Detection Method of Apple Mould Core Based on Dielectric Characteristics

doi:10.12133/j.smartag.2021.3.4.202102-SA035

Abstract

Abstract:

Apple mouldy core disease often occurs in the ventricle of apples and cannot be effectively identified by appearance. Near-infrared spectroscopy, nuclear magnetic resonance and other methods are usually used in traditional apple mouldy core disease detection, but these methods require complex equipment and high detection costs. In this research, a simple and fast nondestructive detection method of apple mouldy core disease was proposed by using a dielectric method to construct an apple mouldy core disease detection model. Japan's Hioki 3532-50 LCR tester was used to collect 108 dielectric indicators (12 dielectric indicators at 9 frequencies) of 220 apples as the original data. Due to the large differences in the distribution of data collected with different dielectric indexes and different frequencies, a standardized method was used for data preprocessing to eliminate the problem of large differences in dielectric data distribution. Afterwards, in order to eliminate the redundant information between the data, the principal component analysis algorithm was used to reduce the data dimensionality, and finally the three algorithms of BP neural network (BPNN), support vector machine (SVM) and random forest (RF) were used to construct the mouldy core disease detection model. After pre-experiment, the most effective parameters of each algorithm were selected, the test results showed that the apple mouldy core disease detection model based on the RF algorithm obtained the best performance, and the detection accuracy rate reached 96.66% and 95.71% in the training set (150 apples) and the test set (70 apples). The mouldy core disease detection model constructed by using BPNN was the second most effective, and the detection accuracy could reach 94.66% and 94.29%, respectively. The detection effect of the model built by using SVM was relatively poor, and the detection accuracies were 93.33% and 91.43%, respectively. The experimental results showed that the model constructed by using RF can more effectively identify mouldy core disease apples and healthy apples. This study could provide references for apple diseases and insect pests and non-destructive testing of apple quality.

Key words: apple mouldy core disease, dielectric characteristics, random forest, BP neural network, support vector machine

CLC Number:

S126

LI Dongbo, HUANG Lyuwen, ZHAO Xubo. Detection Method of Apple Mould Core Based on Dielectric Characteristics[J]. Smart Agriculture, 2021, 3(4): 66-76.

Figures/Tables 11

Fig. 1

Table 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Table 2

Table 3

Fig. 6

Fig.7

Table 4

References 23

1	PATRIARCA A. Fungi and mycotoxin problems in the apple industry[J]. Current Opinion in Food Science, 2019, 29: 42-47.
2	ZHONG L, CARERE J, LU Z, et al. Patulin in apples and apple-based food products: The burdens and the mitigation strategies[J]. Toxins, 2018, 10(11): ID 475.
3	郭志明, 黄文倩, 陈全胜, 等. 近红外光谱的苹果内部品质在线检测模型优化[J]. 现代食品科技, 2016, 32(9): 147-153.
	GUO Z, HUANG W, CHEN Q, et al. Optimization of online detection model for internal quality of apple by near infrared spectroscopy[J]. Modern Food Science and Technology, 2016, 32(9): 147-153.
4	王转卫, 迟茜, 郭文川, 等. 基于近红外光谱技术的发育后期苹果内部品质检测[J]. 农业机械学报, 2018, 49(5): 348-354.
	WANG Z, CHI Q, GUO W, et al. Internal quality detection of apple in late development stage based on near infrared spectroscopy[J]. Transactions of the CSAM, 2018, 49(5): 348-354.
5	高辉, 马国峰, 刘伟杰. 基于机器视觉的苹果缺陷快速检测方法研究[J]. 食品与机械, 2020, 36(10): 125-129.
	GAO H, MA G, LI W. Research on rapid detection method of apple defects based on machine vision[J]. Food & Machinery, 2020, 36(10): 125-129.
6	BHARGAVA A,BANSAL A. Quality evaluation of Mono & bi-Colored apples with computer vision and multispectral imaging[J]. Multimedia Tools and Applications, 2020, 79(11): 7857-7874.
7	张京平, 朱建锡, 孙腾. 苹果内部品质的CT成像结合傅里叶变换方法检测[J]. 农业机械学报, 2014, 45(5): 197-204.
	ZHANG J, ZHU J, SUN T. Detection of apple internal quality by CT imaging combined with Fourier transform method[J]. Transactions of the CSAM, 2014, 45(5): 197-204.
8	曹玉栋, 祁伟彦, 李娴, 等. 苹果无损检测和品质分级技术研究进展及展望[J]. 智慧农业, 2019, 1(3): 29-45.
	CAO Y, QI W, LI X, et al. Research progress and prospect on non-destructive detection and quality grading technology of apple[J]. Smart Agriculture, 2019, 1(3): 29-45.
9	蔡骋, 李永超, 马惠玲, 等. 基于介电特征选择的苹果内部品质无损分级[J]. 农业工程学报, 2013, 29(21): 279-287.
	CAI C, LI Y, MA H, et al. Nondestructive grading of apple internal quality based on dielectric feature selection[J]. Transactions of the CSAE, 2013, 29(21): 279-287.
10	王若琳, 王栋, 任小林, 等. 基于电学特征的苹果水心病无损检测[J]. 农业工程学报, 2018, 34(5): 129-136.
	WANG R, WANG D, REN X, et al. Nondestructive detection of apple water core disease based on electrical characteristics[J]. Transactions of the CSAE, 2018, 34 (5): 129-136.
11	MCGLONE V A, MARTINSEN P J, CLARK C J, et al. On-line detection of Brown heart in Braeburn apples using near infrared transmission measurements[J]. Postharvest Biology and Technology, 2005, 37(2):56-63.
12	SHENDEREY C, SHMULEVICH I, ALCHANATIS V, et al. NIRS detection of moldy core in apples[J]. Food & Bioprocess Technology, 2010, 3(1): 79-83.
13	李顺峰, 张丽华, 刘兴华, 等. 基于主成分分析的苹果霉心病近红外漫反射光谱判别[J]. 农业机械学报, 2011, 42(10): 158-161.
	LI S, ZHANG L, LIU X, et al. Discrimination of apple moldy heart disease by near infrared diffuse reflectance spectroscopy based on principal component analysis[J]. Transactions of the CSAM, 2011, 42(10): 158-161.
14	王富春, 李军, 张润浩, 等. 基于计算机视觉的苹果霉心病病变程度测量方法[J]. 农机化研究, 2015, 37(6): 189-193.
	WANG F, LI J, ZHANG R, et al. Measurement method of apple mold heart disease lesion degree based on computer vision[J]. Journal of Agricultural Mechanization Research, 2015, 37(6): 189-193.
15	STROSHINE C R. Rapid sensing of internal browning in whole apples using a low-cost, low-field proton magnetic resonance sensor[J]. Postharvest Biology and Technology, 2005, 3: 56-64.
16	张立彬, 胥芳贾, 灿纯, 等. 苹果内部品质的电特性无损检测研究[J]. 农业工程学报, 2000(3): 104-106.
	ZHANG L, XU F, CAN C, et al. Study on nondestructive testing of internal quality of Apple[J]. Transactions of the CSAE, 2000(3): 104-106.
17	李芳, 蔡骋, 马惠玲, 等. 基于生物阻抗特性分析的苹果霉心病无损检测[J]. 食品科学, 2013, 34(18): 197-202.
	LI F, CAI C, MA H, et al. Nondestructive detection of apple moldy heart disease based on bioelectrical impedance analysis[J]. Food Science, 2013, 34(18): 197-202.
18	蔡骋, 李晓龙, 马惠玲, 等. 基于生物阻抗特性的苹果新鲜度无损测定[J]. 农业机械学报, 2013, 44(2): 147-152.
	CAI C, LI X, MA H, et al. Nondestructive determination of apple freshness based on bioelectrical impedance characteristics[J]. Transactions of the CSAM, 2013, 44(2): 147-152.
19	耿晗, 蔡骋, 刘斌. 基于介电特性的苹果内部品质预测方法研究[J]. 农机化研究, 2019, 41(10): 186-191.
	GENG H, CAI C, LIU B. Study on prediction method of apple internal quality based on dielectric properties[J]. Journal of Agricultural Mechanization Research, 2019, 41(10): 186-191.
20	SIDHU K, GILL A, ARORA A, et al. Advancements in farming and related activities with the help of artificial intelligence: A review[J]. Environment Conservation Journal, 2021, 22(SE): 55-62.
21	OMRANI E, KHOSHNEVISAN B, SABOOHI H, et al. Potential of radial basis function-based support vector regression for apple disease detection[J]. Measurement, 2014, 55: 512-519.
22	SAMAJPATI B, DEGADWALA S. Hybrid approach for apple fruit diseases detection and classification using random forest classifier[C]// 2016 International Conference on Communication and Signal Processing (ICCSP). Piscataway, New York, USA: IEEE, 2016: 1015-1019.
23	GRANATO D,SANTOS J, ESCHER G, et al. Use of principal component analysis (PCA) and hierarchical cluster analysis (HCA) for multivariate association between bioactive compounds and functional properties in foods: A critical perspective[J]. Trends in Food Science & Technology, 2018, 72: 83-90.

介电参数编号	符号	解释	单位
1	Z	复阻抗	Ω
2	Cs	串联电容	F
3	Cp	并联电容	F
4	Rs	串联电阻	Ω
5	Rp	并联电阻	Ω
6	Ls	串联电感	H
7	Lp	并联电感	H
8	G	电导	S
9	Y	导纳	S
10	θ	复阻抗相角	（^o）
11	D	损耗系数	——
12	Q	品质因子	——

主成分编号	PC1	PC2	PC3	PC4	PC5	PC6	PC7
贡献率/%	43.69	14.19	10.53	8.61	4.87	4.23	3.06
累计贡献率/%	43.69	57.88	68.41	77.02	81.89	86.12	89.18
主成分编号	PC8	PC9	PC10	PC11	PC12	PC13	PC14
贡献率/%	2.22	1.77	1.13	1.04	0.71	0.56	0.46
累计贡献率/%	91.40	93.17	94.31	95.34	96.05	96.61	97.07

建模方法	训练集误判数		分类准确率/%	测试集误判数		分类准确率/%
建模方法	好果（40个）	霉心果（110个）	分类准确率/%	好果（16个）	霉心果（54个）	分类准确率/%
PCA-SVM	2	8	93.33	2	4	91.43
PCA-BP	2	4	94.66	1	3	94.29
PCA-RF	1	4	96.66	0	3	95.71

[1]	XIAO Shijie, WANG Qiaohua, LI Chunfang, ZHAO Limei, LIU Xinya, LU Shiyu, ZHANG Shujun. Construction of Milk Purchase Classification Model Based on Shuffled Frog Leaping Algorithm and Support Vector Machine [J]. Smart Agriculture, 2021, 3(4): 77-85.
[2]	YIN Hang, LI Xiangtong, XU Longqin, LI Jingbin, LIU Shuangyin, CAO Liang, FENG Dachun, GUO Jianjun, LI Liqiao. EMD-RF-LSTM: Combination Prediction Model of Dissolved Oxygen Concentration in Prawn Culture [J]. Smart Agriculture, 2021, 3(2): 115-125.
[3]	LI Zhijun, YANG Shenghui, SHI Deshuai, LIU Xingxing, ZHENG Yongjun. Yield Estimation Method of Apple Tree Based on Improved Lightweight YOLOv5 [J]. Smart Agriculture, 2021, 3(2): 100-114.
[4]	LIU Tianlin, ZHU Xicun, BAI Xueyuan, PENG Yufeng, LI Meixuan, TIAN Zhongyu, JIANG Yuanmao, YANG Guijun. Hyperspectral Estimation Model Construction and Accuracy Comparison of Soil Organic Matter Content [J]. Smart Agriculture, 2020, 2(3): 129-138.
[5]	SHAO Guomin, WANG Yajie, HAN Wenting. Estimation Method of Leaf Area Index for Summer Maize Using UAV-Based Multispectral Remote Sensing [J]. Smart Agriculture, 2020, 2(3): 118-128.
[6]	YU Weige, WU Huarui, PENG Cheng. Short-Term Price Forecast of Vegetables Based on Combination Model of Lasso Regression Method and BP Neural Network [J]. Smart Agriculture, 2020, 2(3): 108-117.
[7]	FLORES Paulo, ZHANG Zhao, MATHEW Jithin, JAHAN Nusrat, STENGER John. Distinguishing Volunteer Corn from Soybean at Seedling Stage Using Images and Machine Learning [J]. Smart Agriculture, 2020, 2(3): 61-74.
[8]	Zhou Chao, Xu Daming, Lin Kai, Chen Lan, Zhang Song, Sun Chuanheng, Yang Xinting. Evaluation of fish feeding intensity in aquaculture based on near-infrared machine vision [J]. Smart Agriculture, 2019, 1(1): 76-84.