Repository logo
 

IMPROVING MULTI-VARIATE TIME SERIES FORECASTING WITH DYNAMIC MULTI-HEAD ATTENTION ADJACENCY MATRIX

dc.contributor.advisorDr. Qin Ding
dc.contributor.authorBruce, Ashley Denise
dc.contributor.committeeMemberDr. Sinan Sousan
dc.contributor.committeeMemberDr. Nic Herndon
dc.contributor.departmentComputer Science
dc.date.accessioned2025-06-05T17:30:22Z
dc.date.available2025-06-05T17:30:22Z
dc.date.created2025-05
dc.date.issuedMay 2025
dc.date.submittedMay 2025
dc.date.updated2025-05-22T21:15:04Z
dc.degree.collegeCollege of Engineering and Technology
dc.degree.grantorEast Carolina University
dc.degree.majorMS-Data Science
dc.degree.nameM.S.
dc.degree.programMS-Data Science
dc.description.abstractTime series data is prevalent in many fields, such as finance, weather forecasting, and economics. Predicting future values of a time series can offer valuable insights for decision-making, such as identifying trends, detecting anomalies, and improving resource allocation. Existing research, including neural network-based models and transformer-based models, has demonstrated high performance in learning temporal information. However, capturing spatial information within time series data remains a significant challenge. In this project, we explored whether the attention mechanism can be effectively integrated into non-transformer-based models to enhance their ability to learn spatial information. To achieve this goal, we propose a novel framework that uses a dynamically learned adjacency matrix based on related work called the Multi-variate Time-series Graph Neural Network(MTGNN). Instead of using a correlation-based learned adjacency matrix, the adjacency matrix and graph modules are replaced with a dynamically learned adjacency matrix with multi-attention. This framework shows that a dynamically learned attention adjacency matrix can perform as well as other frameworks when learning spatial information.
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/10342/14041
dc.publisherEast Carolina University
dc.subjectStatistics
dc.subjectComputer Science
dc.titleIMPROVING MULTI-VARIATE TIME SERIES FORECASTING WITH DYNAMIC MULTI-HEAD ATTENTION ADJACENCY MATRIX
dc.typeMaster's Thesis
dc.type.materialtext

Files

Original bundle

Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
1765443891\1744897137305-BRUCE-PRIMARY-2025.pdf
Size:
479 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
private\-1765443891\1744897117530-Denise Thesis 2025.zip
Size:
9.01 MB
Format:
Unknown data format