arXiv · · Notable
A research paper proposes a smart waste management system called TUHR for Makkah, Saudi Arabia, leveraging IoT and AI to handle waste accumulation during the annual pilgrimage. The system uses ultrasonic sensors to monitor waste levels and gas detectors to identify harmful substances, alerting authorities when containers are full or hazards are detected. The proposed system aligns with Saudi Vision 2030 by promoting sustainability and improving public health through optimized waste management.
waste management · smart city · Makkah · Internet of Things · artificial intelligence
Get the weekly digest
Top AI stories from the GCC region, every week.
arXiv ·
A proposed recognition system aims to identify missing persons, deceased individuals, and lost objects during the Hajj and Umrah pilgrimages in Saudi Arabia. The system intends to leverage facial recognition and object identification to manage the large crowds expected in the coming decade, estimated to reach 20 million pilgrims. It will be integrated into the CrowdSensing system for crowd estimation, management, and safety.
arXiv ·
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.
arXiv ·
This paper proposes a smart dome model for mosques that uses AI to control dome movements based on weather conditions and overcrowding. The model utilizes Congested Scene Recognition Network (CSRNet) and fuzzy logic techniques in Python to determine when to open and close the domes to maintain fresh air and sunlight. The goal is to automatically manage dome operation based on real-time data, specifying the duration for which the domes should remain open each hour.
arXiv ·
This paper introduces a hybrid deep learning and machine learning pipeline for classifying construction and demolition waste. A dataset of 1,800 images from UAE construction sites was created, and deep features were extracted using a pre-trained Xception network. The combination of Xception features with machine learning classifiers achieved up to 99.5% accuracy, demonstrating state-of-the-art performance for debris identification.