首页> 外国专利> METHOD OF CLASSIFICATION OF A TOBACCO SAMPLE, APPLIANCE FOR CLASSIFYING A TOBACCO SAMPLE, GENERATING A MULTI-VARIANT STATISTICAL REGRESSION MODEL AND ESTIMATE AT LEAST ONE PROPERTY OF A TOBACCO SAMPLE

METHOD OF CLASSIFICATION OF A TOBACCO SAMPLE, APPLIANCE FOR CLASSIFYING A TOBACCO SAMPLE, GENERATING A MULTI-VARIANT STATISTICAL REGRESSION MODEL AND ESTIMATE AT LEAST ONE PROPERTY OF A TOBACCO SAMPLE

机译：烟草样品的分类方法，烟草样品的分类，生成多元统计回归模型并估计至少一个属性的方法

页面导航

摘要
著录项
相似文献

摘要

A method and apparatus for classifying a tobacco sample of a particular tobacco type into a taste category is provided among a predefined set of taste categories for that tobacco type. the method comprises acquiring mass spectrometry data (in) from the tobacco sample; the identification, from acquired data, of various chemical components and their respective concentration levels within the tobacco sample; and assigning the tobacco sample to a taste category from a predefined set of taste categories for that tobacco based on the various chemical components and their respective concentration levels identified in the tobacco sample. The assignment uses a multivariate regression statistical model that represents a relationship between chemical components and flavor categories.

机译：在用于该烟草类型的预定义的一组味道类别中，提供了一种用于将特定烟草类型的烟草样品分类为味道类别的方法和设备。该方法包括从烟草样品获取质谱数据。从获取的数据中识别烟草样品中各种化学成分及其各自的浓度水平;并根据烟草样品中识别出的各种化学成分及其各自的浓度水平，从该烟草的一组预定义的味道类别中为该烟草样品分配一个味道类别。该分配使用多元回归统计模型，该模型表示化学成分与风味类别之间的关系。

著录项

公开/公告号BR102017007458A2

专利类型
公开/公告日2018-01-16

原文格式PDF
申请/专利权人 SOUZA CRUZ LTDA;
展开▼

申请/专利号BR20171007458
发明设计人 GUILHERME POST SABIN;JAILSON CARDOSO DIAS;JOSE ROBERTO PEREIRA DA SILVA;OSCAR PONTES;SAMUEL KAISER;
展开▼

申请日2017-04-11
分类号A24B15;G01N30/72;G01N33/483;G06F19/12;
国家 BR
入库时间 2022-08-21 12:53:56

相似文献

专利
外文文献
中文文献