Scalable and explainable self-supervised motif discovery in temporal data

Author

Somayeh Bakhtiari Ramezani, Mississippi State UniversityFollow

ORCID

https://orcid.org/0000-0002-5230-8723

Issuing Body

Mississippi State University

Advisor

Rahimi, Shahram

Committee Member

Perkins, Andy

Committee Member

Mittal, Sudip

Committee Member

Chen, Zhiqian

Committee Member

Seale, Maria

Date of Degree

12-8-2023

Original embargo terms

Embargo 1 Year

Document Type

Dissertation - Open Access

Major

Computer Science

Degree Name

Doctor of Philosophy (Ph.D)

College

James Worth Bagley College of Engineering

Department

Department of Computer Science and Engineering

Abstract

The availability of a scalable and explainable rule extraction technique via motif discovery is crucial for identifying the health states of a system. Such a technique can enable the creation of a repository of normal and abnormal states of the system and identify the system’s state as we receive data. In complex systems such as ECG, each activity session can consist of a long sequence of motifs that form different global structures. As a result, applying machine learning algorithms without first identifying the local patterns is not feasible and would result in low performance. Thus, extracting unique local motifs and establishing a database of prototypes or signatures is a crucial first step in analyzing long temporal data that reduces the computational cost and overcomes imbalanced data. The present research aims to streamline the extraction of motifs and add explainability to their analysis by identifying their differences. We have developed a novel framework for unsupervised motif extraction. We also offer a robust algorithm to identify unique motifs and their signatures, coupled with a proper distance metric to compare the signatures of partially similar motifs. Defining such distance metrics allows us to assign a degree of semblance between two motifs that may have different lengths or contain noise. We have tested our framework against five different datasets and observed excellent results, including extraction of motifs from 100 million samples in 8.02 seconds, 99.90% accuracy in self-supervised ECG data classification, and an average error of 16.66% in RUL prediction of bearing failure.

Sponsorship

Engineer Research and Development Center (ERDC)

Recommended Citation

Bakhtiari Ramezani, Somayeh, "Scalable and explainable self-supervised motif discovery in temporal data" (2023). Theses and Dissertations. 6001.
https://scholarsjunction.msstate.edu/td/6001