Smart mosquito detection: leveraging AI and IoT for vector-borne disease prevention

Abstract

Vector-borne diseases such as malaria, dengue, Zika, and West Nile virus remain among the world’s most severe public health threats, causing more than 700,000 deaths annually. The objective of this work is to demonstrate how artificial intelligence (AI), Internet of Things (IoT), and edge computing technologies can transform mosquito surveillance from reactive, manual monitoring into a proactive, data-driven ecosystem for early outbreak prevention. Traditional control methods, spraying, net distribution, and manual inspection, have proven life-saving but inefficient, particularly as climate change and globalization expand mosquito habitats. Recent advances in AI and IoT have enabled automated detection, species identification, and predictive modeling, but large-scale integration remains limited. This study analyzes smart mosquito detection systems that combine IoT-enabled traps, AI-based image and sound recognition, and real-time data analytics platforms. These systems identify species via wingbeat frequency and computer vision, transmit encrypted data through MQTT or LoRaWAN, and integrate environmental and meteorological data for predictive modeling. Field demonstrations show significant improvements in detection accuracy, latency, and outbreak prediction capabilities, enabling timely public health interventions such as targeted spraying and community alerts. For health authorities and policymakers, the implementation of smart detection networks enhances preparedness, reduces chemical use, and lowers operational costs. This paper highlights how interconnected AI- and IoT-based mosquito surveillance represents a paradigm shift from reactive disease control to predictive prevention, offering a scalable, sustainable model for global health security and smart city resilience.