Variable Length Motif Mining Method Based on Suffix Array Index

Existing time series variable-length motif mining algorithms based on suffix arrays suffer from long running times and are prone to premature termination of matching due to variations in individual characters, which hampers the discovery of longer motifs. To address these issues, we propose a novel time series variable-length motif mining algorithm based on suffix array indexing. This algorithm employs PAA and SAX methods for the symbolic representation of time series data, while the DC3 algorithm is utilized for the rapid construction of suffix arrays. Similarity matching is performed based on edit distance, enabling the extraction of variable-length motifs. This approach facilitates the identification of longer motifs with an edit distance less than specified parameters. Experimental results demonstrate that, compared to representative algorithms, our method significantly enhances mining accuracy, maximizes motif length, and improves time efficiency.