基于北方苍鹰优化核极限学习机的玉米品种鉴别研究  

Identification of Corn Varieties Based on Northern Goshawk Optimization Kernel Based Extreme Learning Machine

作　　者：倪金 索丽敏[1] 刘海龙 赵蕊[2] NI Jin;SUO Li-min;LIU Hai-long;ZHAO Rui(College of Information and Electrical Engineering,Heilongjiang Bayi Agricultural University,Daqing 163319,China;College of Life Science and Technology,Heilongjiang Bayi Agricultural University,Daqing 163319,China)

机构地区：[1]黑龙江八一农垦大学信息与电气工程学院,黑龙江大庆163319 [2]黑龙江八一农垦大学生命科学技术学院,黑龙江大庆163319

出　　处：《光谱学与光谱分析》2024年第6期1584-1590,共7页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金项目(31772789)资助。

摘　　要：玉米作为我国种植最为广泛的农作物,其产量对于我国粮食安全具有重大意义,由于不同品种具有不同的特性,根据种植条件科学选种能够很大限度上提高产量并且降低生产成本,但不同玉米种子外观极其相似,导致科学选种工作产生了一定难度。该研究基于近红外光谱技术结合核极限学习机(KELM)针对玉米品种分类问题构建鉴别模型,利用甜糯黄玉米、甜妃、昌甜、金色超人、香甜5号五种玉米种子,每种取(13±0.5)g作为一份样品,共计126个样品作为研究对象,对采集的近红外光谱数据进行标准正态变量变换(SNV)处理后采用竞争性自适应重加权采样法(CARS)对数据集进行降维。按照5∶1的比例将样本随机分为训练集和测试集,探讨北方苍鹰优化算法(NGO)对KELM模型性能的影响。分别使用NGO算法、粒子群算法(PSO)和灰狼算法(GWO)对KELM模型的两个重要参正则化参数C和高斯核函数γ进行寻优,选择五折交叉验证识别准确率最高时对应的C和γ作为建模参数,建立KELM分类模型。将各算法寻优后建立的KELM模型性能进行对比。实验发现,通过NGO算法寻优后建立的KELM模型性能高于其他两种算法优化的KELM模型,测试集识别准确率可达100%。在CARS降维的基础上分别建立CARS-NGO-KELM、CARS-PSO-KELM和CARS-GWO-KELM模型,结果表明,在面对降维后的数据时NGO算法仍能表现较好的性能,其测试集准确率和F 1值均达到了100%。为了验证样本数量对模型的影响,使用各品种样品数量同步后的共计90个样品重新训练KELM模型。结果表明,在同步各类样品数量后,各个模型在训练集和测试集上的表现均有提升。该研究在近红外光谱的基础上引入多种优化算法构建核极限学习机模型并将识别准确率提升至100%,实现了对玉米种子快速、无损、准确的品种鉴别,研究结果为玉米品种快速鉴别提供了一种新方法,同时也对�As one of the most widely planted crops in China,the yield of corn is of great significance to China's food security.Since different varieties have different characteristics,scientific seed selection according to planting conditions can significantly improve the yield and reduce the cost of production.Still,the appearance of different corn seeds is extremely similar,which leads to a certain degree of difficulty in scientific seed selection.In this study,based on near-infrared spectroscopy combined with the Kernel Extreme Learning Machine(KELM)to construct a discrimination model for the classification of corn varieties,the use of sweet glutinous yellow corn,sweet princess,Chang sweet,golden superman,sweet No.5 five kinds of maize seeds,each kind of 6 grains as a sample,a total of 126 samples as the object of the study,the near-infrared spectroscopy data collected by the standard normal variate transformation(SNV)treatment.Competitive Adaptive Re-weighted Sampling(CARS)was used to downscale the dataset.The samples were randomly divided into training and test sets according to the ratio of 5∶1 to explore the effect of the Northern Goshawk Optimization Algorithm(NGO)on the performance of the KELM model.The two important parametric regularization parameters C and Gaussian kernel functionγof the KELM model was optimized using the NGO algorithm,particle swarm algorithm(PSO),and gray wolf algorithm(GWO),respectively,and the C andγcorresponding to the highest accuracy rate of the 50-50 cross-validation recognition were selected as the modeling parameters to build the KELM classification model.The KELM model's performance is established after each algorithm's optimisation is compared.It is found that the performance of the KELM model established after optimization by the NGO algorithm is higher than that of the KELM model optimized by the other two algorithms,and the recognition accuracy of the test set can reach 100%.The CARS-NGO-KELM,CARS-PSO-KELM and CARS-GWO-KELM models are built based on CARS dimensionality reduct

关 键 词：近红外光谱 玉米 北方苍鹰 竞争性自适应加权采样 核极限学习机 

分 类 号：O433.4[机械工程—光学工程]