A Fast Algorithm of Correlation Dimension Estimation for Nonlinear Time Series
- Resource Type
- Conference
- Authors
- Fan, Zhenyan; Dong, Shumin; Chi, Jieru; Zhuang, Xiaodong; Mastorakis, Nikos E.
- Source
- 2018 2nd European Conference on Electrical Engineering and Computer Science (EECS) EECS Electrical Engineering and Computer Science (EECS),2018 2nd European Conference on. :595-597 Dec, 2018
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
Robotics and Control Systems
Signal Processing and Analysis
Europe
Electrical engineering
Computer science
Phase Space Reconstruction
Correlation Dimension
Fast Algorithm
- Language
The computation cost of traditional correlation dimension algorithm is large, which prevents its real-time application. The fast algorithm of correlation dimension computation is proposed in this paper. The distance between signal sequence points is compared with a given threshold and the results are transformed into a binary neighbor matrix. Then the binary nearest neighbor matrix of high dimensional signal vector is recurred by the binary nearest neighbor matrix of low dimensional signal vector. The real operations are converted into a logical AND operation and a logical summation operation. Difference-comparison operations of correlation integral are reduced. The results show that the fast algorithm can greatly improve the calculating speed of correlation dimension.