Loading…
Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity
Time series forecasting (TSF) is crucial in various fields and has gained extensive research. However, most studies are conducted based on TS data with scale homogeneity. This paper proposes a self-Adaptive Scale-handling (AS) module to improve the performance of forecasting TS with scale heterogene...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 7489 |
| container_issue | |
| container_start_page | 7485 |
| container_title | |
| container_volume | |
| creator | Zhang, Xu Huang, Zhengang Wu, Yunzhi Lu, Xun Qi, Erpeng Chen, Yunkai Xue, Zhongya Wang, Peng Wang, Wei |
| description | Time series forecasting (TSF) is crucial in various fields and has gained extensive research. However, most studies are conducted based on TS data with scale homogeneity. This paper proposes a self-Adaptive Scale-handling (AS) module to improve the performance of forecasting TS with scale heterogeneity. It consists of scale scaling selection and calibrating. We first calculate the priori scale factors of each time variable and then selectively calibrate the priori scale factors through neural networks. Hence, we can improve the performance of TSF algorithms by reducing scale restoration errors. We validate our method in collected industrial fund sales datasets from Ant Fortune and Alipay APP. Our AS module can easily be integrated into popular TSF models. |
| doi_str_mv | 10.1109/ICASSP48485.2024.10446923 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10446923</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10446923</ieee_id><sourcerecordid>10446923</sourcerecordid><originalsourceid>FETCH-LOGICAL-i723-379df69acdc604948d5f02dc79106b21a1c461c564c46057d03d6c82de7a8a5f3</originalsourceid><addsrcrecordid>eNo1kM9KAzEYxKMgWGvfwMP6ALt--Z8cS7FWKKjsHryVmHypkW23ZBelb-8W7WkY5scwDCH3FCpKwT48L-Z1_SqMMLJiwERFQQhlGb8gM6ut4RK4GEN6SSaMa1tSC-_X5KbvvwDAaGEm5K3GNpbz4A5D-sai9q7FYuX2oU37bRG7XCy7jN71w8k3aTcymBP2xU8aPs88Dpi7Le4xDcdbchVd2-PsX6ekWT42i1W5fnkaF6_LpBkvxzkhKut88AqEFSbICCx4bSmoD0Yd9UJRL5UYFaQOwIPyhgXUzjgZ-ZTc_dUmRNwcctq5fNycH-C_mblQ5g</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity</title><source>IEEE Xplore All Conference Series</source><creator>Zhang, Xu ; Huang, Zhengang ; Wu, Yunzhi ; Lu, Xun ; Qi, Erpeng ; Chen, Yunkai ; Xue, Zhongya ; Wang, Peng ; Wang, Wei</creator><creatorcontrib>Zhang, Xu ; Huang, Zhengang ; Wu, Yunzhi ; Lu, Xun ; Qi, Erpeng ; Chen, Yunkai ; Xue, Zhongya ; Wang, Peng ; Wang, Wei</creatorcontrib><description>Time series forecasting (TSF) is crucial in various fields and has gained extensive research. However, most studies are conducted based on TS data with scale homogeneity. This paper proposes a self-Adaptive Scale-handling (AS) module to improve the performance of forecasting TS with scale heterogeneity. It consists of scale scaling selection and calibrating. We first calculate the priori scale factors of each time variable and then selectively calibrate the priori scale factors through neural networks. Hence, we can improve the performance of TSF algorithms by reducing scale restoration errors. We validate our method in collected industrial fund sales datasets from Ant Fortune and Alipay APP. Our AS module can easily be integrated into popular TSF models.</description><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 9798350344851</identifier><identifier>DOI: 10.1109/ICASSP48485.2024.10446923</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustics ; Deep Learning ; Forecasting ; Multivariate Time Series ; Neural networks ; Scale Handling ; Scale Heterogeneity ; Signal processing ; Signal processing algorithms ; Task analysis ; Time series analysis ; Time Series Prediction</subject><ispartof>ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, p.7485-7489</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10446923$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27923,54553,54930</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10446923$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zhang, Xu</creatorcontrib><creatorcontrib>Huang, Zhengang</creatorcontrib><creatorcontrib>Wu, Yunzhi</creatorcontrib><creatorcontrib>Lu, Xun</creatorcontrib><creatorcontrib>Qi, Erpeng</creatorcontrib><creatorcontrib>Chen, Yunkai</creatorcontrib><creatorcontrib>Xue, Zhongya</creatorcontrib><creatorcontrib>Wang, Peng</creatorcontrib><creatorcontrib>Wang, Wei</creatorcontrib><title>Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity</title><title>ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</title><addtitle>ICASSP</addtitle><description>Time series forecasting (TSF) is crucial in various fields and has gained extensive research. However, most studies are conducted based on TS data with scale homogeneity. This paper proposes a self-Adaptive Scale-handling (AS) module to improve the performance of forecasting TS with scale heterogeneity. It consists of scale scaling selection and calibrating. We first calculate the priori scale factors of each time variable and then selectively calibrate the priori scale factors through neural networks. Hence, we can improve the performance of TSF algorithms by reducing scale restoration errors. We validate our method in collected industrial fund sales datasets from Ant Fortune and Alipay APP. Our AS module can easily be integrated into popular TSF models.</description><subject>Acoustics</subject><subject>Deep Learning</subject><subject>Forecasting</subject><subject>Multivariate Time Series</subject><subject>Neural networks</subject><subject>Scale Handling</subject><subject>Scale Heterogeneity</subject><subject>Signal processing</subject><subject>Signal processing algorithms</subject><subject>Task analysis</subject><subject>Time series analysis</subject><subject>Time Series Prediction</subject><issn>2379-190X</issn><isbn>9798350344851</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2024</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1kM9KAzEYxKMgWGvfwMP6ALt--Z8cS7FWKKjsHryVmHypkW23ZBelb-8W7WkY5scwDCH3FCpKwT48L-Z1_SqMMLJiwERFQQhlGb8gM6ut4RK4GEN6SSaMa1tSC-_X5KbvvwDAaGEm5K3GNpbz4A5D-sai9q7FYuX2oU37bRG7XCy7jN71w8k3aTcymBP2xU8aPs88Dpi7Le4xDcdbchVd2-PsX6ekWT42i1W5fnkaF6_LpBkvxzkhKut88AqEFSbICCx4bSmoD0Yd9UJRL5UYFaQOwIPyhgXUzjgZ-ZTc_dUmRNwcctq5fNycH-C_mblQ5g</recordid><startdate>20240414</startdate><enddate>20240414</enddate><creator>Zhang, Xu</creator><creator>Huang, Zhengang</creator><creator>Wu, Yunzhi</creator><creator>Lu, Xun</creator><creator>Qi, Erpeng</creator><creator>Chen, Yunkai</creator><creator>Xue, Zhongya</creator><creator>Wang, Peng</creator><creator>Wang, Wei</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20240414</creationdate><title>Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity</title><author>Zhang, Xu ; Huang, Zhengang ; Wu, Yunzhi ; Lu, Xun ; Qi, Erpeng ; Chen, Yunkai ; Xue, Zhongya ; Wang, Peng ; Wang, Wei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i723-379df69acdc604948d5f02dc79106b21a1c461c564c46057d03d6c82de7a8a5f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Acoustics</topic><topic>Deep Learning</topic><topic>Forecasting</topic><topic>Multivariate Time Series</topic><topic>Neural networks</topic><topic>Scale Handling</topic><topic>Scale Heterogeneity</topic><topic>Signal processing</topic><topic>Signal processing algorithms</topic><topic>Task analysis</topic><topic>Time series analysis</topic><topic>Time Series Prediction</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Xu</creatorcontrib><creatorcontrib>Huang, Zhengang</creatorcontrib><creatorcontrib>Wu, Yunzhi</creatorcontrib><creatorcontrib>Lu, Xun</creatorcontrib><creatorcontrib>Qi, Erpeng</creatorcontrib><creatorcontrib>Chen, Yunkai</creatorcontrib><creatorcontrib>Xue, Zhongya</creatorcontrib><creatorcontrib>Wang, Peng</creatorcontrib><creatorcontrib>Wang, Wei</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zhang, Xu</au><au>Huang, Zhengang</au><au>Wu, Yunzhi</au><au>Lu, Xun</au><au>Qi, Erpeng</au><au>Chen, Yunkai</au><au>Xue, Zhongya</au><au>Wang, Peng</au><au>Wang, Wei</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity</atitle><btitle>ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</btitle><stitle>ICASSP</stitle><date>2024-04-14</date><risdate>2024</risdate><spage>7485</spage><epage>7489</epage><pages>7485-7489</pages><eissn>2379-190X</eissn><eisbn>9798350344851</eisbn><abstract>Time series forecasting (TSF) is crucial in various fields and has gained extensive research. However, most studies are conducted based on TS data with scale homogeneity. This paper proposes a self-Adaptive Scale-handling (AS) module to improve the performance of forecasting TS with scale heterogeneity. It consists of scale scaling selection and calibrating. We first calculate the priori scale factors of each time variable and then selectively calibrate the priori scale factors through neural networks. Hence, we can improve the performance of TSF algorithms by reducing scale restoration errors. We validate our method in collected industrial fund sales datasets from Ant Fortune and Alipay APP. Our AS module can easily be integrated into popular TSF models.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP48485.2024.10446923</doi><tpages>5</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2379-190X |
| ispartof | ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, p.7485-7489 |
| issn | 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_10446923 |
| source | IEEE Xplore All Conference Series |
| subjects | Acoustics Deep Learning Forecasting Multivariate Time Series Neural networks Scale Handling Scale Heterogeneity Signal processing Signal processing algorithms Task analysis Time series analysis Time Series Prediction |
| title | Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T19%3A34%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Self-Adaptive%20Scale%20Handling%20for%20Forecasting%20Time%20Series%20with%20Scale%20Heterogeneity&rft.btitle=ICASSP%202024%20-%202024%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing%20(ICASSP)&rft.au=Zhang,%20Xu&rft.date=2024-04-14&rft.spage=7485&rft.epage=7489&rft.pages=7485-7489&rft.eissn=2379-190X&rft_id=info:doi/10.1109/ICASSP48485.2024.10446923&rft.eisbn=9798350344851&rft_dat=%3Cieee_CHZPO%3E10446923%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i723-379df69acdc604948d5f02dc79106b21a1c461c564c46057d03d6c82de7a8a5f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10446923&rfr_iscdi=true |