Low-Power Weakly-Supervised Audio Detection for Real-World Mosquito Surveillance (Proposals Track)
Danika Gupta (The Harker Upper School); Ming Zhao (Arizona State University); Neha Rajendra Vadnere (Arizona State University)
Abstract
Climate change is expanding the geography and altering habitats of mosquitoes that transmit Dengue, Zika, etc. For example, China’s first large-scale chikungunya outbreak in August 2025 underscores the urgency for scalable and adaptive mosquito surveillance. Existing approaches often rely on expert entomologists or extensive labeled datasets, making them poorly suited for rapid deployment in low-resource settings. Our approach uses weak labels from time-aligned video recordings to train audio classifiers via Multi Instance Learning (MIL). This approach combines local data, citizen labelers and low power audio classification to enable rapid adaptation to climate driven outbreaks. Early proof points suggest potential for MIL in audio classification from mosquito video labels.