编码输入法在PCB分配参数预测中的应用

根据Free-Wilson法中化合物结构表达的思想，采用两种简单的编码输入方法对58个多氯联苯(PCB)的结构进行表征，并基于模型简单性原则对多元线性回归(MLR)与误差反向传递(BP)人工神经网络、模拟退火(SA)人工神经网络和遗传算法(GA)人工神经网络PCB分配参数预测模型的预测能力进行了比较，试验证实，粗略考虑PCB结构对称性的简单编码输入规则可以简化PCB分配参数预测模型的数字形式，所获得的MLR模型具备广泛的应用前景。     

基于人工神经网络法的绿色建筑评价

以实际建筑物为例,介绍了用层次分析法建立绿色建筑评价模型的过程,并分别用层次分析法和人工神经网络法对实际建筑物进行了评价。评价结果显示,人工神经网络法与层次分析法相对误差不到0.5%,表明人工神经网络法作为一种客观科学的评价方法,应用于绿色建筑的评价,能有效降低主观因素带来的影响,会使结果更具有客观性。     

应用自组织人工神经网络预报黄土高原生态破坏程度的初探

运用三维Ｔ Ｋｏｈｏｎｅｎ自组织人工神经网络，分析预测黄土高原生态经济破坏程度，预测成功率１００％。结果表明，神经网络方法性能良好，可望成为生态经济破坏程度预测的有效的辅助手段。     

应用自组织人工神经网络预报黄土高原生态破坏程度的初探

运用三维ＴＫｏｈｏｎｅｎ自组织人工神经网络，分析预测黄土高原生态经济破坏程度，预测成功率１００％。结果表明，神经网络方法性能良好，可望成为生态经济破坏程度预测的有效的辅助手段。     

化学品厌氧生物降解QSBR预测模型研究

收集了155种有机化学品厌氧生物降解数据,以随机抽取的109种物质作为训练集,另外46种物质作为验证集,通过结构式拆分得到各基团,分别采用多元线性回归和BP人工神经网络2种算法对有机化合物结构与生物降解性定量关系(QSBR)进行研究。结果表明,多元线性回归模型验证集正确率为78.26%,总正确率为84.52%;BP人工神经网络模型验证集正确率为82.61%,总正确率为90.32%。可见,BP人工神经网络算法相对优于多元线性回归算法。     

基于人工神经网络的燃煤汞排放预测模型

利用GA-BP的人工神经网络算法建立燃煤汞排放预测模型,确定煤中汞含量、煤的发热量、煤中硫含量、煤中氯含量、挥发份含量、排烟温度作为输入矢量,元素态汞、氧化态汞和颗粒态汞3个因素作为输出参数,通过对20个燃煤锅炉汞排放形态的测试数据进行模型训练,结合实际测试数据和预测数据对误差来源进行了分析.通过对3个样本进行验证,分析人工神经网络的实际预测效果.研究结果表明,训练与预测的精度都是符合汞排放预测实际要求的,预测精度达0.895,分析表明利用人工神经网络建立预测模型可对燃煤汞排放进行预测.     

有机化合物厌氧生物降解性的测定和预测

测定有机物厌氧生物降解性的方法包括非特性参数和特性参数测定法。本文着重介绍有机物厌氧生物降解性的筛选测定法，以基团贡献法为基础，不外加其它理化参数的有机物结构与生物降解性关系的预测已经由简单的线性模型发展至专家系统和人工神经网络模型，并显示出极好的应用前景。     

多氯代苯并噻吩分子空间坐标指数与气相色谱保留时间的QSPR研究

运用Chem Office软件绘制37个多氯代苯并噻吩三维图,并得到对应的分子空间坐标Pi(xi,yi,zi)。以多氯代苯并噻吩分子的原子距离指数、分子空间特征指数、分子电性距离矢量、氯原子数为分子描述变量,采用多元线性回归和BP人工神经网络建立描述变量与多氯代苯并噻吩的气相色谱保留时间的QSPR模型。结果表明:多元线性回归建模相关系数R=0.9970,SD=2.1830,基于BP人工神经网络建立的模型R=0.9996,SD=0.3123。为多氯代苯并噻吩分子结构与物性的QSPR研究提供了新思路。     

太阳黑子与杉木生长关系

根据多层误差板传网络结构模型和三次设计发展了一种太阳黑子人工神经网络预报方法,以杉木胸径生长的年轮指数和太阳黑子自相关因子输入变量,应用改进的人工神经网络方法建立了太阳黑子相对数年平均值的预测模型,模型的模拟回归优度为93．3％,预测精度达到95．74％,并对网络模型中变量进行灵敏度分析,分析表明,杉木胸径生长的年轮指数对太阳黑子对相对数年平均值影响较平坦,而太阳黑子自相关因子Yt-4和Yt-2对太阳子相对数年平均值影响较灵敏,3个因子对太阳黑子相对数年平均值均在一定的影响。图2表5参19     

应用于水文预报的优化BP神经网络研究

利用广东省滨江流域的水文观测资料，建立了以前期降水量为预报因子、以水位为输出的BP人工神经网络水文预报模型。首先采用了合理的方法进行样本组织，进而利用最优子集回归技术进行输入因子的确定，然后进行了不同隐层节点数、不同转移函数、不同训练算法的组合试验，确定了应用于水文预报中的优化BP神经网络：网络结构为8-9-1；转移函数的组合方式为tansig-线性函数；训练算法为采用evenberg-Marquardt(Lm)算法。为便于精度分析，还采用了最优子集回归模型作了研究。结果表明，优化BP网络模型无论在拟合精度还是在预测精度上都高于最优子集模型。总的来说BP网络是一种精度较高的水文预测模型。     

利用人工神经网络预测芳香化合物的生物可降解性

本文采用简单的化学基团描述符来表征化学物质的结构,以底物的最大比去除速度表征生物可降解性的大小,运用自编的人工神经网络对芳香族化合物的生物可降解性进行了研究。试验过程中,按芳香族化合物最大比底物去除速度的大小将其生物可降解性分为四组：不降解,难降解,可降解,易降解。     

Individual-based modelling of fishermen search behaviour with neural networks and reinforcement learning

A model to mimic the search behaviour of fishermen is built with two neural networks to cope with two separate decision-making processes in fishing activities. One neural network deals with decisions to stay or move to new fishing grounds and the other is constructed for the purpose of finding prey within the fishing areas. Some similarities with the behaviour of real fishermen are found: concentrated local search once a prey has been located to increase the probability of remaining near a prey patch and the straightforward movement to other fishing grounds. The artificial fisherman prefers areas near the port when conditions in different fishing grounds are similar or when there is high uncertainty in its world. In the latter case a reluctance to navigate to other areas is observed. The artificial fisherman selects areas with higher concentration of prey, even if they are far from the port of departure, unless a high uncertainty is related to the fishing ground. Connected areas are preferred and followed in orderly fashion if a higher catch is expected. The observed behaviour of the artificial fisherman in uncertain scenarios can be described as a risk-averse attitude. The approach seems appropriate for an individual-based modelling of fishery systems, focusing on the learning and adaptive characteristics of fishermen and on interactions that take place at a fine scale.     

Testing the generalization of artificial neural networks with cross-validation and independent-validation in modelling rice tillering dynamics

Neural networks (NN) rely on the inner structure of available data sets rather than on comprehension of the modeled processes between inputs and outputs. Therefore, neural networks have been regarded as highly empirical models with limited extrapolation capability to situations outside the range of the training and validation data sets. In this study, the generalization ability of neural networks in predicting rice tillering dynamics was tested and several techniques inducing the generalization ability of neural networks were compared. We compared the performance of cross-validated neural networks with independent-validated neural networks and found that neural networks were able to extrapolate and predict tillering dynamics if the data were within the range of inputs of the training set. An inadequate training set resulted in overfitting of available data and neural networks that were not generalizable. The training set size required to enable a neural network to generalize and predict rice tillering dynamics was found to be at least 9 times as many training patterns for each weight. When a large number of variables are included in the input vector of a neural network with inadequate amounts of training data, we strongly recommend that the dimension of the input vector is reduced using principle component analysis (PCA), correspondence analysis (CA) or similar techniques to decrease the number of weights before the training procedure to improve the generalization ability of the NN. If the amount of training data still is not sufficient after the dimension of the input vector is reduced, regularization techniques, such as early stopping, jittering, and especially the embedment of estimated results by a theoretical model into the training set, should be used to improve the generalization ability of the neural network. The generalization of neural networks presents a wide spectrum of problems, and the proposed approaches are not confined strictly to modelling rice tillering dynamics but can be applied to other agricultural and ecological systems.     

基于人工神经网络方法的河北省近海沉积物重金属污染综合评价

利用误差反相传播神经（BP）网络对河北省近海沉积物中的铅、镉、锌、汞、砷5种重金属元素的污染水平进行分析,利用自组织特征映射（SOFM）网络对上述重金属元素分布特征进行分类,通过分类与污染水平量化值的结合,进行综合评价。SOFM把52个沉积物样品分别划分为3、4、6类和9类。对比各种分类,分为3类的物理意义较明确。每个类别分别对应高中低不同的污染物浓度水平,差异显著、分类方式比较合理。通过此种分类可以判断河北省近海的沉积物重金属污染在不同海域存在一定的差别,整体上是离海岸越远,沉积物的重金属污染水平越高,距海岸较近的海域内,沉积物的重金属污染水平较低,但渤海湾内的重金属污染水平高于其他海域。     

城市给水管网余氯的预测模型

选择余氯为研究对象,以南方某市给水管网水质监测的数据为基础,使用线性回归和非线性神经网络(ANN)方法建立模型,找到了一种利用在线监测数据和人工监测数据实时预测管网余氯的方法。通过建立给水管网水质模型,可以由监测系统动态回传的数据来实时的预测下一天人工点的水质。模拟的结果显示ANN模型比线性回归模型有更好的预测能力,预测的平均相对误差:ANN模型为14.9%,线性回归模型为25.8%。使用ANN模型可以实现实时预测。     

毛竹林各组分能量估算模型的研究

在建瓯设置40块毛竹林标准地,分别测定了毛竹单株各部分干重与能量,建立了各部分生物量模型,并在此基础上,运用人工神经网络方法对毛竹林各组分能量进行估测.结果表明毛竹林各组分秆、枝叶和地下部分的平均能量依次为4.23225×10     

Neural network modelling of coastal algal blooms

An artificial neural network (ANN), a data driven modelling approach, is proposed to predict the algal bloom dynamics of the coastal waters of Hong Kong. The commonly used back-propagation learning algorithm is employed for training the ANN. The modeling is based on (a) comprehensive biweekly water quality data at Tolo Harbour (1982–2000); and (b) 4-year set of weekly phytoplankton abundance data at Lamma Island (1996–2000). Algal biomass is represented as chlorophyll-a and cell concentration of Skeletonema at the two locations, respectively. Analysis of a large number of scenarios shows that the best agreement with observations is obtained by using merely the time-lagged algal dynamics as the network input. In contrast to previous findings with more complicated neural networks of algal blooms in freshwater systems, the present work suggests the algal concentration in the eutrophic sub-tropical coastal water is mainly dependent on the antecedent algal concentrations in the previous 1–2 weeks. This finding is also supported by an interpretation of the neural networks’ weights. Through a systematic analysis of network performance, it is shown that previous reports of predictability of algal dynamics by ANN are erroneous in that ‘future data’ have been used to drive the network prediction. In addition, a novel real time forecast of coastal algal blooms based on weekly data at Lamma is presented. Our study shows that an ANN model with a small number of input variables is able to capture trends of algal dynamics, but data with a minimum sampling interval of 1 week is necessary. However, the sufficiency of the weekly sampling for real time predictions using ANN models needs to be further evaluated against longer weekly data sets as they become available.