RANCANG BANGUN ELECTRONIC NOSE DENGAN VARIASI SENSOR MQ UNTUK KLASIFIKASI JENIS TEH

HUFFAZ MUHAMMAD ABDURROFI BAITH, . (2024) RANCANG BANGUN ELECTRONIC NOSE DENGAN VARIASI SENSOR MQ UNTUK KLASIFIKASI JENIS TEH. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text COVER.pdf Download (2MB)
	Text BAB I.pdf Download (1MB)
	Text BAB II.pdf Restricted to Repository staff only Download (2MB) | Request a copy
	Text BAB III.pdf Restricted to Repository staff only Download (2MB) | Request a copy
	Text BAB IV.pdf Restricted to Repository staff only Download (2MB) | Request a copy
	Text BAB V.pdf Restricted to Repository staff only Download (1MB) | Request a copy
	Text DAFTAR PUSTAKA.pdf Download (1MB)
	Text LAMPIRAN.pdf Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Berbagai jenis teh di industri membutuhkan alat quality control yang mampu mengklasifikasikan jenis teh untuk mengendalikan waktu fermentasi dan menghasilkan teh yang diinginkan. Penelitian ini bertujuan merancang dan membangun sistem Electronic Nose (E-Nose) berbasis sensor gas MQ untuk mengklasifikasikan teh hijau dan teh hitam. Sistem E-Nose menggunakan 8 sensor gas MQ (MQ2, MQ3, MQ5, MQ6, MQ7, MQ8, MQ9, dan MQ135) dan desain cylindrical chamber sebagai ruang sensor. Fitur yang diekstraksi meliputi nilai maksimum, nilai mean, dan Area Under Curve (AUC). Berdasarkan Mutual Information (MI), dibuat subset fitur dengan 24, 20, 15, 10, dan 5 fitur. Model klasifikasi dibangun menggunakan Support Vector Machine (SVM) dan Artificial Neural Network (ANN) dengan hyperparameter tuning. Kedua model menunjukkan akurasi tidak kurang dari 96% pada proses training, validation, dan testing di semua subset fitur. Penelitian ini membuktikan bahwa sistem E-Nose yang dirancang mampu mengklasifikasikan jenis teh dengan akurasi tinggi, sehingga berpotensi sebagai alat bantu quality control dalam industri teh. Kata Kunci: electronic nose, sensor MQ, ekstraksi fitur, machine learning, jenis teh ***** Various types of tea in the industry require quality control tools that are able to classify tea types to control fermentation time and produce the desired tea. This research aims to design and build an Electronic Nose (E-Nose) system based on MQ gas sensors to classify green tea and black tea. The E-Nose system uses 8 MQ gas sensors (MQ2, MQ3, MQ5, MQ6, MQ7, MQ8, MQ9, and MQ135) and a cylindrical chamber design as the sensor room. The extracted features include maximum value, mean value, and Area Under Curve (AUC). Based on Mutual Information (MI), feature subsets with 24, 20, 15, 10, and 5 features were created. Classification models were built using Support Vector Machine (SVM) and Artificial Neural Network (ANN) with hyperparameter tuning. Both models showed accuracy of no less than 96% in the training, validation, and testing processes across all feature subsets. This research proves that the designed E-Nose system is able to classify tea types with high accuracy, so it has potential as a quality control tool in the tea industry. Keywords: electronic nose, MQ sensor, feature extraction, machine learning, tea type

Item Type:	Thesis (Sarjana)
Additional Information:	1.) Dr.rer.nat. Bambang Heru Iswanto, M.Si. 2.) Haris Suhendar, M.Sc.
Subjects:	Sains > Fisika
Divisions:	FMIPA > S1 Fisika
Depositing User:	Users 24818 not found.
Date Deposited:	14 Aug 2024 04:07
Last Modified:	14 Aug 2024 04:07
URI:	http://repository.unj.ac.id/id/eprint/49926

Actions (login required)

View Item