Implementasi Machine Learning Untuk Memprediksi Tingkat Stres Berdasarkan Gaya Hidup

Rahman, Widyasmara Afif Nur and , Endang Wahyu Pamungkas, S.Kom., M.Kom, Ph.D (2024) Implementasi Machine Learning Untuk Memprediksi Tingkat Stres Berdasarkan Gaya Hidup. Skripsi thesis, Universitas Muhammadiyah Surakarta.

BACA FULLTEXT
[img] PDF (Surat Pernyataan Publikasi)
UNGGAH Widyasmara.pdf
Download (303kB)
[img] PDF (Naskah Publikasi)
Naskah Publikasi.pdf
Download (571kB)

Abstract

Stress is a major issue today, especially in the younger generation. This mental problem can lead to various problems such as depression, heart attacks, stress and worse, suicide. The aim of this research is to predict stress levels based on a person's lifestyle. The author will conduct a factor analysis of lifestyle factors and look for correlations between lifestyle factors and stress levels. The dataset for this research was taken from Kaggle and consists of 15,977 data. The classification algorithms used are Support Vector Machine (SVM) and Random Forest. Accuracy will be used as a performance parameter. Next, a better algorithm will be determined that will be used to deploy using Streamlit. Then the application will be tested using the System Usability Scale method. Model building will be carried out in three experiments, without data modification, Category Grouping, and Category Grouping and Handling Imbalance data. From the experiments carried out, the highest accuracy was obtained at 0.7667 using a model with Category Grouping and ROS. The model obtained was then made into a simple website with streamlit. The website created had three page sections, namely a landing page, a data entry page, and a prediction results page. The system created was tested using the System Usability Scale (SUS) with 30 respondents and obtained an average score of 76.5 in the Good and Acceptable category with grade C.

Item Type: Thesis (Skripsi)
Uncontrolled Keywords: machine learning, stress, classification, svm, random forest, streamlit
Subjects: T Technology > TZ Technical Information
Divisions: Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika
Depositing User: WIDYASMARA AFIF NUR RAHMAN
Date Deposited: 06 Aug 2024 03:53
Last Modified: 06 Aug 2024 03:56
URI: http://eprints.ums.ac.id/id/eprint/125907

Actions (login required)

View Item View Item
UMS ETD-db is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.