Abdurohman Abdurohman

Abdurohman Abdurohman

Auto-generated profile, based on publicly available information

Abdurohman Abdurohman

Graduate School of Electrical Engineering, School of Bioscience, Technology and Innovation (SBTI), Atma Jaya Catholic University of Indonesia, Jakarta, Indonesia

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 November 2024 in International Journal of Engineering Continuity
Verified
Journal Article
Open access
PDF file
AAAbdurohman Abdurohman
Abdurohman Abdurohman
MSMarsul Siregar
Marsul Siregar
CSCatherine Olivia Sereati
Catherine Olivia Sereati
SWSilviana Windasari
Silviana Windasari
MPMm. Lanny W. Pandjaitan
Mm. Lanny W. Pandjaitan
Efficient water management in agriculture is crucial due to dynamic environmental conditions and increasing resource scarcity. Fuzzy Inference System (FIS) is widely applied in irrigation control for its ability to handle uncertaintys using rule-based domain knowledge. However, conventional FIS lacks adaptability to environmental changes, limiting its long-term accuracy and responsiveness. Adaptive Neuro-Fuzzy Inference System (ANFIS) addresses this limitation by combining fuzzy logic with neural network learning, enabling automatic adjustment of model parameters based on data patterns. This study compares the performance of FIS and ANFIS in predicting optimal irrigation levels based on soil moisture, air temperature, relative humidity, and solar radiation. A synthetic dataset of 1,000 samples simulating realistic agricultural conditions was generated and normalized to improve computational consistency. The FIS model uses triangular membership functions and five expert-defined fuzzy rules, while ANFIS employs Gaussian membership functions with parameters optimized using the ADAM algorithm over 50 training epochs. Results show that ANFIS outperforms FIS, lowering RMSE from 0.13 to 0.07, halving MAE from 0.10 to 0.05, and increasing R² from 0.85 to 0.93, indicating a substantially better predictive performance. This study demonstrates that ANFIS is more adaptive, accurate, and computationally efficient, contributing to the advancement of intelligent and sustainable irrigation systems in precision agriculture.

18 November 2024 in International Journal of Engineering Continuity
Verified
Journal Article
Open access
PDF file
SWSilviana Windasari
Silviana Windasari
AAAbdurohman Abdurohman
Abdurohman Abdurohman
IRImbuh Rochmad
Imbuh Rochmad
SBSetiyo Budiyanto
Setiyo Budiyanto
Laboratory incidents are often precipitated by misplacement of hazardous materials and delayed recognition of unsafe conditions. Earlier laboratory safety solutions typically centered on sensors and dashboards, including IoT monitoring, improve situational awareness but remain largely reactive, operate at room/building scale, seldom enforce item-level storage rules, and rarely report alert selectivity (false-alarm behaviour). This work presents a compact prototype that combines RFID-based storage-zone verification with environmental sensing to support Health, Safety, Security, and Environment (HSSE) compliance at the storage-unit level. An ESP32-based controller integrates three RFID readers (low/medium/high-risk compartments) with temperature humidity and gas sensors; data are streamed to an IoT interface for real-time visualization and notification (e.g., implemented via Blynk), while rule-based logic triggers local (buzzer) and remote alerts when a tagged item is placed in the wrong zone or thresholds are exceeded. A scenario-driven evaluation across 18 cases (correct/mismatched placements for representative items) yielded 100% RFID tag detection and placement validation, an average response time of 2.37 s, and no false alarms under correct placements. These results indicate that joining placement verification with multi-sensor monitoring provides selective, low-latency warnings while avoiding nuisance alerts, establishing quantitative baselines for scalable smart-laboratory HSSE enforcement.

24 September 2025 in International Journal of Engineering Continuity
Verified
Journal Article
Open access
PDF file
SWSilviana Windasari
Silviana Windasari
AAAbdurohman Abdurohman
Abdurohman Abdurohman
ARAdi Affandi Ratib
Adi Affandi Ratib
AFAde Frihadi
Ade Frihadi
KMKhalid Montazi
Khalid Montazi
This study proposes an optimization model integrating Internet of Things (IoT) and Machine Learning (ML) for renewable energy-powered aeroponic systems as a conceptual framework to enhance sustainable agriculture and address global food security challenges. The model is designed to mitigate land degradation, water scarcity, and the impacts of climate variability on crop productivity. It combines IoT-based real-time monitoring of key environmental variables temperature, humidity, pH, electrical conductivity, and light intensity with Long Short-Term Memory (LSTM) networks for time-series prediction of crop growth and resource requirements. Renewable energy sources, particularly solar photovoltaic systems with battery storage, ensure reliable and environmentally friendly power supply. The proposed approach emphasizes predictive optimization, where IoT data streams inform adaptive LSTM algorithms for precise irrigation and nutrient control. Model performance is evaluated using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R²). Although the study remains conceptual and simulation-based, validation results demonstrate high predictive accuracy and efficiency. This research establishes a foundational framework for subsequent prototype development, experimental validation, and techno-economic evaluation toward scalable, energy-efficient, and sustainable smart farming systems.