View in EDS HTML Full Text PDF Full Text

Real-Time Cell Gap Estimation in LC-Filled Devices Using Lightweight Neural Networks for Edge Deployment.

Saved in:
Bibliographic Details
Title: Real-Time Cell Gap Estimation in LC-Filled Devices Using Lightweight Neural Networks for Edge Deployment.
Authors: Huang, Chi-Yen1 (AUTHOR) chiyen@cc.ncue.edu.tw, Zhang, You-Lun2 (AUTHOR), Liao, Su-Yu2,3 (AUTHOR), Huang, Wen-Chun3,4 (AUTHOR), Chen, Jiann-Heng4,5 (AUTHOR), Dong, Bo-Chang5,6 (AUTHOR), Hsu, Che-Ju1,6 (AUTHOR), Huang, Chun-Ying2 (AUTHOR)
Source: Nanomaterials (2079-4991). Aug2025, Vol. 15 Issue 16, p1289. 11p.
Subjects: Liquid crystal devices, Artificial neural networks, Real-time computing, Optical devices, Edge computing, Optical measurements
Abstract: Accurate determination of the liquid crystal (LC) cell gap after filling is essential for ensuring device performance in LC-based optical applications. However, the introduction of birefringent materials significantly distorts the transmission spectrum, complicating traditional optical analysis. In this work, we propose a lightweight machine learning framework using a shallow multilayer perceptron (MLP) to estimate the cell gap directly from the transmission spectrum of filled LC cells. The model was trained on experimentally acquired spectra with peak-to-peak interferometry-derived ground truth values. We systematically evaluated different optimization algorithms, activation functions, and hidden neuron configurations to identify an optimal model setting that balances prediction accuracy and computational simplicity. The best-performing model, using exponential activation with eight hidden units and BFGS optimization, achieved a correlation coefficient near 1 and an RMSE below 0.1 μm across multiple random seeds and training–test splits. The model was successfully deployed on a Raspberry Pi 4, demonstrating real-time inference with low latency, memory usage, and power consumption. These results validate the feasibility of portable, edge-based LC inspection systems for in situ diagnostics and quality control. [ABSTRACT FROM AUTHOR]
Copyright of Nanomaterials (2079-4991) is the property of MDPI 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
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 187612659
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Real-Time Cell Gap Estimation in LC-Filled Devices Using Lightweight Neural Networks for Edge Deployment.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Huang%2C+Chi-Yen%22">Huang, Chi-Yen</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> chiyen@cc.ncue.edu.tw</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+You-Lun%22">Zhang, You-Lun</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liao%2C+Su-Yu%22">Liao, Su-Yu</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Huang%2C+Wen-Chun%22">Huang, Wen-Chun</searchLink><relatesTo>3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Jiann-Heng%22">Chen, Jiann-Heng</searchLink><relatesTo>4,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dong%2C+Bo-Chang%22">Dong, Bo-Chang</searchLink><relatesTo>5,6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hsu%2C+Che-Ju%22">Hsu, Che-Ju</searchLink><relatesTo>1,6</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Huang%2C+Chun-Ying%22">Huang, Chun-Ying</searchLink><relatesTo>2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Nanomaterials+%282079-4991%29%22">Nanomaterials (2079-4991)</searchLink>. Aug2025, Vol. 15 Issue 16, p1289. 11p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Liquid+crystal+devices%22">Liquid crystal devices</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Real-time+computing%22">Real-time computing</searchLink><br /><searchLink fieldCode="DE" term="%22Optical+devices%22">Optical devices</searchLink><br /><searchLink fieldCode="DE" term="%22Edge+computing%22">Edge computing</searchLink><br /><searchLink fieldCode="DE" term="%22Optical+measurements%22">Optical measurements</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Accurate determination of the liquid crystal (LC) cell gap after filling is essential for ensuring device performance in LC-based optical applications. However, the introduction of birefringent materials significantly distorts the transmission spectrum, complicating traditional optical analysis. In this work, we propose a lightweight machine learning framework using a shallow multilayer perceptron (MLP) to estimate the cell gap directly from the transmission spectrum of filled LC cells. The model was trained on experimentally acquired spectra with peak-to-peak interferometry-derived ground truth values. We systematically evaluated different optimization algorithms, activation functions, and hidden neuron configurations to identify an optimal model setting that balances prediction accuracy and computational simplicity. The best-performing model, using exponential activation with eight hidden units and BFGS optimization, achieved a correlation coefficient near 1 and an RMSE below 0.1 μm across multiple random seeds and training–test splits. The model was successfully deployed on a Raspberry Pi 4, demonstrating real-time inference with low latency, memory usage, and power consumption. These results validate the feasibility of portable, edge-based LC inspection systems for in situ diagnostics and quality control. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Nanomaterials (2079-4991) is the property of MDPI 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=187612659
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/nano15161289
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 1289
    Subjects:
      – SubjectFull: Liquid crystal devices
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Real-time computing
        Type: general
      – SubjectFull: Optical devices
        Type: general
      – SubjectFull: Edge computing
        Type: general
      – SubjectFull: Optical measurements
        Type: general
    Titles:
      – TitleFull: Real-Time Cell Gap Estimation in LC-Filled Devices Using Lightweight Neural Networks for Edge Deployment.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Huang, Chi-Yen
      – PersonEntity:
          Name:
            NameFull: Zhang, You-Lun
      – PersonEntity:
          Name:
            NameFull: Liao, Su-Yu
      – PersonEntity:
          Name:
            NameFull: Huang, Wen-Chun
      – PersonEntity:
          Name:
            NameFull: Chen, Jiann-Heng
      – PersonEntity:
          Name:
            NameFull: Dong, Bo-Chang
      – PersonEntity:
          Name:
            NameFull: Hsu, Che-Ju
      – PersonEntity:
          Name:
            NameFull: Huang, Chun-Ying
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 08
              Text: Aug2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 20794991
          Numbering:
            – Type: volume
              Value: 15
            – Type: issue
              Value: 16
          Titles:
            – TitleFull: Nanomaterials (2079-4991)
              Type: main
ResultId 1