主题：【讨论】近红外光谱分析技术与网络技术联用

具体的内容是：
September/October 2001, Volume 78, Number 5
Pages 572-577
DOI:10.1094/CCHEM.2001.78.5.572

Performance of European Artificial Neural Network (ANN) Calibrations for Moisture and Protein in Cereals Using the Danish Near-Infrared Transmission (NIT) Network

Nils Bo Büchmann,1,2,4 Henrik Josefsson,2 and Ian A. Cowe3
1 DLG (Danish Cooperative Farm Supply), Axelborg, DK 1503, Copenhagen.
2 Foss Tecator AB, Box 70, SE 26321, Höganäs, Sweden.
3 Foss Electric Development (UK) Ltd., Millfield Lane Industrial Estate, Wheldrake, York, YO 19 6NA, UK.
4 Corresponding author. E-mail: bo.buchmann@foss.tecator.se Phone: +46 42 361507. Fax: +46 42 34 0349.

PDF Print (138 KB) | PDF with Links (138 KB)




Three problems need to be addressed in networks of Infratec Grain Analysers: 1) the networks are not interconnected, 2) the partial least squares (PLS) calibrations used so far have to be individually adjusted for bias when transferred to the slave instruments, and 3) the calibrations are not entirely stable over time. Nonlinear artificial neural network (ANN) calibrations based on a large common European data set (≈4,000 samples in the training sets and ≈1,000 samples in the stop sets) were introduced to overcome these constraints. The performance of these ANN calibrations was compared with Danish PLS models for protein and moisture in cereals during the 1998 harvest in Denmark, and subsequently with PLS models based on the same European data set. ANN models were more accurate than PLS and, unlike PLS, were linear and transferable up to 25% moisture. It is suggested that the improved performance of the ANN models is attributable to the modeling technique rather than the size and nature of the European data set. In most cases, ANN models could be applied directly and without bias adjustment to slave instruments. The ANN models were also more stable, they required fewer bias adjustments or remodeling over time compared with Danish PLS models. ANN calibrations using shared data have been adopted for commercial use in several European countries and work is in progress to develop global ANN models for determination of protein in wheat and barley.

Cited by
The effect of tillage intensity on soil structure and winter wheat root/shoot growth
Lars J. Munkholm, Elly M. Hansen, and Jørgen E. Olesen
Soil Use and Management 2009, Volume 24, Number 4: 392-400
CrossRef
A pathway-specific microarray analysis highlights the complex and co-ordinated transcriptional networks of the developing grain of field-grown barley
M. Hansen, C. Friis, S. Bowra, P. B. Holm, and E. Vincze
Journal of Experimental Botany 2008, Volume 60, Number 1: 153-167
CrossRef
Yield and flour quality of spring wheat as affected by soil tillage and animal manure
Ingrid K Thomsen, Lene Pedersen, and Johannes R Jørgensen
Journal of the Science of Food and Agriculture 2008, Volume 88, Number 12: 2117-2124
CrossRef
Catch crop strategy and nitrate leaching following grazed grass-clover
E. M. Hansen, J. Eriksen, and F. P. Vinther
Soil Use and Management 2008, Volume 23, Number 4: 348-358
CrossRef
Near-infrared spectroscopy and imaging in food quality and safety
Wenbo Wang and Jitendra Paliwal
Sensing and Instrumentation for Food Quality and Safety 2008, Volume 1, Number 4: 193-207
CrossRef

这里有很多内容的：
http://www.google.cn/search?hl=zh-CN&newwindow=1&q=NIR+network+french+grain&meta=&aq=f&oq=

关于谷物的近红外研究

德国的研究

日本的研究
Title: Factors affecting in determining constituent content of grain by NIR spectroscopy (Part 1). Effects of grain and milling condition on the Factors affecting in determining constituent content of grain by NIR spectroscopy (Part 1). Effects of grain and milling condition on the whole-meal granularity and moisture.
Personal Authors: Natsuga, M., Kawamura, S., Itoh, K.
Author Affiliation: Faculty of Agriculture, Hokkaido University, Sapporo-shi, 060 Japan.
Editors: No editors
Document Title: Journal of the Japanese Society of Agricultural Machinery

Abstract:
The effect of milling conditions on whole-meal granularity and m.c. was investigated for 3 types of milling machine and 3 wheat and 1 brown rice varieties using near-infrared reflectance spectroscopy. Granularity and m.c. were significantly affected by variety, type of milling machine and milling temp.


Publisher:


About CAB Abstracts
CAB Abstracts is a unique and informative resource covering everything from Agriculture to Entomology to Public Health. In April 2006 we published our 5 millionth abstract, making it the largest and most comprehensive abstracts database in its field.

哇！！这么多相关的消息啊！！好好。。。。。我一定要好好研究一下。谢谢斑竹加精！！

原文由 capezx 发表:

原文由 ruojun 发表:

原文由 capezx 发表:
我通过看资料知道法国在光谱库，网络模型库的建设上比较好。已经有了一定的发展。就是找不到文献或者报道类的东西具体说明。模型转移和光谱转移我认为还是有研究意义的，关于联用技术应该是能提高准确性的才对，可这方面的文献和资料我都没能接触到。希望大家多讨论吧。

你知道法国哪个单位么？我询问一下加拿大的朋友，看看他们的进展。

是看的袁洪福教授的访谈。上面这么说：袁洪福教授指出：“限制近红外分析技术大规模推广的技术瓶颈是模型，因为模型建立工作需要收集大量具有代表性的样品，由具备熟悉光谱、化学计量学和具体分析专业知识的专业人员来完成；显然，一般用户不具备这样的条件。发达国家已经开始建立近红外光谱网络中心，负责建立模型和模型更新，通过Internet将模型传递到用户，用户也可以将样品光谱和性质发送到网路中心，用户可以不必进行复杂的建模工作，就可以方便使用近红外技术。例如，法国的农业粮食收购领域拥有5个近红外光谱网络中心、6000多台仪器。”
我查这个信息很久了，就是找不到相关的报道。

  近红外光谱分析技术与网络技术联用这项技术不错，对于近红外技术的推广、帮助用户用好近红外以及减少用户开发模型的成本意义重大，只是现在国内的近红外仪器还不多，使用仪器的单位可能为了数据保密也不会公开，要想实现道路比较漫长啊！