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

Dengue fever poses a growing public health threat, necessitating enhanced vector surveillance focused on Aedes aegypti. While recent efforts integrate artificial intelligence (AI) and Internet of Things (IoT) into traditional traps (Biogents (BG) traps, ovitraps), inherent limitations persist, including poor adult density correlation and species specificity. Here, we present the Male Aedes Sound Trap (MAST)-CloudNet, an automated optical-acoustic measurement instrument combining selective acoustic capture with real-time cloud connectivity for precise target population quantification. The core component is the MAST, employing a 350–500-Hz frequency sweep proven in controlled trials to capture significantly more Aedes mosquitoes (83.3 % versus 50 % control). Captured mosquitoes are imaged at the edge, with data transmitted to a cloud server for processing. A preliminary three-day outdoor field test on the University of Dhaka campus showed that the active acoustic configuration captured 49 Aedes and ten non-Aedes mosquitoes, with 83.1 % target selectivity. In comparison, the silent control captured only one Aedes and three non-Aedes mosquitoes. These results demonstrate the potential of MAST-CloudNet as a scalable early-warning tool for dengue vector surveillance and outbreak prevention.

DOI: https://doi.org/10.1109/TIM.2026.3738168