Aedes aegypti is a mosquito species known for its role in transmitting dengue fever, a viral disease prevalent in tropical and subtropical regions. Recognizable by its white markings and preference for urban habitats, this mosquito breeds in standing water near human dwellings. A promising approach to combat the proliferation of mosquitoes is the use of smart traps, equipped with advanced technologies to attract, capture, and monitor them. The most significant results include 97% accuracy in detecting Aedes aegypti, 100% accuracy in identifying bees, and 90.1% accuracy in classifying butterflies in the laboratory. Field trials successfully validated and identified areas for continued improvement. The integration of technologies such as Internet of Things (IoT), cloud computing, big data, and artificial intelligence has the potential to revolutionize pest control, significantly improving mosquito monitoring and control. The application of machine learning (ML) algorithms and computer vision for the identification and classification of Aedes aegypti is a crucial part of this process. This article proposes the development of a smart trap for selective control of winged insects, combining IoT devices, high-resolution cameras, and advanced ML algorithms for insect detection and classification. The intelligent system features the YOLOv7 algorithm (You Only Look Once v7) that is capable of detecting and counting insects in real time, combined with LoRa/LoRaWan connectivity and IoT system intelligence. This adaptive approach is effective in combating Aedes aegypti mosquitoes in real time.
Read full abstract