An Optimum ICA Based Multiuser Data Separation for Short Message Service

This paper presents a new algorithm for efficient separation of short messages which are mixed in a multi user short message system. Separation of mixed random binary sequences of data is more difficult than mixed sequences of multivalued signals. The proposed algorithm applies Kullback leibler independent component analysis (ICA) over mixed binary sequences of received data. Normally, the length of binary codes of short messages are less than the required length that makes ICA algorithm sufficiently work. To overcome this problem, a random binary tail is inserted after each user short message at the transmitter side. The inserted tails for different users are acquired in a way to conclude the least correlation between them. The optimum choice of random binary tail not only increase the performance of separation by increasing the data length but also by minimizing the correlation between multiuser data.