Spectral Detection Method for Chilling Damage of Sweet Potato Based on Support Vector Machine

被引：1

作者：

Zhang X. ^{[1
]}

Yang Z. ^{[2
]}

Cao S. ^{[1
]}

Si Y. ^{[1
]}

机构：

[1] College of Information Science and Technology, Hebei Agricultural University, Baoding

[2] College of Plant Protection, Hebei Agricultural University, Baoding

来源：

Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2020年 / 51卷

关键词：

Feature selection; Spectral technology; Support vector machines; Sweet potato chilling damage;

D O I：

10.6041/j.issn.1000-1298.2020.S2.058

中图分类号：

学科分类号：

摘要：

The storage of sweet potato is susceptible to chilling damage, which not only affects its quality but also is susceptible to other diseases, which greatly reduces the commercial and economic value of sweet potato. For the biological detection technology and traditional detection methods will cause irreversible damage to sweet potato, so a non-destructive detection method of sweet potato chilling damage based on optical fiber spectroscopy technology was established. The feature spectrum bands were selected by the key feature ranking method based on the class separability criterion. And the support vector machine algorithm was used to train and evaluate the data set to detect the accuracy of the characteristic spectrum and the occurrence of sweet potatoes before the symptoms of chilling damage were visible to the human eyes. Totally five sweet potato varieties were used for experiments. The accuracy of detecting chilling damage in sweet potatoes was as high as 99.52% with the ratio of training data and test data of 5:5, and the incidence of the ratio of 7:3 was as high as 99.63%. The results proved the correctness of the characteristic spectrum, and the characteristic spectral bands were as follows: Jishu26 was 821.3~823.5 nm; Yanshu25 was 810.5~821.9 nm; Xiguahong was 818.8~821.9 nm; Xinong431 was 601.5~606.4 nm; and Longshu9 was 759.6~761.2 nm. The results showed that the spectroscopy technology can effectively detect and identify sweet potato chilling damage. This research provided technical method for subsequent work for sweet potato storage classification. © 2020, Chinese Society of Agricultural Machinery. All right reserved.

引用

页码：471 / 477

页数：6

共 33 条

[21]

KHORRAMNIA K, KHOT L R, SHARIFF A R B M, Et al., Oil palm leaf nutrient estimation by optical sensing techniques, Transactions of the ASABE, 57, 4, pp. 1267-1277, (2014)

[22]

XIAO Zhiyun, LIU Hong, Features selection and recognition of potato typical insect pest images in wavelet domain[J/OL], Transactions of the Chinese Society for Agricultural Machinery, 48, 9, pp. 24-31, (2017)

[23]

AFIFI S, GHOLAM H H, SINHA R., A system on chip for melanoma detection using FPGA-based SVM classifier, Microprocessors and Microsystems, 65, pp. 57-68, (2019)

[24]

KHOSRVI A A, AMINI A, POURMOHAMMAD A., Random forest and SVM based face recognition using subspace methods, Information Systems and Signal Processing Journal, 3, 1, pp. 5-13, (2018)

[25]

WEI Liran, YUE Jun, LI Zhenbo, Et al., Multi-classification detection method of plant leaf disease based on kernel function SVM, Transactions of the Chinese Society for Agricultural Machinery, 48, pp. 166-171, (2017)

[26]

CHEN L, FENG Y, MARAM M A, Et al., Multi-SVM based Dempster-Shafer theory for gesture intention understanding using sparse coding feature, Applied Soft Computing, 85, (2019)

[27]

JIAN Xianzhong, GU Yiting, Short-term electric load forecasting method based on global optimization support vector machine, Electric Power Science and Engineering, 34, 11, pp. 45-51, (2018)

[28]

CHEN Fangyuan, ZHOU Xin, CHEN Yiyun, Et al., Estimating biochemical component contents of diverse plant leaves with different kernel based support vector regression models and VNIR spectroscopy, Spectroscopy and Spectral Analysis, 39, 2, pp. 428-434, (2019)

[29]

LI Ziwen, LI Zongpeng, MAI Shukui, Et al., Determination of fat in walnut beverage based on least squares support vector machine, Spectroscopy and Spectral Analysis, 39, 12, pp. 3916-3920, (2019)

[30]

CHOI I H, KOO J B, WOO J W, Et al., Damage evaluation of porcelain insulators with 154 kV transmission lines by various support vector machine (SVM) and ensemble methods using frequency response data, Applied Sciences, 10, 1, (2020)

← 1 2 3 4 →