{"title":"AI-Assisted Antenna Optimization: Integrating Evolutionary and Inverse Cascade Neural Networks With Differential Evolution","authors":"Fengling Peng;Xing Chen;Jingkai Xue","doi":"10.1109/TAP.2025.3553761","DOIUrl":"https://doi.org/10.1109/TAP.2025.3553761","url":null,"abstract":"Combining artificial intelligence (AI) technology with antenna optimization has long been a research direction with significant potential. However, most contributions in this area have focused on constructing surrogate models for antenna optimization using supervised machine learning. These surrogate models can quickly evaluate antenna design solutions but cannot directly modify the design variables to drive optimization. To address this limitation, this article designs two neural networks to assist the differential evolution (DE) algorithm in optimizing antennas. The first is an evolutionary neural network (ENN), which learns the modification patterns of DE on antenna design variables, thereby enhancing the probability of producing more optimal solutions. The second is an inverse cascade network, constructed by first creating multiple inverse subnetworks for each frequency point and then synthesizing the outputs of these subnetworks using a cascade network. This type of neural network can directly output high-quality solutions based on specific requirements. Finally, by integrating these two networks with DE, an AI-assisted antenna optimization method is realized. Experimental results show that with the assistance of these two neural networks, DE can achieve faster optimization of antennas.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 7","pages":"4384-4396"},"PeriodicalIF":4.6,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dreamer: Dual-RIS-Aided Imager in Complementary Modes","authors":"Fuhai Wang;Yunlong Huang;Zhanbo Feng;Rujing Xiong;Zhe Li;Chun Wang;Tiebin Mi;Robert Caiming Qiu;Zenan Ling","doi":"10.1109/TAP.2025.3553767","DOIUrl":"https://doi.org/10.1109/TAP.2025.3553767","url":null,"abstract":"Reconfigurable intelligent surfaces (RISs) have emerged as a promising auxiliary technology for radio frequency imaging. However, existing works face challenges of faint and intricate backscattered waves and the restricted field of view (FoV), both resulting from complex target structures and a limited number of antennas. The synergistic benefits of multi-RIS-aided imaging hold promise for addressing these challenges. Here, we propose a dual-RIS-aided imaging system, Dreamer, which operates collaboratively in complementary modes (reflection mode and transmission mode). Dreamer significantly expands FoV and enhances perception by deploying dual-RIS across various spatial and measurement patterns. Specifically, we perform a fine-grained analysis of how radio-frequency (RF) signals encode scene information in the scattered object modeling. Based on this modeling, we design illumination strategies to balance spatial resolution and observation scale and implement a prototype system in a typical indoor environment. Moreover, we design a novel artificial neural network with a CNN-external-attention mechanism to <italic>translate</i> RF signals into high-resolution images of human silhouettes. Our approach achieves an impressive structural similarity index (SSIM) score of 0.83 surpassing state-of-the-art solutions, validating its effectiveness in broadening perception modes and enhancing imaging capabilities. The code to reproduce our results is available at: <uri>https://github.com/fuhaiwang/Dreamer</uri>.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 7","pages":"4863-4878"},"PeriodicalIF":4.6,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144606369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ziheng Fu;Swagato Mukherjee;Michael T. Lanagan;Prasenjit Mitra;Tarun Chawla;Ram M. Narayanan
{"title":"Transfer Learning and Double U-Net Empowered Wave Propagation Model in Complex Indoor Environments","authors":"Ziheng Fu;Swagato Mukherjee;Michael T. Lanagan;Prasenjit Mitra;Tarun Chawla;Ram M. Narayanan","doi":"10.1109/TAP.2025.3553952","DOIUrl":"https://doi.org/10.1109/TAP.2025.3553952","url":null,"abstract":"A machine learning (ML) network based on transfer learning and transformer networks is applied to wave propagation models for complex indoor settings. This network is designed to predict signal propagation in environments with a variety of objects, effectively simulating the diverse range of furniture typically found in indoor spaces. We propose Attention U-Net with efficient networks as the backbone, to process images encoded with the essential information of the indoor environment. The indoor environment is defined by its fundamental structure, such as the arrangement of walls, windows, and doorways, alongside varying configurations of furniture placement. An innovative algorithm is introduced to generate a 3-D environment from a 2-D floorplan, which is crucial for the efficient collection of data for training. The model is evaluated by comparing the predicted signal coverage map with ray-tracing (RT) simulations. The prediction results show a root-mean-square error (RMSE) of less than 3 dB across all tested scenarios, with significant improvements observed when using a double U-Net structure compared to a single U-Net model.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 7","pages":"4814-4828"},"PeriodicalIF":4.6,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144606354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Virtual VNA 2.0: Ambiguity-Free Scattering Matrix Estimation by Terminating Not-Directly-Accessible Ports With Tunable and Coupled Loads","authors":"Philipp del Hougne","doi":"10.1109/TAP.2025.3553371","DOIUrl":"https://doi.org/10.1109/TAP.2025.3553371","url":null,"abstract":"We recently introduced the “virtual vector network analyzer (VNA)” concept, which estimates the <inline-formula> <tex-math>$N times N$ </tex-math></inline-formula> scattering matrix characterizing an arbitrarily complex linear reciprocal system with N monomodal lumped ports by inputting and outputting waves only via <inline-formula> <tex-math>$N_{mathrm {A}}lt N$ </tex-math></inline-formula> ports while terminating the <inline-formula> <tex-math>$N_{mathrm {S}}=N-N_{mathrm {A}}$ </tex-math></inline-formula> remaining ports with known tunable individual loads. However, vexing ambiguities about the signs of the off-diagonal scattering coefficients involving the <inline-formula> <tex-math>$N_{mathrm {S}}$ </tex-math></inline-formula> not-directly-accessible (NDA) ports remained. If only phase-insensitive measurements were used, an additional blockwise phase ambiguity ensued. Here, inspired by the emergence of “beyond-diagonal reconfigurable intelligent surfaces (BD-RISs)” in wireless communications, we lift all ambiguities with at most <inline-formula> <tex-math>$N_{mathrm {S}}$ </tex-math></inline-formula> additional measurements involving a known multiport load network (MPLN). We experimentally validate our approach based on an eight-port chaotic cavity, using a simple coaxial cable as a two-port load network (2PLN). Endowed with the MPLN, the “Virtual VNA 2.0” now can estimate the entire scattering matrix without any ambiguity, even without ever measuring phase information explicitly. Potential applications include the challenging characterization of large and/or embedded antenna arrays.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 7","pages":"4903-4908"},"PeriodicalIF":4.6,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144606416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Highly Efficient Hybrid WPT System Possessing Beam-Steering Beam-Splitting and Near-Field Focusing Capability at ISM Band","authors":"Nilanjan Dutta;Shrabani Mukherjee;Kaushik Mandal","doi":"10.1109/TAP.2025.3553772","DOIUrl":"https://doi.org/10.1109/TAP.2025.3553772","url":null,"abstract":"This article proposes a new hybrid wireless power transfer (WPT) system that can charge: a single target (fixed/moving), multiple targets simultaneously, and a single target quickly. The proposed WPT system can operate either in beam-steering mode for charging a device in motion or in focusing mode for faster charging of a single device. In addition, the beam-splitting capability of the proposed WPT system ensures simultaneous charging of up to four devices. The proposed system utilizes a <inline-formula> <tex-math>$2times 2$ </tex-math></inline-formula> array antenna as its transmitting element and a flexible receiving antenna operating at the industrial, scientific, and medical (ISM) band (2.40–2.50 GHz). An innovative feeding network consisting of active switches, radial stubs, and quarter-wave transformers has been designed. By controlling the biasing of active switches, the beam pattern of transmitting array can be switched between its ten operating states. In seven of its operating states, the transmitting array steers the radiated beam in seven different directions, while in the other three states, it splits the radiated beam into two, three, or four beams. To realize faster charging, a near-field focusing (NFF) metasurface (MTS) has also been designed and integrated to enhance the power transfer efficiency (PTE) to 40.27% over a transfer distance of 50 mm.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 7","pages":"4397-4408"},"PeriodicalIF":4.6,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Tensor-Train FDTD: Implementation Aspects and Performance Analysis","authors":"Qiping Zhou;Fernando L. Teixeira","doi":"10.1109/TAP.2025.3551598","DOIUrl":"https://doi.org/10.1109/TAP.2025.3551598","url":null,"abstract":"Tensor-train (TT) decompositions have the potential to significantly improve the performance of finite-difference time-domain (FDTD) algorithms in terms of CPU time and memory storage. To this end, we extend TT-format FDTD implementations to cases incorporating perfectly matched layer (PML) boundaries. We assess the performance of TT-format FDTD implementations for different error tolerance levels. In particular, the tradeoff between accuracy and efficiency is analyzed. Additionally, a regularization approach is proposed to control rank growth in TT-format FDTD simulations with highly disparate field amplitude levels across the domain brought forth by PML absorption and diverse source excitations.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 7","pages":"4637-4645"},"PeriodicalIF":4.6,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"TE–TM Balanced Wide-Angle Metacells for Low Scan-Loss Metalens Antenna Using Prior Knowledge-Guided Generative Deep Learning-Enabled Method","authors":"Yanhe Lyu;Theng Huat Gan;Zhi Ning Chen","doi":"10.1109/TAP.2025.3552837","DOIUrl":"https://doi.org/10.1109/TAP.2025.3552837","url":null,"abstract":"The miniaturized cage-like metacell is proposed for TE–TM balanced wide-angle transmission using the prior knowledge (PK)-guided generative deep learning (DL) method, enabling a low scan-loss metalens antenna. An initial metacell topology and pattern generation rules are proposed, guided by physical constraints and engineering experience, and efficiently construct a high-degree-of-freedom (DoF) dataset for training a conditional deep convolutional generative adversarial network (cDCGAN). With a trained generator, diverse DL-enabled miniaturized cage-like metacells achieve a transmittance higher than 0.75 with fluctuations below 0.15 and a phase shift range of 295° with variations less than 15° at 10 GHz under TM and TE polarized incident waves from 0° to 45°. To verify the generative designs, a metalens antenna prototype consisting of the proposed metacells shows a realized gain of 26.2 dBi with an aperture efficiency of 36.3% and measured scan losses lower than 2.6 and 2.4 dB as TE- and TM-polarized beams scanning from −40° to 40° at 10 GHz.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 5","pages":"2940-2949"},"PeriodicalIF":4.6,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An Efficient Wide-Angle/Wideband RCS Prediction Method for PEC Targets With Indeterminate Shape","authors":"Min Zhao;Yu-Xi Zhu;Zi He;Da-Zhi Ding","doi":"10.1109/TAP.2025.3553771","DOIUrl":"https://doi.org/10.1109/TAP.2025.3553771","url":null,"abstract":"A multidomain prediction method (MDPM) is introduced for computing radar cross section (RCS) across the frequency, angular, and spatial (geometric shape) domains. Then, the electromagnetic scattering characteristics for targets of indeterminate geometries are obtained rapidly in scalar domains. Compared with the traditional 1-D estimation methods, the proposed method in this article can achieve effective prediction in both scalar and vector domains. Specifically, the vector domain is derived from the point clouds of the model. The surface current can be approximated using a uniformly convergent bivariate Chebyshev polynomial. In previous studies, the Chebyshev polynomial has often been replaced by the Maehly approximation (a rational polynomial) to extend the prediction range. However, due to the singularity of the coefficient matrix and the lack of certain coefficients, this substitution does not always result in increased accuracy. Consequently, the classical Chebyshev polynomial approach is adopted to enhance the stability and accuracy of the results. Additionally, the coefficient matrix is calculated using circular indexing, thereby optimizing the algorithmic framework further. The derivative calculations are not involved in the proposed method. It not only simplifies the solution process and reduces memory consumption but also calculates the scattering characteristics of complex targets. Compared to the Monte Carlo (MC) method, the proposed method can significantly enhance efficiency while ensuring accuracy.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 7","pages":"4677-4688"},"PeriodicalIF":4.6,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multideflection Angle Quasi-Nondiffractive Beams Generating Metasurface Based on Polarization Multiplexing Technology","authors":"Yi-Zhu Yan;Shuai Ding;Xu Han;Qing-Song Jia;Hao Tang;Wei-Hao Zhang;Qiao-Li Zhang;Xiong Wang;Zhen-Ping Zhang;Bing-Zhong Wang","doi":"10.1109/TAP.2025.3553770","DOIUrl":"https://doi.org/10.1109/TAP.2025.3553770","url":null,"abstract":"Polarization multiplexing technology holds significant potential for applications in the next generation of microwave wireless information encryption and storage systems. However, nonorthogonal linear polarization multiplexing often results in high crosstalk between different channels. Moreover, the multidegree-of-freedom control of the Jones matrix on a single meta-atom structure is very complex. In this article, a new supercell is designed by combining the polarization response characteristics of four independent meta-atoms, resulting in a subwavelength structure (<inline-formula> <tex-math>$0.64lambda $ </tex-math></inline-formula>) that precisely satisfies the target Jones matrix requirements, with nearly 360° phase coverage from a single meta-atom. In addition, artificially designed noncorrelated noise is introduced to eliminate crosstalk between different channels, ensuring that the correlation coefficients of the target channels do not deteriorate significantly. To verify the feasibility of this method, the functionality of the four channels is designed with quasi-nondiffractive beams with different deflection angles, and the performance of the proposed polarization multiplexing metasurface is analyzed using simulations and experiments. The experimental results show that nearly 50% of the energy is distributed to the target areas, and the signal-to-noise ratio (SNR) of each channel also exhibits good performance close to 10. These results demonstrate the feasibility of using noncorrelated noise to improve crosstalk in polarization multiplexing techniques within the microwave frequency range and validate the effectiveness of using supercells for multidegree-of-freedom control of the Jones matrix in the microwave band.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 7","pages":"4559-4571"},"PeriodicalIF":4.6,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144598017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuanxi Cao;Sifan Wu;Jiahao Zhang;Jianxing Li;Sen Yan
{"title":"Compact 2-D Passive Beam-Scanning Multibeam Antenna Based on Rotman Lens and Mechanical Sweeping Phase Gradient Metasurface","authors":"Yuanxi Cao;Sifan Wu;Jiahao Zhang;Jianxing Li;Sen Yan","doi":"10.1109/TAP.2025.3553748","DOIUrl":"https://doi.org/10.1109/TAP.2025.3553748","url":null,"abstract":"A compact multibeam antenna is proposed with passive 2-D beam scanning capability. The antenna is composed of a Rotman lens beamformer, a slotted waveguide array (SWA), and a mechanical sweeping phase gradient metasurface (PGM). The Rotman lens and the PGM together provide a wide range of scanning angles, enabling 2-D beam steering. To improve the crossover level (COL) and the sidelobe level (SLL) of the beams steered by the Rotman lens, the technology of dual sources excitation (DSE) is used, optimizing the COL and the SLL by the tapered magnitude distribution from the sources. Numerical analysis and full-wave simulation are used to verify the performance variations with different source aperture sizes. Since the SWA array can generate a quasi-plane wave above its aperture, the PGM can be fitted close to the SWAs with low spillover loss, resulting in a low antenna profile (<inline-formula> <tex-math>$lt 0.41lambda $ </tex-math></inline-formula>). Then, the phase distributions of the PGM are optimized to suppress the edge negative phase mutation, further optimizing the gain and SLL. To verify the feasibility, a prototype is designed and fabricated at 5.8 GHz. The measured results show that ±50° and ±40° beam scanning ranges in the multibeam and PGM mechanical sweeping planes are realized with the minimum COL and SLL of −2.6 and −8.8 dB. With the wide angle 2-D beam scanning range, low SLL, and COL, the proposed antenna would be attractive for low-cost sensing and communication applications.","PeriodicalId":13102,"journal":{"name":"IEEE Transactions on Antennas and Propagation","volume":"73 7","pages":"4993-4998"},"PeriodicalIF":4.6,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144606243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}