and suitable prediction power for use in Multiple Linear Regression (MLR). The resulting SPA-MLR models have advantages in terms of simplicity and ease of interpretation as compared to latent-variable models, such as Partial-Least-Squares (PIS). However, PLS tends to be less sensitive to instrumental noise. The present paper proposes an extension of SPA to combine the noise-reduction properties of PLS with the possibility of discarding non-informative variables in SPA. For this purpose, SPA is modified in order to select intervals of variables for use in PLS. The proposed iSPA-PLS algorithm is evaluated in two case studies involving near-infrared spectrometric analysis of wheat and beer extract samples. As compared to full-spectrum PLS, the resulting iSPA-PLS models exhibited better performance in terms of both cross-validation and external prediction. On the other hand, iSPA-PLS and SPA-MLR presented similar cross-validation performance, but the iSPA-PLS models clearly outperformed SPA-MLR in the external prediction. Such results indicate that iSPA-PLS may be more robust with respect to differences between the external prediction set and the calibration set used in the cross-validation procedure. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Variable selection iPLS successive projections algorithm Partial Least Squares NIR spectrometry

来源：评论

学校读者我要写书评

暂无评论

A fast and direct spectrophotometric method for the simultaneous determination of methyl paraben and hydroquinone in cosmetic products using successive projections algorithm

引用

INTERNATIONAL JOURNAL OF COSMETIC SCIENCE 2016年第1期38卷 25-34页

作者： Esteki, M. Nouroozi, S. Shahsavari, Z. Univ Zanjan Dept Chem Zanjan 45195313 Iran

OBJECTIVE: To develop a simple and efficient spectrophotometric technique combined with chemometrics for the simultaneous determination of methyl paraben (MP) and hydroquinone (HQ) in cosmetic products, and specifically, to: (i) evaluate the potential use of successive projections algorithm (SPA) to derivative spectrophotometric data in order to provide sufficient accuracy and model robustness and (ii) determine MP and HQ concentration in cosmetics without tedious pre-treatments such as derivatization or extraction techniques which are time-consuming and require hazardous solvents. METHODS: The absorption spectra were measured in the wavelength range of 200-350 nm. Prior to performing chemometric models, the original and first-derivative absorption spectra of binary mixtures were used as calibration matrices. Variable selected by successive projections algorithm was used to obtain multiple linear regression (MLR) models based on a small subset of wavelengths. The number of wavelengths and the starting vector were optimized, and the comparison of the root mean square error of calibration (RMSEC) and cross-validation (RMSECV) was applied to select effective wavelengths with the least collinearity and redundancy. Principal component regression (PCR) and partial least squares (PLS) were also developed for comparison. The concentrations of the calibration matrix ranged from 0.1 to 20 mu g mL(-1) for MP, and from 0.1 to 25 mu g mL(-1) for HQ. The constructed models were tested on an external validation data set and finally cosmetic samples. RESULTS: The results indicated that successive projections algorithm-multiple linear regression (SPA-MLR), applied on the first-derivative spectra, achieved the optimal performance for two compounds when compared with the full-spectrum PCR and PLS. The root mean square error of prediction (RMSEP) was 0.083, 0.314 for MP and HQ, respectively. To verify the accuracy of the proposed method, a recovery study on real cosmetic samples was ca

关键词： chemometrics cosmetics derivative spectrophotometry hydroquinone methyl paraben successive projections algorithm

来源：评论

学校读者我要写书评

暂无评论

Aspects of the successive projections algorithm for variable selection in multivariate calibration applied to plasma emission spectrometry

引用

ANALYTICA CHIMICA ACTA 2001年第1期443卷 107-115页

作者： Galvao, RKH Pimentel, MF Araujo, MCU Yoneyama, T Visani, V Univ Fed Paraiba CCEN Dept Quim BR-58051970 Joao Pessoa Paraiba Brazil Inst Tecnol Aeronaut Div Engn Eletron BR-12228900 Sao Jose Dos Campos SP Brazil Univ Fed Pernambuco CTG Dept Engn Quim BR-50740521 Recife PE Brazil

The successive projections algorithm (SPA) was recently proposed as a variable selection strategy to minimize collinearity problems in multivariate calibration. Although SPA has been successfully applied to UV-VIS spectrophotometric multicomponent analysis, no evidence of its ability to deal with variable sets with both high and low signal-to-noise ratios has been presented. This issue is addressed by the present work, which applies SPA to the simultaneous determination of Mn, Mo, Cr, Ni and Fe using a low-resolution plasma spectrometer/diode array detection system. This problem is of particular interest since strong interanalyte spectral interferences arise and regions with high and low signal intensity alternate in the spectra. Results show that multiple linear regression (MLR) on the wavelengths selected by SPA yields models with better prediction capabilities than principal component regression (PCR) and partial least squares (PLS) models. A standard genetic algorithm (GA) used for comparison yielded results similar to SPA for Mn, Cr and Fe, and better predictions for Mo and Ni. However, in all cases, the GA resulted in models less parsimonious than SPA. The average of the root mean square relative error of prediction (RMSREP) obtained for the five analytes was 1.4% for MLR-SPA, 1.0% for MLR-GA, 2.2% for PCR, and 2.1% for PLS. Since the computational time demanded by SPA grows with the square of the number of spectral variables, a pre-selection procedure based on the identification of emission peaks is proposed. This procedure decreased selection time by a factor of 20, without significantly degrading the results. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： variable selection successive projections algorithm plasma emission spectrometry multivariate calibration

来源：评论

学校读者我要写书评

暂无评论

Neural Networks Calibration Model Optimizing of Wheat Protein Based on successive projections algorithm

Neural Networks Calibration Model Optimizing of Wheat Protei...

引用

3rd International Conference on Frontiers of Manufacturing Science and Measuring Technology (ICFMM 2013)

作者： Mao, Xiaodong Sun, Laijun Hao, Gang Xu, Lulu Hui, Guangyan Heilongjiang Univ Coll Heilongjiang Prov Key Lab Elect Engn Harbin Peoples R China

ISBN: (纸本)9783037858462

In order to reduce computational complexity of modeling and improve the model's robustness and prediction accuracy, successive projections algorithm is used in the Neural Networks calibration modeling of wheat protein. Firstly, the spectral data is pretreated with first-order differential method and SNV method, and then a representative set of calibration samples are selected by SPXY algorithm. Secondly, making use of successive projections algorithm(SPA) to extract sensitive wave points of the original spectrum and the pretreated spectrum, and then the neural networks calibration model of wheat protein is established. The results show that the calibration model based on successive projections algorithm has a fast convergence speed and high accuracy, both of which are better than the calibration model established with the original data. Root mean square error of prediction(RMSEP) and prediction correlation coefficient(r) are 1.3332 and 0.94319 respectively, which can basically complete the grain reserves and the food processing profession division and the breeding preliminary generation.

关键词： wheat protein near infrared spectroscopy successive projections algorithm neural networks

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：