回归系数迭代改进法在近红外光谱定量分析中应用的研究

本研究对多元线性回归模型中的残差部分再次进行回归分析 ,提取其中与自变量相关的成分 .用所得回归系数与初次回归所得系数相加作为新的回归系数 ,建立改进的回归方程 .将此建模方法用于近红外光谱定量分析 ,提高了预测精度     

数字图像处理技术在叶面积测量中的应用

传统测量叶面积方法费时、低效,叶面积仪法高成本、维修不便.本研究利用图像处理技术测量叶面积,从解决图像阈值的分割、叶片阴影去除以及叶片边缘检测算法等问题出发,应用大津法求得阈值,中值滤波法去除杂点,采用Roberts算子检测边缘,进而计算叶面积.叶面积仪法与图像处理法比较叶面积值相关系数R2为0.962,剪纸法与图像处...     

渔业水域污染死鱼的ANN识别模型的建立

本文应用人工神经网络（ANN）方法，对渔业水域污染死鱼特征进行提取，建立了导致污染死鱼的毒物类型的识别模型，其人工神经网络结构选输入层18个神经元，中间层9个神经元，输出层为1个神经元，并对网络参数的优化进行讨论。结果显示通过运用已训练好的渔业水域污染互鱼的B-P人工神经网络识别模型，只要通过简单的加法和乘法运算，就可以对任何一例污染死鱼的实际样本进行死鱼原因的判断，该方法具有较好的适用性和较高的实用性。     

基于统计学原理的JPEG量化表的算法

JPEG图像压缩算法有较优秀的压缩品质，但在量化阶段引用的是心理视觉阀值构成的量化表，造成了大量具有统计意义的信息的损失，给还原后的图像识别带来了困难。为此，本文提出了一种新的量化表设计方案，并运用数理统计理论推导出判别最优划分的标准，进而导出量化表的算法和实现步骤。此算法还可广泛地应用于非均匀量化的A／D、D／A转换等方面。     

血管连续切片图象的计算机三维重建

为实现血管的三维重建 ,先将原 R.G.B.模式转化为灰度模式 ,通过计算机辅助用半色调技术将灰度图象二值化 ,并进行轮廓提取 ,提取已取出的轮廓图象的黑点坐标值 ,再对半径进行搜索 ,同时记录中轴线与切片交点 ,利用有理参数逐点生成算法进行曲线合成。结果表明 ,与该法的传统多项式拟合图形相比 ,此法可表示的曲线类型更加广泛。另外 ,该法只用到整数加减法 ,因而此法较多项式拟合更精确、更有效。     

Evaluation Method Based on Artificial Neural Network in Contractor Prequalification of Tenderers

Both tenderees and tenderers attach much importance to contractor prequalification before bidding because it plays important roles for both and so far the Score Method has been widely used in our country. But the weights in the method are man-made, which may be affected by personality inevitably. In order to avoid this influence, this thesis will introduce another method based on artificial neural network. This thesis expatiates the principle of artificial neural network, and analyzes the characters of prequalification. Then, the author sets up the mathematics model. In the end, the author analyzes this method by an example.     

喷灌水量分布的遗传神经网络模拟与组合均匀度计算

喷头的水量分布与工作压力 H、风速 V等密切相关 ,但难以找出描述其间关系的显式方程。这使得喷灌系统的布置优化、模拟仿真乃至运行控制不太方便 ,不利于电算。采用遗传神经网络较好地模拟了喷头水量分布及其与 H、V的关系 ,给出了基于这种模拟的喷灌组合均匀度计算方法 ,并通过实例验证了该方法。     

Nonlinear Forecast System for River Water Pollution Based on GIS

Based on the analysis of the water pollution spatial distribution characters of Yangtze River in Chongqing,a new method based on the integration of BP neural network and genetic arithmetic(GA) is proposed.For some shortcomings existed in the standard BP neural network,this method has ultimately overcome these shortcomings by combining the GA with BP artificial neural network through altering stimulating function,adding momentum factor to power value for BP algorithm and introducing genetic arithmetic to searching for the knots of the hidden layer,momentum factor and learning level.Using this method can easily overcome the difficulty of measuring the water prediction model's parameters.GIS is used as a tool for data management and spatial analysis,and the prediction result of the model for the water pollution spatial distribution characters of Yangtze River in Chongqing is visualized and explored with the precision of more than 78%.     

One Auto-optimized Fuzzy Control of Car-engines Based on GA

One new auto-optimized fuzzy control model of car-engines based on genetic arithmetic was introduced aiming at the problem that the parameters of car-engine are of the discreteness, the nonlinear and the uncertain characteristics, with which it is difficult to control accurately the excess air coefficient and the spark advance angle in dynamic procedure when using a conventional control model. The rule of the design scheme of the controller achieving the model based on embedded operating system is discussed. Further more, it is probed that the fuzzy control parameters are optimized automatically using GA based on on-line real-time simulation. The results of experiments show that the dynamic indexes and the fuel economy indexes are all improved greatly and the advantage of the model on reducing fuel consumption is obvious.     

渔业水域污染死鱼的ANN识别模型的建立

本文应用人工神经网络（ANN）方法，对渔业水域污染死鱼特征进行提取，建立了导致污染死鱼的毒物类型的识别模型，其人工神经网络结构选输入层18个神经元，中间层9个神经元，输出层为1个神经元，并对网络参数的优化进行讨论。结果显示通过运用已训练好的渔业水域污染互鱼的B-P人工神经网络识别模型，只要通过简单的加法和乘法运算，就可以对任何一例污染死鱼的实际样本进行死鱼原因的判断，该方法具有较好的适用性和较高的实用性。