干贝水分检测的建模及分级方法
|
摘要
高光谱成像已被应用于建立干贝水分含量预测模型,其模型性能受样本划分方法及建模方法影响。样本划分方法决定着所选样本是否具有代表性,而建模方法决定着如何利用样本建立模型,但样本划分方法与建模方法的内在联系却鲜有研究报道。在方法优选上,将样本划分方法与建模方法进行组合,探究不同方法组合对干贝水分含量预测模型性能的影响,对干贝水分检测建模及分级方法的优选具有重要意义,同时也能为其他样本的光谱建模提供参考。采集380～1 030nm波段下270个干贝样本的高光谱图像,提取干贝样本的光谱数据,通过RS,KS,SPXY和CG四种常用的方法划分样本,并以PLSR和LS-SVM两种常用的建模方法建立多个干贝水分含量预测模型,计算和比较各模型的性能指标。结果表明:PLSR模型使用RS法划分干贝水分含量样本最为适宜(其RPD为4.079 6),LS-SVM模型使用SPXY划分法最为适宜(其RPD为4.175 6),划分样本方法的优劣与建模方法有关,其优选需要结合特定的建模方法进行。在常用的四种样本划分方法和两种建模方法中,采用SPXY法划分干贝水分含量样本并结合LS-SVM法建模的效果和精度最好。
Hyperspectral imaging technology has been used to establish the prediction model of moisture content in dehydrated scallops,and the model performance is affected by sample division method and modeling method.The method of sample division determines whether the selected sample is representative,and the modeling method determines how to use the sample to build the model,but the internal relationship between the sample division method and the modeling method has been rarely reported.It is important to explore the effects of different sample division methods and modeling methods on the prediction of the moisture content of scallops,and it can also provide reference for the study of spectral modeling of other samples.In this paper,the hyperspectral data of 270 scallops were extracted from spectral images captured by a hyperspectral imaging system in the 380～1 030 nm range.The samples were divided by RS,KS,SPXY and CG.The prediction models were established by PLSR and LSSVM.The performance indexes of each model were calculated and compared.The results showed that the best sample division method is RS when using PLSR building prediction model(the RPD is 4.079 6)and SPXY is most suitable for LS-SVM model(the RPD is 4.175 6).The advantages and disadvantages of the division of the sample set are related to the modeling method,and the best choice should take modeling method into account.In this commonly used four sample division methods and two modeling methods,SPXY method is used to classify the sample set of moisture content and combine with LS-SVM method to optimize the effect and precision.
Hyperspectral imaging technology has been used to establish the prediction model of moisture content in dehydrated scallops,and the model performance is affected by sample division method and modeling method.The method of sample division determines whether the selected sample is representative,and the modeling method determines how to use the sample to build the model,but the internal relationship between the sample division method and the modeling method has been rarely reported.It is important to explore the effects of different sample division methods and modeling methods on the prediction of the moisture content of scallops,and it can also provide reference for the study of spectral modeling of other samples.In this paper,the hyperspectral data of 270 scallops were extracted from spectral images captured by a hyperspectral imaging system in the 380～1 030 nm range.The samples were divided by RS,KS,SPXY and CG.The prediction models were established by PLSR and LSSVM.The performance indexes of each model were calculated and compared.The results showed that the best sample division method is RS when using PLSR building prediction model(the RPD is 4.079 6)and SPXY is most suitable for LS-SVM model(the RPD is 4.175 6).The advantages and disadvantages of the division of the sample set are related to the modeling method,and the best choice should take modeling method into account.In this commonly used four sample division methods and two modeling methods,SPXY method is used to classify the sample set of moisture content and combine with LS-SVM method to optimize the effect and precision.
引文
[1] Huang H,Shen Y,Guo Y L,et al.Journal of Food Engineering,2017,205:47.
[2] Emerson R W.Journal of Visual Impairment&Blindness,2015,109(2):164.
[3] Claeys D D,Verstraelen T,Pauwels E,et al.The Journal of Physical Chemistry A,2010,114(25):6879.
[4] Gani W,Limam M.Journal of Statistical Computation&Simulation,2016,86(1):135.
[5] FU Miao-miao,LIU Mei-ying,NIU Zhi-you,et al(付苗苗,刘梅英,牛智有,等).Journal of Huazhong Agricultural University(华中农业大学学报),2016,2:115.
[6] LIU Shan-mei,LI Xiao-yu,ZHONG Xiong-bin,et al(刘善梅,李小昱,钟雄斌,等).Transactions of The Chinese Society of Agricultural Machinery(农业机械学报),2013,44(s1):165.
[7] Abdi H.Wiley Interdisciplinary Reviews:Computational Statistics,2010,2(1):97.
[8] Shawe-Taylor J,Sun S.Neurocomputing,2011,74(17):3609.
[9] Jian L,Shen S,Li J,et al.IEEE Transactions on Neural Networks and Learning Systems,2016,(99):1.
[10] Jiang L,Fei L,Yong H.Sensors,2012,12(3):3498.
[11] Aydogdu M,Firat M.Water Resources Management,2015,29(5):1575.
[12] LIU Jie,LI Xiao-yu,LI Pei-wu,et al(刘洁,李小昱,李培武,等).Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2010,26(2):338.
[2] Emerson R W.Journal of Visual Impairment&Blindness,2015,109(2):164.
[3] Claeys D D,Verstraelen T,Pauwels E,et al.The Journal of Physical Chemistry A,2010,114(25):6879.
[4] Gani W,Limam M.Journal of Statistical Computation&Simulation,2016,86(1):135.
[5] FU Miao-miao,LIU Mei-ying,NIU Zhi-you,et al(付苗苗,刘梅英,牛智有,等).Journal of Huazhong Agricultural University(华中农业大学学报),2016,2:115.
[6] LIU Shan-mei,LI Xiao-yu,ZHONG Xiong-bin,et al(刘善梅,李小昱,钟雄斌,等).Transactions of The Chinese Society of Agricultural Machinery(农业机械学报),2013,44(s1):165.
[7] Abdi H.Wiley Interdisciplinary Reviews:Computational Statistics,2010,2(1):97.
[8] Shawe-Taylor J,Sun S.Neurocomputing,2011,74(17):3609.
[9] Jian L,Shen S,Li J,et al.IEEE Transactions on Neural Networks and Learning Systems,2016,(99):1.
[10] Jiang L,Fei L,Yong H.Sensors,2012,12(3):3498.
[11] Aydogdu M,Firat M.Water Resources Management,2015,29(5):1575.
[12] LIU Jie,LI Xiao-yu,LI Pei-wu,et al(刘洁,李小昱,李培武,等).Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2010,26(2):338.