• 主题
高级搜索  >
历史搜索 清空历史
首页> 外国专利> MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURON NETWORK MIXED MODEL, PREDICTING MAGNETIC SUSCEPTIBILITY OF A PURE ORGANIC COMPOUND, CAPABLE OF GUESSING A VALUE WHEN AN EXPERIMENT CANNOT BE CONDUCTED

MULTIPLE LINEAR REGRESSION-ARTIFICIAL NEURON NETWORK MIXED MODEL, PREDICTING MAGNETIC SUSCEPTIBILITY OF A PURE ORGANIC COMPOUND, CAPABLE OF GUESSING A VALUE WHEN AN EXPERIMENT CANNOT BE CONDUCTED

机译：多种线性回归-人工神经网络混合模型，预测纯有机化合物的磁化率，能够进行无法进行实验的值

页面导航
  • 摘要
  • 著录项
  • 相似文献

摘要

PURPOSE: A MLR(Multiple Linear Regression)-ANN(Artificial Neuron Network) mixed model, predicting magnetic susceptibility of a pure organic compound, is provided to guess a value when an experiment cannot be conducted, thereby vitalizing research and development of a related industry.;CONSTITUTION: A molecular descriptor value for magnetic susceptibility of a sample organic compound is prepared. Experimental data is separated into a training set and a test set. An optimum MLRM for the training set is explored. The predicted performance of the optimum MLRM is tested on the test set. After an optimum ANNM(Artificial Neural Network Model) divides every samples into three sets, it is explored. If the absolute value of the difference of a magnetic susceptibility prediction value, figured out by the MLRM and the ANNM, is greater than an over- suitability preventing standard value, a magnetic susceptibility prediction value by the MLRM is selected as a magnetic susceptibility value.;COPYRIGHT KIPO 2012
机译：目的：提供MLR（多元线性回归）-ANN（人工神经元网络）混合模型，该模型可预测纯有机化合物的磁化率，以猜测无法进行实验时的价值，从而振兴相关行业的研发组成：制备了样品有机化合物的磁化率分子描述值。实验数据分为训练集和测试集。探索了针对训练集的最佳MLRM。在测试集上测试最佳MLRM的预测性能。在最优的ANNM（人工神经网络模型）将每个样本分为三组之后，对其进行了探索。如果由MLRM和ANNM计算出的磁化率预测值之差的绝对值大于防止过度适应性的标准值，则选择MLRM的磁化率预测值作为磁化率值。 ; COPYRIGHT KIPO 2012

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号