CNN-Based Deep Learning Architecture for Electromagnetic Imaging of Rough Surface Profiles

被引：12

作者：

Aydin, Izde ^{[1
]}

Budak, Guven ^{[1
]}

Sefer, Ahmet ^{[2
]}

Yapar, Ali ^{[1
]}

机构：

[1] Istanbul Tech Univ, Elect & Commun Engn Dept, TR-34469 Istanbul, Turkey

[2] Isik Univ, Dept Elect & Elect Engn, TR-34980 Istanbul, Turkey

来源：

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION | 2022年 / 70卷 / 10期

关键词：

Surface roughness; Rough surfaces; Imaging; Surface waves; Surface treatment; Inverse problems; Electromagnetics; Convolutional neural network (CNN); deep learning (DL); electromagnetics (EMs); inverse scattering problems; rough surface imaging; INVERSE SCATTERING; NEURAL-NETWORKS; RECONSTRUCTION; CLASSIFICATION; 2-D;

D O I：

10.1109/TAP.2022.3177493

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A convolutional neural network (CNN)-based deep learning (DL) technique for electromagnetic (EM) imaging of rough surfaces separating two dielectric media is presented. The direct scattering problem is formulated through the conventional integral equations, and the synthetic scattered field data are produced by a fast numerical solution technique, which is based on method of moments (MoM). Two different special CNN architectures are designed and implemented for the solution of the inverse rough surface imaging problem, wherein both random and deterministic rough surface profiles can be imaged. It is shown by a comprehensive numerical analysis that the proposed DL inversion scheme is very effective and robust.

引用

页码：9752 / 9763

页数：12

共 50 条

[21] Deep learning models based on CNN architecture for early keratoconus detection using corneal topographic maps
Kallel, Imen Fourati
Mahfoudhi, Oussema
Kammoun, Sonda
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (16) : 49173 - 49193
[22] CNN-based Classification of Contaminated High Voltage Insulator Surface
Serikbay, Arailym
Bagheri, Mehdi
Zollanvari, Amin
Saukhimov, Almaz A.
2022 IEEE INTERNATIONAL CONFERENCE ON ENVIRONMENT AND ELECTRICAL ENGINEERING AND 2022 IEEE INDUSTRIAL AND COMMERCIAL POWER SYSTEMS EUROPE (EEEIC / I&CPS EUROPE), 2022,
[23] CNN-based End-to-End Learning for Lane Centering
Ebu, Iffat Ara
Islam, Fahmida
Ball, John E.
Goodin, Christopher T.
AUTONOMOUS SYSTEMS:SENSORS, PROCESSING, AND SECURITY FOR GROUND, AIR, SEA, AND SPACE VEHICLES AND INFRASTRUCTURE 2024, 2024, 13052
[24] CNN-Based Machine Learning Channel on TDMR Drive Data
Qin, Yuwei
Bellam, Pradhan
Galbraith, Rick
Hanson, Weldon
Ravindran, Niranjay
Oboukhov, Iouri
Zhu, Jian-Gang
IEEE TRANSACTIONS ON MAGNETICS, 2022, 58 (04)
[25] Deep CNN-based visual defect detection: Survey of current literature
Jha, Shashi Bhushan
Babiceanu, Radu F.
COMPUTERS IN INDUSTRY, 2023, 148
[26] CNN-Based Target Recognition and Identification for Infrared Imaging in Defense Systems
d'Acremont, Antoine
Fablet, Ronan
Baussard, Alexandre
Quin, Guillaume
SENSORS, 2019, 19 (09)
[27] Comparison performance of the CNN-based deep learning models for the distinguishing ultrasound pretreated and microwave dried jujube fruits
Ulu, Banu
Gunaydin, Seda
Cetin, Necati
MEASUREMENT, 2025, 249
[28] Monitoring of Arc Plasma Process Parameter Using CNN-Based Deep Learning Algorithm to Accommodate Sensor Failure
Sethi, Shakti Prasad
Das, Debi Prasad
Behera, Santosh Kumar
IEEE TRANSACTIONS ON PLASMA SCIENCE, 2023, 51 (06) : 1434 - 1445
[29] Tensor Factorization and Attention-Based CNN-LSTM Deep-Learning Architecture for Improved Classification of Missing Physiological Sensors Data
Akmal, Muhammad
IEEE SENSORS JOURNAL, 2023, 23 (02) : 1286 - 1294
[30] A CNN-Based Adaptive Surface Monitoring System for Fused Deposition Modeling
Wang, Yuanbin
Huang, Jiakang
Wang, Yuan
Feng, Sihang
Peng, Tao
Yang, Huayong
Zou, Jun
IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2020, 25 (05) : 2287 - 2296

← 1 2 3 4 5 →