Identifikasi Jenis Bubuk Kopi menggunakan Electronic Nose dengan Metode Pembelajaran Backpropagation

Abstract

The development of technology allows the creation of a system in a manner resembling a nose job, the electronic nose (e-nose). E-nose can be utilized in various application fields, one of which is to distinguish the type of coffee. There are two main types of coffee, Arabica (Coffea arabica) and robusta (Coffea Robusta). Coffee has different characteristics and unique for its kind. Characteristics of coffee can be determined based on the gas content of coffee using e-nose. This device consists of 5 units of gas sensors that TGS 2610, TGS 2611, TGS 2602, TGS and TGS 2620 822. The pattern of data obtained from the respective resistance change, if the sensors detect coffee that resulted in a change in voltage. Pattern data will be processed using backpropagation neural network. Backpropagation architecture used is formed from the 5 input nodes, 6 hidden nodes and 2 output nodes. The result are expected to distinguish between arabica and robusta and be able to recognize the state of free air (without coffee). The test showed backpropagation NN able to identify with a success rate of 40% for arabica, robusta and 100% to 100% for free air (without coffee). Keywords