Non-linear regression methods in NIRS quantitative analysis

Due to its speed and precision, near-infrared reflectance spectroscopy (NIRS) has become a widely used analytical technique in many industries. It offers, moreover, a number of other advantages which make it ideal for meeting current demands in terms of control and traceability: low cost per sample analysed; little or no need for sample preparation; ability to analyse a wide range of products and parameters; a high degree of reproducibility and repeatability. NIRS can be built into in-line processes, and - since no reagents are required - produces no waste. However, the major drawback to the use of NIRS for its most traditional application (the generation of prediction equations) is that it is a secondary method, and as such needs to be calibrated using a conventional reference method. For quantitative applications, calibration involves ascertaining the optimum mathematical relationship between spectral data and data provided by the reference method. The model may be fairly complex, since the NIRS spectrum is highly variable and contains physical/chemical information for the sample which may be redundant. As a result, multivariate calibration is required, based on a set of absorption values from several wavelengths. Since the relationship to be modelled is often non-linear, classical regression methods are unsuitable, and more complex strategies and algorithms must be sought in order to model this non-linearity. This overview addresses the most widely used non-linear algorithms in the management of NIRS data.     

有机磷农药构效关系的主成分分析-人工神经网络研究

采用主成分分析法对样本数据集进行预处理，将得到的新的样本数据集输入人工神经网络，对有机磷农药的毒性参数进行预报。研究结果表明，主成分分析－人工神经网络的预报精度优于单纯的人工神经网络。     

2D bitmapping approach for identification and quantitation of common base flavor adulterants using surface acoustic wave arrays and artificial neural network data analysis

Arrays of polymer-coated surface acoustic wave microsensors are used in conjunction with a variety of signal-processing algorithms known as artificial neural networks (ANN). This format of data analysis has the capability to characterize complex mixtures of volatile and semi-volatile organic compounds commonly found in base flavors. The approach described, which minimizes the number of training sets while retaining the robustness of an ANN, utilizes a 2D bitmap matrix. The matrix is obtained by converting the time domain kinetics of sensor response into a bitmap. The high data throughput of this approach enables quantitation on the order of ppm of common base flavor adulterants.     

Molecular docking studies on tetrahydroimidazo-[4,5,1-jk][1,4]-benzodiazepinone (TIBO) derivatives as HIV-1 NNRT inhibitors

At present, chemotherapy seems to be the main weapon in the arsenal of remedies for the ongoing crusade against AIDS. The mode of binding of the TIBO family of inhibitors has been of interest because these compounds do not fit the two-hinged-ring model as generally observed in the NNRTIs. Flexible docking simulations were performed with a series of 53 TIBO derivatives as NNRTIs. Binding preferences as well as the structural and energetic factors associated with them were studied. A good correlation (r ² = 0.849, q ² = 0.843) was observed between the biological activity and binding affinity of the compounds which suggest that the identified binding conformations of these inhibitors are reliable. Further screening of PubChem database yielded novel scaffolds. Our studies suggest that modifications to the TIBO group of inhibitors might enhance their binding efficacy and hence, potentially, their therapeutic utility.     

A Simple Closed-form Formula for Backward-Wave Start-Oscillation Condition for Millimeter-Wave Helix TWTs

An accurate and simple closed-form formula, for backward-wave start-oscillation condition for a millimeter-wave helix traveling-wave tube amplifier was developed, using an artificial neural network (ANN) algorithm. The analysis considers the effects of circuit loss and also the variation of electron beam diameter corresponding to beam filling. The formula is simple and amenable to easy computation, even using a scientific calculator, and without resorting to exhaustive numerical iterative search followed in conventional analyses and, at the same time, without sacrificing the accuracy in results. The formula was validated against published results, and excellent accuracy was observed. The analysis has been further used for inferring some physical interpretations on the effects of beam-filling factor and circuit loss on the start-oscillation condition of a typical millimeter-wave helix traveling-wave tube.     

基于机载高光谱成像的柑橘产量预测模型研究

果树的隔年结果现象严重影响果园的果实产量和经济效益。选择受隔年结果现象影响较为严重的柑橘作为研究对象,运用机载高光谱成像仪在较早生长季节(2003年4、5、6月)获取柑橘果树的高光谱图像,利用偏最小二乘回归(PLS)确定基于高光谱图像数据的模型预测变量,建立柑橘产量的多元线性回归(MLR)和人工神经网络(ANN)预测模型。研究结果表明,利用5月份获得的高光谱图像建立的模型具有最优的产量预测效果, 而且PLS-MLR模型比PLS-ANN模型具有更好的稳定性和一致性。该研究结果为今后研制和开发基于高光谱成像技术的柑橘产量预测方法提供了重要的理论和技术基础。     

一种快速分类的神经元网络算法

深入分析了BP(Back-Propagation)算法的缺陷,在BP算法的基础上,提出逐层训练多层网络的快速算法,主要精神是:a)逐层地训练多层网络而不是一起训练;b)对隐单元层给以具体指导;c)根据具体问题给予合适的权重分配规则即合适的"能量函数";d)保持BP算法的优点。对一些问题的训练速度与BP算法比较有几个数量级的提高。这一算法还可对多层网络的运行机制作一些研究.     

Application of Artificial Neural Network Based on Traditional Detection and GC-MS in Prediction of Free Radicals in Thermal Oxidation of Vegetable Oil

In this study, electron paramagnetic resonance (EPR) and gas chromatography-mass spectrometry (GC-MS) techniques were applied to reveal the variation of lipid free radicals and oxidized volatile products of four oils in the thermal process. The EPR results showed the signal intensities of linseed oil (LO) were the highest, followed by sunflower oil (SO), rapeseed oil (RO), and palm oil (PO). Moreover, the signal intensities of the four oils increased with heating time. GC-MS results showed that (E)-2-decenal, (E,E)-2,4-decadienal, and 2-undecenal were the main volatile compounds of oxidized oil. Besides, the oxidized PO and LO contained the highest and lowest contents of volatiles, respectively. According to the oil characteristics, an artificial neural network (ANN) intelligent evaluation model of free radicals was established. The coefficients of determination (R2) of ANN models were more than 0.97, and the difference between the true and predicted values was small, which indicated that oil profiles combined with chemometrics can accurately predict the free radical of thermal oxidized oil.     

基于近红外光谱技术和人工神经网络的玉米品种鉴别方法研究

提出了一种采用近红外光谱技术结合人工神经网络对玉米品种进行鉴别的方法。在3 800～10 000 cm-1(波长1 000～2 632 nm)范围内采集四种玉米单粒完整籽粒的近红外漫反射光谱,经Savitky-Golay平滑和多重散 射校正预处理后,对数据进行主成分分析,再结合人工神经网络技术进行品种鉴别。主成分分析表明,前8个主成分的累积贡献率达到99.602%。以前8个主成分作为网络输入,品种类型作为输出,建立三层LMBP神经网络模型。每个品种 各取30粒共120个样本用于建模,10粒共40个样本用于预测。模型对建模集120个样本鉴别率为100%,对预测集40个样本的鉴别率为95%。实验结果说明该方法能快速无损地鉴别玉米品种,为玉米的品种鉴别提供了一种新方法。     

人工神经网络预测非环状亚硝胺急性毒性的QSAR研究

在DFT-B3LYP/6-311+G(d,p)水平对60种非环状亚硝胺分子结构进行几何全优化,通过多元逐步线性回归(MSR)分析筛选出9个量子化学描述符作为自变量,log LD50(lethal dose 50％,LD50:大鼠口服急性毒性)作为因变量,采用人工神经网络(ANN)方法构建QSAR模型.经Levenber...