Abstract
In wireless communication, modulation classification is an important part of the non-cooperative communication, and it is difficult to classify the various modulation schemes using conventional methods. The deep learning network has been used to handle the problem and acquire good results. In the deep convolutional neural network (CNN), the data length in the input is fixed. However, the signal length varies in communication, and it causes that the network cannot take advantage of the input signal data to improve the classification accuracy. In this paper, a novel deep network method using a multi-stream structure is proposed. The multi-stream network form increases the network width, and enriches the types of signal features extracted. The superposition convolutional unit in each stream can further improve the classification performance, while the shallower network form is easier to train for avoiding the over-fitting problem. Further, we show that the proposed method can learn more features of the signal data, and it is also shown to be superior to common deep networks.
Highlights
Automatic modulation classification (AMC) is a key technology for the non-cooperative communication system [1], and there are many application scenarios in both civilian and military fields
The denoising automatic encoder was employed as a preprocessor to enhance the signal, and the result used as a dataset to train the deep sparse autoencoder to classify modulation schemes
Each length of the signal sequence is input into the multi-stream network, obtaining the rich modulation recognition characteristics to achieve the better signal modulation classification
Summary
Automatic modulation classification (AMC) is a key technology for the non-cooperative communication system [1], and there are many application scenarios in both civilian and military fields. In [32], DLM was used to learn the signal characteristics in the time domain to recognize the modulation schemes, avoiding the artificial feature extraction and the signal characteristic loss, which can cause classification errors. The denoising automatic encoder was employed as a preprocessor to enhance the signal, and the result used as a dataset to train the deep sparse autoencoder to classify modulation schemes. The contributions of this paper are mainly as follows: (1) With the multi-stream wide network structure, the structure design of the deep network is extended horizontally, which allows for extracting richer signal features. It is very suitable for the classification of the signal dataset with various modulation schemes. The transmitted signal can be digital (e.g. quadrature amplitude modulation) or analog (e.g. frequency shift keying)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have