Matrix Profile I: All Pairs Similarity Joins for Time Series: A Unifying View That Includes Motifs, Discords and Shapelets

Yeh, Chin‐Chia Michael; Zhu, Yada; Ulanova, Liudmila; Begum, Nurjahan; Ding, Yifei; Dau, Son Hoang; Silva, Diego Furtado; Mueen, Abdullah; Keogh, Eamonn

doi:10.1109/icdm.2016.0179

Cited by 424 publications

(426 citation statements)

References 18 publications

Supporting

Mentioning

367

Contrasting

Unclassified

Order By: Relevance

“…The authors defined the discord to be the subsequence that has the largest 1-nearest-neighbor distance in a single long series, and proposed an efficient algorithm by reordering the candidate subsequences. Recently, Matrix Profile based techniques [24,26] have provided acceleration on computing the 1-nearest-neighbor distances.…”

Section: Background and Related Workmentioning

confidence: 99%

Semantic Discord: Finding Unusual Local Patterns for Time Series

Zhang¹,

Gao

Lin

2020

Proceedings of the 2020 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Finding anomalous subsequence in a long time series is a very important but difficult problem. Existing state-of-the-art methods have been focusing on searching for the subsequence that is the most dissimilar to the rest of the subsequences; however, they do not take into account the background patterns that contain the anomalous candidates. As a result, such approaches are likely to miss local anomalies. We introduce a new definition named semantic discord, which incorporates the context information from larger subsequences containing the anomaly candidates. We propose an efficient algorithm with a derived lower bound that is up to 3 orders of magnitude faster than the brute force algorithm in real world data. We demonstrate that our method significantly outperforms the state-of-the-art methods in locating anomalies by extensive experiments. We further explain the interpretability of semantic discord.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Semantic Discord: Finding Unusual Local Patterns for Time Series

Zhang¹,

Gao

Lin

2020

Proceedings of the 2020 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

show abstract

“…LCS‐Jocor transforms the time series into a string using PAA and SAX, finds the longest common substrings (LCSs) and computes the correlations of corresponding subsequences. Yeh et al introduced matrix profile, a data structure for time series data analysis and related work exploiting this data structure . The matrix profile contains, in fact, the precomputed similarities of all possible subsequences in the time series.…”

Section: Related Workmentioning

confidence: 99%

“…Yeh et al 17 introduced matrix profile, a data structure for time series data analysis and related work exploiting this data structure. 18 The matrix profile contains, in fact, the precomputed similarities of all possible subsequences in the time series. Based on the matrix profile, all similar sub-time-series can be retrieved.…”

Section: Related Workmentioning

confidence: 99%

Parallel time series join using spark

Rong

Chen

Silva

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary A time series is a sequence of data points in successive temporal order. Time series data is produced in many applications scenarios, and the techniques for its analysis have generated substantial interest. Time series join is a primitive operation that retrieves all pairs of correlated subsequences from two given time series. As the Pearson correlation coefficient, a measure of the correlation between two variables, has multiple beneficial mathematical properties, for example, the fact that it is invariant with respect to scale and offset, it is used to measure the correlation between two time series. Considering the need to analyze big time series data, we focus on the study of scalable and distributed techniques to process massive data sets. Specifically, we propose a parallel approach to perform time series joins using Spark, a popular analytics engine for large‐scale data processing. Our solution builds on (1) a fast method to compute the fast Fourier transform on the times series to calculate the correlation between two time series, (2) a lossless partition method to divide the time series into multiple subsequences and enable a parallel and correct computation of the join result, and (3) optimization techniques to avoid redundant computations. We performed extensive tests and showed that the proposed approach is efficient and scalable across different data sets and test configurations.

show abstract

“…Similarly, in TrailMarker [15], the authors segment trajectory data as well as clustering the trajectories based on their similarities by minimizing model description cost and coding cost of describing data. In [16], pairwise distances among all subsequences in time-series data are efficiently computed. The authors segment time-series data based on the fact that the distance between subsequences in the same segment is small.…”

Section: Research Goalmentioning

confidence: 99%

Automatic Measurement of Lead Time of Repetitive Assembly Work in a Factory Using a Wearable Sensor

Namioka

Nakai

Ohara

et al. 2017

Journal of Information Processing

View full text Add to dashboard Cite

Abstract:In this paper, we attempt to estimate lead time (duration) of each period of an operation process by a factory worker using a wrist-worn accelerometer. In a factory line production system, a worker repetitively performs predefined operation processes, and the lead time greatly affects productivity of the line production system. Our proposed method automatically finds a frequent sensor data segment as a "motif" that occurs once in each operation period using only prior knowledge about predefined standard lead time of the operation process, and uses the occurrence intervals of the motif to estimate the lead time.

show abstract

Matrix Profile I: All Pairs Similarity Joins for Time Series: A Unifying View That Includes Motifs, Discords and Shapelets

Cited by 424 publications

References 18 publications

Semantic Discord: Finding Unusual Local Patterns for Time Series

Semantic Discord: Finding Unusual Local Patterns for Time Series

Parallel time series join using spark

Automatic Measurement of Lead Time of Repetitive Assembly Work in a Factory Using a Wearable Sensor

Contact Info

Product

Resources

About