基于BP算法的信用风险评价模型研究

本文利用神经网络技术建立基于 BP算法的信用风险评价模型 ,为我国某商业银行 12 0家贷款企业进行信用风险评价 ,按照企业的信用等级分为“信用好”、“信用中等”和“信用差”三个小组 .仿真结果表明 ,本文所建立的神经网络信用风险评价模型的分类准确率高于传统的参数统计分类方法——线性判别分析法的分类准确率 .文中还详细给出神经网络信用风险评价模型的网络构建方法及基于 BP网络的学习算法和步骤 .     

Neural Network Classification of Mutagens Using Structural Fragment Data

Abstract

A neural network was applied to a large, structurally heterogeneous data set of mutagens and nonmutagens to investigate structure-property relationships. Substructural data comprising a total of 1280 fragments were used as inputs. The training of the back-propagation networks was directed by an algorithm which selected an optimal subset of fragments in order to maximize their discriminating power, and a good predictive network.

The system comprised three programs: the first used a keyfile of 100 fragments to generate training and test files, the second was the network itself and a procedure for ranking the effectiveness of these fragments and the third randomly replaced the lowest fragments. This cycle was then repeated. After running on a 386/33 PC several networks produced approximately 11% failures in the test set and 6% in the training set.

By simplifying the output of the hidden layer it was possible to describe the hidden layer states in terms of clusters of mutagens and non-mutagens. Some of these clusters were structurally homogeneous and contained known mutagenic and non-mutagenic structural classes. This analysis provided a useful means of demonstrating how the network was classifying the data.     

A 21st century technique for food control: Electronic noses

This work examines the main features of modern electronic noses (e-noses) and their most important applications in food control in this new century. The three components of an electronic nose (sample handling system, detection system, and data processing system) are described. Special attention is devoted to the promising mass spectrometry based e-noses, due to their advantages over the more classical gas sensors. Applications described include process monitoring, shelf-life investigation, freshness evaluation, authenticity assessment, as well as other general aspects of the utilization of electronic noses in food control. Finally, some interesting remarks concerning the strengths and weaknesses of electronic noses in food control are also mentioned.     

人工神经网络用于裂解质谱研究漆器漆膜

本文用裂解质谱方法，得到漆器漆膜裂解谱数据，然后用变频长误差反向传播算法的人工神经网络模型处理，初步结果证明人工神经网络方法为解析古代漆膜的年代信息提供了一条有效的新途径。     

测定电位滴定终点的神经网络法

本文利用改进的“反向传播”神经网络模型,在滴定突跃附近,建立了E-V曲线的神经网络插值模型,由其二阶微商求得滴定终点。计算实例中,拟合最大相对误差不超过0.1％,计算机CPU时间不超过20s,实验结果表明,该方法性能良好,在电容量分析方面有广阔的应用前景。     

基于BP神经网络的图像质量评价参数优化

 在基于噪声图像的无参考峰值信噪比质量评价方法中,为了得到最优的阈值参数,提出以图像块均方误差阈值threshold1、噪声检测阈值threshold2为输入因子, 以Pearson相关系数和Spearman等级相关系数为输出因子, 以实验值为样本建立［2 7 2］单隐层BP神经网络模型,应用BP神经网络的泛化能力实现对相关阈值参数的预测优化,为阈值参数的选择提供理论依据。实验结果表明,所建立的数学模型可靠,预测结果与试验值的偏差小,训练好的BP神经网络能够比较准确地预测不同阈值参数下的相关系数。优化后,选取threshold1=101,threshold2=4,Pearson相关系数达到了-0.895 0,Spearman等级相关系数达到了-0.913 6,评价效果得到提高,且节省大量时间。