Novel Online Censoring Based Learning Algorithm For Complex-Valued Big Data Streams

This study introduces a novel online censoring (OC) strategy based learning algorithm for complex-valued big data streams. First of all, the kurtosis-based cost function is redefined considering the OC strategy, and then the OC-based complexvalued least mean kurtosis (OC-based complex-valued least mean kurtosis, OC-CLMK) learning algorithm is designed by minimizing it. The learning performance of the proposed OC-CLMK is compared with the performances of the well-known learning algorithms in the literature in terms of mean square error and correlation coefficient on a real-world linear regression problem. Simulation results show that the proposed algorithm thanks to its OC strategy reduces the computational complexity by censoring noninformative training data and produces satisfactory mean square error, training and test regression performances. As a result, this study shows that the proposed algorithm can be easily used in the processing of big data streams because it uses only informative data in the training process with the help of its OC mechanism and reduces the input data size to half by working in the complex domain.