基于GPR模型的用户量预测优化方法

TP391.7; 高斯过程回归(Gaussian process regression,GPR)是一种基于高斯过程的非参数化贝叶斯回归方法,其可以灵活适应不同类型数据,用于建模和预测数据之间的复杂关系,具有拟合能力强、泛化能力好等特点.针对海量用户场景下用户量实时预测问题,提出一种基于GPR的用户量预测优化方法.在滑动窗口方法处理数据的基础上,选择合适的核函数,基于k折交叉验证得到最佳超参数组合以实现GPR模型训练,完成在线用户量的实时预测并进行性能评估.实验结果表明,相比于采用训练集中输出数据方差的50％作为信号噪声估计量的传统方案,所提方法具有较高的预测准确度,并且在测试集均方根误差(ro...

Full description

Saved in:
Bibliographic Details
Published in系统工程与电子技术 Vol. 46; no. 8; pp. 2721 - 2729
Main Authors 刘学浩, 刘文学, 杨超三, 祝文晶, 宋玉, 李金海
Format Journal Article
LanguageChinese
Published 中国科学院大学集成电路学院,北京 100049%中国科学院微电子研究所通信与信息工程研发中心,北京 100029 01.08.2024
中国科学院微电子研究所通信与信息工程研发中心,北京 100029
Subjects
高斯过程回归
Gaussian process regression(GPR)
user quantity prediction
滑动窗口
交叉验证
用户量预测
cross-validation
超参数优化
sliding window
hyperparameter optimization
Online AccessGet full text
ISSN1001-506X
DOI10.12305/j.issn.1001-506X.2024.08.19

Cover

Abstract TP391.7; 高斯过程回归(Gaussian process regression,GPR)是一种基于高斯过程的非参数化贝叶斯回归方法,其可以灵活适应不同类型数据,用于建模和预测数据之间的复杂关系,具有拟合能力强、泛化能力好等特点.针对海量用户场景下用户量实时预测问题,提出一种基于GPR的用户量预测优化方法.在滑动窗口方法处理数据的基础上,选择合适的核函数,基于k折交叉验证得到最佳超参数组合以实现GPR模型训练,完成在线用户量的实时预测并进行性能评估.实验结果表明,相比于采用训练集中输出数据方差的50％作为信号噪声估计量的传统方案,所提方法具有较高的预测准确度,并且在测试集均方根误差(root mean square,RMS)、平均绝对误差(mean absolute error,MAE)、平均偏差(mean bias error,MBE)和决定系数R2这4个评估指标方面均有提升,其中MBE至少提升了 43.3％.
AbstractList TP391.7; 高斯过程回归(Gaussian process regression,GPR)是一种基于高斯过程的非参数化贝叶斯回归方法,其可以灵活适应不同类型数据,用于建模和预测数据之间的复杂关系,具有拟合能力强、泛化能力好等特点.针对海量用户场景下用户量实时预测问题,提出一种基于GPR的用户量预测优化方法.在滑动窗口方法处理数据的基础上,选择合适的核函数,基于k折交叉验证得到最佳超参数组合以实现GPR模型训练,完成在线用户量的实时预测并进行性能评估.实验结果表明,相比于采用训练集中输出数据方差的50％作为信号噪声估计量的传统方案,所提方法具有较高的预测准确度,并且在测试集均方根误差(root mean square,RMS)、平均绝对误差(mean absolute error,MAE)、平均偏差(mean bias error,MBE)和决定系数R2这4个评估指标方面均有提升,其中MBE至少提升了 43.3％.
Abstract_FL Gaussian process regression(GPR)is a non-parametric Bayesian regression method based on Gaussian processes.It is flexible in adapting to different types of data,and it is used to model and predict complex relationships between different types of data.It has strong fitting capabilities and good generalization abilities.A user quantity prediction optimization method based on GPR is proposed to tackle the problem of real-time user quantity prediction in the context of massive user scenario.Building upon the sliding window method for data processing,the method selects a suitable kernel function and uses k-fold cross-validation to determine the optimal hyperparameter combination for training the GPR model,which enables the real-time prediction of online user quantity.Finally,the performance of the model is evaluated.The experimental results demonstrate that compared with the traditional approach that uses half of the variance of the output data in the training set as the signal noise estimator,the proposed method has higher prediction accuracy and improvements in the four following evaluation metrics of root mean square(RMS),mean absolute error(MAE),mean bias error(MBE)and determination coefficient R2 on the test set.Specifically,the MBE shows an improvement of at least 43.3％.
Author 祝文晶
李金海
杨超三
刘学浩
宋玉
刘文学
AuthorAffiliation 中国科学院微电子研究所通信与信息工程研发中心,北京 100029;中国科学院大学集成电路学院,北京 100049%中国科学院微电子研究所通信与信息工程研发中心,北京 100029
AuthorAffiliation_xml – name: 中国科学院微电子研究所通信与信息工程研发中心,北京 100029;中国科学院大学集成电路学院,北京 100049%中国科学院微电子研究所通信与信息工程研发中心,北京 100029
Author_FL LIU Xuehao
ZHU Wenjing
LI Jinhai
LIU Wenxue
YANG Chaosan
SONG Yu
Author_FL_xml – sequence: 1
  fullname: LIU Xuehao
– sequence: 2
  fullname: LIU Wenxue
– sequence: 3
  fullname: YANG Chaosan
– sequence: 4
  fullname: ZHU Wenjing
– sequence: 5
  fullname: SONG Yu
– sequence: 6
  fullname: LI Jinhai
Author_xml – sequence: 1
  fullname: 刘学浩
– sequence: 2
  fullname: 刘文学
– sequence: 3
  fullname: 杨超三
– sequence: 4
  fullname: 祝文晶
– sequence: 5
  fullname: 宋玉
– sequence: 6
  fullname: 李金海
BookMark eNo9T8tKAzEUzaKCtfYvXAkT703mlaUUrUJBEQV3JZlkSgdJwSg-1gWFim60iAtFV92LiMXP6UzpXzhFcXU4h8N5LJGK7VlDyAoCRcYhWMto1zlLEQC9AMJDyoD5FGKKokKq__IiqTvXVRAgjwKI_Crx8pfxZHzb3N0rRq_582D61J_ej4rrz9nV3eytX3wMJt-P-c2wGH4V7w_LZCGVR87U_7BGDjY39htbXmunud1Yb3kOIRAehkqC0gkwlWquWElCJXiUIviam9hwo02cytKh0Q85SzjI-SoRgpA-4zWy-pt7Jm0qbaed9U6PbdnYPj_pJBf6MnPzgxADCv4DCwpZYQ
ClassificationCodes TP391.7
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.12305/j.issn.1001-506X.2024.08.19
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
DocumentTitle_FL Optimization method of user quantity prediction based on GPR model
EndPage 2729
ExternalDocumentID xtgcydzjs202408019
GrantInformation_xml – fundername: (地球观测与导航); (中国科学院“西部之光”人才培养引进计划)
  funderid: (地球观测与导航); (中国科学院“西部之光”人才培养引进计划)
GroupedDBID -0Y
2B.
4A8
5XA
5XJ
92E
92I
93N
ABJNI
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CUBFJ
CW9
PSX
TCJ
TGP
U1G
U5S
ID FETCH-LOGICAL-s1059-16ba0bdc02bfd3b2a0b6b937f104d3e8e3ede8fadc0d14632c30ab0519609a423
ISSN 1001-506X
IngestDate Thu May 29 04:00:31 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 8
Keywords 高斯过程回归
Gaussian process regression(GPR)
user quantity prediction
滑动窗口
交叉验证
用户量预测
cross-validation
超参数优化
sliding window
hyperparameter optimization
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1059-16ba0bdc02bfd3b2a0b6b937f104d3e8e3ede8fadc0d14632c30ab0519609a423
PageCount 9
ParticipantIDs wanfang_journals_xtgcydzjs202408019
PublicationCentury 2000
PublicationDate 2024-08-01
PublicationDateYYYYMMDD 2024-08-01
PublicationDate_xml – month: 08
  year: 2024
  text: 2024-08-01
  day: 01
PublicationDecade 2020
PublicationTitle 系统工程与电子技术
PublicationTitle_FL Systems Engineering and Electronics
PublicationYear 2024
Publisher 中国科学院大学集成电路学院,北京 100049%中国科学院微电子研究所通信与信息工程研发中心,北京 100029
中国科学院微电子研究所通信与信息工程研发中心,北京 100029
Publisher_xml – name: 中国科学院微电子研究所通信与信息工程研发中心,北京 100029
– name: 中国科学院大学集成电路学院,北京 100049%中国科学院微电子研究所通信与信息工程研发中心,北京 100029
SSID ssib051375074
ssib002263377
ssib001102898
ssib057620160
ssib023168126
ssib023646287
ssj0042237
Score 2.4446254
Snippet TP391.7; 高斯过程回归(Gaussian process regression,GPR)是一种基于高斯过程的非参数化贝叶斯回归方法,其可以灵活适应不同类型数据,用于建模和预测数据之间的复杂关系,具...
SourceID wanfang
SourceType Aggregation Database
StartPage 2721
Title 基于GPR模型的用户量预测优化方法
URI https://d.wanfangdata.com.cn/periodical/xtgcydzjs202408019
Volume 46
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVEBS
  databaseName: Inspec with Full Text
  issn: 1001-506X
  databaseCode: ADMLS
  dateStart: 20180801
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text
  omitProxy: false
  ssIdentifier: ssib057620160
  providerName: EBSCOhost
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1NaxQxNJQtiB7ET_ymYHOSqZOZZCY5ZnZnLWJFtIXeys5XxcMK7ha054JCRS9axIOip95FxOLPabf0X_heJjsz1VWql5BJXt5HXibvvZAPQmZDppI8EMzJ8G_iKswd6SWu46ahUmHGeCHwcPLC3WB-id9eFstTrUFj19LaMJlL1yeeK_kfrUIZ6BVPyf6DZiukUAB50C-koGFIj6RjGguqujTSNOaYyvjWvfs0DqiWVDNTG1MZ0TikCmq5yXCsBRgpaRTSWFEZUtnFjPYMTEAjYVoBzjZVEvFIyARYBWmkDIxPy3crx64tIofCyJCDFBiDhkBCCywBohYnZGLLCRACGN2hyjUsadx4gVTaVFdbjg19aRkBWB1YHrWaAGJYBJHGsDUI1HSM7CA4gIgxMw0shlmAqrFARgF4c3HE49XWvHI4W0RADns8olHHYAIJWYNlhZigi7GEY-2hqojKwGoF-6LqHaMk3Z2Ax2uPFRNa9ev2DWaCMeqJf-YpiqmeqBZo5WIhZrArDJfKKMqkqhx9XTPiKvVWJQDMrAC_joUKs8ABqNghnqG59P8spF3AKs0pbtgTrnmrsrK3dsm5nFdk03iG5WF564jBp5po5CFqFsbKI425isYcDgC8j9fa4MPXqD8drqbPsvVHA8_c6ufiVcHTHrgCbotM687CnQd1FIFOd2MVAiIU36-Pa3v41huroxZ8giHw6ihHMB_c8DqqEkiE4SpE6SBy8MjNm09jxo-R2bFYN_8ilDlW2C96_dWGB7x4ipy0oeuMLueh02Rq_eEZcqJxoelZ4ux93NndeQWz0Gj7096Hzf33G_tvtkcvvh08f33weWP0dXP3x7u9l1ujre-jL2_PkaVuvNied-yDLM4AwzCHBUnPTbLU9ZIi8xMPPoIE4puCuTzzc5n7eZbLogcQMMsHvpf6bg87BK-17EHgdp60-o_7-QUyE4Tc5YFI0VRwyQrlC5YWYC_cHksFDy6S61bYFTvhDlZ-V-GlI0FdJsfrueEKaQ2frOVXIZQYJtes6n8CZJ7Eig
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8EGPR%E6%A8%A1%E5%9E%8B%E7%9A%84%E7%94%A8%E6%88%B7%E9%87%8F%E9%A2%84%E6%B5%8B%E4%BC%98%E5%8C%96%E6%96%B9%E6%B3%95&rft.jtitle=%E7%B3%BB%E7%BB%9F%E5%B7%A5%E7%A8%8B%E4%B8%8E%E7%94%B5%E5%AD%90%E6%8A%80%E6%9C%AF&rft.au=%E5%88%98%E5%AD%A6%E6%B5%A9&rft.au=%E5%88%98%E6%96%87%E5%AD%A6&rft.au=%E6%9D%A8%E8%B6%85%E4%B8%89&rft.au=%E7%A5%9D%E6%96%87%E6%99%B6&rft.date=2024-08-01&rft.pub=%E4%B8%AD%E5%9B%BD%E7%A7%91%E5%AD%A6%E9%99%A2%E5%A4%A7%E5%AD%A6%E9%9B%86%E6%88%90%E7%94%B5%E8%B7%AF%E5%AD%A6%E9%99%A2%2C%E5%8C%97%E4%BA%AC+100049%25%E4%B8%AD%E5%9B%BD%E7%A7%91%E5%AD%A6%E9%99%A2%E5%BE%AE%E7%94%B5%E5%AD%90%E7%A0%94%E7%A9%B6%E6%89%80%E9%80%9A%E4%BF%A1%E4%B8%8E%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E7%A0%94%E5%8F%91%E4%B8%AD%E5%BF%83%2C%E5%8C%97%E4%BA%AC+100029&rft.issn=1001-506X&rft.volume=46&rft.issue=8&rft.spage=2721&rft.epage=2729&rft_id=info:doi/10.12305%2Fj.issn.1001-506X.2024.08.19&rft.externalDocID=xtgcydzjs202408019
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fxtgcydzjs%2Fxtgcydzjs.jpg