基于人工神经网络的淫羊藿红外光谱的研究

对于不同产地和不同栽培条件的药材, 其药效的不同是由于其所含化学成分和各成分含量的比例不同所造成的, 这种差异将造成红外图谱的差异。但这些差异非常细微,单纯地从谱图去区分其特征是非常困难的。文章利用傅里叶变换红外光谱,测定了42种来自吉林3个不同产地的淫羊藿样品的红外光谱,并对光谱数据进行了相应的预处理。为了提高神经网络的训练速度,在利用人工神经网络建立模型之前,通过小波变换的方法对光谱变量进行了压缩。同时对建立的模型的相关参数进行了详细的讨论。实验表明,建立的模型能够正确地对42个淫羊藿样品进行产地鉴别,同时避免了传统光谱分析对药材的分离和提取,从而为中药质量的科学控制和现代化管理提供了可靠的依据。     

可见光通信系统的非线性失真抑制研究北大核心CSCD

发光二极管的非线性特性是引起光信号出现非线性失真的一个重要因素,针对该问题,采用人工神经网络在接收端对信号的非线性失真进行抑制,进而降低可见光通信系统的误码率。将发光二极管的输入电信号与接收端转换后的电信号组成成对数据,将成对数据集送入神经网络进行训练,学习信号在电光转换、信道传输及光电转换过程中的非线性失真特性,通过神经网络对信号的非线性失真进行估计与抑制。此外,在训练过程中采用分布估计算法搜索神经网络的超参数集,以降低训练难度。实验结果表明,该方法在不同的信道环境下均能有效地改善可见光通信的性能。     

二维光电位置敏感器件的非线性修正

根据二维光电位置敏感器件 (PSD)的工作原理 ,分析了影响PSD线性度的主要因素 ,提出了一种用神经网络对PSD进行非线性修正的方法。以PSD的输入输出数据对作为样本训练的神经网络 ,利用神经网络所具有地能够以任意精度逼近非线性函数的能力 ,实现PSD的输出与实际光点位置之间的映射 ,在神经网络的输出端得到线性响应。该方法的优点是不需要很大的数据存储量即可得到很好的修正效果。结果表明 ,修正后的PSD能在较宽的位置范围内输出高线性度的信号     

Artificial neural network method for determining optical properties from double-integrating-spheres measurements

<正>Accurate measurement of the optical properties of biological tissue is very important for optical diagnosis and therapeutics.An artificial neural network(ANN)-based inverse reconstruction method is introduced to determine the optical properties of turbid media,which is based on the reflectance(R) and transmittance (T) of a thin sample measured by a double-integrating-spheres system.The accuracy and robustness of the method has been validated,and the results show that the root mean square errors(RMSEs) of the absorption coefficientμ_a and scattering coefficientμ'_s reconstruction are less than 0.01 cm~(-1) and 0.02 cm~(-1),respectively.The algorithm is not only very accurate in the case of a lower albedo(~0.33),but also very robust to the noise of R and T especially for theμ'_s reconstruction.     

泛权网场结合的逻辑守恒性及其在人工神经网络中的应用

给出了泛权网场复合的几个定义,证明了泛权网场复合的一组有关逻辑守恒性的定理。结合均场模型,探讨了泛权网场在人工神经网络中的应用前景。     

Pattern recognition and data mining software based on artificial neural networks applied to proton transfer in aqueous environments

In computational physics proton transfer phenomena could be viewed as pattern classification problems based on a set of input features allowing classification of the proton motion into two categories： transfer ＇occurred＇ and transfer ＇not occurred＇. The goal of this paper is to evaluate the use of artificial neural networks in the classification of proton transfer events, based on the feed-forward back propagation neural network, used as a classifier to distinguish between the two transfer cases. In this paper, we use a new developed data mining and pattern recognition tool for automating, controlling, and drawing charts of the output data of an Empirical Valence Bond existing code. The study analyzes the need for pattern recognition in aqueous proton transfer processes and how the learning approach in error back propagation （multilayer perceptron algorithms） could be satisfactorily employed in the present case. We present a tool for pattern recognition and validate the code including a real physical case study. The results of applying the artificial neural networks methodology to crowd patterns based upon selected physical properties （e.g., temperature, density） show the abilities of the network to learn proton transfer patterns corresponding to properties of the aqueous environments, which is in turn proved to be fully compatible with previous proton transfer studies.     

人工神经网络研究进展及其在光谱分析中的应用

介绍最常用的人工神经网络——BP神经网络的原理、结构及其研究进展,评述了人工神经网络在光谱分析中的应用。     

分子三维投影法在苯酚类化合物构效关系研究中的应用

对苯酚类化合物进行三维投影得到了5个形状参数,将其与3个Am指数及8个量子化学参数相结合.由最佳变量子集回归法对变量进行了压缩与选择,运用多元回归分析和人工神经网络法分别构造了预测数学模型,得到了满意的结果.     

偏最小二乘-速差动力学分光光度法同时测定杀虫剂残杀威和异丙威两组分

采用速差动力学分光光度法对氨基甲酸脂类杀虫剂残杀威和异丙威进行同时测定，这两种化 的能在碱性条件下水解生成酚盐，进而与对氨基苯酚及高碘酸钾的反应产物醌亚胺发生偶联反应，生成蓝色化合物。反应的速率适中，可用于动力学分析。实验采集了多个时间点下538－700nm间的动力学－吸光度数据，构成量测矩阵，并采用偏最小二乘（PLS）法对量测数据进行解析。本文还对合成样品和环境水样中的残杀威和异丙威含量进行测定，获较好的结果。     

Prediction of Decomposition Temperature for Lanthanide Complexes Involving Cyclopentadienyl and Benzohydroxamic Acid Ligand by ANNs

The decomposition temperatures of the lanthanide organic complexes(η^5-C5H5)2Ln(C6H5CONHO)involving cyclopentadienyl and benzohydroxamic acid ligands were calculated and predicted by the model based on ANNs(artificial neural netowrks)method.The comparison was carried out between results from ANNs method and traditinal regression method.It is proved that ANNs could be used more efficiently for the prediction of decomposition temperature of lanthanide organic complexes.