Almohab, Hadi
Unknown Affiliation

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

Causal Inference in Observational Studies: Assessing the Impact of Lifestyle Factors on Diabetes Risk Witarsyah, Deden; Almohab, Hadi; A A Abushammala, Haneen
JOIV : International Journal on Informatics Visualization Vol 9, No 2 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.2.1295

Abstract

The global prevalence of type 2 diabetes has escalated in recent decades, prompting an urgent need for effective prevention strategies. Physical activity has emerged as a significant modifiable risk factor for mitigating diabetes risk, yet the precise causal relationship remains a subject of debate, particularly in observational studies. This research leverages advanced causal inference methods to rigorously estimate the effect of physical activity on the risk of developing type 2 diabetes. By employing Propensity Score Matching (PSM), we address confounding biases inherent in observational data, ensuring more reliable estimates of treatment effects. Additionally, we integrate machine learning techniques, including causal forests, to explore heterogeneous treatment effects (HTEs) across different population subgroups. Our findings highlight that the benefits of physical activity in reducing diabetes risk are not uniform but are more pronounced among individuals with higher body mass index (BMI), further underlining the necessity of tailored interventions. The application of advanced causal inference models allows us to account for confounders such as diet, socioeconomic status, and pre-existing health conditions, offering a more comprehensive understanding of the relationship between physical activity and diabetes prevention. This study contributes to the growing literature by demonstrating that physical activity significantly reduces diabetes risk, with particular benefits for high-risk subgroups. Our findings provide evidence for public health policies that emphasize physical activity as a cornerstone of diabetes prevention, promoting individualized approaches to intervention.
Deep Learning CNN for Pneumonia Detection: Advancing Digital Health in Society 5.0 Almohab, Hadi
Jurnal Ilmiah Profesi Pendidikan Vol. 10 No. 4 (2025): November
Publisher : Fakultas Keguruan dan Ilmu Pendidikan, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jipp.v10i4.4001

Abstract

Pneumonia merupakan masalah kesehatan global yang serius dan menyumbang tingkat morbiditas serta mortalitas yang tinggi, terutama di wilayah dengan keterbatasan alat diagnostik dan sumber daya kesehatan. Penelitian ini bertujuan mengembangkan model Convolutional Neural Network (CNN) berbasis deep learning untuk mendeteksi pneumonia secara otomatis menggunakan citra X-ray dada. Metode yang digunakan meliputi pelatihan model pada dataset berlabel dengan serangkaian teknik pra-pemrosesan, seperti normalisasi, augmentasi data, dan peningkatan kualitas citra untuk memperbaiki ketahanan dan kemampuan generalisasi model. Hasil pengujian menunjukkan bahwa model yang dioptimalkan mencapai akurasi uji 91,67%, dengan nilai ROC-AUC 0,96 dan PR-AUC 0,95, yang menandakan performa kuat dalam membedakan pneumonia dari citra normal. Kesimpulannya, model CNN ini memiliki potensi signifikan sebagai alat bantu diagnostik yang cepat, konsisten, dan andal, serta mendukung visi Society 5.0 dalam integrasi kecerdasan buatan untuk meningkatkan layanan kesehatan dan kesejahteraan masyarakat.
Machine Learning-Based Multi-Sensor IoT System for Intelligent Indoor Fire Detection Junfithranaa, Anggy Pradifta; Almohab, Hadi; Dewi, Deshinta Arrova
Journal of Educational Technology and Learning Creativity Vol. 4 No. 1 (2026): June
Publisher : Cahaya Ilmu Cendekia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37251/jetlc.v4i1.2614

Abstract

Purpose of the study: This study aims to develop an intelligent indoor fire detection system by integrating low-cost Internet of Things (IoT) sensors with machine learning-based multi-sensor data fusion to improve early fire hazard detection accuracy while reducing false alarms compared to conventional single-sensor fire detection systems. Methodology: The system is implemented using an ESP32 microcontroller connected to temperature, humidity, flame, and sound sensors for real-time data acquisition. A dataset of 1,500 sensor samples is collected and labeled into Normal, Fire-Risk, and Fire classes. Decision Tree, Support Vector Machine, and Random Forest classifiers are trained and evaluated using Python-based machine learning libraries. Main Findings: Experimental results indicate that the Random Forest model outperforms the other classifiers, achieving 95% overall accuracy, perfect recall for fire events, and a Macro ROC-AUC score of 0.993. Feature importance analysis reveals that humidity and temperature are the most influential parameters for early fire detection in indoor environments. Novelty/Originality of this study: This study proposes a lightweight intelligent fire detection framework that integrates multi-sensor Internet of Things data including temperature, humidity, flame, and sound signals with machine learning–based classification for indoor environments. Unlike conventional systems that rely on single-sensor or threshold-based detection, the proposed approach utilizes multi-sensor data fusion and ensemble learning to improve early fire-risk identification while remaining computationally efficient for low-cost platforms such as the ESP32 microcontroller.
Machine Learning-Based Multi-Sensor IoT System for Intelligent Indoor Fire Detection Junfithranaa, Anggy Pradifta; Almohab, Hadi; Dewi, Deshinta Arrova
Journal of Educational Technology and Learning Creativity Vol. 4 No. 1 (2026): June
Publisher : Cahaya Ilmu Cendekia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37251/jetlc.v4i1.2614

Abstract

Purpose of the study: This study aims to develop an intelligent indoor fire detection system by integrating low-cost Internet of Things (IoT) sensors with machine learning-based multi-sensor data fusion to improve early fire hazard detection accuracy while reducing false alarms compared to conventional single-sensor fire detection systems. Methodology: The system is implemented using an ESP32 microcontroller connected to temperature, humidity, flame, and sound sensors for real-time data acquisition. A dataset of 1,500 sensor samples is collected and labeled into Normal, Fire-Risk, and Fire classes. Decision Tree, Support Vector Machine, and Random Forest classifiers are trained and evaluated using Python-based machine learning libraries. Main Findings: Experimental results indicate that the Random Forest model outperforms the other classifiers, achieving 95% overall accuracy, perfect recall for fire events, and a Macro ROC-AUC score of 0.993. Feature importance analysis reveals that humidity and temperature are the most influential parameters for early fire detection in indoor environments. Novelty/Originality of this study: This study proposes a lightweight intelligent fire detection framework that integrates multi-sensor Internet of Things data including temperature, humidity, flame, and sound signals with machine learning–based classification for indoor environments. Unlike conventional systems that rely on single-sensor or threshold-based detection, the proposed approach utilizes multi-sensor data fusion and ensemble learning to improve early fire-risk identification while remaining computationally efficient for low-cost platforms such as the ESP32 microcontroller.