Research & Publications
Health
Cross-sectional study of 384 deliveries in Mogadishu (May–July 2024) showing a 17.9% LBW rate; linked to maternal age, education, residence, ANC, anemia, nutrition, birth spacing, BMI, complications, and iron‑folate supplementation
Health
School-age survey in Mogadishu IDP camps reporting 72.5% STH infection; lower risk linked to paternal secondary education and location (Kahda)
Agriculture
This paper reviews how modern technologies—such as IoT sensors, blockchain, AI/ML analytics, and mobile platforms—are revolutionizing agricultural supply chains from production to distribution. It evaluates their impact on reducing waste, improving coordination, and stabilizing farmer income while addressing challenges like infrastructure gaps, data standards, and financing. The study introduces a framework linking specific technologies (e.g., RFID + blockchain) to measurable supply chain performance, offering both policymakers and managers a roadmap for gradual digital transformation in agriculture.
Agriculture
Grounded in the Technology Acceptance Model (TAM), this study investigates how perceived usefulness and ease of use affect the intention of Somali agribusiness practitioners to adopt ICT tools such as mobile apps, digital payments, and farm advisory platforms. Using survey data and structural equation modeling, it identifies which technology features most strongly influence adoption. The findings emphasize the importance of user-friendly designs, localized content, and supportive policies to overcome digital barriers, providing a roadmap for expanding ICT adoption in Somalia’s agricultural sector.
Health
This research presents a machine learning framework for predicting cardiovascular disease risk using clinical, demographic, and lifestyle data. It compares different feature selection methods and models—such as logistic regression, random forests, and gradient boosting—to achieve accurate and interpretable predictions. Using SHAP analysis for explainability, the study identifies key risk factors and proposes ways to integrate predictive tools into clinical workflows, offering a transparent and data-driven approach to early diagnosis and prevention of heart disease.
Health
Leveraging Machine Learning to Predict COVID-19 Vaccination Adoption among Healthcare Professionals in Somalia: A Comparative Analysis
Construction
Examining the Effect of Interoperability Factors on Building Information Modelling (BIM) Adoption in Malaysia
Agriculture
Revolutionizing Somali Agriculture: Harnessing Machine Learning and IoT for Optimal Crop Recommendations
This research develops a smart agricultural decision-support system that combines IoT sensors and machine learning to optimize crop recommendations for Somali farmers. The system collects soil and weather data to predict yield and profitability for different crops, providing localized and explainable suggestions through a mobile interface. Field tests show improvements in productivity, water use, and income stability. The paper offers a practical framework for applying smart farming technologies in low-resource settings, promoting sustainable and data-driven agriculture in Somalia.
Agriculture
Development and Implementation of an IoT-Based Smart Home Security System in Mogadishu, Somalia
This paper presents the design and deployment of an affordable IoT-based home security system tailored for Mogadishu’s urban environment. The system integrates motion detectors, door sensors, and camera modules with an ESP32-based controller that connects through Wi-Fi or GSM. A mobile app in Somali and English provides real-time alerts and allows users to monitor their homes remotely. The study evaluates detection accuracy, false alarm rates, power backup, and user satisfaction, concluding that IoT can significantly improve safety and awareness in Somali households while remaining cost-effective and easy to maintain.
Agriculture
Transforming Educational Outcomes with IoT: Opportunities and Challenges in Somalia
This conceptual paper explores how IoT technologies can enhance education in Somalia through smart classrooms, attendance monitoring, campus safety, and efficient facility management. It reviews global best practices and aligns them with Somalia’s context—limited connectivity, affordability, and maintenance challenges. The study proposes a phased approach to adopting IoT in education, starting with simple, high-impact use cases such as smart attendance and environmental monitoring. It highlights the importance of teacher training, privacy protection, and sustainable planning to ensure IoT deployment leads to measurable improvements in learning and school management.
Health
Real-Time Somali License Plate Recognition Using Deep Learning Model
This work develops a deep learning system capable of detecting and reading Somali license plates in real time. The model combines object detection (YOLO) with sequence recognition (CRNN/Transformer) to handle different fonts, lighting conditions, and motion blur. Optimized for lightweight devices like Jetson Nano and Raspberry Pi, the system achieves fast and accurate results while respecting data privacy. The paper demonstrates applications in traffic monitoring, parking control, and road safety, showing how AI-based recognition can modernize Somalia’s transportation infrastructure.
Agriculture
This research develops a smart agricultural decision-support system that combines IoT sensors and machine learning to optimize crop recommendations for Somali farmers. The system collects soil and weather data to predict yield and profitability for different crops, providing localized and explainable suggestions through a mobile interface. Field tests show improvements in productivity, water use, and income stability. The paper offers a practical framework for applying smart farming technologies in low-resource settings, promoting sustainable and data-driven agriculture in Somalia.
Agriculture
Development and Implementation of an IoT-Based Smart Home Security System in Mogadishu, Somalia
This paper presents the design and deployment of an affordable IoT-based home security system tailored for Mogadishu’s urban environment. The system integrates motion detectors, door sensors, and camera modules with an ESP32-based controller that connects through Wi-Fi or GSM. A mobile app in Somali and English provides real-time alerts and allows users to monitor their homes remotely. The study evaluates detection accuracy, false alarm rates, power backup, and user satisfaction, concluding that IoT can significantly improve safety and awareness in Somali households while remaining cost-effective and easy to maintain.
Agriculture
Transforming Educational Outcomes with IoT: Opportunities and Challenges in Somalia
This conceptual paper explores how IoT technologies can enhance education in Somalia through smart classrooms, attendance monitoring, campus safety, and efficient facility management. It reviews global best practices and aligns them with Somalia’s context—limited connectivity, affordability, and maintenance challenges. The study proposes a phased approach to adopting IoT in education, starting with simple, high-impact use cases such as smart attendance and environmental monitoring. It highlights the importance of teacher training, privacy protection, and sustainable planning to ensure IoT deployment leads to measurable improvements in learning and school management.
Health
Real-Time Somali License Plate Recognition Using Deep Learning Model
This work develops a deep learning system capable of detecting and reading Somali license plates in real time. The model combines object detection (YOLO) with sequence recognition (CRNN/Transformer) to handle different fonts, lighting conditions, and motion blur. Optimized for lightweight devices like Jetson Nano and Raspberry Pi, the system achieves fast and accurate results while respecting data privacy. The paper demonstrates applications in traffic monitoring, parking control, and road safety, showing how AI-based recognition can modernize Somalia’s transportation infrastructure.
Agriculture
This research develops a smart agricultural decision-support system that combines IoT sensors and machine learning to optimize crop recommendations for Somali farmers. The system collects soil and weather data to predict yield and profitability for different crops, providing localized and explainable suggestions through a mobile interface. Field tests show improvements in productivity, water use, and income stability. The paper offers a practical framework for applying smart farming technologies in low-resource settings, promoting sustainable and data-driven agriculture in Somalia.
Agriculture
Development and Implementation of an IoT-Based Smart Home Security System in Mogadishu, Somalia
This paper presents the design and deployment of an affordable IoT-based home security system tailored for Mogadishu’s urban environment. The system integrates motion detectors, door sensors, and camera modules with an ESP32-based controller that connects through Wi-Fi or GSM. A mobile app in Somali and English provides real-time alerts and allows users to monitor their homes remotely. The study evaluates detection accuracy, false alarm rates, power backup, and user satisfaction, concluding that IoT can significantly improve safety and awareness in Somali households while remaining cost-effective and easy to maintain.
Agriculture
Transforming Educational Outcomes with IoT: Opportunities and Challenges in Somalia
This conceptual paper explores how IoT technologies can enhance education in Somalia through smart classrooms, attendance monitoring, campus safety, and efficient facility management. It reviews global best practices and aligns them with Somalia’s context—limited connectivity, affordability, and maintenance challenges. The study proposes a phased approach to adopting IoT in education, starting with simple, high-impact use cases such as smart attendance and environmental monitoring. It highlights the importance of teacher training, privacy protection, and sustainable planning to ensure IoT deployment leads to measurable improvements in learning and school management.
Health
Real-Time Somali License Plate Recognition Using Deep Learning Model
This work develops a deep learning system capable of detecting and reading Somali license plates in real time. The model combines object detection (YOLO) with sequence recognition (CRNN/Transformer) to handle different fonts, lighting conditions, and motion blur. Optimized for lightweight devices like Jetson Nano and Raspberry Pi, the system achieves fast and accurate results while respecting data privacy. The paper demonstrates applications in traffic monitoring, parking control, and road safety, showing how AI-based recognition can modernize Somalia’s transportation infrastructure.
Agriculture
This research develops a smart agricultural decision-support system that combines IoT sensors and machine learning to optimize crop recommendations for Somali farmers. The system collects soil and weather data to predict yield and profitability for different crops, providing localized and explainable suggestions through a mobile interface. Field tests show improvements in productivity, water use, and income stability. The paper offers a practical framework for applying smart farming technologies in low-resource settings, promoting sustainable and data-driven agriculture in Somalia.