Smart Vector Surveillance: Integrating AI-Based Identification with Ecological Monitoring of Mosquito-Borne Diseases

Abstract

Mosquito-borne diseases such as malaria, dengue, Zika, chikungunya, and yellow fever continue to pose serious global health threats. Conventional vector surveillance systems are labor-intensive, delayed, and limited in spatial resolution. This study presents a Smart Vector Surveillance framework integrating artificial intelligence (AI)-based mosquito identification with ecological and environmental monitoring for real-time disease risk prediction. The system combines computer vision models, acoustic classification, IoT-enabled environmental sensing, and geospatial modeling. Field validation demonstrated 96.8% image-based classification accuracy and 93.4% acoustic classification accuracy. Ecological modeling improved disease risk prediction by 28% compared to conventional regression models. The proposed framework enhances surveillance precision, scalability, and timeliness, offering a transformative tool for vector-borne disease control programs.