检索结果-内蒙古大学图书馆

The continuous wavelet projections algorithm: A practical spectral-feature-mining approach for crop detection

The Crop Journal 2022年第5期10卷 1264-1273页

作者： Xiaohu Zhao Jingcheng Zhang Ruiliang Pu Zaifa Shu Weizhong He Kaihua Wu College of Artificial Intelligence Hangzhou Dianzi UniversityHangzhou 310018ZhejiangChina School of Geosciences University of South FloridaTampaFL 33620USA Lishui Institute of Agriculture and Forestry Sciences Lishui 323000ZhejiangChina

Spectroscopy can be used for detecting crop characteristics. A goal of crop spectrum analysis is to extract effective features from spectral data for establishing a detection model. An ideal spectral feature set should have high sensitivity to target parameters but low information redundancy among ***, feature-selection methods that satisfy both requirements are lacking. To address this issue,in this study, a novel method, the continuous wavelet projections algorithm(CWPA), was developed,which has advantages of both continuous wavelet analysis(CWA) and the successive projections algorithm(SPA) for generating optimal spectral feature set for crop detection. Three datasets collected for crop stress detection and retrieval of biochemical properties were used to validate the CWPA under both classification and regression scenarios. The CWPA generated a feature set with fewer features yet achieving accuracy comparable to or even higher than those of CWA and SPA. With only two to three features identified by CWPA, an overall accuracy of 98% in classifying tea plant stresses was achieved, and high coefficients of determination were obtained in retrieving corn leaf chlorophyll content(R^(2)= 0.8521)and equivalent water thickness(R^(2)= 0.9508). The mechanism of the CWPA ensures that the novel algorithm discovers the most sensitive features while retaining complementarity among features. Its ability to reduce the data dimension suggests its potential for crop monitoring and phenotyping with hyperspectral data.

关键词： Hyperspectral Crop parameters Crop phenotyping Continuous wavelet analysis successive projections algorithm

来源：评论

学校读者我要写书评

暂无评论

Online monitoring of red meat color using hyperspectral imaging

引用

MEAT SCIENCE 2016年 116卷 110-117页

作者： Kamruzzaman, Mohammed Makino, Yoshio Oshita, Seiichi Univ Tokyo Tokyo 1138654 Japan Bangladesh Agr Univ Fac Agr Engn & Technol Dept Food Technol & Rural Ind Mymensingh 2202 Bangladesh

A hyperspectral imaging system in the spectral range of 400-1000 nm was tested to develop an online monitoring system for red meat (beef, lamb, and pork) color in the meat industry. Instead of selecting different sets of important wavelengths for beef, lamb, and pork, a set of feature wavelengths were selected using the successive projection algorithm for red meat colors (L*, a*, b) for convenient industrial application. Only six wavelengths (450, 460, 600, 620, 820, and 980 nm) were further chosen as predictive feature wavelengths for predicting L*, a*, and b* in red meat. Multiple linear regression models were then developed and predicted L*, a*, and b* with coefficients of determination (R-p(2)) of 0.97, 0.84, and 0.82, and root mean square error of prediction of 1.72, 1.73, and 1.35, respectively. Finally, distribution maps of meat surface color were generated. The results indicated that hyperspectral imaging has the potential to be used for rapid assessment of meat color. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Hyperspectral imaging Beef Lamb Pork Multivariate analysis Image processing successive projections algorithm

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral band selection based on dual evaluation measures and improved nondominated sorting genetic algorithm

引用

JOURNAL OF APPLIED REMOTE SENSING 2021年第2期15卷

作者： Yang, Yu Wang, Xin Huang, Min Zhu, Qibing Guo, Ya Xu, Libing Zhou, Zheng Jiangnan Univ Key Lab Adv Proc Control Light Ind Minist Educ Wuxi Jiangsu Peoples R China Natl Supercomp Ctr Wuxi Wuxi Jiangsu Peoples R China Tsinghua Univ Dept Earth Syst Sci Beijing Peoples R China

Awide variety of swarm intelligence algorithm-based approaches have been recently developed for selecting the near-optimal bands from hyperspectral images (HSIs). However, such methods [including the nondominated sorting genetic algorithm (NSGA)] for HSIs pixel classification are limited by the lack of effective initialization and directional evolution. This research proposed a successive projections algorithm (SPA) and individual repair operation for NSGA (named Sr-NSGA) for band selection. Specifically, Sr-NSGA used the SPA to initialize the population and construct repair sequences that optimize new generated individuals in evolution. Meanwhile, with the guidance of two mutually restricted fitness functions, i.e., average mutual information and classification accuracy, Sr-NSGA searched for the near-optimal band set in an iterative way. Different combinations obtained by SR-NSGA and three effective band selection methods were tested and compared on the Botswana, KSC, and Indian Pines datasets. The results show that Sr-NSGA yielded better performance than the other three methods. Furthermore, support vector machine was used as the classifier for the pixel classification of the Indian Pines dataset to test Sr-NSGA. Experimental result show that Sr-NSGA achieves an overall accuracy of 95.57% and adapts to different classifiers. (C) 2021 Society of PhotoOptical Instrumentation Engineers (SPIE)

关键词： hyperspectral image band selection successive projections algorithm repair operation Sr-NSGA

来源：评论

学校读者我要写书评

暂无评论

Rapid and Non-destructive Detection of Iron Porphyrin Content in Pork Using Multispectral Imaging Approach

引用

FOOD ANALYTICAL METHODS 2016年第5期9卷 1180-1187页

作者： Ma, Fei Qin, Hao Zhou, Cunliu Wang, Xia Chen, Conggui Zheng, Lei Hefei Univ Technol Sch Biotechnol & Food Engn Hefei 230009 Anhui Peoples R China Hefei Univ Technol Sch Med Engn Hefei 230009 Anhui Peoples R China

The feasibility of using multispectral imaging (MSI) technique (405-970 nm) for predicting iron porphyrin (IP) content in pork was assessed. Based on nine feature wavelengths identified by successive projections algorithm (SPA), a partial least squares regression (PLSR) calibration model was established, leading to a determination coefficient (R (2)) of 0.996 for the prediction set. Visualization of IP content in each pixel of the multispectral images using the prediction model offers an effective way to monitor the distribution and real-time evolution of IP content during the manufacturing process. The results revealed the potentiality of MSI technique combined with PLSR calibration analysis as a rapid and non-destructive evaluation method of IP content for the agri-food industry.

关键词： Multispectral imaging Iron porphyrin Pork Partial least squares regression successive projections algorithm Visualization

来源：评论

学校读者我要写书评

暂无评论

NIR spectrometric determination of quality parameters in vegetable oils using iPLS and variable selection

引用

FOOD RESEARCH INTERNATIONAL 2008年第4期41卷 341-348页

作者： Costa Pereira, Alessandra Felix Coelho Pontes, Marcio Jose Gambarra Neto, Francisco Fernandes Bezerra Santos, Sergio Ricardo Harrop Galvao, Roberto Kawakami Ugulino Araujo, Mario Cesar Univ Fed Paraiba Dept Quim Lab Automacao & Instrument Quim Analit Quimiometr BR-58051970 Joao Pessoa Paraiba Brazil Inst Tecnol Aeronaut Div Engn Eletron Sao Jose Dos Campos Brazil

This paper proposes an analytical method for simultaneous near-infrared (NIR) spectrometric determination of acidity, refractive index and viscosity in four types of edible vegetable oils (corn, soya, canola and sunflower). For this purpose, a combination of spectral range selection by interval partial least squares (iPLS) and variable selection by the successive projections algorithm (SPA) is proposed to obtain simple multiple linear regression (MLR) models based on a small subset of wavenumbers. An independent set of samples was employed to evaluate the prediction ability of the resulting MLR-SPA models. As a result, correlation values of 0.94, 0.98, and 0.96 were obtained between model predictions and reference values for acidity, refractive index, and viscosity, respectively. The results show that a single calibration can be successfully performed for each parameter, without the need for developing a separate model for each vegetable oil type. (c) 2008 Elsevier Ltd. All rights reserved.

关键词： edible vegetable oils near-infrared spectrometry acidity refractive index viscosity interval partial least squares successive projections algorithm multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Using UV-Vis spectroscopy for simultaneous geographical and varietal classification of tea infusions simulating a home-made tea cup

引用

FOOD CHEMISTRY 2016年 192卷 374-379页

作者： Goncalves Dias Diniz, Paulo Henrique Barbosa, Mayara Ferreira Tavares de Melo Milanez, Karla Danielle Fabian Pistonesi, Marcelo Ugulino de Araujo, Mario Cesar Univ Fed Paraiba CCEN Dept Quim BR-58051970 Joao Pessoa Paraiba Brazil Univ Nacl Sur INQUISUR Dept Quim RA-8000 Bahia Blanca Buenos Aires Argentina

In this work we proposed a method to verify the differentiating characteristics of simple tea infusions prepared in boiling water alone (simulating a home-made tea cup), which represents the final product as ingested by the consumers. For this purpose we used UV-Vis spectroscopy and variable selection through the successive projections algorithm associated with Linear Discriminant Analysis (SPA-LDA) for simultaneous classification of the teas according to their variety and geographic origin. For comparison, KNN, CART, SIMCA, PLS-DA and PCA-LDA were also used. SPA-LDA and PCA-LDA provided significantly better results for tea classification of the five studied classes (Argentinean green tea;Brazilian green tea;Argentinean black tea;Brazilian black tea;and Sri Lankan black tea). The proposed methodology provides a simpler, faster and more affordable classification of simple tea infusions, and can be used as an alternative approach to traditional tea quality evaluation as made by skilful tasters, which is evidently partial and cannot assess geographic origins. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Tea Classification Variety Geographical origin UV-Vis spectroscopy successive projections algorithm

来源：评论

学校读者我要写书评

暂无评论

Voltammetric e-Tongue Based on a Single Sensor and Variable Selection for the Classification of Teas

引用

FOOD ANALYTICAL METHODS 2018年第7期11卷 1958-1968页

作者： Rodrigues, Dayvison R. de Oliveira, Diana S. M. Pontes, Marcio J. C. Lemos, Sherlan G. Univ Fed Paraiba Dept Quim CP 5093 BR-58051970 Joao Pessoa PB Brazil

This work presents a simple and low-cost strategy to obtain voltammetric tongues by using a single voltammetric sensor aided by variable selection techniques. A usual electronic tongue consists of an array of physical sensors followed by data compression before pattern recognition modeling. Alternatively, a single voltammetric sensor can also act as an array of pseudo-sensors-applied potentials in a voltammogram-that can be properly selected to perform a given discrimination. The applicability of this strategy was evaluated in the discrimination of teas. Teas prepared for immediate intake (simulating a home-made tea cup) were analyzed with staircase voltammetry at an epoxy-graphite electrode. Voltammograms were submitted to variable selection previously to linear discriminant analysis (LDA) to identify the applied potentials that improve discrimination of teas according to variety, country of origin, and manufacturer. successive projections algorithm (SPA), genetic algorithm (GA), and stepwise (SW) formulation were the variable selection techniques evaluated. Best results were achieved with SPA/LDA models, with correct classification rates for the prediction set close to 100%.

关键词： Tea Voltammetric electronic tongue Multivariate classification successive projections algorithm

来源：评论

学校读者我要写书评

暂无评论

Measurement of moisture content in lubricating oils of high-speed rail gearbox by Vis-NIR spectroscopy

引用

OPTIK 2020年 224卷 165694-165694页

作者： Liu, Chenyang Tang, Xingjia Yu, Tao Wang, Taisheng Lu, Zhenwu Yu, Weixing Chinese Acad Sci R&D Ctr Precis Instruments & Equipment Changchun Inst Opt Fine Mech & Phys 3888 Dongnanhu Rd Changchun Jilin Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Chinese Acad Sci Xian Inst Opt & Precis Mech Key Lab Spectral Imaging Technol 17 Xinxi Rd Xian 710119 Peoples R China

The moisture content in lubricating oil is one of the most important factors to reflect the health and effectiveness of it, thus to monitor the moisture content in lubricating oil in real time is crucial for high speed rail. In this paper, we developed a compact moisture-content monitoring system based on the visible-near-infrared (Vis-NIR) spectroscopy technology, which was shown to be able to determine the moisture content in lubricating oil in a fast, simple and accurate way. In this system, a reflection mode optical probe was developed for sending and receiving optical signals through the viewport of gear box. By employing the reflection optical probe, one can measure the spectrum of the lubricating oil in a fast way by simply putting the probe on viewport of gear box, and therefore has the potential to realize the real-time monitoring of the status of the lubricating oil. In order to verify the feasibility of the system, both reflection and transmission spectral of lubricating oil were taken. Partial least square regression (PLS) and back propagation neural network (BPNN) algorithms were used to establish the processing model. Modelling results show a good agreement in between two different probing modes. As a result, the effectiveness and reliability of the system have been proved, which provides a simple yet accurate method for real time monitoring the healthy status of the lubricating oil for the safe operation of the high-speed rail.

关键词： Vis-NIR spectroscopy Lubricating oils Moisture content The reflection probe successive projections algorithm Partial least square regression Back propagation neural network

来源：评论

学校读者我要写书评

暂无评论

Classification of edible vegetable oils using square wave voltammetry with multivariate data analysis

引用

TALANTA 2009年第5期77卷 1660-1666页

作者： Gambarra-Neto, Francisco Fernandes Marino, Glimaldo Ugulino Araujo, Mario Cesar Harrop Galvao, Roberto Kawakami Coelho Pontes, Marcio Jose de Medeiros, Everaldo Paulo Lima, Renato Sousa 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 EMBRAPA Ctr Nacl Pesquisa Algodao Campina Grande PB Brazil

This paper proposes a simple and non-expensive electroanalytical methodology for classification of edible vegetable oils with respect to type (canola, sunflower, corn and soybean) and conservation state (expired and non-expired shelf life). The proposed methodology employs an alcoholic extraction procedure followed by square wave voltammetry (SWV). Two chemometric methods were compared for classification of the resulting voltammograms, namely Soft Independent Modelling of Class Analogy (SIMCA) and Linear Discriminant Analysis (LDA) with variable selection by the successive projections algorithm (SPA). The results were evaluated in terms of errors in a set of samples not included in the modelling process. The best results were obtained with the SPA-LDA method, which correctly classified all samples in terms of type and conservation state. (C) 2008 Elsevier B.V. All rights reserved.

关键词： Vegetable oil Square wave voltammetry Soft Independent Modelling of Class Analogy Linear Discriminant Analysis successive projections algorithm

来源：评论

学校读者我要写书评

暂无评论

Non-destructive prediction of protein content in wheat using NIRS

引用

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2018年 189卷 463-472页

作者： Ye, Dandan Sun, Laijun Zou, Borui Zhang, Qian Tan, Wenyi Che, Wenkai Heilongjiang Univ Coll Heilongjiang Prov Key Lab Elect Engn Harbin Heilongjiang Peoples R China Heilongjiang Univ Room 503Bldg A874 Xuefu Rd Harbin 150080 Heilongjiang Peoples R China

A steady and accurate model used for quality detection depends on precise data and appropriate analytical methods. In this study, the authors applied partial least square regression (PLSR) to construct a model based on the spectral data measured to predict the protein content in wheat, and proposed a new method, global search method, to select PLSR components. In order to select representative and universal samples for modeling, Monte Carlo cross validation (MCCV) was proposed as a tool to detect outliers, and identified 4 outlier samples. Additionally, improved simulated annealing (ISA) combined with PLSR was employed to select most effective variables from spectral data, the data's dimensionality reduced from 100 to 57, and the standard error of prediction (SEP) decreased from 0.0716 to 0.0565 for prediction set, as well as the correlation coefficients (R-2) between the, predicted and actual protein content of wheat increased from 0.9989 to 0.9994. In order to reduce the dimensionality of the data further, successive projections algorithm (SPA) was then used, the combination of these two methods was called ISA-SPA. The results indicated that calibration model built using ISA-SPA on 14 effective variables achieved the optimal performance for prediction of protein content in wheat comparing with other developed PLSR models (ISA or SPA) by comprehensively considering the accuracy, robustness, and complexity of models. The coefficient of determination increased to 0.9986 and the SEP decreased to 0.0528, respectively. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Partial least square regression Monte Carlo cross validation Outliers PLSR components Improved simulated annealing successive projections algorithm

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：