Penggunaan electronic nose dan metode K-Nearest Neighbors (K-NN) dalam mendeteksi daging sapi dan babi

Temiesela, Agung Wijaya (2024) Penggunaan electronic nose dan metode K-Nearest Neighbors (K-NN) dalam mendeteksi daging sapi dan babi. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text (COVER)
1_cover.pdf

Download (254kB) | Preview
[img]
Preview
Text (ABSTRAK)
2_abstrak.pdf

Download (136kB) | Preview
[img]
Preview
Text (DAFTAR ISI)
3_daftarisi.pdf

Download (136kB) | Preview
[img]
Preview
Text (BAB I)
4_bab1.pdf

Download (121kB) | Preview
[img] Text (BAB II)
5_bab2.pdf
Restricted to Registered users only

Download (2MB) | Request a copy
[img] Text (BAB III)
6_bab3.pdf
Restricted to Registered users only

Download (13MB) | Request a copy
[img] Text (BAB IV)
7_bab4.pdf
Restricted to Registered users only

Download (741kB) | Request a copy
[img] Text (BAB V)
8_bab5.pdf
Restricted to Registered users only

Download (110kB) | Request a copy
[img] Text (DAFTAR PUSTAKA)
9_daftarpustaka.pdf
Restricted to Registered users only

Download (147kB) | Request a copy

Abstract

INDONESIA : Permintaan akan daging sapi di Indonesia terus meningkat seiring dengan pertumbuhan jumlah penduduk, namun pertumbuhan produksi daging sapi tidak sebanding. Kondisi ini memberi peluang bagi pedagang nakal untuk mencampur daging sapi dengan daging babi guna memperoleh keuntungan yang lebih besar melalui penjualan. Sebagai negara dengan jumlah Muslim terbesar di dunia, Indonesia mendorong adopsi gaya hidup halal yang meliputi berbagai aspek kehidupan, termasuk aspek pangan. Penelitian ini bertujuan untuk membedakan antara daging sapi dan daging babi, baik dalam keadaan murni maupun saat dicampur, menggunakan sistem Electronic Nose (E-Nose). Sistem E-Nose pada penelitian ini terdiri dari 16 sensor gas, yaitu sensor Gas MQ dan TGS, yang dirancang untuk mengukur tingkat gas dalam proses membedakan daging sapi dan daging babi. Gas yang terdeteksi dalam daging sapi dan babi dikonversi menjadi sinyal analog to digital converter (ADC) oleh Arduino, kemudian diubah menjadi parts per million (PPM). Nilai PPM yang dihasilkan diuji dan disimpan dalam database yang terletak di Raspberry Pi 4. Klasifikasi daging sapi dan babi dilakukan menggunakan metode K-NN. Evaluasi analisis mencakup akurasi, presisi, recall, F1-score, dan confusion matrix. Akurasi hasil prediksi yang didapat dari metode K-NN adalah 99.65% untuk K = 3, sedangkan untuk parameter lainnya, yaitu K = 11, menghasilkan akurasi 98.43%. Oleh karena itu, penelitian ini mampu membedakan secara efektif antara daging sapi dan babi, baik dalam keadaan murni maupun saat dicampur, sehingga memungkinkan individu untuk menghindari konsumsi makanan yang diharamkan (haram) dan menanggulangi praktik curang oleh pedagang. ENGLISH : The demand for beef in Indonesia continues to increase alongside population growth, yet the growth in beef production is not proportional. This condition provides an opportunity for unscrupulous traders to mix beef with pork to gain greater profits through sales. As the country with the largest Muslim population in the world, Indonesia promotes the adoption of a halal lifestyle encompassing various aspects of life, including food. This research aims to distinguish between beef and pork, both in their pure form and when mixed, using the Electronic Nose (E-Nose) system. The E-Nose system in this study consists of 16 gas sensors, namely MQ and TGS gas sensors, designed to measure gas levels in the process of differentiating between beef and pork. The gases detected in beef and pork are converted into analog to digital converter (ADC) signals by Arduino, then converted into parts per million (PPM). The resulting PPM values are tested and stored in a database located on Raspberry Pi 4. Beef and pork classification is performed using the K-Nearest Neighbors (KNN) method. Evaluation analysis includes accuracy, precision, recall, F1-score, and confusion matrix. The accuracy of the prediction results obtained from the KNN method is 99.65% for K=3, while for other parameters, namely K=11, it yields an accuracy of 98.43%. Therefore, this research is able to effectively distinguish between beef and pork, both in their pure form and when mixed, enabling individuals to avoid consuming prohibited (haram) food and counteracting fraudulent practices by traders.

Item Type: Thesis (Sarjana)
Uncontrolled Keywords: Electronic Nose; K-Nearest Neighbors; Raspberry Pi 4
Subjects: Technology, Applied Sciences
Divisions: Fakultas Sains dan Teknologi > Program Studi Fisika
Depositing User: Agung Wijaya Temiesela
Date Deposited: 27 May 2024 09:15
Last Modified: 28 May 2024 02:05
URI: https://digilib.uinsgd.ac.id/id/eprint/88124

Actions (login required)

View Item View Item