Hybrid Quantum ResNet for Time Series Classification

IF 5.4 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Dae-Il Noh;Seon-Geun Jeong;Won-Joo Hwang
{"title":"Hybrid Quantum ResNet for Time Series Classification","authors":"Dae-Il Noh;Seon-Geun Jeong;Won-Joo Hwang","doi":"10.1109/TETC.2025.3563944","DOIUrl":null,"url":null,"abstract":"Residual networks (ResNet) are known to be effective for image classification. However, challenges such as computational time remain because of the significant number of parameters. Quantum computing using quantum entanglement and quantum parallelism is an emerging computing paradigm that addresses this issue. Although quantum advantage is still studied in many research fields, quantum machine learning is a research area that leverages the strengths of quantum computing and machine learning. In this study, we investigated the quantum speedup with respect to the number of parameters in each model for a time-series classification task. This paper proposes a novel hybrid quantum residual network (HQResNet) inspired by the classical ResNet for time-series classification. HQResNet introduces a classical layer before a quantum convolutional neural network (QCNN), where the QCNN is used as a residual block. These structures enable shortcut connections and are particularly effective in achieving classification tasks without a data re-uploading scheme. We used ultra-wide-band (UWB) channel impulse response data to demonstrate the performance of the proposed algorithm and compared the state-of-the-art benchmarks with HQResNet using evaluation metrics. The results show that HQResNet achieved high performance with a small number of trainable parameters.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 3","pages":"1083-1098"},"PeriodicalIF":5.4000,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Emerging Topics in Computing","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10981540/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Residual networks (ResNet) are known to be effective for image classification. However, challenges such as computational time remain because of the significant number of parameters. Quantum computing using quantum entanglement and quantum parallelism is an emerging computing paradigm that addresses this issue. Although quantum advantage is still studied in many research fields, quantum machine learning is a research area that leverages the strengths of quantum computing and machine learning. In this study, we investigated the quantum speedup with respect to the number of parameters in each model for a time-series classification task. This paper proposes a novel hybrid quantum residual network (HQResNet) inspired by the classical ResNet for time-series classification. HQResNet introduces a classical layer before a quantum convolutional neural network (QCNN), where the QCNN is used as a residual block. These structures enable shortcut connections and are particularly effective in achieving classification tasks without a data re-uploading scheme. We used ultra-wide-band (UWB) channel impulse response data to demonstrate the performance of the proposed algorithm and compared the state-of-the-art benchmarks with HQResNet using evaluation metrics. The results show that HQResNet achieved high performance with a small number of trainable parameters.
时间序列分类的混合量子ResNet
残差网络(ResNet)是一种有效的图像分类方法。然而,由于参数数量巨大,计算时间等挑战仍然存在。使用量子纠缠和量子并行的量子计算是解决这一问题的新兴计算范式。虽然量子优势在很多研究领域仍在研究,但量子机器学习是一个利用量子计算和机器学习优势的研究领域。在本研究中,我们研究了时间序列分类任务中每个模型中参数数量的量子加速。本文在经典量子残差网络的基础上,提出了一种新的用于时间序列分类的混合量子残差网络(HQResNet)。HQResNet在量子卷积神经网络(QCNN)之前引入了一个经典层,其中QCNN用作残差块。这些结构支持快捷连接,并且在无需数据重新上传方案的情况下特别有效地完成分类任务。我们使用超宽带(UWB)信道脉冲响应数据来演示所提出算法的性能,并使用评估指标将最先进的基准与HQResNet进行比较。结果表明,HQResNet在训练参数较少的情况下取得了较高的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IEEE Transactions on Emerging Topics in Computing
IEEE Transactions on Emerging Topics in Computing Computer Science-Computer Science (miscellaneous)
CiteScore
12.10
自引率
5.10%
发文量
113
期刊介绍: IEEE Transactions on Emerging Topics in Computing publishes papers on emerging aspects of computer science, computing technology, and computing applications not currently covered by other IEEE Computer Society Transactions. Some examples of emerging topics in computing include: IT for Green, Synthetic and organic computing structures and systems, Advanced analytics, Social/occupational computing, Location-based/client computer systems, Morphic computer design, Electronic game systems, & Health-care IT.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信