灵芝孢子受冷等静高压作用破壁提取机理的探讨

按照普通植物种子的情况,推定灵芝孢子的结构有完全充满、部分充满、有大空隙和无种仁4种形式。为此,按照这4种形式分别说明了灵芝孢子受高等静压作用时,孢子壁的破坏方式和灵芝孢子有效成分的溶出方式。     

Pd Pattern Recognition Based on Linear Discriminant Analysis in GIS

According to the character of PD in GIS, the authors design four kinds of GIS defection models. The GIS gray intensity images are constructed based on mass specimens gathered by the ultra - high frequency and high speeds systems, Aiming at the PD characteristics and its defections, A PCA-FDA method is put forward based on PD images. The principal component analysis is employed to condense the dimension of PD images, then the optimal sets of statistically uncorrelated discriminant vectors are extracted, and the minimum distance classifier is constructed as classifier. The identified results show that this method can effectively elevated the discrimination of the four kinds of defects in GIS PD.     

Temporal-spatial Filtering in the Preprocessing of Clinical EEG Signals

EEG spot-recording for clinical patients in the bed is always advocated due to easing patients and making them comfortable. But EEG signals recorded in the ward exposed to various noisesand interference is less effective in the EEG analysis. Atemporal-spatial filter is designed for noise removing of clinical EEG signals, the first filtering is temporal filtering using band-pass filter, and the second filtering is spatial filtering with ICA-based spatial filter. Experimental results indicate that various noises and interferences, such as power interference, blinking, eyes movements, muscle moments, ECG artifacts, etc., are removed effectively, individually or simultaneously.     

THE STUDY OF SINGLE CHIP COMPUTER BASED SYMMETRICAL COMPONENT DISTANCE PROTECTION

In this paper, a new microcomputer distance protection scheme with high property-cost ratio has been approached. The paper presents the performance equations based on the symmetrical components of current and voltage, proposes a new (1,a) coordinate plane and derives a Fourier symmetrical component algorithem with high accuracy and less calculation amount on the (1,a) plane. The protection program is debugged on the developing system of single chip computer. The digital imitation tests indicate that the proposed relaying system is satisfactory.     

Application of Principal Component Analysis on Workable Competition Evaluation

The effective competition is an effective organizational form of the industry in modem market economy. It is a form accompanied with large - scale production and vigor competition. The analysis of effective competition has been the focus that people have paid close attention to it very much all the time. It is a basis of industrial policy, on the basis of the former research, the aufhors bring out 9 indexes according to the actual situation of our country, then take automobile trade as an example, we analyze the automobile trade with principal component.     

基于KPCA-WLSSVM的建筑能耗预测模型

为降低建筑能耗影响因素间复杂相关性对模型性能的影响,建立了一种基于KPCA-WLSSVM的建筑能耗预测模型。利用核主元分析(KPCA)对输入变量进行数据压缩,消除变量之间的相关性,简化模型结构;进一步采用加权最小二乘支持向量机(WLSSVM)方法建立建筑能耗预测模型,同时结合一种新型混沌粒子群-模拟退火混合优化(CPSO-SA)算法对模型参数进行优化,以提高模型的预测性能及泛化能力。通过将KPCA-WLSSVM模型方法应用于某办公建筑能耗的预测中,并与WLSSVM、LSSVM及RBFNN模型相比,实验结果表明,KPCA-WLSSVM模型方法能有效提高建筑能耗预测精度。     

新疆阿瓦提灌区土壤盐渍化状况的

采用主成分分析方法对阿瓦提灌区土壤盐渍化状况进行了研究，结果表明，该地属于中重度硫酸盐盐渍地，0～30cm耕作层含盐量在0.5%-4%之间，在灌区内部土壤盐分存在多次积盐和脱盐过程，耕作层第一、二主成分显著，累计贡献率高达90%，第一主成分综合反映灌区内土壤盐渍化程度，第二、第三主成分联合反映了土壤的碱性特征。     

玉米籽粒内部组分低对比度透射图像精确分割研究

为解决玉米籽粒透射图像由于对比度较低造成内部组分提取不精确的问题,提出一种基于色彩通道非线性变换的多通道重叠区域分割方法,对玉米籽粒图像在灰度、R通道及b通道下得到的二值图像使用重叠区域原理,实现玉米籽粒组分的精确分割。首先,采集不同玉米品种的籽粒透射图像,提取单粒玉米籽粒;其次,采用多通道重叠区域法分割单粒籽粒图像,得到玉米籽粒胚部、角质胚乳和粉质胚乳3部分的图像;最后,以查全率和查准率评价多通道重叠区域法与传统图像分割方法对不同品种玉米籽粒的分割效果。不同品种玉米籽粒的分割试验表明:多通道重叠区域分割方法的查全率、查准率及综合评价指标均达到98%以上,分割效果优于传统的图像分割方法,能够实现不同品种透明角质玉米籽粒透射图像的精确组分分割。     

基于多源数据融合的盐分遥感反演与季节差异性研究

为提高多光谱盐分遥感反演的精度,利用实测高光谱与多光谱进行数据融合,并分析了不同季节盐分遥感的差异性。以河套灌区永济灌域为研究区域,以实测光谱仪测定的土壤高光谱数据和Landsat-8 OLI多光谱数据为基础,通过光谱变换和多元逐步回归方法筛选特征波段和特征光谱指数,构建了春、秋两季土壤盐分多光谱、高光谱反演模型,并利用特征光谱指数的线性回归构建了高-多光谱数据融合反演模型。结果表明:高光谱的反射率总体比多光谱高36. 83%,春季反射率比秋季平均高23. 78%。利用模型中最优变量-特征光谱指数对多光谱模型与高光谱模型进行融合,高-多光谱融合反演模型训练集和验证集R2平均值分别为0. 651和0. 635,RMSE平均值分别为2. 44 g/kg和2. 49 g/kg,精度明显高于对应的多光谱反演模型,其中训练集、验证集的R2平均值分别提高了36. 19%和35. 64%,RMSE平均值分别降低了34. 28%和41. 72%。春季多光谱、高光谱和融合反演模型的精度均高于秋季,其中训练集R2平均值比秋季模型分别提高了6. 03%、6. 05%和4. 40%,验证集R2平均值分别提高了19. 07%、12. 21%和1. 75%。构建的高-多光谱融合模型反演灌域春秋两季平均盐分含量分别为6. 05、5. 97 g/kg,平均相对误差分别为9. 65%和10. 68%,总体上该区域春季土壤主要为重盐化土,秋季土壤主要为中盐化土。     

基于PCA-GA-SVM的甘蔗收获机运行状态识别

由于甘蔗收获机在收获过程中智能化水平较低,依靠人工操作很容易对甘蔗收获机的运行状态产生误判,从而造成物流通道堵塞、能源浪费、收割效率低。针对这些问题,提出一种基于主成分分析(PCA)、遗传算法(GA)和支持向量机(SVM)状态识别模型。首先,通过实地采集甘蔗收获机刀盘轴、行走轴、切段轴和风机轴扭矩和行驶速度特征信息,然后通过PCA进行数据降维,最后利用GA优化参数C、γ,使用每个特性信息来训练SVM,对甘蔗收获机运行状态进行分类。结果表明:PCA-GA-SVM状态识别模型对甘蔗收获机运行状态的识别准确率为93.75%,建模时间为3.688 s,与SVM(81.25%,9.487 s)、PCA-SVM(87.5%,5.817 s)和GA-SVM(90%,8.969 s)进行对比,该模型具有最高准确识别率和最快建模速度,具有较大的应用价值。