Tools

LEADER 03261cam a2200505 i 4500

001 on1523697734;

003 OCoLC;

005 20260604115859.0;

006 m o d ;

007 cr unu||||||||;

008 250616s2025 ncua obm 000 0 eng d;

035 a| (Sirsi) o1523697734;

035 a| (OCoLC)1523697734;

049 a| EREE;

090 a| QA280;

100 1 a| Bruce, Ashley Denise,e| author.?| UNAUTHORIZED;

245 10 a| Improving multi-variate time series forecasting with dynamic multi-head attention adjacency matrix /c| by Ashley Denise Bruce.;

264 1 a| [Greenville, N.C.] :b| [East Carolina University],c| 2025.;

300 a| 1 online resource (32 pages) :b| illustrations (some color);

336 a| textb| txt2| rdacontent;

337 a| computerb| c2| rdamedia;

338 a| online resourceb| cr2| rdacarrier;

347 a| text fileb| application/pdfc| 479 KB2| rda;

538 a| System requirements: Adobe Reader.;

538 a| Mode of access: World Wide Web.;

502 b| M.S.c| East Carolina Universityd| 2025.;

500 a| Presented to the Faculty of the Department of Computer Science.;

500 a| Advisor: Qin Ding;

500 a| Title from PDF t.p. (viewed June 2, 2026).;

520 3 a| Time 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.;

504 a| Includes bibliographical references.;

650 0 a| Time-series analysis.=| ^A7961;

650 0 a| Machine learning.=| ^A145211;

650 0 a| Neural networks (Computer science)=| ^A263002;

653 a| attention;

700 1 a| Ding, Qin,e| degree supervisor.=| ^A1464811;

710 2 a| East Carolina University.b| Department of Computer Science.?| UNAUTHORIZED;

856 40 z| Access via ScholarShipu| http://hdl.handle.net/10342/14041;

949 o| wjh;

994 a| C0b| ERE;

596 a| 1 4;

998 a| 6584073;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 6584073-1001l| JNETm| JOYNERr| Ys| Yt| JNE3ETDu| 6/16/2025x| ETDz| JERESOURCE;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 6584073-2001l| HSLELECm| HSLr| Ys| Yt| HEETDu| 6/16/2025x| ETDz| HERESOURCE;

Improving multi-variate time series forecasting with dynamic multi-head attention adjacency matrix / by Ashley Denise Bruce.

Author/creator	Bruce, Ashley Denise author.
Other author	Ding, Qin, degree supervisor.
Other author	East Carolina University. Department of Computer Science.
Format	Theses and dissertations
Publication	[Greenville, N.C.] : [East Carolina University], 2025.
Description	1 online resource (32 pages) : illustrations (some color)
Supplemental Content	Access via ScholarShip
Subjects	Time-series analysis. Machine learning. Neural networks (Computer science)

Summary	Time 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.
General note	Presented to the Faculty of the Department of Computer Science.
General note	Advisor: Qin Ding
General note	Title from PDF t.p. (viewed June 2, 2026).
Dissertation note	M.S. East Carolina University 2025.
Bibliography note	Includes bibliographical references.
Technical details	System requirements: Adobe Reader.
Technical details	Mode of access: World Wide Web.

Availability

Library	Location	Call Number	Status	Item Actions
	Electronic Resources	Access Content Online	✔ Available

Improving multi-variate time series forecasting with dynamic multi-head attention adjacency matrix / by Ashley Denise Bruce.

Click here for more information about this title

Availability