Perbandingan Performa Naïve Bayes & Knearest Neighbor dalam Mengklasifikasi Status Pasien Coronavirus Disease (Covid-19)

Danang, Wicaksana (2021) Perbandingan Performa Naïve Bayes & Knearest Neighbor dalam Mengklasifikasi Status Pasien Coronavirus Disease (Covid-19). Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text COVER.pdf Download (457kB)
	Text ABSTRACT.pdf Download (65kB)
	Text ABSTRAK.pdf Download (67kB)
	Text BAB I.pdf Download (241kB)
	Text BAB II.pdf Download (299kB)
	Text BAB III.pdf Download (535kB)
	Text BAB IV.pdf Restricted to Registered users only Download (159kB) | Request a copy
	Text BAB V.pdf Download (67kB)
	Text DAFTAR PUSTAKA.pdf Download (148kB)
	Text LAMPIRAN.pdf Restricted to Registered users only Download (134kB) | Request a copy

Abstract

There is no priority for the treatment of COVID-19 patients based on Age, Gender, and Nationality attributes, therefore a comparison of the performance of 2 algorithms, namely Naive Bayes and K-Nearest Neighbor, is to classify the status of COVID-19 patients based on Age, Gender, and Nationality attributes. The dataset used to conduct classification is the COVID-19 dataset for Indonesia and India which is accessed from the Kaggle website,, namely https://www.kaggle.com/ardisragen/indonesia-coronavirus-cases?select=pati ent.csv for the Indonesian dataset and https://www.kaggle.com/sudalairajkumar/covid19-in-india/version/204?select =IndividualDetails.csv for the Indian dataset. The method used in this research is Naïve Bayes and K-nearest Neighbor. By using the confusion matrix measurement method, the results obtained from the K-Nearest Neighbor algorithm have a better accuracy rate of 90.416%, while Naïve Bayes has an accuracy rate of 85%. The precision obtained by Naïve Bayes is 24% for released class, 0.93% for an isolated class, and 0% for the deceased class. The recall obtained by Naïve Bayes is 35% for a released class, 0.91% for isolated class, and 0% for a deceased class. The precision obtained by a K-Nearest Neighbor is 0% for released class, 91% for isolated class, and 0% for deceased class. The recall obtained by a K-Nearest Neighbor is 0% for released class, 100% for isolated class, and 0% for deceased class. Keyword: Coronavirus, COVID-19, Classification, Naïve Bayes, K-Nearest Neighbor

Actions (login required)

View Item