Insect Detection Using mm-Waves: Integrated Communication and Biodiversity Sensing Based on Micro-Doppler Effects

Wing flapping of insects can cause micro-Doppler patterns in the reflected signals. Here we study the feasibility of insect sensing from a joint waveform from a near-field continuous-wave micro-Doppler radar and a digitally modulated signal at mm-Wave frequencies. We use experiments to capture reflected signals from live insects, and introduce a semi-supervised algorithm that automatically detects signal portions exhibiting micro-Doppler effects of wing flapping. Performance evaluation using precision, recall, F1-score, and ROC-AUC demonstrates the robustness of the approach, while the extracted wing-beat frequencies from various species further validate its effectiveness. Due to the simplicity of this proposed method, the technique can be integrated into the mm-Wave telecommunication system to monitor flying insects to bring about a step-change in our understanding of the dynamics of insect communities and the critical roles they play in ecosystem functioning and biodiversity.