Pulses Classification Based on Sparse Auto-Encoders Neural Networks

Abstract

Unsupervised learning is applicable to classification that does not know the number of specific categories in advance, and sparse auto-encoders (SAE) are widely used for feature extraction of unsupervised learning. Therefore, this paper proposes an electromagnetic signal classification system based on SAE which is combined with the machine learning clustering algorithm. In particular, we propose to perform feature preprocessing on signals using STFT. Then, the features extracted by SAE training are clustered by t-SNE and DBSCAN to obtain clustering results. Finally, we prove the feasibility of this method classification by comparing with traditional clustering methods. Because of the feature extraction, SAE not only learns the key feature information but also effectively compresses the data content, which greatly reduces the data dimension that the clustering algorithm needs to deal with and improves the clustering accuracy. As the experimental results show, the evaluation indicators of the result obtained by our method are significantly improved compared with the traditional clustering algorithms, the compactness (CP) index decreases by 73.76%; the Davies-Bouldin Index (DB) decreases by 18.50%; the Dunn Validity Index (DVI) increases by 6.24%; and the Rand Index (RI) increases by 43.14%.