专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

EP1008952A3 System and method for identifying the geographic origin of a fresh commodity 审中-公开
标题翻译：系统和方法，用于识别新鲜消耗品的地理起源
公开(公告)号：EP1008952A3
公开(公告)日：2003-11-12
申请号：EP99309933.2
申请日：1999-12-10
申请人： Florida Department of Citrus , Florida Department of Citrus and Idaho Potato Commission
发明人： Anderson, Kim A. , Smith, Brian , Magnuson, Bernadene
IPC分类号： G06N3/04 , G01N33/02
CPC分类号： G06N3/0454 , G06K9/62 , G06K2209/17
摘要： The detection method includes generating a plurality of neural network models. Each model has as a training set a data set from a plurality of samples of a commodity of known origins. Each sample has been analyzed for a plurality of elemental concentrations. Each neural network model is presented for classification a test data set from a plurality of samples of a commodity of unknown origins. As with the training set, the samples have been analyzed for the same plurality of elemental concentrations. Next a bootstrap aggregating strategy is employed to combine the results of the classifications for each sample in the test data set made by each neural network model. Finally, a determination is made from the bootstrap aggregating strategy as to a final classification of each sample in the test data set. This final classification is indicative of the geographical origin of the commodity. The system includes software for generating the neural network models and a software routine for performing the bootstrap aggregating strategy.

2. 发明公开

EP1008952A2 System and method for identifying the geographic origin of a fresh commodity 审中-公开
标题翻译：系统和方法，用于识别新鲜消耗品的地理起源
公开(公告)号：EP1008952A2
公开(公告)日：2000-06-14
申请号：EP99309933.2
申请日：1999-12-10
申请人： Florida Department of Citrus
发明人： Anderson, Kim A. , Smith, Brian , Magnuson, Bernadene
IPC分类号： G06N3/04
CPC分类号： G06N3/0454 , G06K9/62 , G06K2209/17
摘要： The detection method includes generating a plurality of neural network models. Each model has as a training set a data set from a plurality of samples of a commodity of known origins. Each sample has been analyzed for a plurality of elemental concentrations. Each neural network model is presented for classification a test data set from a plurality of samples of a commodity of unknown origins. As with the training set, the samples have been analyzed for the same plurality of elemental concentrations. Next a bootstrap aggregating strategy is employed to combine the results of the classifications for each sample in the test data set made by each neural network model. Finally, a determination is made from the bootstrap aggregating strategy as to a final classification of each sample in the test data set. This final classification is indicative of the geographical origin of the commodity. The system includes software for generating the neural network models and a software routine for performing the bootstrap aggregating strategy.
摘要翻译：该检测方法包括：产生的神经网络模型的复数。每个模型具有作为训练从已知的起点的商品样品的多个设定的数据集。每个样品已分析元素浓度的多元性。每个神经网络模型提出了一种用于分类测试数据从未知起源的商品的样本的多个设定。与训练集，样品已分析元素浓度的相同的多个。接着自举聚集的策略被用于分类的结果结合起来，在由每个神经网络模型进行的测试数据集合中的每个样本。最后，确定从引导聚集的策略，以在测试数据集合中的每个样品的最终分类制成。这最后的分类是表示商品的地理来源。该系统包括用于生成神经网络模型和进行引导聚集策略的软件程序软件。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式