Efficient Time Series Matching by Wavelets
ICDE '99 Proceedings of the 15th International Conference on Data Engineering
Scaling and time warping in time series querying
VLDB '05 Proceedings of the 31st international conference on Very large data bases
HOT SAX: Efficiently Finding the Most Unusual Time Series Subsequence
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Approximately Processing Multi-granularity Aggregate Queries over Data Streams
ICDE '06 Proceedings of the 22nd International Conference on Data Engineering
Suppressing model overfitting in mining concept-drifting data streams
Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
Disk Aware Discord Discovery: Finding Unusual Time Series in Terabyte Sized Datasets
ICDM '07 Proceedings of the 2007 Seventh IEEE International Conference on Data Mining
Finding time series discords based on haar transform
ADMA'06 Proceedings of the Second international conference on Advanced Data Mining and Applications
Discord region based analysis to improve data utility of privately published time series
ADMA'10 Proceedings of the 6th international conference on Advanced data mining and applications: Part I
Hi-index | 0.00 |
Time discord detection is an important problem in a great variety of applications. In this paper, we consider the problem of discord detection for time series stream, where time discords are detected from local segments of flowing time series stream. The existing detections, which aim to detect the global discords from time series database, fail to detect such local discords. Two online detection algorithms are presented for our problem. The first algorithm extends the existing algorithm HOT SAX to detect such time discords. However, this algorithm is not efficient enough since it needs to search the entire time subsequences of local segment. Then, in the second algorithm, we limit the search space to further enhance the detection efficiency. The proposed algorithms are experimentally evaluated using real and synthesized datasets.