Talk is cheap, show you my code!

This is a repository to public the source codes of my papers. I would be very happy if they help you with your research. But please give me a ⭐️ and cite my papers~

A high-efficiency modulation classification model.

Efficiency is now a key challenge in automatic modulation classification (AMC), particularly in resource-constrained en- vironments like mobile devices in 6G networks. This pa- per presents a framework based on the filter-bank channel- izer (FBNet) for AMC, which gracefully strikes a balance between accuracy, complexity, and speed. By channelizing signals into simpler sub-band sequences, FBNet captures de- pendencies in both temporal and frequency dimensions, mak- ing modulation features more distinct. Therefore, we use a compact architecture with the custom-designed temporal convolution blocks (TCB) and the adaptive channel aggrega- tion (ACA) module as the backbones. Experimental results demonstrate that, under the same resource constraints, our model consistently outperforms the leading models in accu- racy. Further evaluation conducted on the Jetson Nano, an edge platform with computing power similar to a mobile de- vice, reveals a 42.4% advantage in inference speed for our model, underscoring that FBNet holds great potential for de- ployment in resource-constrained systems.