The comparison of decision tree and k-NN to analyze fertility using 2 different filters

Open

N. Rochmawati, H.B. Hidayati, Y. Yamasari, I.G.P. Asto, L. Rakhmawati

2018 IOP Conference Series: Materials Science and Engineering Vol. 434 Issue 1 Conference paper Cited by 0 SDG 5SDG 17 Quartile

Abstract

Fertility is a crucial issue for married couples for ages and a significant clinical problem today. Not only do women have an undue burden of responsibility in fertility regulation but also men. There are some major causes and risk factors for male infertility i.e., environmental factors, life style factors etc. In this paper, we will analyse the infertility using two algorithms, decision tree and k-nearest neighbours. We will do experiments using different splits of training data and different filters. The purpose is to determine which algorithm is more accurate between 2 algorithms either using filter or not. The result shows DT has better performance in accuracy when using dataset without filter and when using randomize filter while k-NN has better performance when using resample filter. © Published under licence by IOP Publishing Ltd.

Affiliations

Department of Informatics, Engineering Faculty, Universitas Negeri Surabaya, Surabaya, Indonesia; Department of Electrical Engineering, Engineering Faculty, Universitas Negeri Surabaya, Surabaya, Indonesia; Department of Neurology, Medical Faculty, Airlangga University, Surabaya, Indonesia; Department of Electrical Engineering, Engineering Faculty, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia

Research at a Glance

Premium content — register to unlock

Research at a Glance

Register to unlock

Topics & SDG Alignment

Premium content — register to unlock

Topics & SDG Alignment

Register to unlock

Collaboration

Premium content — register to unlock

Collaboration

Register to unlock

Author Profile (Selected)

Premium content — register to unlock

Author Profile (Selected)

Register to unlock

References Overview

Premium content — register to unlock

References Overview

Register to unlock

Journal & Source

Premium content — register to unlock

Journal & Source

Register to unlock

Metadata & Integrity

Premium content — register to unlock

Metadata & Integrity

Register to unlock