摘要(Abstract):
为了提高苹果自动分级分拣系统的性能,提出一种基于证据有序极限学习机Bagging集成的无损苹果分级模型。使用苹果近红外光谱中提取的特征作为输入,根据可溶性固形物含量将苹果分为3个等级;考虑等级类标的认知不确定性和有序性,在Dempster-Shafer理论框架内提出高斯质量函数生成方法和证据编码方案;构造以证据编码为输出的证据有序极限学习机作为基学习器,通过Bagging算法实现集成学习;选取435个红富士苹果作为实验样本生成数据集,并进行交叉验证。结果表明,所提出的证据有序极限学习机Bagging集成模型的分级准确率达到91%,该模型训练时间比证据有序神经网络集成模型的缩减至少2个数量级。
关键词(KeyWords):苹果分级;近红外光谱;Dempster-Shafer理论;有序分类;集成学习
基金项目(Foundation):国家自然科学基金项目(61803175);; 山东省自然科学基金项目(ZR2021MF074,ZR2023MF094)
作者(Author): 马荔瑶,卫鹏,范肖辰,徐元,毕淑慧
DOI: 10.13349/j.cnki.jdxbn.20250116.003
参考文献(References):
[1] PANG G J,ZHANG F H,SONG X L.Path and countermeasures for transformation and upgrading of apple industry in China[J].Cooperative Economy and Technology,2018,598(23):24.
[2] 陈庆光,刘强,张竞成,等.多视角三维视觉成像的苹果果形测量与分类[J].杭州电子科技大学学报(自然科学版),2022,42(4):34.
[3] 乔正明,詹成.基于近红外光谱和SSA-ELM的苹果糖度预测[J].食品与机械,2021,37(9):121.
[4] 李速专,童何馨,袁雷明,等.间隔连续投影算法应用于近红外光谱苹果糖度模型的优化[J].食品安全质量检测学报,2019,10(14):4608.
[5] 王迎超,张婧婧,贾东霖,等.基于K-means聚类和改进MLP的苹果分级研究[J].河南农业科学,2023,52(1):161.
[6] 耿新雪,张婧婧,梁雪林,等.红富士苹果在线分级系统的设计与实现[J].电子设计工程,2023,31(10):124.
[7] 马斌,韩俊英.基于深度学习的苹果果实品种鉴定与识别研究[J].软件,2022,43(6):17.
[8] 孟庆龙,尚静,黄人帅,等.基于主成分回归的苹果可溶性固形物含量预测模型[J].保鲜与加工,2020,20(5):185.
[9] MA L Y,BI S H,ZHANG C F.Apple grading system based on near infrared spectroscopy and evidential classification forest[C]//2019 International Conference on Advanced Mechatronic Systems(ICAMechS),August 26-28,2019,Kusatsu,Japan.New York:IEEE,2019:326.
[10] BI S H,LI X,MA L Y,et al.Apple internal quality fusion prediction by multi-pattern recognition technology and evidence theory[J/OL].Mobile Networks and Applications,2022:1[2022-02-05].https://doi.org/10.1007/s11036-021-01899-y.
[11] GUTIéRREZ P A,PéREZ-ORTIZ M,SáNCHEZ-MONEDERO J,et al.Ordinal regression methods:survey and experimental study[J].IEEE Transactions on Knowledge and Data Engineering,2016,28(1):127.
[12] 阮腾飞,张三国,申立勇.基于比例优势模型的有序数据分类[J].系统科学与数学,2022,42(10):2817.
[13] GU B,GENG X,SHI W L,et al.Solving large-scale support vector ordinal regression with asynchronous parallel coordinate descent algorithms[J].Pattern Recognition,2021,109:107592.
[14] 吴迎岗.基于有序神经元LSTM的短文本相似性检测[J].计算机应用与软件,2021,38(12):314.
[15] RAJASEKHAR G P,GRANGER E,CARDINNAL P.Deep domain adaptation with ordinal regression for pain assessment using weakly-labeled videos[J].Image and Vision Computing,2021,110:104167.
[16] GRIGOROUDIS E,NOEL L,GALARIOTIS E,et al.An ordinal regression approach for analyzing consumer preferences in the art market[J].European Journal of Operational Research,2021,29(2):718.
[17] 王曙光,郭枫,丁时磊,等.帕金森病患者服药依从性变化轨迹及预测因素的纵向研究[J].齐齐哈尔医学院学报,2023,44(6):583.
[18] DEMPSTER A P.Upper and lower probabilities induced by a multivalued mapping[J].The Annals of Mathematical Statistics,1967,38(2):325.
[19] SHAFER G.A mathematical theory of evidence[M]//Princeton:Princeton University Press,1976.
[20] MA L Y,WEI P,QU X H,et al.Apple grading method based on neural network with ordered partitions and evidential ensemble learning[J].CAAI Transactions on Intelligence Technology,2022,7(4):561.