التفاصيل البيبلوغرافية
| العنوان: |
A Convolutional Neural Network with Multifrequency and Structural Similarity Loss Functions for Electromagnetic Imaging. |
| المؤلفون: |
Chiu CC; Department of Electrical and Computer and Engineering, Tamkang University, New Taipei City 251301, Taiwan., Lin CY; Department of Electrical and Computer and Engineering, Tamkang University, New Taipei City 251301, Taiwan., Chi YJ; Department of Electrical and Computer and Engineering, Tamkang University, New Taipei City 251301, Taiwan., Hsu HH; Department of Electrical and Computer and Engineering, Tamkang University, New Taipei City 251301, Taiwan., Chen PH; Department of Electrical and Computer and Engineering, Tamkang University, New Taipei City 251301, Taiwan., Jiang H; School of Engineering, San Francisco State University, San Francisco, CA 94117-1080, USA. |
| المصدر: |
Sensors (Basel, Switzerland) [Sensors (Basel)] 2024 Aug 01; Vol. 24 (15). Date of Electronic Publication: 2024 Aug 01. |
| نوع المنشور: |
Journal Article |
| اللغة: |
English |
| بيانات الدورية: |
Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: PubMed not MEDLINE; MEDLINE |
| أسماء مطبوعة: |
Original Publication: Basel, Switzerland : MDPI, c2000- |
| مستخلص: |
In this paper, artificial intelligence (AI) technology is applied to the electromagnetic imaging of anisotropic objects. Advances in magnetic anomaly sensing systems and electromagnetic imaging use electromagnetic principles to detect and characterize subsurface or hidden objects. We use measured multifrequency scattered fields to calculate the initial dielectric constant distribution of anisotropic objects through the backpropagation scheme (BPS). Later, the estimated multifrequency permittivity distribution is input to a convolutional neural network (CNN) for the adaptive moment estimation (ADAM) method to reconstruct a more accurate image. In the meantime, we also improve the definition of loss function in the CNN. Numerical results show that the improved loss function unifying the structural similarity index measure (SSIM) and root mean square error (RMSE) can effectively enhance image quality. In our simulation environment, noise interference is considered for both TE (transverse electric) and TM (transverse magnetic) waves to reconstruct anisotropic scatterers. Lastly, we conclude that multifrequency reconstructions are more stable and precise than single-frequency reconstructions. |
| معلومات مُعتمدة: |
NSTC 112-2221-E-032-028 National Science and Technology Council, Taiwan |
| فهرسة مساهمة: |
Keywords: anisotropic objects; artificial intelligence; back-propagation scheme; convolutional neural network; electromagnetic imaging; loss function |
| تواريخ الأحداث: |
Date Created: 20240810 Latest Revision: 20240812 |
| رمز التحديث: |
20240813 |
| مُعرف محوري في PubMed: |
PMC11314793 |
| DOI: |
10.3390/s24154994 |
| PMID: |
39124041 |
| قاعدة البيانات: |
MEDLINE |
Full Text Finder