--This paper explores the design of beamforming codebooks for the base station (BS) and for the reconfigurable intelligent surfaces (RISs) in an active sensing scheme for uplink localization, in which the mobile user transmits a sequence of pilots to the BS through reflection at the RISs, and the BS and the RISs are adaptively configured by carefully choosing BS beamforming codeword and RIS codewords from their respective codebooks in a sequential manner to progressively focus onto the user . Most existing codebook designs for RIS are not tailored for active sensing, by which we mean the choice of the next codeword should depend on the measurements made so far, and the sequence of codewords should dynamically focus reflection toward the user . Moreover, most existing codeword selection methods rely on exhaustive search in beam training to identify the codeword with the highest signal-to-noise ratio (SNR), thus incurring substantial pilot overhead as the size of the codebook scales. This paper proposes a learning-based approach for codebook construction and for codeword selection for active sensing. The proposed learning approach aims to locate a target in the service area by recursively selecting a sequence of BS beamforming codewords and RIS codewords from the respective codebooks as more measurements become available without exhaustive beam training. The codebook design and the codeword selection fuse key ideas from the vector quantized variational autoencoder (VQ-V AE) and the long short-term memory (LSTM) network to learn respectively the discrete function space of the codebook and the temporal dependencies between measurements. The device is typically placed in the reflecting path between the transceivers, with its configuration wirelessly controlled by the transceivers via a control link. Manuscript submitted to IEEE Transactions on Wireless Communications on September 6, 2024, revised on January 12, 2025, accepted on March 5, 2025. Wei Y u is with The Edward S. Rogers Sr. This work is supported by the Natural Sciences and Engineering Research Council of Canada via the Canada Research Chairs program. The materials in this paper have been accepted in part at the IEEE Workshop on Signal Processing Advances in Wireless Communications (SP A WC), Lucca, Italy, September 2024 [1]. Codebook-based limited control link rate protocol can substantially reduce the control overhead [7], [8]. With the RIS codebook stored at the controller and at the RIS, the controller only needs to send the codeword index in order to configure the RIS.

In this paper, a regression-based machine learning model is used for the design of cavity backed slotted antenna. This type of antenna is commonly used in military and aviation communication systems. Initial reflection coefficient data of cavity backed slotted antenna is generated using electromagnetic solver. These reflection coefficient data is then used as input for training regression-based machine learning model. The model is trained to predict the dimensions of cavity backed slotted antenna based on the input reflection coefficient for a wide frequency band varying from 1 GHz to 8 GHz. This approach allows for rapid prediction of optimal antenna configurations, reducing the need for repeated physical testing and manual adjustments, may lead to significant amount of design and development cost saving. The proposed model also demonstrates its versatility in predicting multi frequency resonance across 1 GHz to 8 GHz. Also, the proposed approach demonstrates the potential for leveraging machine learning in advanced antenna design, enhancing efficiency and accuracy in practical applications such as radar, military identification systems and secure communication networks.

In this paper, deep learning-based approach for the design of radar absorbing structure using resistive frequency selective surface is proposed. In the present design, reflection coefficient is used as input of deep learning model and the Jerusalem cross based unit cell dimensions is predicted as outcome. Sequential neural network based deep learning model with adaptive moment estimation optimizer is used for designing multi frequency band absorbers. The model is used for designing radar absorber from L to Ka band depending on unit cell parameters and thickness. The outcome of deep learning model is further compared with full-wave simulation software and an excellent match is obtained. The proposed model can be used for the low-cost design of various radar absorbing structures using a single unit cell and thickness across the band of frequencies.

Reconfigurable intelligent surface (RIS) is a two-dimensional periodic structure integrated with a large number of reflective elements, which can manipulate electromagnetic waves in a digital way, offering great potentials for wireless communication and radar detection applications. However, conventional RIS designs highly rely on extensive full-wave EM simulations that are extremely time-consuming. To address this challenge, we propose a machine-learning-assisted approach for efficient RIS design. An accurate and fast model to predict the reflection coefficient of RIS element is developed by combining a multi-layer perceptron neural network (MLP) and a dual-port network, which can significantly reduce tedious EM simulations in the network training. A RIS has been practically designed based on the proposed method. To verify the proposed method, the RIS has also been fabricated and measured. The experimental results are in good agreement with the simulation results, which validates the efficacy of the proposed method in RIS design.

Single-snapshot signal processing in sparse linear arrays has become increasingly vital, particularly in dynamic environments like automotive radar systems, where only limited snapshots are available. These arrays are often utilized either to cut manufacturing costs or result from unintended antenna failures, leading to challenges such as high sidelobe levels and compromised accuracy in direction-of-arrival (DOA) estimation. Despite deep learning's success in tasks such as DOA estimation, the need for extensive training data to increase target numbers or improve angular resolution poses significant challenges. In response, this paper presents a novel Siamese neural network (SNN) featuring a sparse augmentation layer, which enhances signal feature embedding and DOA estimation accuracy in sparse arrays. We demonstrate the enhanced DOA estimation performance of our approach through detailed feature analysis and performance evaluation. The code for this study is available at https://github.com/ruxinzh/SNNS_SLA.

Ray tracing is widely employed to model the propagation of radio-frequency (RF) signal in complex environment. The modelling performance greatly depends on how accurately the target scene can be depicted, including the scene geometry and surface material properties. The advances in computer vision and LiDAR make scene geometry estimation increasingly accurate, but there still lacks scalable and efficient approaches to estimate the material reflectivity in real-world environment. In this work, we tackle this problem by learning the material reflectivity efficiently from the path loss of the RF signal from the transmitters to receivers. Specifically, we want the learned material reflection coefficients to minimize the gap between the predicted and measured powers of the receivers. We achieve this by translating the neural reflectance field from optics to RF domain by modelling both the amplitude and phase of RF signals to account for the multipath effects. We further propose a differentiable RF ray tracing framework that optimizes the neural reflectance field to match the signal strength measurements. We simulate a complex real-world environment for experiments and our simulation results show that the neural reflectance field can successfully learn the reflection coefficients for all incident angles. As a result, our approach achieves better accuracy in predicting the powers of receivers with significantly less training data compared to existing approaches.

This paper addresses an uplink localization problem in which a base station (BS) aims to locate a remote user with the help of reconfigurable intelligent surfaces (RISs). We propose a strategy in which the user transmits pilots sequentially and the BS adaptively adjusts the sensing vectors, including the BS beamforming vector and multiple RIS reflection coefficients based on the observations already made, to eventually produce an estimated user position. This is a challenging active sensing problem for which finding an optimal solution involves searching through a complicated functional space whose dimension increases with the number of measurements. We show that the long short-term memory (LSTM) network can be used to exploit the latent temporal correlation between measurements to automatically construct scalable state vectors. Subsequently, the state vector is mapped to the sensing vectors for the next time frame via a deep neural network (DNN). A final DNN is used to map the state vector to the estimated user position. Numerical result illustrates the advantage of the active sensing design as compared to non-active sensing methods. The proposed solution produces interpretable results and is generalizable in the number of sensing stages. Remarkably, we show that a network with one BS and multiple RISs can outperform a comparable setting with multiple BSs.

With the increasing operating frequencies and clock speeds in processors, interconnects affect both the reliability and performance of entire electronic systems. Fault detection and diagnosis of the interconnects are crucial for prognostics and health management (PHM) of electronics. However, traditional approaches using electrical signals as prognostic factors often face challenges in distinguishing defect root causes, necessitating additional destructive evaluations, and are prone to noise interference, leading to potential false alarms. To address these limitations, this paper introduces a novel approach for non-destructive detection and diagnosis of defects in Cu interconnects, offering early detection, enhanced diagnostic accuracy, and noise resilience. Our approach uniquely analyzes both the root cause and severity of interconnect defects by leveraging graph patterns of reflection coefficient, a technique distinct from traditional time series signal analysis. We experimentally demonstrate that the graph patterns possess the capability for fault diagnosis and serve as effective input data for learning algorithms. Additionally, we introduce a novel severity rating ensemble learning (SREL) approach, which significantly enhances diagnostic accuracy and noise robustness. Experimental results demonstrate that the proposed method outperforms conventional machine learning methods and multi-class convolutional neural networks (CNN), achieving a maximum accuracy of 99.3%, especially under elevated noise levels.

The past decade has witnessed the advances of artificial intelligence with various applications in engineering. Recently, artificial neural network empowered inverse design for metasurfaces has been developed that can design on-demand meta-atoms with diverse shapes and high performance, where the design process based on artificial intelligence is fast and automatic. However, once the inverse-designed static meta-atom is fabricated, the function of the metasurface is fixed. Reconfigurable metasurfaces can realize dynamic functions, while applying artificial intelligence to design practical reconfigurable meta-atoms inversely has not been reported yet. Here, we present a deep-learning-empowered inverse design method for freeform reconfigurable metasurfaces, which can generate on-demand reconfigurable coding meta-atoms at self-defined frequency bands. To reduce the scale of dataset, a decoupling method of the reconfigurable meta-atom based on microwave network theory is proposed at first, which can convert the inverse design process for reconfigurable coding meta-atoms to the inverse design for static structures. A convolutional neural network model is trained to predict the responses of free-shaped meta-atoms, and the genetic algorithm is applied to generate the optimal structure patterns rapidly. As a demonstration of concept, several inverse-designed examples are generated with different self-defined spectrum responses in microwave band, and an inverse-designed wideband reconfigurable metasurface prototype is fabricated and measured for beam scanning applications with broad bandwidth. Our work paves the way for the fast and automatic design process of high-performance reconfigurable metasurfaces.

Passive beamforming in reconfigurable intelligent surfaces (RISs) enables a feasible and efficient way of communication when the RIS reflection coefficients are precisely adjusted. In this paper, we present a framework to track the RIS reflection coefficients with the aid of deep learning from a time-series prediction perspective in a terahertz (THz) communication system. The proposed framework achieves a two-step enhancement over the similar learning-driven counterparts. Specifically, in the first step, we train a liquid state machine (LSM) to track the historical RIS reflection coefficients at prior time steps (known as a time-series sequence) and predict their upcoming time steps. We also fine-tune the trained LSM through Xavier initialization technique to decrease the prediction variance, thus resulting in a higher prediction accuracy. In the second step, we use ensemble learning technique which leverages on the prediction power of multiple LSMs to minimize the prediction variance and improve the precision of the first step. It is numerically demonstrated that, in the first step, employing the Xavier initialization technique to fine-tune the LSM results in at most 26% lower LSM prediction variance and as much as 46% achievable spectral efficiency (SE) improvement over the existing counterparts, when an RIS of size 11x11 is deployed. In the second step, under the same computational complexity of training a single LSM, the ensemble learning with multiple LSMs degrades the prediction variance of a single LSM up to 66% and improves the system achievable SE at most 54%.