Classification of The Coffee Roasting Level Based On Electronic Nose
Penulis/Author
Dr. Danang Lelono, S.Si., M.T. (1); LUTHFI SATRIO ADI (2); Dr. Andi Dharmawan, S.Si., M.Cs. (3); Muhammad Idham Ananta Timur, M.Kom. (5)
Tanggal/Date
8 2022
Kata Kunci/Keyword
Abstrak/Abstract
Coffee beans must be roasted before serving for drinks. While the taste of coffee is largely determined by the
quality and results of the roasted beans. So far, testing the aroma of coffee is still using the eyes, tongue and nose of people
who are experts in their fields. Electronic nose exists as a device with the design to imitate human smell. This instrument can be
used classify coffee's aroma based on the roasting level that is commonly used as a non-subjective method. Four types of
Arabica coffee bean roasting level which are green, light, medium, and dark are used as an input to the electronic nose.
Ten gas sensors as detector system, and the data acquisition consist of one cycle per sample which includes five phases of
collecting phase. After pre-processing and feature extraction has been done to the data set, analysis is carried out using
Principal Component Analysis (PCA) and K-Nearest Neighbour (KNN). The Results show the best K value of the KNN method
for the sample is K=5, a system performance evaluation shows the test data and training data into 5-fold with an accuracy value
of 67.5%, a precision value of 70.22%, and a recall value of 67.5%.
