thumbnail

Topic

Technical equipment testing

Volume

Volume 73 / No. 2 / 2024

Pages : 501-512

Metrics

Volume viewed 0 times

Volume downloaded 0 times

DETECTION OF BLACK HEART DISEASE IN SEED POTATO BASED ON TRANSMISSION SPECTROSCOPY TECHNIQUE

基于透射光谱技术的马铃薯种薯黑心病检测研究

DOI : https://doi.org/10.35633/inmateh-73-42

Authors

Xianhe WANG

College of Electromechanical Engineering, Inner Mongolia Agricultural University

(*) Min HAO

College of Electromechanical Engineering, Inner Mongolia Agricultural University

Xingtai CAO

College of Electromechanical Engineering, Inner Mongolia Agricultural University

Yutao ZHANG

College of Electromechanical Engineering, Inner Mongolia Agricultural University

(*) Corresponding authors:

Abstract

Black heart disease is one of the screening indicators of seed potatoes, which has a serious impact on the quality and yield of potato, and at present there are fewer non-destructive testing methods for internal defects of seed potatoes. This paper aims to utilize non-destructive testing technology to quickly identify qualified and black hearted seed potatoes, and then to protect yield and food security. In this paper, transmission spectroscopy system was utilized to collect the spectral data of 104 qualified seed potatoes and 104 black hearted seed potatoes in 450~940 nm band. Subsequently, four algorithms, namely Savitzky-Golay (SG), Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC) and First-order Derivative (FD), were utilized to pre-process the seed potatoes spectral data to improve the data noise ratio. Feature wavelength extraction was made using Competitive Adaptive Reweighted Sampling (CARS) and Successive Projections Algorithm (SPA) to enhance the sample data characteristics and improve the model interpretability. The construction of classification models for qualified and black hearted seed potatoes relied on two deep learning techniques, Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN), which were trained and tested for the feature bands respectively. The experimental results showed that SG-CARS-CNN was the optimal combination of classification algorithms, and the classification accuracies of both the training set and the test set reached 100%, which improved the accuracy of the test set by 3.85% compared with that of the traditional machine learning algorithms, and provided an accurate method for the rapid screening of qualified seed potatoes.

Abstract in Chinese

黑心病是马铃薯种薯筛选指标之一,对马铃薯的品质和产量有严重的影响,而目前针对马铃薯种薯内部缺陷无损检测方法较少,本文旨在利用无损的检测技术快速识别合格与黑心马铃薯种薯,进而保障马铃薯产量和粮食安全。本文利用透射光谱系统采集104个合格种薯和104个黑心种薯450~940nm波段光谱数据,随后利用SG卷积平滑(SG)、标准正态变换法(SNV)、多元散射校正法(MSC)和一阶导数(FD)4种算法对马铃薯种薯光谱数据预处理,以提高数据信噪比;利用竞争性自适应重加权采样法(CARS)和连续投影算法(SPA)进行特征波长提取,以强化样本数据特征和提高模型可解释性;合格与黑心马铃薯种薯分类模型的构建依赖于卷积神经网络(CNN)和循环神经网络(RNN) 2种深度学习技术,分别对特征波段进行训练与测试。试验结果表明,SG-CARS-CNN为最优分类算法组合,训练集和测试集分类准确度均达到100%,相比于传统机器学习算法测试集准确率提高了3.85%,为快速筛选合格马铃薯种薯提供准确方法。

Indexed in

Clarivate Analytics.
 Emerging Sources Citation Index
Scopus/Elsevier
Google Scholar
Crossref
Road