scholarly journals Embedding of the Matrix Profile Concept Into a Relational DBMS for Time Series Mining

2021 ◽  
Vol 10 (3) ◽  
Keyword(s):  
Time Series ◽  
The Matrix ◽  
Time Series Mining

Temporary rules of retail product sales time series based on the matrix profile

2021 ◽  
Vol 60 ◽  
pp. 102431
Author(s):  
Hailin Li ◽  
Yenchun Jim Wu ◽  
Shijie Zhang ◽  
Jinchuan Zou
Keyword(s):  
Time Series ◽  
The Matrix ◽  
Product Sales

An approach based on satellite image time series mining to identify region susceptible to desertification

2014 ◽  
Author(s):  
R. Scrivani ◽  
R. R. V. Goncalves ◽  
L. A. S. Romani ◽  
S. R. M. Oliveira ◽  
E. D. Assad
Keyword(s):  
Time Series ◽  
Satellite Image ◽  
Time Series Mining

Time Series Mining

2008 ◽  
pp. 14-43
Author(s):  
Wynne Hsu ◽  
Mong Li Lee ◽  
Junmei Wang
Keyword(s):  
Time Series ◽  
Dimension Reduction ◽  
Similarity Measures ◽  
Sequential Patterns ◽  
Sequence Mining ◽  
Periodic Patterns ◽  
Background Material ◽  
Time Series Mining ◽  
Data Discretization

In this chapter, we will first give the background and review existing works in time series mining. The background material will include commonly used similarity measures and techniques for dimension reduction and data discretization. Then we will examine techniques to discover periodic and sequential patterns. This will lay the groundwork for the subsequent three chapters on mining dense periodic patterns, incremental sequence mining, and mining progressive patterns.

Matrix Profile XVIII: Time Series Mining in the Face of Fast Moving Streams using a Learned Approximate Matrix Profile

2019 ◽  
Author(s):  
Zachary Zimmerman ◽  
Nader Shakibay Senobari ◽  
Gareth Funning ◽  
Evangelos Papalexakis ◽  
Samet Oymak ◽  
...  
Keyword(s):  
Time Series ◽  
Fast Moving ◽  
The Face ◽  
Time Series Mining

Time series joins, motifs, discords and shapelets: a unifying view that exploits the matrix profile

2017 ◽  
Vol 32 (1) ◽  
pp. 83-123 ◽  
Author(s):  
Chin-Chia Michael Yeh ◽  
Yan Zhu ◽  
Liudmila Ulanova ◽  
Nurjahan Begum ◽  
Yifei Ding ◽  
...  
Keyword(s):  
Time Series ◽  
The Matrix

An Improved Method for the Generating of Spectrum-Compatible Time Series Using Wavelets

2014 ◽  
Vol 30 (4) ◽  
pp. 1467-1485 ◽  
Author(s):  
Yufeng Gao ◽  
Yongxin Wu ◽  
Dayong Li ◽  
Ning Zhang ◽  
Fei Zhang
Keyword(s):  
Time Series ◽  
Cross Correlation ◽  
Response Spectrum ◽  
Target Response ◽  
Improved Method ◽  
Seismic Input ◽  
Dynamic Analyses ◽  
The Matrix ◽  
Matching Procedure ◽  
The Stability

In dynamic analyses of important structures, seismic input may be defined in the form of time series. It is required that the response spectrum of this input time series be compatible with a specified target response spectrum. Time domain spectral matching, which is used to generate spectrum compatible acceleration time series, is investigated in some detail. First, a new, improved wavelet is presented, and the new adjustment wavelet can prevent drifts in the resulting velocity and displacement time series without applying a baseline correction. Next, the analytical solution of the matrix accounting for the cross correlation of each wavelet is given in order to ensure the speed of the matching procedure. Finally, some aspects, such as the reduction factors and the matching order, are discussed to ensure the stability and efficiency of the matching procedure. Accordingly, the characteristics of the matching procedure are illustrated by numerical examples.

Sign in / Sign up

Export Citation Format

Share Document