Fast Identification of Soybean Seed Varieties Using Laser-Induced Breakdown Spectroscopy Combined With Convolutional Neural Network

Abstract

Soybean seed purity is a critical factor in agricultural products, standardization of seed quality, and food processing. In this study, laser-induced breakdown spectroscopy (LIBS) as an effective technology was successfully used to identify ten varieties of soybean seeds. We improved the traditional sample preparation scheme for LIBS. Instead of grinding and squashing, we propose a time-efficient method by pressing soybean seeds into rubber sand filled with culture plates through a ruler to ensure a relatively uniform surface height. In our experimental scheme, three LIBS spectra were finally collected for each soybean seed. A majority vote based on three spectra was applied as the final decision judging the attribution of a single soybean seed. The results showed that the support vector machine (SVM) obtained the optimal identification accuracy of 90% in the prediction set. In addition, PCA-ResNet (propagation coefficient adaptive ResNet) and PCSA-ResNet (propagation coefficient synchronous adaptive ResNet) were designed based on typical ResNet structure by changing the way of self-adaption of propagation coefficients. Combined with a new form of input data called spectral matrix, PCSA-ResNet obtained the optimal performance with the discriminate accuracy of 91.75% in the prediction set. T-distributed stochastic neighbor embedding (t-SNE) was used to visualize the clustering process of the extracted features by PCSA-ResNet. For the interpretation of the good performance of PCSA-ResNet coupled with the spectral matrix, saliency maps were further applied to visually show the pixel positions of the spectral matrix that had a significant influence on the discrimination results, indicating that the content and proportion of elements in soybean seeds could reflect the variety differences.

Laser induced breakdown spectroscopy (LIBS) combined with adaptive particle swarm optimization-based radial basis neural network (APSO-RBF) for rapid identification of soils from different regions

“…Dimitrios Stefas et al [19] processed LIBS spectral data of different honey species using PCA, LDA, SVM and RF, and obtained classification accuracies of no less than 95% in all cases, providing an easy-to-use and effective method for honey classification based on floral origin. Li et al [20] combined portable LIBS with a deep convolutional neural network (CNN) to analyze and identify copper concentrates, and the highest classification accuracy reached 96.20%, realizing an effective and fast classification of copper concentrates.…”

Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of Brachiaria brizantha Seed Vigor

“…Thinking about on-field application, the LIBS systems can be a useful alternative, which has been proven as a versatile technique for qualitative and quantitative analysis in agricultural studies through evaluation of several samples [ 14 ] such as rice [ 15 ], maize [ 16 ], grape seeds [ 17 ], cucurbit seeds [ 18 ], coffee beans [ 19 ], and soybean seeds [ 13 , 20 ]. However, there are some critical issues to overcome and a need to provide a reliable method, mainly due to the lack of a consistent protocol, which may consider experimental aspects (number of samples, validation, experimental parameters, software, etc.…”

“…Then, a prediction model was developed by machine learning algorithms using Phyton code. The choice of adequate models and methods used for the analysis of the spectra set is crucial to achieving a good result and fast and accurate analysis [ 20 ]. Finally, an external validation test provided 100% of accuracy for seed vigor classification.…”

Chitosan Homogenizing Coffee Ring Effect for Soil Available Potassium Determination Using Laser-Induced Breakdown Spectroscopy

“…Besides, the development of a portable LIBS instrument has made rapid on-site field detection possible [9,16]. Therefore, LIBS technology can solve the problems above and has been widely used in various fields, including agricultural products [17], industrial application [18], mineral resources [19] and so on. LIBS technology has great potential in the rapid determination of K in the soil solution.…”