Detection of Binary Signals using Linear Classifiers

C. Lee, Heeyoung Kim, and B. Baek (Korea)


detection of binary signals, equalization,classification, channels, multiclass.


In this paper, we treat detection of binary signals in the presence of noise, delay and interference as a pattern classification problem which is solved by utilizing second order statistics. The proposed method can be used for a linear dispersive channel with known channel characteristics. The method can be also used for unknown channel characteristics when training sequences are provided. Then, the proposed equalization is extended as multiclass problem in order to obtain higher accuracy. Experiments show that the proposed algorithm significantly outperforms the conventional LMS algorithm.

Important Links:

Go Back