A Convolutional Neural Network with Multifrequency and Structural Similarity Loss Functions for Electromagnetic Imaging

doi:10.3390/s24154994

淡江大學機構典藏 > 工學院 > 電機工程學系暨研究所 > 期刊論文 > Item 987654321/126940

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/126940

题名:	A Convolutional Neural Network with Multifrequency and Structural Similarity Loss Functions for Electromagnetic Imaging
作者:	Chiu, Chien-ching;Lin, Che-yu;Chi, Yu-jen;Hsu, Hsiu-hui;Chen, Po-hsiang
关键词:	electromagnetic imaging;artificial intelligence;anisotropic objects;back-propagation scheme;loss function;convolutional neural network
日期:	2024-08
上传时间:	2025-03-20 09:31:59 (UTC+8)
出版者:	MDPI
摘要:	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.
關聯:	Sensors 24(15),　4994
DOI:	10.3390/s24154994
显示于类别:	[電機工程學系暨研究所] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	19	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章

数据加载中.....