Abstrak-Perkembangan teknologi memungkinkan penciptaan sebuah sistem dengan cara kerja menyerupai hidung, yaitu electronic nose (e-nose). E-nose dapat dimanfaatkan dalam berbagai bidang aplikasi, salah satunya untuk membedakan jenis kopi. Terdapat dua jenis utama kopi, yaitu kopi arabika (Coffea Arabica) dan kopi robusta (Coffea Robusta). Kopi memiliki karakteristik yang berbeda dan unik untuk masing -masing jenisnya. Karakteristik kopi dapat ditentukan berdasarkan kandungan gas pada kopi menggunakan e-nose. Perangkat ini terdiri dari 5 unit sensor gas yaitu TGS 2610, TGS 2611, TGS 2602, TGS 2620 dan TGS 822. Pola data diperoleh dari perubahan resistansi masing -masing sensor apabila mendeteksi aroma kopi yang mengakibatkan perubahan tegangan. Pola data tersebut akan diolah menggunakan jaringan saraf tiruan (JST) backpropagation. Arsitektur JST backpropagation yang digunakan dibentuk dari 5 node input, 6 node hidden dan 2 node output. Hasil output JST backpropagation yang diharapkan dapat membedakan kopi arabika dan robusta serta mampu mengenali keadaan udara bebas (tanpa kopi). Hasil pengujian memperlihatkan JST backpropagation mampu melakukan identifikasi dengan tingkat keberhasilan 40 % untuk arabika, 100 % untuk robusta dan 100 % untuk udara bebas (tanpa kopi). Kata Kunci : Electronic Nose, Jaringan saraf tiruan, JST backpropagationAbstract-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).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.