Computer Science ETDs

Publication Date

Spring 5-11-2024

Abstract

Time series data mining and learning serve as a cornerstone across various domains, including finance, healthcare, and science. Recent advancements in network and sensor technologies have ignited an increasing interest in real-time temporal data mining and learning techniques. Various tasks benefit from these techniques, such as environmental monitoring, event detection, anomaly identification, and forecasting. However, these techniques still face significant challenges in the online environment settings, encompassing aspects like efficiency, accuracy, robustness, and scarcity of labeled data. This dissertation presents four innovative solutions: FilCorr, DCT-MASS, FewSig, and BitLINK to overcome these challenges. We evaluate each method and showcase their practical significance through applications in earthquake early warning systems, aftershock sequence detection, and blockchain address identification. We hope this research will enhance our understanding of the challenges and opportunities in online temporal data mining and learning, ultimately leading to more efficient and robust algorithms.

Language

English

Keywords

Time series, Streaming, Distance Profile, Online Learning, Earthquake, Bitcoin

Document Type

Dissertation

Degree Name

Computer Science

Level of Degree

Doctoral

Department Name

Department of Computer Science

First Committee Member (Chair)

Abdullah Mueen

Second Committee Member

Shuang Luan

Third Committee Member

Bruna Jacobson

Fourth Committee Member

Jessica Lin

Download

Share

COinS