東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Enhancing Long Sequence Time-Series ...

Harris, Dorothy S.,

FindBook

Google Book

Amazon

博客來

Enhancing Long Sequence Time-Series Forecasting through Spatial Embedding Integration /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Enhancing Long Sequence Time-Series Forecasting through Spatial Embedding Integration // Dorothy S Harris.
作者:	Harris, Dorothy S.,
面頁冊數:	1 electronic resource (72 pages)
附註:	Source: Masters Abstracts International, Volume: 86-07.
Contained By:	Masters Abstracts International86-07.
標題:	Graphs. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31822896
ISBN:	9798302372598

Enhancing Long Sequence Time-Series Forecasting through Spatial Embedding Integration /
Harris, Dorothy S.,

Enhancing Long Sequence Time-Series Forecasting through Spatial Embedding Integration /Dorothy S Harris. - 1 electronic resource (72 pages)

Source: Masters Abstracts International, Volume: 86-07.

AI is rapidly emerging as the most reliable and effective approach for prediction in all industries. One significant domain where it is applied is long sequence time-series forecasting (LSTF). While current LSTF models excel in temporal dimensions, they often neglect spatial dimensions. However, considering both spatial and temporal dimensions is crucial, as many real-world applications demand it and can benefit from it. Achieving a high prediction capacity is essential in long sequence time-series forecasting and spatiotemporal forecasting. To address this challenge, transformers are employed due to their ability to enhance prediction capacity. This thesis builds upon previous LSTF temporal transformer models and extends them to the spatiotemporal realm to assess if this approach improves predictions on both novel and established data. The findings reveal that models with Spatial Embedding exhibit enhanced prediction capabilities when the data distribution varies across locations. However, such models do not improve prediction in situations where the distribution is similar across locations. It also improves prediction on less complex models.

English

ISBN: 9798302372598Subjects--Topical Terms:

3685259
Graphs.

Enhancing Long Sequence Time-Series Forecasting through Spatial Embedding Integration /
LDR:02357nmm a22003493i 4500 001 2438922
005 20260727135850.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798302372598
035 $a (MiAaPQD)AAI31822896
035 $a AAI31822896
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Harris, Dorothy S., $e author. $3 3830364
245 1 0 $a Enhancing Long Sequence Time-Series Forecasting through Spatial Embedding Integration / $c Dorothy S Harris.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (72 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 86-07.
500 $a Advisors: Zhu, Yifeng Committee members: Weaver, Vincent; Dhiman, Vikas.
502 $b M.S. $c The University of Maine $d 2024.
520 $a AI is rapidly emerging as the most reliable and effective approach for prediction in all industries. One significant domain where it is applied is long sequence time-series forecasting (LSTF). While current LSTF models excel in temporal dimensions, they often neglect spatial dimensions. However, considering both spatial and temporal dimensions is crucial, as many real-world applications demand it and can benefit from it. Achieving a high prediction capacity is essential in long sequence time-series forecasting and spatiotemporal forecasting. To address this challenge, transformers are employed due to their ability to enhance prediction capacity. This thesis builds upon previous LSTF temporal transformer models and extends them to the spatiotemporal realm to assess if this approach improves predictions on both novel and established data. The findings reveal that models with Spatial Embedding exhibit enhanced prediction capabilities when the data distribution varies across locations. However, such models do not improve prediction in situations where the distribution is similar across locations. It also improves prediction on less complex models.
546 $a English
590 $a School code: 0113
650 4 $a Graphs. $3 3685259
650 4 $a Industrial engineering. $3 526216
690 $a 0546
710 2 $a The University of Maine. $e degree granting institution. $3 3816059
720 1 $a Zhu, Yifeng $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-07.
790 $a 0113
791 $a M.S.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31822896