A chaotic map algorithm for knowledge discovery in time series: a case study on biomedical signals

A chaotic map algorithm is proposed to study similarity-based knowledge of temporal patterns. Several information sources can be regarded as time series, both in scientific and technological fields such as nuclear physics, computer network, biomedical signals, and many others. The application of an automatic knowledge discovery mechanism has a strong impact on system science and engineering. The advantage of the proposed algorithm is due to its capability to extract meaningful features from complex data sets, as temporal patterns, without teacher. A case study has been carried on biomedical signals, such as electroencephalographic records, to recognize patterns affected by the Huntington's disease, one of the most dangerous pathology of the central nervous system. The chaotic map algorithm succeeds in distinguishing between pathological and normal patterns, with high values of both sensitivity and specificity.