With the increasing complexity of electromagnetic spectrum, efficient signal modulation identification algorithms are beneficial to electromagnetic spectrum management, which is very important for modern communication systems. However, traditional algorithms have limitations in feature extraction and lack of accuracy.

This paper presents an improved algorithm for electromagnetic signal modulation recognition. This algorithm integrates the temporal convolution network (TCN), the bidirectional long-short-term memory (Bi-LSTM) network, and the improved locality-sensitive hashing attention mechanism (LSH attention) to enhance the accuracy of recognition.

Firstly, Bi-LSTM is designed to capture the bidirectional dependency of time series data and enhance the discrimination ability for complex modulation modes. Secondly, TCN and Bi-LSTM are fused through a cascaded architecture to achieve hierarchical time series feature extraction and bidirectional dynamic modeling. Finally, LSH attention is added to reduce the complexity of the attention matrix while improving the recognition accuracy. In terms of data preprocessing, a KNN-BH processing method is proposed, which can improve the extraction accuracy of spectral features.

Experimental results on the RML2016.10a dataset show that compared with seven baseline algorithms, the TCN-LSTM-LSH attention algorithm has the best recognition performance, with an overall recognition accuracy of 64.71% for 11 types of signal modulations.

This algorithm demonstrates great potential in electromagnetic spectrum applications and is highly suitable for use in high-precision modulation recognition tasks in communication systems.