Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm

• Autor(a) principal: ZOU,Zhiyong
• Data de Publicação: 2022
• Outros Autores: CHEN,Jie, WANG,Li, WU,Weijia, YU,Tingjiang, WANG,Yuchao, ZHAO,Yongpeng, HUANG,Peng, LIU,Bi, ZHOU,Man, LIN,Ping, XU,Lijia
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Food Science and Technology (Campinas)
• Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0101-20612022000101301
• topic: hyperspectral; mildew; optuna; LightGBM

Abstract In order to realize the rapid nondestructive detection of mildew peanut in the process of peanuts storage, hyperspectral imaging technology was proposed to detect mildew peanut. A total of 200 peanuts were selected from 5 kinds of peanuts purchased in the market for moldy treatment, and the remaining 400 peanuts were kept sterile. After completion, samples were collected with a hyperspectral instrument to obtain spectral data of the samples. According to the characteristics of the data, 10 pre-processing algorithms were used to de-noise the data, and Median Filtering (MF) had the best effect, with the recognition accuracy reaching 97.7%. GBDT, LightGBM, CatBoost and XGBoost algorithms were used to extract important feature bands in the spectral data pre-processed by MF. GBDT, LightGBM, CatBoost and XGBoost algorithms were used to model the extracted feature bands. The results showed that LightGBM is the best algorithm with a detection rate of 99.10%. Optuna algorithm was used to tune its parameters. Compared with the previous model, the running time of the optimized model was improved by about 0.25 s. The results showed that hyperspectral imaging provides an efficient and nondestructive method for detecting mildew in peanut storage.