Article Per Year (5 Year)
p-Index From 2021 - 2026
1.978
P-Index
This Author published in this journals
All Journal Telematika Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jurnal Abdimas BSI: Jurnal Pengabdian Kepada Masyarakat JOURNAL OF APPLIED INFORMATICS AND COMPUTING JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Jurnal Abdi Insani Abdimasku : Jurnal Pengabdian Masyarakat Jurnal Pengabdian Masyarakat Indonesia Jurnal Elektrosista The Indonesian Journal of Computer Science
Bambang Pilu Hartato
Universitas Amikom Yogyakarta
Agriculture, Biological Sciences & Forestry Humanities Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Public Health Social Sciences

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
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
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%.
ANALISIS PERFORMA ARSITEKTUR CNN INCEPTIONV3 DAN VGG16 DALAM KLASIFIKASI DETEKSI KANKER OTAK Wicaksono, Aryo Bimo; Hartato, Bambang Pilu
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 2 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i2.6090

Abstract

Kanker otak merupakan salah satu jenis kanker paling mematikan dengan tingkat kematian yang tinggi. Keterlambatan dalam diagnosis dan rendahnya kesadaran masyarakat menjadi faktor utama tingginya angka kematian tersebut, sehingga diperlukan metode deteksi yang efektif untuk diagnosis dini. Penelitian ini bertujuan untuk mengevaluasi kinerja dua arsitektur Convolutional Neural Network (CNN), yaitu InceptionV3 dan VGG16, dalam klasifikasi deteksi kanker otak menggunakan dataset MRI berlabel dari Kaggle. Langkah-langkah penelitian meliputi pengumpulan dataset, Analisis Data Eksplorasi (EDA), preprocessing, pembuatan model, dan evaluasi kinerja model. Hasil penelitian menunjukkan bahwa model InceptionV3 mencapai akurasi sebesar 91,67% dengan test loss 0,3329, sementara VGG16 mencapai akurasi sebesar 82,14% dengan test loss 0,5027. Model VGG16 mengalami fluktuasi signifikan dibandingkan dengan InceptionV3, yang mengindikasikan adanya overfitting. Selain itu, InceptionV3 menunjukkan hasil precision, recall, dan F1-score yang lebih tinggi dibandingkan dengan VGG16. Evaluasi menggunakan confusion matrix menunjukkan bahwa InceptionV3 memiliki performa yang lebih baik dalam memprediksi kanker otak dengan jumlah kesalahan prediksi yang lebih rendah dibandingkan dengan VGG16. Hasil ini menunjukkan bahwa InceptionV3 lebih andal dan akurat dalam mendeteksi kanker otak dibandingkan dengan VGG16.
Co-Authors Abdul Mizwar A. Rahim Agung Prakoso Ahmad Ridwan Alfinsyah, Dimas Ramadhan Asharudin, Firman Chyntia Raras Ajeng Widiawati Danang Wijayanto Danty Kusumaningtyas Dharmasaputra, Kevin Dicky Fiby Nur Afiana Hasri Akbar Awal Rozaq Mitra Yulianti Nila Feby Puspitasari Nur Athif Oldika Gunawan Retno Waluyo Riwanto, Yudha Saeful Haq Faruqi Suliswaningsih Uswatun Hasanah Wajar Bimantoro, Wajar Wicaksono, Aryo Bimo