Implementasi Machine Learning Dengan Metode KNN, SVM, Dan MLP Dalam Mendeteksi Alergen Makanan Pada Resep Makanan

Assa'ad, Ahmad Hafizh (2024) Implementasi Machine Learning Dengan Metode KNN, SVM, Dan MLP Dalam Mendeteksi Alergen Makanan Pada Resep Makanan. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5025201106-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (1MB) | Request a copy

Abstract

Alergen makanan adalah zat yang dapat memicu reaksi alergi atau intoleransi pada beberapa individu. Menurut data terbaru, prevalensi alergi makanan di seluruh dunia berkisar antara 10% hingga 40%. Di Indonesia, sekitar 20% anak pada tahun pertama mereka mengalami reaksi terhadap makanan yang diberikan. Penelitian ini berfokus untuk mengembangkan model machine learning untuk mendeteksi alergen pada resep makanan, menggunakan metode K-Nearest Neighbors (KNN), Support Vector Machine (SVM), dan Multi-Layer Perceptron (MLP) dengan pendekatan multilabel classification. Masalah utama adalah sulitnya mengidentifikasi alergen tersembunyi dalam bahan-bahan resep yang beragam, yang bisa membahayakan individu dengan alergi makanan.
Penelitian ini menggunakan 15.823 data pada dataset resep makanan yang dilabeli secara manual dan otomatis dengan lima jenis alergen utama. Setelah Preprocessing data dan ekstraksi fitur menggunakan TF-IDF, model dilatih dan diuji dengan rasio 80:20. Hasil menunjukkan bahwa SVM dengan tuning hyperparameter pada dataset pelabelan manual memiliki performa terbaik pada semua jenis alergen, dengan nilai F1-Score mencapai 0,9995 dan 0,9921 untuk deteksi alergen telur dan gandum.
======================================================================================================
Food allergens are substances that can trigger allergic reactions or intolerances in some individuals. According to recent data, the prevalence of food allergies worldwide ranges from 10% to 40%. In Indonesia, around 20% of children in their first-year experience reactions to the foods given to them. This research focuses on developing a machine learning model to detect allergens in food recipes, utilizing K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP) methods with a multilabel classification approach. The primary challenge is the difficulty of identifying hidden allergens in the diverse ingredients of recipes, which can be harmful to individuals with food allergies.
This study utilizes 15,823 data points from a food recipe dataset, labeled both manually and automatically with five main types of allergens. After data Preprocessing and feature extraction using TF-IDF, the models were trained and tested with an 80:20 ratio. Results indicate that the SVM with hyperparameter tuning on the manually labeled dataset performed the best across all allergen types, achieving F1-Scores of 0,9995 and 0,9921 for detecting egg and wheat allergens, respectively.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Alergen Makanan, KNN, Machine Learning, MLP, SVM Food Allergens, KNN, Machine Learning, MLP, SVM
Subjects:	T Technology > T Technology (General) > T57.5 Data Processing
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Ahmad Hafizh Assa'ad
Date Deposited:	31 Jul 2024 12:59
Last Modified:	31 Jul 2024 12:59
URI:	http://repository.its.ac.id/id/eprint/110334

Actions (login required)

View Item