Diversity analysis based on ordered patterns

Diversity index based on entropy such as Emlen index (El) is suggested as a highly effective algorithm to detect complexity in nonlinear systems. In this paper, a method considering the amplitude information, called Weighted Emlen index (WEI) is proposed to extract the amplitude information and track the signal changes. And then, we expand EI/WEI methods to multiple time scales. Thus, multiscale Emlen index (MSEI) and multiscale Weighted Emlen index (MSWEI) will be used to discuss the complexity of traffic time series under different scales. Results show that there are differences between the complexity of weekend traffic time series and workday time series, which gives a better classification of traffic systems for making prediction. (C) 2018 Elsevier B.V. All rights reserved.