We are thrilled to announce that our paper MAST-CloudNet: IoT-Enabled Acoustic Trap with Real-Time AI Surveillance of Aedes has been accepted for publication in the IEEE TIM journal, and we proudly congratulate Atique B. Zakir, Asif Rahman Dipto, Fahad Arefin, and AMM Munif Khan for their contributions.
The research introduces MAST-CloudNet, an IoT-enabled acoustic trap that pairs a 350-500 Hz frequency sweep with edge-based imaging to selectively capture male Aedes aegypti mosquitoes. To automate surveillance, the system transmits image data to a central cloud server where a YOLOv11 object detection model quantifies the targets in real-time, achieving an 83.3% capture specificity during laboratory testing. Validated during a three-day outdoor field trial at the University of Dhaka, this automated optical-acoustic framework offers a highly specific, scalable early-warning tool for global dengue outbreak prevention