Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi Journal of Economic, Management, Accounting and Technology (JEMATech)
Bisono, Hadi Hikmadyo
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Electrical & Electronics Engineering

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

Found 2 Documents
Search

 1 
Aplikasi Prediksi Banjir Menggunakan Algoritma XGBoost Berbasis Website Asnawi, Muhamad Fuat; Bisono, Hadi Hikmadyo; Megantara, Muhamad Arldi; Kusrini, Kusrini
Journal of Economic, Management, Accounting and Technology (JEMATech) Vol 7 No 2 (2024): Agustus
Publisher : Fakultas Teknik dan Ilmu Komputer, Universitas Sains Al-Qur'an (UNSIQ) Wonosobo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32500/jematech.v7i2.7644

Abstract

Penelitian ini bertujuan untuk mengembangkan model prediksi risiko banjir menggunakan algoritma XGBoost dengan memanfaatkan dataset yang tersedia di Kaggle. Dataset tersebut mencakup berbagai faktor yang mempengaruhi risiko banjir seperti kualitas bendungan, pengikisan sistem drainase, longsor, dan hilangnya lahan basah. Proses penelitian dimulai dengan pengumpulan data, diikuti oleh preprocessing yang meliputi penanganan missing values, pemilihan fitur menggunakan regresi untuk memastikan fitur yang paling berpengaruh, dan normalisasi data. Model XGBoost kemudian dilatih dengan data yang telah diproses dan dievaluasi menggunakan beberapa metrik evaluasi. Hasil evaluasi menunjukkan bahwa model memiliki performa yang sangat baik dengan nilai Cross-Validation RMSE sebesar 0.00097, Mean Squared Error (MSE) sebesar 1.0336, Root Mean Squared Error (RMSE) sebesar 0.001017, Mean Absolute Error (MAE) sebesar 0.000801, dan Mean Absolute Percentage Error (MAPE) sebesar 0.1605%. Nilai-nilai ini mengindikasikan kesalahan prediksi yang relatif kecil. Visualisasi hasil juga menunjukkan bahwa model tidak memiliki bias sistematis dan kesalahan prediksi tersebar merata. Penelitian ini mendesak mengingat peningkatan frekuensi dan dampak banjir akibat perubahan iklim dan urbanisasi yang pesat. Model ini diharapkan dapat digunakan secara efektif untuk memberikan peringatan dini dan membantu dalam perencanaan tata ruang yang lebih baik untuk mengurangi dampak bencana banjir.
Simple Selection Index (SSI) Method in Electric Vehicle Selection for Logistics Companies Bisono, Hadi Hikmadyo; Utami, Ema
SISTEMASI Vol 14, No 5 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i5.5434

Abstract

The rapid development of electric vehicles (EVs) has encouraged various industrial sectors, including logistics, to transition from fossil fuel-based vehicles to more environmentally friendly solutions. While EVs offer advantages such as energy efficiency, reduced carbon emissions, and lower operating costs, selecting the right electric vehicle for a logistics company is not a straightforward task. The main challenge lies in the wide variety of available models, each with different technical and operational specifications. This complexity increases as companies must consider multiple criteria such as price, payload capacity, vehicle width, battery capacity, and cargo volume. Therefore, a systematic approach is needed to support decision-making. One commonly used approach is the Multi-Criteria Decision-Making (MCDM) method. This study introduces the Simple Selection Index (SSI) method, a newly developed MCDM approach designed as a simplified version of the Preference Selection Index (PSI) method. The novelty of SSI lies in its ability to eliminate complex steps such as the calculation of preference variation values and preference deviation scores, making the ranking process more concise and easier to apply—without compromising the accuracy of the results. The study aims to evaluate the performance of the SSI method in selecting the most suitable electric vehicle by directly comparing its results with those of the PSI method, using a dataset comprising four vehicle alternatives and five key criteria: price, payload, width, battery capacity, and cargo volume. The findings show that the SSI method produces an identical ranking to the PSI method, with EV-4 as the top recommendation and EV-1 as the second-best alternative. With its more efficient process, the SSI method holds strong potential for application in fast and straightforward multi-criteria decision-making scenarios.
Co-Authors Asnawi, Muhamad Fuat Ema Utami Kusrini, Kusrini Megantara, Muhamad Arldi