基于GA的GRNN高光谱遥感反演冬小麦叶片氮含量模型的建立与验证

基于人工神经网络理论,针对高光谱遥感中数据冗余问题,本文建立了基于遗传算法(GA)的广义回归神经网络(GRNN)模型,利用回归分析问题中参数筛选方法,对表征冬小麦叶片全氮的光谱参数进行了筛选,并和线性回归方法对比,线性回归方法的均方根误差(RMSEP):在冬小麦叶片氮含量为34.0g kg-1~62.5g kg-1预测范围内,逐步回归模型为14.4g kg-1,后向选择为11.8g kg-1,而广义回归神经网络为3.40g kg-1。说明神经网络方法所筛选到的光谱参数更能反映小麦叶片全氮含量,且神经网络模型预测精度高。     

用高光谱数据反演健康与病害落叶松冠层光合色素含量的模型研究——基于2005年吉林省敦化、和龙两市落叶松冠层采样测量数据

健康落叶松与遭受病害落叶松的冠层光谱反射率曲线具有明显差异,利用反映这种差异的光谱特征参数建立回归模型,可为反演落叶松冠层光合色素含量进而诊断落叶松健康状况提供方法和途径。以吉林省延边州敦化、和龙两市林场中健康的和遭受落叶松早落病侵害的人工落叶松林为调查对象,在对野外采集的14个落叶松冠层样本进行光谱测量及光合色素含量测量的基础上,选取8个对落叶松冠层光合色素含量变化反映敏感的光谱参数参与建立其光合色素含量的一元线性回归和多元逐步回归模型。研究结果表明,不同健康程度的落叶松冠层光谱曲线在其可见光及近红外波段有3个比较明显的特征差异处,分别位于光谱曲线的“绿峰”、“红谷”和“红边”位置。利用反映这些差异的8个光谱特征参数建立落叶松冠层光合色素含量的回归模型,除 “红边”这一参数回归效果不令人满意外,其余7个参数均得到了较好的回归效果,其中利用峰谷波长差Dgr建立的关于总叶绿素和叶绿素b含量的一元回归模型R²值分别达到0.842 8和0.749 8,利用NDGI建立的关于叶绿素a和类胡萝卜素含量的一元回归模型R²值分别达到0.875 8和0.789 7;多元逐步回归模型的回归效果与一元回归模型相比,各判定系数R²值均有所提高,总叶绿素、叶绿素a、b和类胡萝卜素含量的回归模型R²值分别达到0.885、0.910、0.839和0.862。     

基于混沌免疫粒子群优化和广义回归神经网络的回采工作面瓦斯涌出量预测模型

为提高回采工作面绝对瓦斯涌出量预测的精度和效率,提出了将混沌免疫粒子群优化(CIPSO)算法与广义回归神经网络(GRNN)相耦合的绝对瓦斯涌出量预测模型。该方法采用CIPSO对GRNN的光滑因子进行动态优化调整,减少了人为因素对GRNN网络输出结果的影响,并采用优化后的网络建立瓦斯涌出量预测模型。通过对某煤矿瓦斯涌出量数据的仿真实验结果表明:基于CIPSO-GRNN的回采工作面绝对瓦斯涌出量模型比BP神经网络、Elman网络预测模型具有更好的预测精度和收敛速度,证明了该方法的有效性和可行性。     

基于特征筛选结合PSO-BPNN和GA-BPNN算法的土壤重金属高光谱定量反演

以连州地区土壤重金属含量为研究对象,分析包括土壤原始光谱在内的经过数学变换后的光谱数据与重金属含量之间的相关性,再采用VISSA-IRIV算法进行光谱特征提取,分别建立偏最小二乘回归(PLSR)、BP神经网络(BPNN)、粒子群优化BP神经网络、遗传算法优化BP神经网络模型,对比获取土壤重金属元素Cr、Cu含量最优反演模型。结果表明：VISSA-IRIV算法实现了对光谱数据的高效降维;BPNN模型预测效果明显优于PLSR模型;经过优化的BP神经网络模型反演精度和稳定性得到了极大地提升,其中Cr、Cu元素的最佳反演模型组合分别为FD-GABPNN(R²=0.87、RMSE=13.82、RPD=2.95)、SNV-FD-PSO-BPNN(R²=0.92、RMSE=4.25、RPD=3.41)。该研究对土壤重金属含量的准确、快速分析提供了一种有效的方法,对实现土壤重金属污染治理具有重要的现实意义。     

可见光—近红外光谱估算三江源区不同土壤全氮含量

近年来可见光—近红外反射光谱已被广泛应用于估算土壤全氮含量,为大范围区域土壤全氮含量获取提供了一种快速、有效的方法。基于实验室测定的三江源区146个表层土壤(0~30cm)样品的反射光谱数据(350~2 500nm)与全氮含量数据;利用偏最小二乘回归(PLSR)和反向传播神经网络(BPNN)两种模型方法与光谱反射率(REF)及其4种数学预处理变换相结合,分别建立分土壤类型样本和总体样本全氮估算模型;评估利用可见光—近红外光谱技术预测三江源区土壤全氮含量的能力。结果表明:BPNN模型的R2cal、R2val及验证RPD的平均值分别为0.87、0.81与2.28;而PLSR模型则相应为0.75、0.72和1.95;表明BPNN模型预测能力整体上要优于PLSR模型。BPNN与光谱各种形式的结合均具有良好、或接近良好预测全氮的能力;而PLSR与REF、倒数对数(Log(1/R))及波段深度(BD)的结合仅少部分具有良好估算能力、大部分则为粗略估算能力,一阶微分(FDR)和二阶微分(SDR)估算精度均较低,尤其是SDR(R20.5,RPD=1.10~1.27)均不具备估算能力。总体样本所建模型稳定性好于分土壤类型,分土壤类型建模差异性明显;此外,总体来看,BPNN模型比PLSR建模精度高、模型稳定性好,但PLSR模型可操作性强于BPNN模型。     

基于HS-BP神经网络的认知无线电频谱预测技术

在基于反向传播神经网络(BPNN)的频谱预测中,网络的初始权重与阈值是随机产生的,并且BP算法本身存在陷入局部最优的缺陷,从而导致BPNN训练得到的网络结构具有一定的不确定性。针对上述问题,提出一种基于HS-BP神经网络的频谱预测算法,通过和声搜索算法的全局寻优能力得到BPNN的最优初始权重和阈值,从而BPNN训练可得到最优的频谱预测网络结构,并运用该网络结构进行频谱的预测。仿真结果表明,该算法可以提高频谱预测的准确性及频谱的利用率。     

基于GRNN全信息神经网络的超短期风速预测研究

为了更好地研究风功率预测,风速预测显得至关重要.国内神经网络文献均只表现出了短期风速预测,而对于超短期风速预测的神经网络数学模型却相对稀少.引入了GRNN神经网络,详细说明了该方法的超短期风速预测原理并建立了数学模型;为了使超短期风速预测精度有一个良好的对比性分析,将影响风电输出功率的各NWP(numerical weather prediection)信息(包括风速、风向、气温、气压)进行组合,以国内某风电场2014年5月份的各NWP数据进行算例分析,实验结果表明,GRNN全信息神经网络可以达到很好的预测精度,而且运算网络的稳定性甚优.     

基于日光诱导叶绿素荧光与反射率光谱的小麦条锈病探测研究

综合利用反射率光谱在作物生化参数探测的优势和叶绿素荧光在光合生理诊断的优势,开展了日光诱导叶绿素荧光(SIF)和反射率光谱指数协同的小麦条锈病光谱探测研究,以期提高小麦条锈病病情严重度的预测精度。利用O_2-A波段(760 nm)的SIF信号和对小麦条锈病病情严重度敏感的7种反射率光谱指数,基于支持向量机(SVM)、逐步回归(SR)以及神经网络(BP)算法,定量分析了反射率光谱指数和反射率光谱指数与SIF协同的小麦条锈病病情严重度(DI)光谱探测模型的预测精度。结果表明:①SIF与小麦条锈病病情严重度之间存在极显著的负相关关系,SIF与DI间的响应能有效地应用于小麦条锈病的遥感探测;②SIF结合反射率光谱指数的小麦条锈病病情严重度光谱模型探测精度均高于反射率光谱指数模型,SIF能够显著提高小麦条锈病病情严重度的光谱探测精度;③无论是利用反射率光谱指数还是SIF结合反射率光谱指数作为小麦条锈病病情严重度预测模型的输入参数,训练模型以BP模型的预测精度最高,但验证结果表明SVM与SR方法构建的病情严重度预测模型效果较优。     

新疆棉花LAI和叶绿素密度的高光谱估算研究

利用非成像高光谱仪,对棉花(2品种4水平种植密度)冠层5个关键生育时期进行光谱测定,分析棉花反射光谱及微分光谱生育期的变化规律,并对棉花冠层叶面积指数(LAI)、叶绿素密度(CH.D)与光谱数据进行回归分析,结果表明,用归一化差值植被指数(NDVI)与LAI建立的对数模型能够较好地估测棉花冠层的LAI(r=0.9123**,n=20);近红外729 nm波段处一阶微分光谱数值与CH.D高度相关(r=0.9372**,n=20),用此波段建立的CH.D估算模型,精度达84.3%,标准差为0.234g.m-2,RMSE=0.1569。研究表明,可以用高光谱数据对新疆棉花冠层LAI和CH.D进行遥感估算。     

基于QPSO-GRNN的水质氨氮预测建模

BP(Back Propagation)网络在用于水质预测时,存在运算速度慢和易陷入局部最优的缺点,与传统的BP网络相比,广义回归神经网络(General Regression Neural Network,GRNN)的计算速度快,预测精度较高。光滑因子σ是广义回归神经网络的唯一待确定参数,它对网络的预测性能影响很大,本文采用量子粒子群算法(quantum particle swarm algorithm,QP SO)优化算法对光滑因子进行估算,并通过GRNN构建水质预测模型。实验表明:该模型能较好地预测氨氮变化趋势,为科学管理水质提供必要依据。     

Nondestructive measurement of internal quality attributes of apple fruit by using NIR spectroscopy

Multimedia Tools and Applications - In this paper, a hybrid approach, which combines back propagation neural network (BPNN), generalized regression neural network (GRNN) and particle swarm...     

Generalized regression neural network in modelling river sediment yield

The majority of the artificial neural network applications in water resources involve the employment of feed forward back propagation method (FFBP). In this study another ANN algorithm, generalized regression neural network, GRNN, was used in river suspended sediment estimation. Generalized regression neural network does not require an iterative training procedure as in back propagation method. The GRNN simulations do not face the frequently encountered local minima problem in FFBP applications and GRNN does not generate estimates physically not plausible. The neural networks are trained using daily river flow and suspended sediment data belonging to Juniata Catchment in USA. The suspended sediment estimations provided by two ANN algorithms are compared with conventional sediment rating curve and multi linear regression method results. The mean squared error and the determination coefficient are used as comparison criteria. Also the estimated and observed sediment sums are examined in addition to two previously mentioned performance criteria. The ANN estimations are found significantly superior to conventional method results.     

花生四烯酸发酵过程的建模方法研究

对发酵法生产花生四烯酸的建模方法进行了初步研究,并基于四种温度下的试验数据,建立了发酵过程模型.比较分析了最小二乘支持向量机( LS-SVM)和广义回归神经网络(GRNN)这两种方法的特点.结果表明,这两种方法均能较好地建立该发酵过程的模型,LS-SVM建模的预测能力稍优于GRNN,为后续花生四烯酸发酵过程的优化及控制的研究奠定了基础.     

A novel throughput mapping method for DC-HSDPA systems based on ANN

In order to improve support for higher data rates, third-generation partnership project (3GPP) introduced dual-carrier high-speed downlink packet access (DC-HSDPA), which reaches up to 42-Mbps throughput with the use of two adjacent 5-MHz carriers in Release-8. Defining the dependence of throughput on prevailing channel parameters is crucial because a frequency-selective channel limits achieving these data rates. For this reason, DC-HSDPA throughput real field measurements were taken in different propagation environments by using the “TEMS Investigation” program. The evaluation of the measurements showed that one-parameter linear mapping methods, such as signal-to-interference ratio and channel quality indicator, are insufficient for characterizing user throughput. Therefore, this study will propose a novel mapping method with more than one variable. Although multiple linear regression gives a better normalized root-mean-square error, results have shown that frequently used artificial neural network-based mapping methods—such as those for adaptive network-based fuzzy inference system, multilayer perceptron, and generalized regression neural network (GRNN)—yield improved accuracy. From among these, user throughput can be best estimated with the use of GRNN for a commercial DC-HSDPA system, with approximately 93.3 % precision. The GRNN structure allows system designers to update system parameters to maximize user throughput.

     

A new support vector model-based imperialist competitive algorithm for time estimation in new product development projects

Time estimation in new product development (NPD) projects is often a complex problem due to its nonlinearity and the small quantity of data patterns. Support vector regression (SVR) based on statistical learning theory is introduced as a new neural network technique with maximum generalization ability. The SVR has been utilized to solve nonlinear regression problems successfully. However, the applicability of the SVR is highly affected due to the difficulty of selecting the SVR parameters appropriately. The imperialist competitive algorithm (ICA) as a socio-politically inspired optimization strategy is employed to solve the real world engineering problems. This optimization algorithm is inspired by competition mechanism among imperialists and colonies, in contrast to evolutionary algorithms. This paper presents a new model integrating the SVR and the ICA for time estimation in NPD projects, in which ICA is used to tune the parameters of the SVR. A real data set from a case study of an NPD project in a manufacturing industry is presented to demonstrate the performance of the proposed model. In addition, the comparison is provided between the proposed model and conventional techniques, namely nonlinear regression, back-propagation neural networks (BPNN), pure SVR and general regression neural networks (GRNN). The experimental results indicate that the presented model achieves high estimation accuracy and leads to effective prediction.     

Soft computing methods applied to train station parking in urban rail transit

This paper presents three models - a linear model, a generalized regression neural network (GRNN) and an adaptive network based fuzzy inference system (ANFIS) - to estimate the train station parking (TSP) error in urban rail transit. We also develop some statistical indices to evaluate the reliability of controlling parking errors in a certain range. By comparing modeling errors, the subtractive clustering method other than grid partition method is chosen to generate an initial fuzzy system for ANFIS. Then, the collected TSP data from two railway stations are employed to identify the parameters of the proposed three models. The three models can make the average parking errors under an acceptable error, and tuning the parameters of the models is effective in dynamically reducing parking errors. Experiments in two stations indicate that, among the three models, (1) the linear model ranks the third in training and the second in testing, nevertheless, it can meet the required reliability for two stations, (2) the GRNN based model achieves the best performance in training, but the poorest one in testing due to overfitting, resulting in failing to meet the required reliability for the two stations, (3) the ANFIS based model obtains better performance than model 1 both in training and testing. After analyzing parking error characteristics and developing a parking strategy, finally, we confirm the effectiveness of the proposed ANFIS model in the real-world application.     

Public transportation trip flow modeling with generalized regression neural networks

Artificial neural networks (ANNs) are one of the recently explored advanced technologies, which show promise in the area of transportation engineering. The presented study comprised the employment of this seldom used ANN method, generalized regression neural network (GRNN), in comparison to both a frequently applied neural network training algorithm, feed-forward back-propagation (FFBP), and a stochastic model of auto-regressive structure for the purpose of forecasting daily trip flows, which is an essential component in demand analysis. The study is carried out under the motivation of knowing that modeling daily trips for available transportation modes will facilitate the arrangement for effective public infrastructure investments and the cited papers in the literature did not make use of and handle any comparison with GRNN method. The ANN predictions are found to be quite close to the observations as reflected in the selected performance criteria. The selected stochastic model performance is quite poor compared with ANN results. It is seen that the GRNN did not provide negative forecasts in contrast to FFBP applications. Besides, the local minima problem faced by FFBP algorithm is not encountered in GRNNs.     

支持向量机与神经网络相结合的板带凸度预测

为提高热轧生产过程中板带凸度的预测精度,提出了一种将粒子群优化算法(particle swarm optimization, PSO)、支持向量回归(support vector regression, SVR)和BP神经网络(back propagation neural network, BPNN)相结合的板带凸度预测模型。采用PSO算法优化SVR模型的参数,建立了PSO-SVR板带凸度预测模型,提出采用BPNN建立板带凸度偏差模型与PSO-SVR板带凸度模型相结合的方法对板带凸度进行预测。采用现场数据对模型的预测精度进行验证,并采用统计指标评价模型的综合性能。仿真结果表明,与PSO-SVR、SVR、BPNN和GA-SVR模型进行比较,PSO-SVR+BPNN模型具有较高的学习能力和泛化能力,并且比GA-SVR模型运算时间短。     

An automotive generator fault diagnosis system using discrete wavelet transform and artificial neural network

This paper describes a fault diagnosis system for automotive generators using discrete wavelet transform (DWT) and an artificial neural network. Conventional fault indications of automotive generators generally use an indicator to inform the driver when the charging system is malfunction. But this charge indicator tells only if the generator is normal or in a fault condition. In the present study, an automotive generator fault diagnosis system is developed and proposed for fault classification of different fault conditions. The proposed system consists of feature extraction using discrete wavelet analysis to reduce complexity of the feature vectors together with classification using the artificial neural network technique. In the output signal classification, both the back-propagation neural network (BPNN) and generalized regression neural network (GRNN) are used to classify and compare the synthetic fault types in an experimental engine platform. The experimental results indicate that the proposed fault diagnosis is effective and can be used for automotive generators of various engine operating conditions.     

流形学习与非线性回归结合的头部姿态估计

流形学习的目的是发现非线性数据的内在结构,可用于非线性降维。广义回归网络是人工神经网络的一种,可用于非线性回归。基于流形学习和非线性回归,提出了用于解决头部姿态估计的ManiNLR方法。该方法首先用流形学习对图像数据进行降维,然后用非线性回归的方法将数据映射到线性可分空间,利用非线性回归的结果对人脸的头部姿态进行估计。实验结果表明,ManiNLR算法能够较好地估计图像中的头部姿态,并具有较快的速度和较高的鲁棒性。