Research on intelligent detection technology of wireless communication signals based on Yolov10 model

To address the challenge of efficient communication signal detection in complex electromagnetic environments, this paper proposes an intelligent signal detection method based on the Yolov10-ghost model, incorporating deep learning techniques. Building upon the Yolov10 architecture, the method introduces the C3Ghost module and replaces conventional Conv layers with GhostConv layers to enhance feature extraction and fusion while reducing model complexity. Additionally, the loss function is optimized to WIoU-v2, addressing class imbalance and improving suitability for object detection tasks. Experimental results show that the proposed method can efficiently detect continuous and burst signals in communication data, achieving an average detection accuracy (mAP) of 98.4%. The model parameters are reduced to 1.9M, with an inference time of 80.8ms per frame, demonstrating a strong balance between detection accuracy and real-time performance. Furthermore, the model's successful deployment on embedded platforms highlights its significant engineering application value.