A Generic Approach to Integrating Time into Spatial-Temporal Forecasting via Conditional Neural Fields

Self-awareness is the key capability of autonomous systems, e.g., autonomous driving network, which relies on highly efficient time series forecasting algorithm to enable the system to reason about the future state of the environment, as well as its effect on the system behavior as time progresses....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bui, Minh-Thanh, Ngo, Duc-Thinh, Lu, Demin, Zhang, Zonghua
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Bui, Minh-Thanh
Ngo, Duc-Thinh
Lu, Demin
Zhang, Zonghua
description Self-awareness is the key capability of autonomous systems, e.g., autonomous driving network, which relies on highly efficient time series forecasting algorithm to enable the system to reason about the future state of the environment, as well as its effect on the system behavior as time progresses. Recently, a large number of forecasting algorithms using either convolutional neural networks or graph neural networks have been developed to exploit the complex temporal and spatial dependencies present in the time series. While these solutions have shown significant advantages over statistical approaches, one open question is to effectively incorporate the global information which represents the seasonality patterns via the time component of time series into the forecasting models to improve their accuracy. This paper presents a general approach to integrating the time component into forecasting models. The main idea is to employ conditional neural fields to represent the auxiliary features extracted from the time component to obtain the global information, which will be effectively combined with the local information extracted from autoregressive neural networks through a layer-wise gated fusion module. Extensive experiments on road traffic and cellular network traffic datasets prove the effectiveness of the proposed approach.
doi_str_mv 10.48550/arxiv.2305.06827
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2305_06827</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2305_06827</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-8189e1a7a19dd6fef10edbfb78f16df8fdb25b8e62d8ad682870389c091c25603</originalsourceid><addsrcrecordid>eNotj8FOhDAURbtxYUY_wJX9AbAt0pYlIc44ycRZyJ486OvYBNqm4ET_XkRXN7n35CaHkAfO8mddluwJ0pe75qJgZc6kFuqW2Joe0GNyA61jTAGGD7oEevQLXhIszl9o6yakzq_te1wbGLMWpxgSjHQfEg4wb9jVAW2CN25xwa_bG35uiMPRzHfkxsI44_1_7ki7f2mb1-x0Phyb-pSBVCrTXFfIQQGvjJEWLWdoetsrbbk0VlvTi7LXKIXRYFYBrVihq4FVfBClZMWOPP7dbqJdTG6C9N39CnebcPEDDSBR6Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Generic Approach to Integrating Time into Spatial-Temporal Forecasting via Conditional Neural Fields</title><source>arXiv.org</source><creator>Bui, Minh-Thanh ; Ngo, Duc-Thinh ; Lu, Demin ; Zhang, Zonghua</creator><creatorcontrib>Bui, Minh-Thanh ; Ngo, Duc-Thinh ; Lu, Demin ; Zhang, Zonghua</creatorcontrib><description>Self-awareness is the key capability of autonomous systems, e.g., autonomous driving network, which relies on highly efficient time series forecasting algorithm to enable the system to reason about the future state of the environment, as well as its effect on the system behavior as time progresses. Recently, a large number of forecasting algorithms using either convolutional neural networks or graph neural networks have been developed to exploit the complex temporal and spatial dependencies present in the time series. While these solutions have shown significant advantages over statistical approaches, one open question is to effectively incorporate the global information which represents the seasonality patterns via the time component of time series into the forecasting models to improve their accuracy. This paper presents a general approach to integrating the time component into forecasting models. The main idea is to employ conditional neural fields to represent the auxiliary features extracted from the time component to obtain the global information, which will be effectively combined with the local information extracted from autoregressive neural networks through a layer-wise gated fusion module. Extensive experiments on road traffic and cellular network traffic datasets prove the effectiveness of the proposed approach.</description><identifier>DOI: 10.48550/arxiv.2305.06827</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2023-05</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,782,887</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2305.06827$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2305.06827$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Bui, Minh-Thanh</creatorcontrib><creatorcontrib>Ngo, Duc-Thinh</creatorcontrib><creatorcontrib>Lu, Demin</creatorcontrib><creatorcontrib>Zhang, Zonghua</creatorcontrib><title>A Generic Approach to Integrating Time into Spatial-Temporal Forecasting via Conditional Neural Fields</title><description>Self-awareness is the key capability of autonomous systems, e.g., autonomous driving network, which relies on highly efficient time series forecasting algorithm to enable the system to reason about the future state of the environment, as well as its effect on the system behavior as time progresses. Recently, a large number of forecasting algorithms using either convolutional neural networks or graph neural networks have been developed to exploit the complex temporal and spatial dependencies present in the time series. While these solutions have shown significant advantages over statistical approaches, one open question is to effectively incorporate the global information which represents the seasonality patterns via the time component of time series into the forecasting models to improve their accuracy. This paper presents a general approach to integrating the time component into forecasting models. The main idea is to employ conditional neural fields to represent the auxiliary features extracted from the time component to obtain the global information, which will be effectively combined with the local information extracted from autoregressive neural networks through a layer-wise gated fusion module. Extensive experiments on road traffic and cellular network traffic datasets prove the effectiveness of the proposed approach.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8FOhDAURbtxYUY_wJX9AbAt0pYlIc44ycRZyJ486OvYBNqm4ET_XkRXN7n35CaHkAfO8mddluwJ0pe75qJgZc6kFuqW2Joe0GNyA61jTAGGD7oEevQLXhIszl9o6yakzq_te1wbGLMWpxgSjHQfEg4wb9jVAW2CN25xwa_bG35uiMPRzHfkxsI44_1_7ki7f2mb1-x0Phyb-pSBVCrTXFfIQQGvjJEWLWdoetsrbbk0VlvTi7LXKIXRYFYBrVihq4FVfBClZMWOPP7dbqJdTG6C9N39CnebcPEDDSBR6Q</recordid><startdate>20230511</startdate><enddate>20230511</enddate><creator>Bui, Minh-Thanh</creator><creator>Ngo, Duc-Thinh</creator><creator>Lu, Demin</creator><creator>Zhang, Zonghua</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230511</creationdate><title>A Generic Approach to Integrating Time into Spatial-Temporal Forecasting via Conditional Neural Fields</title><author>Bui, Minh-Thanh ; Ngo, Duc-Thinh ; Lu, Demin ; Zhang, Zonghua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-8189e1a7a19dd6fef10edbfb78f16df8fdb25b8e62d8ad682870389c091c25603</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Bui, Minh-Thanh</creatorcontrib><creatorcontrib>Ngo, Duc-Thinh</creatorcontrib><creatorcontrib>Lu, Demin</creatorcontrib><creatorcontrib>Zhang, Zonghua</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bui, Minh-Thanh</au><au>Ngo, Duc-Thinh</au><au>Lu, Demin</au><au>Zhang, Zonghua</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Generic Approach to Integrating Time into Spatial-Temporal Forecasting via Conditional Neural Fields</atitle><date>2023-05-11</date><risdate>2023</risdate><abstract>Self-awareness is the key capability of autonomous systems, e.g., autonomous driving network, which relies on highly efficient time series forecasting algorithm to enable the system to reason about the future state of the environment, as well as its effect on the system behavior as time progresses. Recently, a large number of forecasting algorithms using either convolutional neural networks or graph neural networks have been developed to exploit the complex temporal and spatial dependencies present in the time series. While these solutions have shown significant advantages over statistical approaches, one open question is to effectively incorporate the global information which represents the seasonality patterns via the time component of time series into the forecasting models to improve their accuracy. This paper presents a general approach to integrating the time component into forecasting models. The main idea is to employ conditional neural fields to represent the auxiliary features extracted from the time component to obtain the global information, which will be effectively combined with the local information extracted from autoregressive neural networks through a layer-wise gated fusion module. Extensive experiments on road traffic and cellular network traffic datasets prove the effectiveness of the proposed approach.</abstract><doi>10.48550/arxiv.2305.06827</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2305.06827
ispartof
issn
language eng
recordid cdi_arxiv_primary_2305_06827
source arXiv.org
subjects Computer Science - Learning
title A Generic Approach to Integrating Time into Spatial-Temporal Forecasting via Conditional Neural Fields
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-03T14%3A10%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Generic%20Approach%20to%20Integrating%20Time%20into%20Spatial-Temporal%20Forecasting%20via%20Conditional%20Neural%20Fields&rft.au=Bui,%20Minh-Thanh&rft.date=2023-05-11&rft_id=info:doi/10.48550/arxiv.2305.06827&rft_dat=%3Carxiv_GOX%3E2305_06827%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true