Intelligent Reflecting Surface‐Aided Wireless Networks: Deep Learning‐Based Channel Estimation Using ResNet+UNet.
Saved in:
| Title: | Intelligent Reflecting Surface‐Aided Wireless Networks: Deep Learning‐Based Channel Estimation Using ResNet+UNet. |
|---|---|
| Authors: | Monga, Sakhshra1 (AUTHOR) sakhshra@chitkara.edu.in, Pathania, Aditya1 (AUTHOR), Saluja, Nitin1 (AUTHOR), Gupta, Gunjan2 (AUTHOR) guptag@cput.ac.za, Sharma, Ashutosh3,4 (AUTHOR) |
| Source: | IET Communications (Wiley-Blackwell). Jan2025, Vol. 19 Issue 1, p1-15. 15p. |
| Subjects: | Channel estimation, Deep learning, Wireless communications, Augmented reality |
| Abstract: | Accurate channel estimation is essential for optimising intelligent reflecting surface‐assisted multi‐user communication systems, particularly in dynamic indoor environments. Conventional techniques such as least squares (LS), linear minimum mean square error (LMMSE), and orthogonal matching pursuit (OMP) suffer from noise sensitivity and fail to effectively capture spatial dependencies in high‐dimensional intelligent reflecting surface (IRS)‐assisted channels. To overcome these limitations, this work proposes a deep learning‐driven ResNet+UNet framework that refines initial LS estimates using residual learning and multi‐scale feature reconstruction. While UNet enhances channel estimation through hierarchical processing, efficiently decreasing noise and enhancing estimate accuracy, ResNet gathers spatial features. Simulation results show that the proposed method significantly outperforms existing methods across various performance metrics. In NMSE versus signal‐to‐noise ratio assessments, the proposed approach surpasses convolutional deep residual network (CDRN) by 59%, OMP by 81%, LMMSE by 114%, and LS by 115%. When IRS elements are modified, it overcomes CDRN by 60%, OMP by 78%, LS by 107%, and LMMSE by 110%. Along with this, recommended structure performs more effectively than CDRN by 39%, OMP by 44%, LS by 122%, and LMMSE by 129% across various antenna configurations. The proposed approach is particularly beneficial for augmented reality (AR) applications, where real‐time, high‐precision channel estimation ensures seamless data streaming and ultra‐low latency, enhancing immersive experiences in AR‐based communication and interactive environments. These results illustrate the proposed method's scalability and resilience, making it a suitable choice for next‐generation IRS‐assisted wireless communication networks. [ABSTRACT FROM AUTHOR] |
| Copyright of IET Communications (Wiley-Blackwell) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 190328046 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Intelligent Reflecting Surface‐Aided Wireless Networks: Deep Learning‐Based Channel Estimation Using ResNet+UNet. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Monga%2C+Sakhshra%22">Monga, Sakhshra</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> sakhshra@chitkara.edu.in</i><br /><searchLink fieldCode="AR" term="%22Pathania%2C+Aditya%22">Pathania, Aditya</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Saluja%2C+Nitin%22">Saluja, Nitin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gupta%2C+Gunjan%22">Gupta, Gunjan</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> guptag@cput.ac.za</i><br /><searchLink fieldCode="AR" term="%22Sharma%2C+Ashutosh%22">Sharma, Ashutosh</searchLink><relatesTo>3,4</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IET+Communications+%28Wiley-Blackwell%29%22">IET Communications (Wiley-Blackwell)</searchLink>. Jan2025, Vol. 19 Issue 1, p1-15. 15p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Channel+estimation%22">Channel estimation</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Wireless+communications%22">Wireless communications</searchLink><br /><searchLink fieldCode="DE" term="%22Augmented+reality%22">Augmented reality</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Accurate channel estimation is essential for optimising intelligent reflecting surface‐assisted multi‐user communication systems, particularly in dynamic indoor environments. Conventional techniques such as least squares (LS), linear minimum mean square error (LMMSE), and orthogonal matching pursuit (OMP) suffer from noise sensitivity and fail to effectively capture spatial dependencies in high‐dimensional intelligent reflecting surface (IRS)‐assisted channels. To overcome these limitations, this work proposes a deep learning‐driven ResNet+UNet framework that refines initial LS estimates using residual learning and multi‐scale feature reconstruction. While UNet enhances channel estimation through hierarchical processing, efficiently decreasing noise and enhancing estimate accuracy, ResNet gathers spatial features. Simulation results show that the proposed method significantly outperforms existing methods across various performance metrics. In NMSE versus signal‐to‐noise ratio assessments, the proposed approach surpasses convolutional deep residual network (CDRN) by 59%, OMP by 81%, LMMSE by 114%, and LS by 115%. When IRS elements are modified, it overcomes CDRN by 60%, OMP by 78%, LS by 107%, and LMMSE by 110%. Along with this, recommended structure performs more effectively than CDRN by 39%, OMP by 44%, LS by 122%, and LMMSE by 129% across various antenna configurations. The proposed approach is particularly beneficial for augmented reality (AR) applications, where real‐time, high‐precision channel estimation ensures seamless data streaming and ultra‐low latency, enhancing immersive experiences in AR‐based communication and interactive environments. These results illustrate the proposed method's scalability and resilience, making it a suitable choice for next‐generation IRS‐assisted wireless communication networks. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IET Communications (Wiley-Blackwell) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=190328046 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1049/cmu2.70075 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 15 StartPage: 1 Subjects: – SubjectFull: Channel estimation Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Wireless communications Type: general – SubjectFull: Augmented reality Type: general Titles: – TitleFull: Intelligent Reflecting Surface‐Aided Wireless Networks: Deep Learning‐Based Channel Estimation Using ResNet+UNet. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Monga, Sakhshra – PersonEntity: Name: NameFull: Pathania, Aditya – PersonEntity: Name: NameFull: Saluja, Nitin – PersonEntity: Name: NameFull: Gupta, Gunjan – PersonEntity: Name: NameFull: Sharma, Ashutosh IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Text: Jan2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 17518628 Numbering: – Type: volume Value: 19 – Type: issue Value: 1 Titles: – TitleFull: IET Communications (Wiley-Blackwell) Type: main |
| ResultId | 1 |
