SVM-based CDMA receiver with incremental active learning

Recently, the feasibility of using support vector machines (SVMs) for multiuser detection in code division multiple access (CDMA) systems has been investigated. Previous results show that SVMs perform well with short training sequences but suffer from two drawbacks that are highly undesirable in real-time applications: the run-time complexity and the block-based learning. To deal with these problems, here we propose a sample-by-sample adaptive algorithm for CDMA systems based on incremental SVMs, incorporating an active learning strategy aimed to reduce the complexity of both the training phase and the final classifier.