MAST-CloudNet: IoT-Enabled Acoustic Trap with Real-Time AI Surveillance of Aedes.

Abstract

The present invention relates to an IoT-enabled mosquito surveillance system that combines species-specific acoustic trapping with automated artificial intelligence (AI) recognition and cloud-based real-time monitoring. The system, termed MAST-CloudNet, employs a Male Aedes Sound Trap (MAST) that generates a 350–500 Hz acoustic frequency sweep mimicking female wingbeats to lure male Aedes aegypti selectively. Captured mosquitoes are immobilized on an adhesive surface and imaged using an edge-based device comprising a Raspberry Pi, camera, and integrated illumination. The captured images are transmitted to a central server where a custom-trained YOLOv11 object detection model identifies and classifies Aedes versus non-Aedes mosquitoes with high accuracy (mAP ≥ 0.96). A web dashboard provides real-time visualization, detection summaries, and data export for remote users. The system demonstrates over 83% selective capture efficiency for Aedes aegypti and enables consumable-free, scalable, and real-time vector monitoring suitable for dengue outbreak prevention.