Improving Modulation Recognition Using Time Series Data Augmentation via a Spatiotemporal Multi-Channel Framework

Abstract

Automatic modulation recognition technology with deep learning has a broad prospective owing to big data and computing power. However, the accuracy of modulation recognition largely depends on the massive volume of data and the applicability of the model. Here, to eliminate the difficulties of manual feature extraction, a low accuracy, and a small sample dataset, we propose an effective recognition method that combines time series data augmentation with a spatiotemporal multi-channel learning framework. Compared with other advanced network models, the results showed that the method gave a positive index in the order of 93.5% for ten modulation signal types, which was increased by at least 15%. Especially for QAM16 and QAM64 signals, the average recognition accuracy was improved by nearly 50% at SNRs as low as −2 dB, showing a significant recognition performance. The proposed method provides an attractive method for signal modulation recognition in wireless or wired communication fields.