Signal Frequency Estimation Based on RNN
Bin Huang, Chun‐Liang Lin, Weihai Chen, Chia‐Feng Juang, Xingming Wu · 2020
Signal frequency estimation is a fundamental issue in the domain of signal processing. In this paper, we proposed a novel framework, named FreqEnet (Frequency estimation network), for estimating frequency based on deep learning method. The signal frequency estimation refers to as a regression issue and predict it with LTSM module. The framework is exceedingly concise, consisted of only three LSTM and one fully connect layers, and the running time is less than 0.3 ms on CPU (i7-7700, 3.60 GHz). Two periodic signals are generated for training our model. In addition, uniform and Gauss white noise are introduce to original signal for evaluating the robustness and generalization of the framework. In addition, the proposed method performs extremely excellence in processing latent. Even if given only one periodic piece of signal, the method could predicts a precise result. Extensive experiments demonstrate that FreqEnet achieves competitive performance of estimating frequency.