Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JUTIK : Jurnal Teknologi Informasi dan Komputer Journal of Education Technology Information Social Sciences and Health
Ayman Human Sukma
Universitas Negeri Medan
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Engineering Neuroscience Nursing Public Health Social Sciences

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Optimasi Estimasi Intensitas Guncangan Gempa Skala MMI Menggunakan XGBoost Berdasarkan Parameter Seismik dan GMPE Felix John Pardamean Hutabarat; Ayman Human Sukma; Azhara Amelia H; Rinto Manik; Sehati Saurmatania Tampubolon; Suvriadi Panggabean
Journal of Education Technology Information Social Sciences and Health Vol. 5 No. 2 (2026): September 2026
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/jetish.v5i2.8966

Abstract

Indonesia merupakan wilayah dengan aktivitas seismik tinggi sehingga estimasi intensitas guncangan gempa yang akurat menjadi komponen penting dalam mitigasi bencana. Persamaan empiris Ground Motion Prediction Equations (GMPE) banyak digunakan untuk mengestimasi intensitas guncangan, namun memiliki keterbatasan dalam merepresentasikan hubungan nonlinier antara parameter seismik dan kondisi lokal. Penelitian ini bertujuan mengembangkan model estimasi Modified Mercalli Intensity (MMI) berbasis physics-informed machine learning dengan mengombinasikan algoritma XGBoost dan GMPE. Dataset yang digunakan berasal dari arsip USGS ShakeMap wilayah Indonesia periode 2004–2025 yang mencakup 528 kejadian gempa dan 6.222 rekaman observasi. Tahapan penelitian meliputi pra-pemrosesan data, rekayasa fitur, perhitungan estimasi awal menggunakan GMPE, pelatihan model XGBoost, serta evaluasi menggunakan Group K-Fold Cross Validation melalui studi ablasi. Hasil penelitian menunjukkan bahwa model hibrida mampu mengatasi keterbatasan model machine learning murni sekaligus mempertahankan stabilitas pendekatan empiris. Model menghasilkan nilai Mean Absolute Error (MAE) 0,435 skala MMI, dengan prediksi GMPE sebagai fitur paling dominan berdasarkan analisis feature importance. Model terbaik selanjutnya diimplementasikan ke dalam prototipe berbasis ONNX yang mampu melakukan estimasi intensitas guncangan secara real-time. Hasil penelitian menunjukkan bahwa pendekatan hibrida berpotensi mendukung sistem peringatan dini dan pengambilan keputusan dalam mitigasi bencana gempa bumi.
KLASIFIKASI STATUS MAHASISWA MENGGUNAKAN ALGORITMA XGBOOST PADA DATASET AKADEMIK Muhammad Rizki Andrian Fitra; Neysa Talitha Jehian; Thania Dealva Arsyad; Ayman Human Sukma; Arnita; Fanny Ramadhani
Jurnal Teknologi Informasi dan Komputer Vol. 12 No. 2 (2026): JUTIK : Jurnal Teknologi Informasi dan Komputer, Edisi Oktober 2026
Publisher : LPPM Universitas Dhyana Pura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36002/jutik.v12i2.3997

Abstract

Monitoring student academic status is an important aspect of supporting the effectiveness of higher education systems. This study aims to classify student status—Dropout, Enrolled, and Graduate—using the XGBoost algorithm on an academic dataset from Kaggle consisting of 4424 entries and 37 features. The research was conducted using a quantitative approach and computational experiment methods. The stages included data pre-processing, training and testing data split (80:20 ratio), model training, and evaluation using classification metrics such as accuracy, precision, recall, and F1-score. The results showed that the XGBoost model was able to classify student status with an accuracy of 79.9%. Further evaluation revealed that the model performed well on the majority class (Graduate), but had low performance on the minority class (Enrolled), especially with recall of 0,48. This indicates challenges in dealing with imbalanced class distributions. Therefore, the use of data balancing techniques must be implemented, thus the accuracy by the model reached 82,65%, for further refining and improving its performace, hyperparameter tuning is recommended for it. The results of this study are expected to assist educational institutions in detecting potential dropouts earlier and supporting data-driven decision making.
Co-Authors Arnita Azhara Amelia H Felix John Pardamean Hutabarat Muhammad Rizki Andrian Fitra Neysa Talitha Jehian Ramadhani, Fanny Rinto Manik Sehati Saurmatania Tampubolon Suvriadi Panggabean Thania Dealva Arsyad