Abstract
In order to quickly and accurately detect the status of paddy during storage, the near infrared (NIR) technique was used to establish classification models for identifying the storage quality of paddy. The NIR data of 285 samples in the range of 1 000～1 800 nm were collected. Based on the measured fatty acid, the storage state of the sample was divided into three categories (good storage quality, moderate storage quality obviously tending to decline, and poor storage quality). The optimal 10 wavelengths were selected by neighborhood rough set (NRS) algorithm. The best classification model was established by the combination of NRS and random forest (RF) algorithm. The correct classification rate (CCR) of the calibration set and the test set are 96.31% and 93.68%, respectively. The results of sensitivity and specificity are distributed in a range of 0.93 to 0.99. Furthermore, the performance of the model is also superior to the other models established by using successive projections algorithm (SPA) and principal component analysis (PCA) algorithms combined with RF. The result indicated that the fusion of NIR technique and the NRS and RF algorithms is feasible for the identification of paddy storage quality, and which can provide a reference for the development of on-site rapid inspection equipment for grain quality and safety.
Publication Date
11-28-2019
First Page
79
Last Page
84
DOI
10.13652/j.issn.1003-5788.2019.11.016
Recommended Citation
Dong, YANG; Qing, CHANG; Jianghao, YUAN; Yang, CAO; and Huiyi, ZHAO
(2019)
"Non-destructive identification of the storage quality of paddy using nearinfrared spectroscopy with neighborhood rough set algorithm,"
Food and Machinery: Vol. 35:
Iss.
11, Article 14.
DOI: 10.13652/j.issn.1003-5788.2019.11.016
Available at:
https://www.ifoodmm.cn/journal/vol35/iss11/14
References
［1］ ORINA I, MANLEY M, WILLIAMS P J. Non-destructive techniques for the detection of fungal infection in cereal grai-ns［J］. Food Research International, 2017, 100(1): 74-86.
［2］ 曹阳, 魏雷, 赵会义, 等. 我国绿色储粮技术现状与展望［J］. 粮油食品科技, 2015, 23(S1): 11-14.
［3］ 唐芳, 欧阳毅, 祁智慧. 基于扫描电镜观察研究真菌孢子检测对稻谷霉变判定［J］. 中国粮油学报, 2018, 33(4): 122-126.
［4］ BIANCOLILLO A, FIRMANI P, BUCCI R, et al. Determination of insect infestation on stored rice by near infrared (NIR) spectroscopy［J］. Microchemical Journal, 2019, 145: 252-258.
［5］ 吴子丹, 赵会义, 曹阳, 等. 粮食储藏生态系统的仿真技术应用研究进展［J］. 粮油食品科技, 2014, 22(1): 1-6.
［6］ 范维燕, 林家永, 邢邯, 等. 稻谷脂肪酸值近红外光谱快速测定技术研究［J］. 食品科学, 2009, 30(24): 347-350.
［7］ 俞法明, 陆艳婷, 严文潮, 等. 用近红外光谱技术快速测定籼稻品种的蛋白质含量［J］. 中国粮油学报, 2009, 24(5): 134-138.
［8］ 田卫新, 何丹丹, 杨东, 等. 一种基于高光谱图像的熟牛肉TVB-N含量预测方法［J］. 食品与机械, 2016, 32(12): 70-74.
［9］ YANG Dong, LU An-xiang, WANG Ji-hua, et al. Detection of the freshness state of cooked beef during storage using hyperspectral imaging［J］. Applied Spectroscopy, 2017， 71(10): 2 286-2 301.
［10］ 徐彦, 李忠海，付湘晋, 等. 近红外光谱技术在稻米品质快速检测中的应用［J］. 食品与机械, 2011, 27(1): 158-161．
［11］ 国家粮食局. GB/T 24895—2010 粮油检验 近红外分析定标模型验证和网络管理与维护通用规则［S］. 北京: 中国标准出版社, 2010: 1-9.
［12］ 蒋晓杰, 周旭, 杨志成, 等. 漫反射红外光谱法结合PLS测定稻谷脂肪酸值研究［J］. 中国粮油学报, 2019, 34(3): 117-120.
［13］ JAMES V A, WITTENBERG A, LI Hui, et al. High throughput phenotyping of Camelina sativa seeds for crude protein, total oil, and fatty acids profile by near infrared spectroscopy［J］. Industrial Crops and Products, 2019, 137: 501-507.
［14］ 文韬, 洪添胜, 李立君, 等. 霉变稻谷脂肪酸含量的光谱检测模型构建与优化分析［J］. 农业工程学报, 2016(1): 193-199.
［15］ LIU Yao, XIE Hong, CHEN Yue-hua, et al. Neighborhood mutual information and its application on hyperspectral band selection for classification［J］. Chemometrics and Intelligent Laboratory Systems, 2016, 157: 140-151.
［16］ 朱启兵, 黄敏, 赵桂林. 基于邻域粗糙集和高光谱散射图像的苹果粉质化检测［J］. 农业机械学报, 2011, 42(10): 154-157.
［17］ BREIMAN L. Bagging predictors［J］. Machine Learning, 1996, 24(2): 123-140.
［18］ BREIMAN L. Random forests［J］. Machine Learning, 2001, 45(1): 5-32.
［19］ DONG Ying, XIANG Bing-ren, GENG Ying, et al. Rough set based wavelength selection in near-infrared spectral analysis［J］. Chemometrics and Intelligent Laboratory Systems, 2013, 126: 21-29.
［20］ 刘瑶, 李梓楠, 吴涛, 等. 基于高光谱图像和邻域粗糙集理论的大豆品种识别算法及其综合性能评估［J］. 大豆科学, 2018, 37(4): 110-119.
［21］ 胡清华, 于达仁, 谢宗霞. 基于邻域粒化和粗糙逼近的数值属性约简［J］. 软件学报, 2008, 19(3): 640-649.
［22］ PARIKH R, MATHAI A, PARIKH S, et al. Understanding and using sensitivity, specificity and predictive values［J］. Indian Journal of Ophthalmology, 2008, 56(1): 45-50.
［23］ 沈飞, 张斌, 刘潇, 等. 基于光谱和气味特征信息的霉变大米无损检测［J］. 中国粮油学报, 2018, 33(4): 127-132.