基于声波信号递归图的鸡蛋裂纹检测

针对基于声波信号的鸡蛋裂纹检测过程中易受到噪音干扰的问题,采集运输线上敲击鸡蛋产生的声波信号,对信号进行递归图分析,采用递归定量分析提取递归图的量化特征参数,用于鸡蛋壳裂纹的分类检测。分别构建基于支持向量机(support vector machine,SVM)、反向传播神经网络模型的鸡蛋裂纹分类检测模型,对300枚鸡蛋进行检测。结果表明,SVM检测模型效果较好;在SVM模型中,完好蛋和裂纹蛋的识别率分别达93.98%和95.52%,效果理想。     

基于声学响应和BP神经网络检测鸡蛋裂纹

为了提高鸡蛋裂纹检测的准确性,建立了声学敲击检测鸡蛋裂纹的装置,采集和分析鸡蛋被敲击后的声音信号。提取了4个特征频率、偏斜度平均值和峰度平均值共6个特征参数,并作为神经网络的输入量,创建了基于MATLAB的结构为6-15-2的3层BP神经网络模型判别鸡蛋裂纹。检测结果显示:对蛋壳受各种程度破坏后的鸡蛋判别精度可达92%以上,对蛋壳完整的鸡蛋判别精度达到96%,对鸡蛋总体的判别精度可达94%。     

基于Adaboosting_SVM算法的多特征蛋壳裂纹识别

以无裂纹蛋和裂纹蛋为测试对象,采用机器视觉技术和支持向量机等技术手段,分析无裂纹蛋和裂纹蛋在图像上的差异,提取特征参数,实现蛋壳裂纹的自动识别;针对蛋壳表面的亮斑,对预处理后的图像运行消除亮斑算法并进行区域标记。在此基础上,从5个不同视角提取13个能够表征无裂纹蛋和裂纹蛋的特征参数,分别是图像标记区域参数(区域标记数和标记点数)、几何特征参数(长轴和短轴)、基于Freeman链码的形状参数(形状数)、纹理特征参数(均值、标准偏差、平滑度、三阶矩、一致性、熵)和频谱特性参数(最大幅值和最大相位)。采用Adaboosting算子对上述特征参数进行优化,突出影响因子较大的参数组合,作为SVM的输入向量,建立蛋壳裂纹的识别模型。结果表明:该方法对蛋壳表面的亮斑、微小裂纹及普通裂纹均具有识别能力,模型正确率达97.5%,符合蛋品企业对蛋壳裂纹检测的精度要求。     

基于声学特性和Labview的鸡蛋裂纹检测研究

鸡蛋裂纹是评价鸡蛋品质好坏的重要指标之一,为寻求更加直观可行的鸡蛋裂纹检测的新方法,利用声学特性,基于Labview虚拟仪器平台自行设计搭建了鸡蛋裂纹检测系统。以鸡蛋赤道部位4个点(1、2、3、4)作为敲击位置,采集获取鸡蛋的声音信号并进行分析,提取鸡蛋最大、最小2个特征频率(fmax,fmin),并计算其差值Δf(Δf=fmax-fmin),以1 000 Hz作为裂纹鸡蛋的识别阈值,分析并剔除裂纹鸡蛋,其准确率达到96.667%。结果表明,基于声学特性和Labview虚拟仪器平台,对裂纹鸡蛋进行裂纹检测不仅可行,且具有一定的准确率。     

基于机器学习算法的河南省冬小麦面积提取研究

为了精准获取河南省冬小麦空间分布及面积数据,基于2003—2021年250 m MODIS-NDVI时间序列遥感数据集,通过设置不同的阈值条件获得高质量的样本数据,采用深度神经网络(DNN)、随机森林(RF)和支持向量机(SVM)算法,自动从NDVI时序数据中提取冬小麦特征,分别训练出非线性模型,在250 m尺度对河南省冬小麦分布和面积进行识别。结果表明,基于DNN算法的河南省冬小麦面积识别模型精确率为97.26%,总体一致性为97.97%;基于RF、SVM算法的精确率分别为91.51%和89.31%,总体一致性均在90%以下。和RF、SVM算法相比,DNN算法在精度上有明显的提升,能够更好地反映河南省冬小麦的时间变化趋势和空间面积分布。该研究说明,运用中等分辨率长时间序列影像结合DNN算法,在一定程度上可以更准确识别大区域的农作物信息。     

高分辨率影像城区建筑物提取研究

【目的】探讨高分辨率遥感影像城区建筑物提取方法,为快速获取城区建筑物分布和辅助制订城区发展规划提供参考。【方法】以陕西杨凌西北农林科技大学北校区为研究对象,采用知识规则与支持向量机(Support vector machines,SVM)相结合的面向对象分析方法,从QuickBird影像中提取建筑物,并与基于SVM的面向对象分析方法及传统的基于像元的分类方法进行比较。【结果】采用知识规则与SVM相结合的面向对象分析方法所得的分类结果表明,提取建筑物总体精度达到90.68%,Kappa系数为0.81,较基于SVM的面向对象分析方法、SVM、最大似然法、K均值法总体精度分别提高了10.38%,15.31%,26.4%和29.2%。【结论】基于知识规则和SVM相结合的面向对象分析方法精度高、速度快,可快速获取建筑物的分布情况。     

电压扰动定位中小波与HHT性能分析

为实现配电网电压扰动的有效检测,分别运用小波变换与希尔伯特-黄(HHT)变换2种方法对电压扰动信号进行定位检测,分析对比2种方法的检测精度和性能。仿真算例结果表明:2种方法均具有较好的多分辨率分析特性,但HHT受噪声影响比较大,因此在合适的小波基下小波分解方法检测精度高于HHT变换检测精度。     

基于近红外光谱的库尔勒香梨等级判别模型研究

以库尔勒香梨的含糖量作为研究和检测指标,使用便携式近红外光谱仪采集香梨样本光谱数据,采用一阶差分、二阶差分、标准正态变量变换(SNV)、多元散射校正(MSC)等预处理方法对原始光谱进行预处理分析,研究香梨糖分的近红外光谱响应,并使用相关系数法提取12个特征波长变量,根据库尔勒香梨标准,以糖度特征光谱数据作为参数,利用最近邻域法(KNN)、支持向量机(SVM)、随机森林(RF)方法建立库尔勒香梨等级判别模型。结果表明,KNN模型的分类结果优于其它两种预测模型,可用于构建基于近红外光谱的库尔勒香梨等级评判模型。MSC+KNN处理方法可用于构建库尔勒香梨等级评判模型,为进一步研究库尔勒香梨等级评判的便携式检测装置提供理论参考。     

基于Radarsat-2的水稻种植面积提取

选用2013年7月23日-10月27日期间5期分辨率为5.2 m×7.6 m的Radarsat-2影像为数据,采用支持向量机法(SVM)和最大似然法(MLC)分别对各时相水稻种植面积进行提取,并以地面实测GPS水稻样方进行精度验证。结果表明SVM和MLC方法的水稻面积提取精度均在9月9日达到最高,所以选择在9月9日的水稻面积提取结果上研究耕地地块优化和碎小图斑去除对精度的影响。通过耕地地块优化和碎小图斑去除处理,水稻面积提取精度显著提高,SVM法由原先的72.876%提高到95.482%,MLC法由74.224%提高到91.792%。     

淅川乌鸡蛋壳质量性状分析

[目的]分析淅川乌鸡的蛋壳质量性状,为品种资源普查提供素材。[方法]在农户散放饲养的鸡中随机收集51枚鸡蛋,对鸡蛋的蛋壳颜色、蛋壳重占总蛋重的比例和不同部位蛋壳厚度进行测定。[结果]蛋壳颜色为浅灰色、灰色、深灰色和浅褐色4种,各自所占比例为19.61%、54.90%、11.76%和13.73%;蛋壳重占总蛋重的比例平均为11.89%;平均蛋壳厚度0.335 mm,大多数鸡蛋的蛋壳锐端厚度比钝端和中间高。[结论]可为该品种蛋品开发提供一定的依据。     

基于近红外光谱的纽荷尔脐橙产地识别研究

【目的】中国柑橘产区分布广、生态类型复杂,不同产地纽荷尔脐橙果实品质和市场效应具有较大差异。研究基于近红外光谱技术的柑橘产地识别技术,利于不同柑橘产地果品的识别和鉴伪。【方法】从中国南方17个纽荷尔脐橙主要产地选择代表性成年果园,分别采摘成熟鲜果样品100个。利用SupNIR-1500近红外分析仪采集脐橙果实赤道部、肩部表面以及果汁滤液的近红外反射光谱,光谱波长范围为1 000-2 499 nm。采用主成分分析法对原始光谱数据进行预处理,提取近红外光谱的特征信息以降低数据集维度以及噪声。研究人工神经网络理论,构建由一个输入层、一个具有非线性激励函数的隐藏层和一个输出层组成的典型的3层人工神经网络识别模型。研究由径向基函数作为核函数、以光谱主成分作为输入的支持向量机模型,构建由126个分类器组成的一对一扩展支持向量机模型。研究遗传算法优异的自然选择特性,利用遗传算法从光谱主成分中选择出最优的特征基因子集作为支持向量机的输入,构建遗传算法-支持向量机模型。利用3种模型分别对果汁滤液的近红外反射光谱数据进行分类,从而实现产地识别测试,并根据产地识别精度筛选出最优的产地识别模型。进一步对比该最优识别模型对果实赤道部、肩部反射光谱数据的识别精度,从而确定识别精度最高的光谱数据采集源。【结果】利用所建立的3层人工神经网络模型对纽荷尔脐橙果汁滤液的近红外光谱进行产地识别测试,确定当输入神经元数量为11、隐藏神经元数量为13时,模型对果实产地识别的最佳精度达81.45%。采用一对一扩展方式建立支持向量机产地识别模型,研究确定采用径向基函数作为核函数,当主成分数量为20时,脐橙产地识别精度最高可达86.98%。测试利用遗传算法-支持向量机混合模型进行脐橙产地分类识别,确定当种群数量为200、遗传代数为100、交叉概率0.7、突变概率0.01时,遗传算法选择出最优的基因子集进行产地识别,遗传算法-支持向量机模型的产地识别精度最高可达89.72%,优于人工神经网络分类模型和支持向量机分类模型的产地识别精度。进一步利用遗传算法-支持向量机产地识别模型对果实赤道部及肩部的果面反射光谱进行产地识别测试,得到对应的最高识别精度分别为80.00%和69.00%。【结论】遗传算法-支持向量机模型对果汁反射近红外光谱进行产地识别精度最高,优于人工神经网络模型和支持向量机模型。该模型对果实赤道部反射光谱进行分类的精度次于果汁滤液反射光谱但优于果实肩部反射光谱,因此,可利用赤道部的反射光谱实现非破坏性果实产地分类识别。     

Comparison of machine learning algorithms for mapping mango plantations based on Gaofen-1 imagery

Mango is a commercial crop on Hainan Island, China, that is cultivated to develop the tropical rural economy. The development of accurate and up-to-date maps of the spatial distribution of mango plantations is necessary for agricultural monitoring and decision management by the local government. Pixel-based and object-oriented image analysis methods for mapping mango plantations were compared using two machine learning algorithms (support vector machine (SVM) and Random Forest (RF)) based on Chinese high-resolution Gaofen-1 (GF-1) imagery in parts of Hainan Island. To assess the importance of different features on classification accuracy, a combined layer of four original bands, 32 gray-level co-occurrence (GLCM) texture indices, and 10 vegetation indices were used as input features. Then five different sets of variables (5, 10, 20, and 30 input variables and all 46 variables) were classified with the two machine learning algorithms at object-based level. Results of the feature optimization suggested that homogeneity and variance were very important variables for distinguishing mango plantations patches. The object-based classifiers could significantly improve overall accuracy between 2–7% when compared to pixel-based classifiers. When there were 5 and 10 input variables, SVM showed higher classification accuracy than RF, and when the input variables exceeded 20, RF showed better performances. After the accuracy achieved saturation points, there were only slightly classification accuracy improvements along with the numbers of feature increases for both of SVM and RF classifiers. The results indicated that GF-1 imagery can be successfully applied to mango plantation mapping in tropical regions, which would provide a useful framework for accurate tropical agriculture land management.     

AdaBoost classifiers for pecan defect classification

One of the constraints in the adoption of machine vision inspection systems for food products is low classification accuracy. This study attempts to improve pecan defect classification accuracy by using machine learning classifiers: AdaBoost and support vector machine (SVM). X-ray images of good and defective pecans, 100 each, were segmented and features were extracted. Twenty classification runs were made to adjust parameters and 300 classification runs to compare classifiers. The Real AdaBoost classifier gave average classification accuracy of 92.2% for the Reverse water flow segmentation method and 92.3% for the Twice Otsu segmentation method. The Linear SVM classifier gave average classification accuracy of 90.1% for the Reverse water flow method and 92.7% for the Twice Otsu method. Computational time for the classifiers varied by two orders of magnitude: Bayesian (10⁻⁴ s), SVM (10⁻⁵ s), and AdaBoost (10⁻⁶ s). AdaBoost classifiers improved classification accuracy by 7% when Bayesian accuracy was poor (less than 89%). The AdaBoost classifiers also adapted well to data variability and segmentation methods. A minimalist AdaBoost classifier, more suitable for real time applications, using fewer features can be built. Overall, the selected AdaBoost classifiers improved classification accuracy, reduced classification time, and performed consistently better for pecan defect classification.     

Application of distributed SVM architectures in classifying forest data cover types

In many ‘real-world’ applications, a classification of large data sets, which are often also imbalanced, is difficult due to the small, but usually more interesting classes. In this study, a large data set, forest cover type classes, which is actually multi-class classification defined with seven imbalanced classes and used as a resource inventory information was analyzed and evaluated. The data set was transformed into seven new data sets and a support vector machine (SVM) was employed to solve a binary classification problem of balanced and imbalanced data sets with various sizes. In the two approaches considered, the use of distributed SVM architectures, which basically reduces the complexity of the quadratic optimization problem of very large data sets, and the use of two sampling approaches for classification of imbalanced data sets were combined and results presented. The experimental results of distributed SVM architectures show the improvement of the accuracy for larger data sets in comparison to a single SVM classifier and their ability to improve the correct classification of the minority class.     

Classification of two different rough soil surfaces by using microwave X-band data through support vector machine (SVM)

Support vector machine (SVM) model is employed and tested for the soil surface roughness classification. SVM is calibrated (trained) and tested with the experimentally obtained data. The experimentally data is obtained by using X-band (9.5 GHz) scatterometer for two soil surface roughness 3.78 cm and 1.83 cm at constant soil surface moisture equal to 22.80%. The measurement of the scattering coefficient was carried out over a range of incidence angle from 20° to 70° at the step of 5° for both the HH and vv polarization. The performance of the SVM model is evaluated from the outcome classification result on trained data set and test data set. Radial Gaussian kernel function results 100% correct Classification and identification of soil surface roughness both in training and validation phase. SVM is a proficient technique for soil surface roughness classification by such experimentation and have numerous of advantages over artificial neural network (ANN) based approaches and other theoretical approaches as its less complexity and less time consumption ability.     

Mapping of Quantitative Trait Loci Affecting Eggshell Quality in an F_2 Population Derived from Strong and Weak Eggshell Lines of the White Leghorn Chicken Breed

Broken and cracked eggshells cause major economic losses to the egg production industry. An F2 population of 262 hens obtained by crossing a strong egg shell line with a weak egg shell line of the White Leghorn breed was used for detecting the quantitative trait loci (QTL) affecting eggshell quality. The 2 lines were developed from the same founder population by two-way selection for egg shell strength with nondestructive deformation. Of the 1 014 microsatellite markers tested, 35 were mapped on 10 autosoma1 linkage groups. There was no informative marker on chromosome Z. The QTLs associated with 7 traits, i.e., body weight, short length of egg, long length of egg, eggshell strength, eggshell thickness (EST), eggshell weight (ESW), and egg weight (EW), were identified. Highly significant (P 0.01) QTLs associated with EST and ESW and a significant (P 0.05) QTL associated with EW were mapped to a region flanking ABR0545 and ABR0362 on chromosome 9. These QTLs are good candidates to be employed in the development of strategies for reducing the number of broken and cracked eggs in commercial layer houses by employing marker assisted selection.     

基于无人机多光谱遥感图像的玉米田间杂草识别

【目的】为了精确高效识别玉米田间杂草,减少除草剂施用,提高玉米种植管理精准性。【方法】通过六旋翼无人机搭载多光谱相机获取玉米田块多光谱图像。为分离图像中植被与非植被像元,计算了7种植被指数,采用最大类间方差法提取植被指数图像中非植被区域,制作掩膜文件并对多光谱图像掩膜。通过主成分分析对多光谱图像进行变换,保留信息量最多的前3个主成分波段。将试验区域分为训练区域和验证区域,在训练区域中分别选取了675处玉米和525处杂草样本对监督分类模型进行训练,在验证区域选取了240处玉米样本及160处杂草样本评价模型分类精度。将7种植被指数、3个主成分波段的24个纹理特征及经过滤波的10个反射率,共计41项特征作为样本特征参数。利用支持向量机-特征递归消除算法(support vector machines-feature recursive elimination,SVM-RFE)和Relief算法从41项特征中各筛选14项特征构成特征子集,采用支持向量机、K-最近邻、Cart决策树、随机森林和人工神经网络对特征子集进行监督分类。【结果】支持向量机与随机森林对全部特征及2个特征子集分类效果较好,支...     

Mapping of Quantitative Trait Loci Affecting Eggshell Quality in an F2 Population Derived from Strong and Weak Eggshell Lines of the White Leghorn Chicken Breed

Broken and cracked eggshells cause major economic losses to the egg production industry. An F2 population of 262 hens obtained by crossing a strong egg shell line with a weak egg shell line of the White Leghorn breed was used for detecting the quantitative trait loci （QTL） affecting eggshell quality. The 2 lines were developed from the same founder population by two-way selection for egg shell strength with nondestructive deformation. Of the 1 014 microsatellite markers tested, 35 were mapped on 10 autosomal linkage groups. There was no informative marker on chromosome Z. The QTLs associated with 7 traits, i.e., body weight, short length of egg, long length of egg, eggshell strength, eggshell thickness （EST）, eggshell weight （ESW）, and egg weight （EW）, were identified. Highly significant （P〈0.01） QTLs associated with EST and ESW and a significant （P〈 0.05） QTL associated with EW were mapped to a region flanking ABR0545 and ABR0362 on chromosome 9. These QTLs are good candidates to be employed in the development of strategies for reducing the number of broken and cracked eggs in commercial layer houses by employing marker assisted selection.     

基于不同分类器的农用地分类提取

【目的】分析Landsat 8 OLI卫星遥感影像数据面向农用地分类的实际应用方法和效果,以新疆奇台县南部为研究对象。【方法】使用随机森林(RF)、支持向量机(SVM)和神经网络(Neural Net)三种分类器进行研究区农用地分类对比。【结果】通过对三种分类器参数设置参数精度检验,利用上述三种算法对农用地地物分类进行精度评价,在整体分类精度中,支持向量机算法(SVM)<随机森林算法(RF)<神经网络算法(Neural Net),分类精度分别为:90.75%,94.30%和94.84%。【结论】神经网络方法(Neural Net)在该地区的农用地物整体分类上,比支持向量机(SVM)和随机森林法(RF)相比具有一定的优势,并获得较好的分类精度。