Triad State Space Construction for Chaotic Signal Classification with Deep Learning
This work addresses chaotic signal classification, a domain-specific problem, with incremental improvements over existing methods like permutation entropy.
The authors tackled chaotic signal classification by proposing Triad State Space Construction (TSSC), an image encoding scheme that recognizes higher-order temporal patterns and identifies new forbidden regions in time series motifs, and demonstrated that a ConvNet classifier based on TSSC images achieves high accuracy and robustness.
Inspired by the well-known permutation entropy (PE), an effective image encoding scheme for chaotic time series, Triad State Space Construction (TSSC), is proposed. The TSSC image can recognize higher-order temporal patterns and identify new forbidden regions in time series motifs beyond the Bandt-Pompe probabilities. The Convolutional Neural Network (ConvNet) is widely used in image classification. The ConvNet classifier based on TSSC images (TSSC-ConvNet) are highly accurate and very robust in the chaotic signal classification.