For eavesdropping of modern telecommunications systems, which employ multiple transmit and receive antennas, the first step is to recognize the space-time code. In this paper, we propose a method to classify within broad categories of space-time codes. The method is based on machine learning and pattern recognition. Compared to the previous published researches, the novelty of this paper is including quasi-orthogonal space-time codes and also single antenna transmitter in identification set. Moreover, the method described in this paper outperforms the current classification methods. It is shown that the decision tree classifier based on several features extracted from correlation matrices, has practical advantages over the current classification methods, especially when data is very noisy.
Teimouri, M., & Rezaei, M. (2019). Blind Classification of Space-Time Codes Using Machine Learning. Journal of Advanced Defense Science & Technology, 10(1), 1-10.
MLA
Mehdi Teimouri; Masoud Rezaei. "Blind Classification of Space-Time Codes Using Machine Learning", Journal of Advanced Defense Science & Technology, 10, 1, 2019, 1-10.
HARVARD
Teimouri, M., Rezaei, M. (2019). 'Blind Classification of Space-Time Codes Using Machine Learning', Journal of Advanced Defense Science & Technology, 10(1), pp. 1-10.
VANCOUVER
Teimouri, M., Rezaei, M. Blind Classification of Space-Time Codes Using Machine Learning. Journal of Advanced Defense Science & Technology, 2019; 10(1): 1-10.
)
