KAUST researchers developed VENTIBAG, a mobile AI-powered ventilator, in response to the COVID-19 pandemic. The device extracts and delivers pure oxygen, adjusting support based on real-time monitoring of the patient's condition via cloud connectivity. Funded by a KAUST Innovation Challenge grant, the portable ventilator is now advancing to the testing stage for medical applications. Why it matters: This innovation addresses critical needs for remote patient care and reducing hospital overcrowding, particularly relevant in resource-constrained environments.
This paper proposes a smart dome system for mosques that uses machine learning to automatically control dome ventilation based on weather conditions and outside temperatures. The system was tested on the Prophet Mosque in Saudi Arabia using K-Nearest Neighbors and Decision Tree algorithms. The Decision Tree algorithm achieved a higher accuracy of 98% compared to 95% for the k-NN algorithm.
Researchers in Saudi Arabia developed and evaluated deep learning models, specifically LSTM and attention-based LSTM, to predict heat stress among construction workers. The study monitored physiological data like heart rate and oxygen saturation from 19 workers using Garmin Vivosmart 5 smartwatches. The attention-based model achieved 95.40% testing accuracy with superior precision, recall, and F1 scores of 0.982, significantly outperforming the baseline. Why it matters: This approach offers a proactive, data-driven solution for enhancing worker safety in extreme heat conditions, particularly relevant for the construction sector in the Middle East.