人工神经网络与遗传算法相结合在作物估产中的应用——以吉林省米估产为例

在遗传算法（Genetic Algorithm）与误差反传（Back Propagation）网络结构模型相结合的基础上,设计了用遗传算法训练神经网络权重的新方法,并对吉林省梨树和德惠县的玉米进行了估产研究,同时与BP算法和灰色系统理论模型进行了比较。经经验,计算值与实际值拉近,并优于灰色理论模型,具有良好的预测效果,从而为农作物估产提供了新方法。     

RS,GPS和GIS集成系统在新疆北部天然草地估产技术中的应用进展

利用１９９１～１９９６年在新疆天山北坡不同草地类型上观测的草地可食产量,环境与遥感资料等,使用ＲＳ技术、ＧＰＳ和ＧＩＳ集成系统进行了多重相关分析和遥感估产技术的深入研究,并在图象处理、信息提取、信息应用和ＲＳ－ＧＰＳ－ＧＩＳ一体化估产方法及遥感知识与草原生态专业知识结合方面获得一定研究进展。研究结果表明,４个草地类型的可食鲜干草产量与两种遥感绿度值间存在着极显著相关性（Ｐ＜０．０１）,ｒ值均在０．６７９以上,且通过Ｆ检查和精度分析。一般在类型Ⅱ、Ⅲ和Ⅳ,是鲜草产量与ＲＶＩ相关性好于ＮＤＶＩ,而在类型Ⅰ则相反。进而从６种数学方程式中选优,建立了地学、光学和非线性遥感估产模型,并在实际估产中加以应用、检验和给出了生态学解释及机理分析,使大面积草地可食牧草遥感估产精度达到７５．８％以上,实现了遥感大面积估产目标和草地生态学意义及ＲＳ－ＧＰＳ－ＧＩＳ与草地专家系统一体化集成的应用。     

基于MODIS-NDVI的区域冬小麦遥感估产——以山东省济宁市为例

以黄淮海平原冬小麦主产区山东省济宁市为研究实例,利用遥感方法,采用250 m分辨率经过Savitzky-Golay滤波技术平滑处理的MODIS-NDVI遥感数据对冬小麦产量进行预测.研究选取了冬小麦关键生育期内0.2～0.8范围的旬NDVI数据,并建立了其与冬小麦产量的关系.同时,采用逐步回归方法筛选建立冬小麦关键生育期旬NDVI与冬小麦产量间关系的估产模型.利用地面实测冬小麦产量数据,对所建的估产模型进行精度检验,结果表明,估产相对误差在-3.6％～3.9％之间.表明利用Savitzky-Golay滤波技术平滑后的作物关键生育期内MODIS-NDVI遥感数据进行冬小麦估产,其方法精度较高,具有一定的可行性.     

RS,GPS和GIS集成系统的新疆北部天然芥地估产技术中的应用进展

利用１９９１￣１９９６年在新疆天山北坡不同草地类型上观测的草地可食产量,环境与遥感资料等,使用ＲＳ技术、ＧＰＳ和ＧＩＳ集成系统进行了交重相关分析和遥感估产技术的深入研究,并在图象处理、信息提取、信息应用和ＲＳ－ＧＰＳ－ＧＩＳ一体化估产方法及遥感知识与草原生态专业知识结合方面获得一定研究进展。研究结果表明,４个草地类型的可食鲜干草产量与两种遥感绿度值间存在着极显著相关性（Ｐ〈０．０１）,ｒ值均在０．     

划分土壤类型的一种新方法--以功能生态学理论为基础

借助功能生态学的理论 ,提出了运用土壤的特征物质 (CM)和特征时间 (CT)区分土壤类型的新方法。通过数学模拟 ,分别计算了灰色森林土和黑钙土的特征物质和特征时间 :当灰色森林土和黑钙土的年凋落物量分别为 5 .5t·hm-2 和 11.2t·hm-2 时 ,它们的CM和CT分别为 133t·hm-2 、80年和 82 0t·hm-2 、6 5 0年。CM和CT的值随着输入土壤的物质量和土壤中分解速度的变化而变化 ,而且受外界环境因素 (包括自然因素和人为因素 )的影响。CT随土壤深度的增加而增大     

基于叶面积指数反演的区域冬小麦单产遥感估测

利用定量遥感技术反演的叶面积指数（LAI）在中国北方黄淮海地区典型县市进行冬小麦单产预测研究.为提高数据质量和减少估产误差,利用Savitzky-Golay滤波技术降低云对NDVI数据的影响及数据缺失;通过冬小麦实测LAI进行时序内插,模拟得到实测点每日冬小麦LAI,继而获得实测点主要生育时期平均LAI;在此基础上,建立了冬小麦主要生育时期平均LAI与作物单产关系模型,改变目前利用生育时期内某一时间点LAI代替整个生育时期LAI的方法;在模型择优基础上,得到最佳遥感估产关键期--开花期LAI与单产统计模型;最后,利用MODIS-NDVI经验模型反演得到的开花期平均LAI进行2008年冬小麦单产预测.结果表明：与地面实测的冬小麦单产相比,研究区估产平均相对误差为1.21%,RMSE达到257.33 kg·hm^-2,可以满足大范围估产的要求.利用上述方法可以在研究区冬小麦收获前20～30 d进行准确的单产估计.     

作物光能利用效率和收获指数时空变化研究进展

1972年Monteith提出的光能利用效率模型是当前大多数作物生长和产量形成模拟研究以及遥感估产所采用的主要方法.光能利用效率(radiation use efficiency, RUE)和收获指数(harvest index, HI)是其中的两个基本参量.鉴于目前作物RUE和HI研究与应用中仍存在着一些问题,本文综述了相关研究进展,总结了不同尺度上作物RUE和HI的研究方法;介绍了当前遥感估产应用中对RUE和HI两个关键参数的处置概况;建议今后研究应在点尺度开展作物RUE和HI研究的基础上,寻求其在区域尺度上定量评估的可行性途径,切实有效地发挥作物RUE和HI研究在作物实际生产管理中和遥感产量估算方面的应用价值及潜力.     

基于机载LiDAR单束激光穿透指数的白桦林LAI估测

森林叶面积指数(LAI)是描述森林冠层结构和树木生长状况的一个重要指标.本研究以内蒙古依根地区为研究区,在充分考虑机载激光雷达不同回波脉冲之间差异的基础上,对LiDAR点云数据进行分束处理,同时利用传感器与目标之间的距离对LiDAR点云强度进行校正,在由点云校正强度计算传统激光穿透指数(LPI)的同时提出了一个新的激光穿透指数,即单束激光穿透指数(LPI_s),并分别采用LPI和LPI_s两种激光穿透指数在4种不同LiDAR数据采样尺度(直径分别为5、10、15和20 m)下分别应用理论模型和经验模型两种不同的建模方法对森林LAI进行估测,以期通过激光分束来提高森林LAI的估测精度.结果表明: 分束激光穿透指数均值(LPI_mean)估测LAI的效果明显好于未分束LPI的估测效果,且当LiDAR数据采样尺度为15 m时,LPI_mean的经验模型(R²=0.80,平均绝对偏差MAD为0.11)和理论模型(R²=0.77,MAD=0.16)的估测结果均达到最佳.最后综合应用最佳经验模型与理论模型各自的优点绘制了研究区的白桦林LAI分布图.     

链霉素产生菌——灰色链霉菌质粒的分离和电镜观察

本工作首次从具有临床应用价值的抗菌素产生菌——灰色链霉菌中分离得到质粒DNA(SGP1),并经电镜观察证实。用琼脂糖凝胶电泳分析,初步证明灰色链霉菌和天蓝色链霉菌质粒DNA分子大小相似,限制性内切酶Eco R1对灰色链霉菌质粒DNA可能只有一个切口。电镜观察表明灰色链霉菌质粒DNA具有共价闭合超盘旋环状和开放形环状两种构型,根据经验公式计算,灰色链霉菌质粒DNA分子量为1．9x107道尔顿左右。经紫外分光光度计测定灰色链霉菌质粒DNA解链温度(Tm值)为80．8u℃ G—C克分子百分数为76．8％。我们所获得的灰色链霉菌质粒DNA(SGP1)是否即是前文报道的[10]经高温消除,并与链霉素生物合成有关的质粒,则尚待进一步证实。     

水稻低温冷害综合评估方法

基于灰色关联分析法,将水稻不同生育期的冷害致灾因子值和产量结构性状、水稻不同生育期的产量结构性状和最终产量分别视作两个灰色系统,通过寻找各个灰色系统的灰映射关系,建立基于多层次灰色关联分析法的水稻低温冷害综合评估模型;并构建了单站各生育期、全生育期的冷害综合评估指数和区域评估指数,对东北水稻主产区27个站1961—2015年水稻冷害进行分生育期评估.结果表明: 水稻冷害影响程度与各生育期产量丰歉能够较好对应.营养生长期、营养和生殖生长并进期、授粉结实期或满浆期受到冷害影响时,株穗数、平均穗粒数或千粒重有一定减少,空壳率有所增加.典型冷害年温度与单站或区域产量丰歉有较好的对应关系.     

Predicting protein solubility with a hybrid approach by pseudo amino acid composition

Protein solubility plays a major role for understanding the crystal growth and crystallization process of protein. How to predict the propensity of a protein to be soluble or to form inclusion body is a long but not fairly resolved problem. After choosing almost 10,000 protein sequences from NCBI database and eliminating the sequences with 90% homologous similarity by CD-HIT, 5692 sequences remained. By using Chou's pseudo amino acid composition features, we predict the soluble protein with the three methods: support vector machine (SVM), back propagation neural network (BP Neural Network) and hybrid method based on SVM and BP Neural Network, respectively. Each method is evaluated by re-substitution test and 10-fold cross-validation test. In the re-substitution test, the BP Neural Network performs with the best results, in which the accuracy achieves 0.9288 and Matthews Correlation Coefficient (MCC) achieves 0.8513. Meanwhile, the other two methods are better than BP Neural Network in 10-fold cross-validation test. The hybrid method based on SVM and BP Neural Network is the best. The average accuracy is 0.8678 and average MCC is 0.7233. Although all of the three methods achieve considerable evaluations, the hybrid method is deemed to be the best, according to the performance comparison.     

BP神经网络在农产品生产与检测中的应用

人工神经网络是人工智能领域中发展迅速的信息处理技术之一,充分发挥人工神经网络的技术优势,是在农业领域内实现生产劳动自动化的重要途径．本文对BP网络模型及其算法进行了分析研究,从农产品的外观评判、生产预测建模和分类分级鉴定等方面综述了国内外最新研究进展,并展望了今后的应用前景。     

BPSI2.0: a C/C++ interface program for species identification via DNA barcoding with a BP-neural network by calling the Matlab engine

BP-Species Identification (BPSI2.0) is a computer program that performs species identification by training a Back-Propagation Neural Network. A short DNA barcoding segment is used as input for training a three-layer BP network. The trained network can assign an unknown query sequence to a known species in the user's database, and provide the corresponding subvector value of the output vector as a relative probability value.     

神经网络提高肝细胞癌磁共振波谱诊断正确率

通过评价31磷磁共振波谱(31Phosphorus Magnetic Resonance Spectroscopy,31P-MRS)来辨别三种诊断类型:肝细胞癌,正常肝和肝硬化。运用反向传输神经网络(BP)和径向基函数神经网络(RBF)分析31P-MRS数据,分别建立神经网络模型,进行肝细胞癌的诊断分类以期提高识别率。实验结果证明,应用神经网络模型后,31P-MR波谱对活体肝细胞癌的诊断正确率从89.47%提高到97.3%,且BP更优于RBF。     

遗传算法优化真菌深层培养过程神经网络模型的研究

提出一种简易的真菌深层培养过程网络模型。输入变量为可在线测量的排气中的二氧化碳浓度,网络权数采用遗传算法进行优化训练。所获神经网络模型能准确预测培养过程的状态变量(生物量浓度,产物浓度等)。研究表明遗传算法训练此类神经网络系统是可行的。     

Untersuchungen zur ernährungsphysiologischen Bedeutung von NPN-Verbindungen

The aims of the experiment were to investigate the variation in ruminal fermentation, milk performance and milk fatty acid profile triggered by induced subacute ruminal acidosis (SARA); and to evaluate the ability of beet pulp (BP) as a replacement for ground maize in order to alleviate SARA. Eight Holstein-Friesian cows were fed four diets (total mixed rations) during four successive periods (each of 17 d): (1) without wheat (W0); (2) with 10% finely ground wheat (FGW) (W10); (3) with 20% FGW (W20); (4) with 20% FGW and 10% pelleted BP (BP10). Inducing SARA by diet W20 decreased the daily mean ruminal pH (6.37 vs. 5.94) and the minimum ruminal pH (5.99 vs. 5.41) from baseline to challenge period. Ruminal concentrations of total volatile fatty acid, propionate, butyrate, valerate and isovalerate increased with the W20 compared with the W0 and W10 treatments. The substitution of BP for maize increased the minimum ruminal pH and molar percentage of acetate and decreased the molar percentage of butyrate. The diets had no effect on dry matter intake (DMI) and milk yield, but the milk fat percentage and yield as well as the amount of fat-corrected milk was reduced in the W20 and BP10 treatments. The cows fed the W20 diet had greater milk concentrations of C11:0, C13:0, C15:0, C14:1, C16:1, C17:1, C18:2n6c, C20:3n6, total polyunsaturated fatty acids (FA) and total odd-chain FA, and lower concentrations of C18:0 and total saturated FA compared with the cows fed the W0 diet. Therefore, it can be concluded that changes in ruminal fermentation, milk fat concentration and fatty acid profile are highly related to SARA induced by feeding high FGW diets, and that the substitution of BP for maize could reduce the risk of SARA in dairy cows.     

采用人工生命方法模拟七星瓢虫捕食行为进化

自从 2 0世纪 70年代Ｂｕｒｋｓ[1] 提出人工生命的概念后 ,人工生命作为一个全新的研究领域 ,以其特有的优势在近些年来得到迅猛地发展。人工生命的基本思想是去构造某种人工系统以达到对生物的生长、发育、遗传、变异、生殖、进化、学习等生命过程重要特征的模拟 ,从而认清这些生命现象的本质。人工生命有广泛的应用 ,它所使用的方法也是多样的。粗略地说 ,可分为湿件 (Ｗｅｔｗａｒｅ ,意为采用化学方法模拟 )、硬件 (Ｈａｒｄｗａｒｅ ,意为用机器人模拟 )和软件 (Ｓｏｆｔｗａｒｅ ,意为用程序模拟 )。本文集中在采用软件方法进行行为…     

Panel semiparametric quantile regression neural network for electricity consumption forecasting

Addressing the forecasting issues is one of the core objectives of developing and restructuring of electric power industry in China. However, there are not enough efforts that have been made to develop an accurate electricity consumption forecasting procedure. In this paper, a panel semiparametric quantile regression neural network (PSQRNN) is developed by combining an artificial neural network and semiparametric quantile regression for panel data. By embedding penalized quantile regression with least absolute shrinkage and selection operator (LASSO), ridge regression and backpropagation, PSQRNN keeps the flexibility of nonparametric models and the interpretability of parametric models simultaneously. The prediction accuracy is evaluated based on China's electricity consumption data set, and the results indicate that PSQRNN performs better compared with three benchmark methods including BP neural network (BP), Support Vector Machine (SVM) and Quantile Regression Neural Network (QRNN).     

Case study: Comparing the use of nonlinear discriminating analysis and Artificial Neural Networks in the classification of three fish species: acaras (Geophagus brasiliensis), tilapias (Tilapia rendalli) and mullets (Mugil liza)

This study used the Discriminant Analysis statistical technique and Artificial Neural Networks, multilayer perceptron, in the classification of three fish species sampled in the state of Rio de Janeiro, Brazil: Geophagus brasiliensis (acaras), Tilapia rendall (tilapias) and Mugil liza (mullets). These fish were sexed when possible, weighed, measured, and had their Gonadosomatic and Hepatosomatic Indices calculated, as well as their Condition Factor. The use of an Artificial Neural Network (ANN) presented satisfactory results, even though the groups were composed of very diverse-sized animals. Without the need for non-violation assumptions and other considerations, the Artificial Neural Network was found to be the excellent alternative to classification problems of unbalanced data, such as the one presented in this study.