The potency of Vis/NIR spectroscopy for classification of soybean based of colour

• Main Authors: Pahlawan, M. F. R., Murti, B. M. A, Masithoh, Rudiati Evi
• Format: Conference or Workshop Item PeerReviewed
• Language: English
• Published: Institute of Physics 2022
• Subjects: Sustainable Agricultural Development; Crop and Pasture Post Harvest Technologies (incl. Transportation and Storage); Post Harvest Horticultural Technologies (incl. Transportation and Storage)
• Online Access: https://repository.ugm.ac.id/282754/1/Pahlawan_2022_IOP_Conf._Ser.__Earth_Environ._Sci._1018_012015.pdf; https://repository.ugm.ac.id/282754/; https://www.scopus.com/inward/record.uri?eid=2-s2.0-85129791216&doi=10.1088%2f1755-1315%2f1018%2f1%2f012015&partnerID=40&md5=fee243dde2524b25fa4b32c9fcc98c88
• Institution: Universitas Gadjah Mada

Soybean in various colour is easy to identify using human eyes. However, it is hard to perform manual method for on-line production. Therefore, detection of colour for sorting the soybean is important especially for industries which require a rapid and real-time task. This research was conducted to study the potency of a modular type of VIS/NIR spectroscopy at wavelength of 350-1000 nm to classify black, green, and yellow of soybean seed and flour. Principal component analysis (PCA) and PCA Linear discriminant analysis (PCA-LDA) were used based on various spectra pre-processing techniques. Results showed that PCA-LDA model was able to classify soybean seeds of 97 accuracy and soybean flour of 100 accuracy. © Published under licence by IOP Publishing Ltd.