SISTEM KLASIFIKASI RASA KOPI BERBASIS ELECTRONIC TONGUE MENGGUNAKAN MADALINE NEURAL NETWORK

• Main Authors: , YUDI ANOM PRIAMBUDI, , Dra. Sri Hartati
• Format: Theses and Dissertations NonPeerReviewed
• Published: [Yogyakarta] : Universitas Gadjah Mada 2013
• Subjects: ETD
• Online Access: https://repository.ugm.ac.id/127040/; http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=67282
• Institution: Universitas Gadjah Mada

This research is motivated by the lack of the nowadays taste sensor development and this study aims ti implement eight computer-based taste sensor with Decyl Alcohol (DA), Oleic Acid (OA), Dioctyl Phosphate (DOP), Trioctylmethyl ammonium chloride (TOMA), Dodecylamine(DDC), DA:OA 5:5, DA:DOP 5:5, and DDC:TOMA 5:5 membranes with semi auto sampler and it could show the measuring result and store the data from eight sensors as one. System implemented on few instant coffees, and patterned characterization on the coffees with physical detection comparation. The membrane character testing was did everyday with some instant coffee samples and then the pattern characterization be done. Tool that used as ADC was PhidgetInterFaceKit 8/8/8 that was an electrometer for this research. And uses program based on Microsoft Visual Basic 2010 as the interface so it can be interacted with the tool. And used the toolbox ofMatlab R2009a program for madaline neural networkutilization. The results showed a pattern characterized using this system can be identified using themadaline neural network. Data results from this system can be stored in the form ofexcel.