{"title":"A Long Short-Term Memory Approach to Incorporating Multifrequency Data Into Deep-Learning-Based Microwave Imaging","authors":"Ben Martin;Colin Gilmore;Ian Jeffrey","doi":"10.1109/TAP.2024.3437241","DOIUrl":null,"url":null,"abstract":"Motivated by the benefits of using multifrequency data in traditional nonlinear iterative optimization approaches in microwave imaging (MWI), this work compares three different approaches to using multifrequency data in deep-learning-based MWI. Specifically, we evaluate the imaging capabilities of the following: 1) a multichannel simultaneous frequency data-to-image U-Net-like network; 2) a novel cascaded multifrequency network; and 3) a novel long short-term memory (LSTM)-based recurrent network. The cascaded and LSTM networks are motivated by marching-on-frequency approaches and attempt to leverage reconstructions at lower frequencies as additional input information at higher frequencies. Results on both synthetic and experimental data show that the LSTM-based approach significantly outperforms the other models.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Antennas and Propagation","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10630655/","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
Motivated by the benefits of using multifrequency data in traditional nonlinear iterative optimization approaches in microwave imaging (MWI), this work compares three different approaches to using multifrequency data in deep-learning-based MWI. Specifically, we evaluate the imaging capabilities of the following: 1) a multichannel simultaneous frequency data-to-image U-Net-like network; 2) a novel cascaded multifrequency network; and 3) a novel long short-term memory (LSTM)-based recurrent network. The cascaded and LSTM networks are motivated by marching-on-frequency approaches and attempt to leverage reconstructions at lower frequencies as additional input information at higher frequencies. Results on both synthetic and experimental data show that the LSTM-based approach significantly outperforms the other models.
期刊介绍:
IEEE Transactions on Antennas and Propagation includes theoretical and experimental advances in antennas, including design and development, and in the propagation of electromagnetic waves, including scattering, diffraction, and interaction with continuous media; and applications pertaining to antennas and propagation, such as remote sensing, applied optics, and millimeter and submillimeter wave techniques