Article Per Year (5 Year)
p-Index From 2020 - 2025
2.304
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Science and Technology Indonesia Jurnal Komputasi Jurnal Teknoinfo Jurnal Pengabdian Kepada Masyarakat (JPKM) Tabikpun Journal Social Science And Technology For Community Service Jurnal Pepadun Integra: Journal of Integrated Mathematics and Computer Science
Shofiana, Dewi Asiah
Jurusan Ilmu Komputer, Fakultas Matematika Dan Ilmu Pengetahuan Alam, Universitas Lampung
Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Environmental Science Health Professions Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Mathematics Physics

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

Found 12 Documents
Search

 1   2 
Traffic Violation Modeling Using K-Means Clustering Method: A Case Study in Bandung, Indonesia Junaidi, Akmal; Manurung, Yunita Rosalina; Shofiana, Dewi Asiah; Lumbanraja, Favorisen Rosyking
Integra: Journal of Integrated Mathematics and Computer Science Vol. 1 No. 3 (2024): November
Publisher : Magister Program of Mathematics, Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/integrajimcs.20241326

Abstract

Violations of traffic regulations are both an issue and a problem that persists as a feature of life, especially in metropolitan regions such as Bandung. Traffic violation has both behavioral and environmental patterns, with different types of violations occurring at different times during the day. This negligence stems largely from not properly equipping the vehicle with the necessary documents, especially for drivers who do not pay attention to proper document preparation. With the goal of increasing road safety, law enforcement bodies face the ongoing challenge of managing rising traffic violation rates which results in a growing backlog of violation cases and a corresponding backlog workload for police departments. Comprehensive preventive strategies for the problem are extremely difficult to implement in the absence of streamlined mechanisms for the efficient allocation of limited police resources. Currently, agencies responsible for managing violation records are still using a manual desktop system based on Microsoft Excel spreadsheets. This method impedes the analysis of large datasets to derive actionable insights that could inform targeted, data-driven strategies needed to guide proactive measures. In this regard, this study attempts to implement the K-Means clustering technique in order to identify and classify high-incidence traffic violation areas in Bandung. Using this technique, the research classifies the city into three violation risk clusters: very prone, prone, and moderately prone areas. The map of the classes demonstrates the distribution of these clusters spatially, illustrating clearly and vividly how stakeholders can visualise the pattern of traffic violations. This method improves the understanding of data and at the same time boosts purposeful planning for the safety and public traffic order anticipations.
Decision Tree Algorithms in Water Quality Classification: A Comparative Study of Random Forest, XGBoost, and C5.0 Shofiana, Dewi Asiah; Caniadi, Melan; Sholehurrohman, Ridho; Aristoteles
Science and Technology Indonesia Vol. 10 No. 4 (2025): October
Publisher : Research Center of Inorganic Materials and Coordination Complexes, FMIPA Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/sti.2025.10.4.999-1011

Abstract

Safe drinking water is more than a convenience; public health officials often call it a cornerstone of survival. United Nations International Children’s Emergency Fund (UNICEF) reported that, shockingly, roughly two billion people still drink water that is neither clean nor tested. Pathogenic bacteria from human feces and livestock waste taint roughly 70% of available sources, creating a silent epidemic. Scientists express water quality into five levels: poor, marginal, fair, good, and excellent – named as the Water Quality Index (WQI) designed by the Canadian Council of Ministers of the Environment (CCME). This research measured the performance of three decision-tree classifiers, including Random Forest, XGBoost, and C5.0 to predict water quality. The preprocessing pipeline was thorough, involving label encoding, use of synthetic minor over-sampling technique (SMOTE) for balancing imbalanced classes, and an exploratory phase to examine outliers and irregularities within the dataset. According to the findings, Random Forest finished at an impressive test result with 98% of accuracy. XGBoost and C5.0 follows close behind at about 96%, but the latter turned out to be the fastest, edging out both XGBoost and Random Forest, making C5.0 a preferable when a time-sensitive or emergency decision is needed. In short, this research highlights the importance of modern preprocessing tools combined with machine learning algorithms in monitoring water quality.
Co-Authors Admi Syarif Akmal Junaidi Aldo Pradipta Aristoteles Caniadi, Melan Favorisen R. Lumbanraja Heningtyas, Yunda Indah Pasaribu Kurnia Muludi Machudor Yusman Manurung, Yunita Rosalina Mohammad Surya Akbar Muhammad Ridho Restu Alam Sobri Mulia Kesuma Putri Naurah Nazhifah Ni Putu Ayu Anesca Prabowo, Rizky Sholehurrohman, Ridho YOHANA TRI UTAMI, YOHANA TRI