Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal INTECOMS: Journal of Information Technology and Computer Science Geosains Kutai Basin
Jailani, Zakiul Fahmi
Unknown Affiliation
Computer Science & IT Earth & Planetary Sciences

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

Found 2 Documents
Search

 1 
Mapping the Golden Hour: A Spatiotemporal Analysis of Ambulance Response Time in Urban Jakarta Jailani, Zakiul Fahmi; Nurmadewi, Dita; Syumanjaya, Raden Bambang; Manik, Ni Kadek Sri
GEOSAINS KUTAI BASIN Vol. 6 No. 2 (2023)
Publisher : Geophysics Study Program, Faculty of Mathematics and Natural Sciences, Mulawarman University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/geofisunmul.v6i2.1188

Abstract

This study aims to map the ambulance response time in Jakarta city and assess the current ambulance to population ratio. The data used in this study include hospital point data retrieved from OpenStreetMap (OSM), manually digitized data points, and a database from community/non-government organizations that manage their own ambulance. The analysis was conducted using a combination of buffer, service area, and overlay tools in GIS (Geo-information System) software. The results show that the current ambulance to population ratio in Jakarta is inadequate, with only 78 ambulances available that can only serve a total population of 5,598,058 out of all 10,748,230 people in Jakarta. This means that at least 215 ambulances are needed to provide comprehensive coverage for the entire population. Furthermore, the golden time for ambulance response, as set by the Ministry of Health in Indonesia, is less than 15 minutes. However, the current ambulance to population ratio in Jakarta makes it difficult to meet this standard.
Hybrid Machine Learning Predicts Flooding Using Lstm And Random Forests On Geodata Jailani, Zakiul Fahmi; Nurmadewi, Dita
INTECOMS: Journal of Information Technology and Computer Science Vol 8 No 1 (2025): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/intecoms.v8i1.13991

Abstract

Flood prediction remains a critical concern in Indonesia, a nation frequently affected by seasonal deluges. This research aims to predict flood occurrences in five key provinces by employing a hybrid machine learning approach using Long Short-Term Memory (LSTM) networks and Random Forest models. Leveraging geospatial and temporal data from Petabencana.id, collected between January 2018 and February 2024, the study develops a predictive framework for flood forecasting. The analysis integrates flood depth and historical disaster data to estimate the time to the next flood, with predictions starting after the last data entry in February 2024. The model accurately predicted that Jakarta would experience flooding within 25–50 days post-February, a forecast corroborated by significant floods in April 2024. Other provinces, including Central Java and East Java, displayed longer flood risk windows extending further into the year. With a training accuracy of 99%, the model underscores its reliability in predicting flood events. This study emphasizes the strength of LSTM in capturing temporal patterns and the role of Random Forests in identifying key predictive features. The proposed model offers a valuable tool for disaster management agencies and local governments, enabling them to anticipate and mitigate flood impacts using real-time data from Petabencana.id.
Co-Authors Manik, Ni Kadek Sri Nurmadewi, Dita Syumanjaya, Raden Bambang