Claim Missing Document
Check
Articles

Found 13 Documents
Search

Design and Simulation of an IoT-Based Adaptive Control System for Urban Hydroponic Farming Maulana, Nurhuda; Novi Trisman Hadi
Informatik : Jurnal Ilmu Komputer Vol 21 No 3 (2025): Desember 2025
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52958/iftk.v21i3.12815

Abstract

Efficient water circulation is an essential requirement in urban hydroponic farming, yet many systems still depend on fixed timer control that cannot adjust to changing environmental conditions. This study develops an Internet of Things based adaptive pump control system that responds to real-time temperature and humidity data collected using DHT22 and DS18B20 sensors. An ESP32 microcontroller manages the sensing and control process, while MQTT and Blynk Cloud enable continuous monitoring and data exchange. The system is evaluated through a six hour hydroponic simulation on the Wokwi platform under three environmental scenarios: Normal, Heatwave, and Humid. Two control strategies are compared, the fixed interval mode (K1) and an adaptive mode (K2) based on threshold rules. The results show that the adaptive mode improves water efficiency by reducing pump operation by 23.4 percent on average while maintaining more stable temperature and humidity conditions. These findings indicate that lightweight IoT solutions can support responsive and efficient operation in urban hydroponic systems, offering a practical basis for further development of intelligent control in urban farming.
Anomaly Detection of Road Ranking Shifts Due to Traffic Accidents Using Deep Learning on Time Series Data Adita Utami; Novi Trisman Hadi
Journal of Computing Innovations and Emerging Technologies Vol. 1 No. 1 (2025): Volume 1 No 1
Publisher : novamindpress

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64472/jciet.v1i1.5

Abstract

This study developed an anomaly detection model based on Long Short-Term Memory (LSTM) autoencoders to identify abnormal shifts in road ranking scores caused by traffic accidents in Magelang, Indonesia. Road rankings were derived from time-series data of traffic indicators collected between 2015 and 2020, including volume-to-capacity ratios, heavy vehicle proportions, and average speed. The model was trained on non-accident data to learn normal traffic behavior and subsequently detect deviations. Anomalies were identified when reconstruction errors exceeded statistically defined thresholds and were evaluated against verified accident records. The model achieved a precision of 82%, recall of 75%, and an AUC-ROC of 0.87, demonstrating strong performance in detecting significant disruptions, particularly severe accidents involving fatalities or serious injuries. Analysis showed that detected anomalies were concentrated on high-risk roads and during peak traffic hours. These findings highlight the potential of LSTM-based models for integration into intelligent transportation systems to support real-time accident detection and proactive traffic management in developing urban environments.
Development and Validation of GIS-Based Multi-Vulnerability Mapping for Floods and Landslides in Parung Panjang Hadi, Novi Trisman; Gusti, Kharisma Wiati; Prasetyo, Rizky Tito; Utami, Adita
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 02 (2026): MAY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i02.2623

Abstract

Rapid peri-urban development in Indonesia, particularly in metropolitan buffer areas such as Bogor Regency, has intensified land use change and increased vulnerability to hydrometeorological disasters. Parung Panjang Subdistrict faces significant environmental pressure from settlement expansion, industrial activity, and mining, which contribute to increased surface runoff, reduced infiltration capacity, and land instability. This study aims to develop and validate a Geographic Information System (GIS)-based model for flood and landslide vulnerability mapping to support sustainable spatial planning at the subdistrict scale. The analysis integrates remote sensing, topographic, and climatic data, while vulnerability weights were determined using the Analytical Hierarchy Process (AHP) and combined through a weighted overlay approach to produce flood, landslide, and multi-hazard vulnerability maps. Model validation was conducted using a confusion matrix, resulting in an Overall Accuracy of 88.4% and a Kappa coefficient of 0.84, indicating strong agreement. The developed flood vulnerability map was further implemented in a web-based GIS platform and functionally tested, achieving a 95% success rate. The findings show that high flood vulnerability is concentrated in low-elevation areas with high moisture indices and dense built-up land use, while multi-hazard zones identify priority areas for mitigation. This study demonstrates the integration of validated multi-hazard spatial modeling with web-based implementation, providing a practical decision-support tool for local disaster mitigation and spatial planning.