perbandingan metode KNN dan Logistic Regression dalam penerapan machine learning untuk klasifikasi potensi bencana banjir

Dennis, Dennis (2023) perbandingan metode KNN dan Logistic Regression dalam penerapan machine learning untuk klasifikasi potensi bencana banjir. Bachelor thesis, Universitas Pelita Harapan.

Preview	Text (Title) Title.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (32kB) | Preview
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (192kB) | Preview
Preview	Text (ToC) ToC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (478kB) | Preview
Preview	Text (Chapter1) Chapter1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (567kB) | Preview
	Text (Chapter2) Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
	Text (Chapter3) Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter4) Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter5) Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (189kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (324kB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (3MB)

Abstract

The most frequent and harmful natural disasters that affect large-scale societies are floods. The goal of this project is to create a model that uses machine learning approaches to anticipate the likelihood of flood disasters, offering early warning to avert or limit damage. The KNN and Logistic Regression approaches are used in this study to forecast the likelihood of flood disasters. The dataset utilized is the Kerala rainfall dataset, which includes 118 data points from 2018 to 2018. The research will be managed and carried out in Google Collab with the Phyton programming language. KNN and Logistic Regression produce accuracy scores of 88.89% and 91.67%, respectively, based on the outcomes of the planned training and testing data. Based on the achieved accuracy rate target, the outcomes of this study are judged suitable for implementation in anticipating the potential of flood disasters./ Bencana banjir merupakan salah satu bencana yang selain sering terjadi, juga merugikan dan memberikan dampak kepada masyarakat dalam skala besar. Penelitian bertujuan untuk merancang model dengan memanfaatkan metode machine learning untuk memprediksi potensi bencana banjir sehingga dapat memberikan peringatan awal potensi bencana banjir. Penelitian ini menggunakan metode KNN dan Logistic Regression untuk memprediksi potensi bencana banjir. Data set yang digunakan adalah data set curah hujan Kerala berjumlah 118 data dari tahun 2018 sampai 2018. Penelitian ini akan dikelola dan dilakukan di Google Collab dengan bahasa pemrograman Python. Berdasarkan hasil data training dan data testing yang telah dirancang, KNN dan Logistic Regression menghasilkan tingkat akurasi (accuracy score) sebesar 88.89% dan 91.67%. Hasil penelitian ini dinilai layak untuk diimplementasikan untuk memprediksi potensi bencana banjir berdasarkan target hasil tingkat akurasi yang didapat.

Actions (login required)

View Item