Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal UG Journal Jurnal Sisfokom (Sistem Informasi dan Komputer) JURNAL AKUNTANSI KEUANGAN DAN MANAJEMEN The Indonesian Journal of Computer Science
Danang Wijayanto
Politeknik Negeri Jakarta
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Health Professions Mathematics

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : The Indonesian Journal of Computer Science

 1 
Analisis Perbandingan Performa Algoritma XGBoost dan LightGBM pada Klasifikasi Kanker Payudara Wijayanto, Danang; Bambang Pilu Hartato
The Indonesian Journal of Computer Science Vol. 13 No. 2 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i2.3901

Abstract

Breast cancer is one of the most common types of cancer and attacks women throughout the world. Judging from death cases, breast cancer is in second place in deaths caused by cancer. The fine needle aspiration method is one way to detect breast cancer early, but there are several disadvantages such as limited samples which affect the accuracy of the diagnosis or dependence on the skill and experience of the person carrying out the method. Machine learning is considered to be able to help overcome problems in the health sector, including being able to diagnose whether someone has cancer or not using the XGBoost and LightGBM algorithms. XGBoost and LightGBM are efficient algorithms for learning and have differences in learning strategies, namely level-wise and leaf-wise. This research will compare the accuracy, sensitivity and specificity performance of two algorithms, namely XBoost and LightGBM, to see which algorithm can perform better classification. From the experimental results, it was found that XGBoost had better performance by obtaining an average accuracy of 97.03%, an average sensitivity of 97.40% and an average specificity of 96.81%, while LightGBM obtained an average accuracy of 95.59%, average sensitivity 94.70% and average specificity 96.10%.
Co-Authors Acihmah Sidauruk Bambang Pilu Hartato Dianwicaksih Arieftiara Mulia Sulistiyono Rahayu, Andini Dwi Robert Marco, Robert