Application of deep learning and near infrared spectroscopy in cereal analysis

•A method for quickly analyzing cereal characteristics.•The method is based on deep learning and near infrared spectroscopy.•Uses stacked sparse autoencoder to extract features of near infrared spectral data.•A near infrared spectroscopy analysis model was proposed.•Compared with other methods, the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Vibrational spectroscopy Ročník 106; s. 103009
Hlavní autor: Le, Ba Tuan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.01.2020
Témata:
Cereal analysis
Deep learning
Extreme learning machine
Near-Infrared spectroscopy
sTacked sparse autoencoder
Deep learning
Near-Infrared spectroscopy
Cereal analysis
Extreme learning machine
sTacked sparse autoencoder
ISSN:0924-2031, 1873-3697
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•A method for quickly analyzing cereal characteristics.•The method is based on deep learning and near infrared spectroscopy.•Uses stacked sparse autoencoder to extract features of near infrared spectral data.•A near infrared spectroscopy analysis model was proposed.•Compared with other methods, the method proposed has better predictive ability. Deep learning is an important research achievement of artificial intelligence in recent years and has received special attention from scientists around the world. This study applies deep learning to spectral analysis techniques and proposes a rapid analysis method for cereals. First, the advanced features of the near infrared spectroscopy (NIR) were extracted by the deep learning-stacked sparse autoencoder (SSAE) method, and then the prediction model is built using the affine transformation (AT) and the extreme learning machine (ELM). Experiments were conducted on corn and rice data sets to verify the effectiveness of the method. The results show that the proposed method achieves good prediction results and is superior to other typical NIR analysis methods.
ISSN:0924-2031
1873-3697
DOI:10.1016/j.vibspec.2019.103009