Research on Drones Audio Signal Recognition Algorithm Based on RNN Model
In recent years, the widespread application of drones has caused many privacy and security issues. To address this issue, a drone audio signal recognition algorithm based on Recurrent Neural Network (RNN) model is studied. Firstly, feature value extraction is performed on the audio signal of the drone. Based on the designed RNN model, a 3-layer Long Short-Term Memory (LSTM) network and a 3-layer Dropout are set up. Secondly, in the output layer, Softmax is used as the activation function to output the results, and the parameters of neurons and Dropout are continuously updated during the experiment. Finally, based on the actual audio data collected, perform drone detection. The experimental results show that the accuracy of the proposed algorithm reaches 96.33％, which can meet the practical needs of drone detection.
NETL
NSTL
万方数据
