Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal SINTECH (Science and Information Technology) Journal Jurnal Tekno Kompak
Firgiawan, Wawan
Unknown Affiliation
Computer Science & IT

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

Found 2 Documents
Search

 1 
A Graph Theory Approach for Spatial Data-Based Surface Water Flow Modeling Firgiawan, Wawan; Nirwana, Hafsah; Wajidi, Farid; Zainuddin, Zahir; Ahyar, Muh.
SINTECH (Science and Information Technology) Journal Vol. 7 No. 1 (2024): SINTECH Journal Edition April 2024
Publisher : Prahasta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/sintechjournal.v7i1.1480

Abstract

This research proposes an innovative approach that combines graph theory with spatial data to model surface water flow with the Single Flow Direction (SFD) concept, also known as the D8 algorithm. The objective is to show the water flow from the ground surface to a lower place. The research methodology involves collecting spatial data from the Digital Elevation Model (DEMNAS) in raster data type format. Test results show that the effectiveness of the graph approach in modeling water flow can produce clear flow output. This happens because each pixel traversed by water is connected by a line that forms a well-defined water flow path. This study significantly stimulates the development of more sophisticated modeling tools and practical applications in the future. This can help in more efficient management of water resources or produce more accurate flow modeling, contributing to improved understanding and better management of the environment.
Hyperparameter Tuning for Optimizing Stunting Classification with KNN, SVM, and Naïve Bayes Algorithms Firgiawan, Wawan; Yustianisa, Dita; Nur, Nurrahmi Afiah; Gabrelia, Gabrelia
Jurnal Tekno Kompak Vol 19, No 1 (2025): FEBRUARI (In Progress)
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jtk.v19i1.4574

Abstract

The purpose of this study is to illuminate and compare the performance of three classifiers, namely Naive Bayes (NB), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), in classifying stunting data. Using evaluation measures such as accuracy, precision, recall, and F1 score, the performance of each algorithm is measured before and after hyperparameter adjustment. The experimental results show that SVM provides a strong balance between precision and recall before hyperparameter adjustment, KNN excels in recall, and NB achieves the highest precision. After hyperparameter adjustment, all models show improved performance, with SVM achieving the best accuracy and F1 score. While NB remains highly precise and reduces false positives, KNN continues to win the recall. The results show that hyperparameter adjustment is critical to optimizing algorithm performance and that algorithms should be selected according to specific research objectives to maximize detection accuracy and balance recall and precision.
Co-Authors Ahyar, Muh. Farid Wajidi Gabrelia, Gabrelia Nirwana, Hafsah Nur, Nurrahmi Afiah Yustianisa, Dita Zahir Zainuddin