Time-series anomaly detection using dynamic programming based longest common subsequence on sensor data
作者：
Highlights：
• Measure the similarity of two time-series based on the longest common subsequence (LCS).
• Investigate a gap search constraint to limit the searching range to find the LCS.
• Provide a threshold to define the matching of a pair of time-series.
• Detect the anomalous time-series based on the similarity-based LCS.
• Apply on a case study of big multisensory data.
摘要
•Measure the similarity of two time-series based on the longest common subsequence (LCS).•Investigate a gap search constraint to limit the searching range to find the LCS.•Provide a threshold to define the matching of a pair of time-series.•Detect the anomalous time-series based on the similarity-based LCS.•Apply on a case study of big multisensory data.
论文关键词：Anomaly detection,Dynamic programming,Fixed gap longest common subsequence,Longest common subsequence,Time-series
论文评审过程：Received 30 June 2021, Revised 26 August 2022, Accepted 22 September 2022, Available online 26 September 2022, Version of Record 30 September 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.118902
