arXiv subjects

Sina Beyraghi

Publications and source records attributed to Sina Beyraghi.

10 recordsLinked to original sources

arXiv2026

Site-Specific MIMO Channel Generation via Diffusion and Flow Matching: Fidelity, Efficiency, and Downstream Utility

This paper explores the use of generative models to synthesize high-quality, site-specific multiple-input multiple-output (MIMO) channel data, addressing the high cost of the extensive measurement campaigns required to acquire real-world data for AI-native wireless networks. Two location-conditioned generative paradigms are compared: a conditional denoising diffusion implicit model (cDDIM), and a conditional flow matching model (cFMM). Both these models generate MIMO channel matrices conditioned on user coordinates, to preserve the spatial structure of the deployment site. The approaches are evaluated across three dimensions: statistical fidelity (including beam consistency and effective rank), generation efficiency, and utility in downstream tasks such as channel-state information compression and beam alignment. Results across diverse propagation scenarios (28 GHz and 3.5 GHz, both line-of-sight and non-line-of-sight) demonstrate that both models accurately capture site-specific characteristics, even when trained on scarce ground-truth data. Notably, cFMM achieves a quality comparable to cDDIM with roughly an order of magnitude less inference time. Augmenting scarce site-specific datasets with these synthetic channels yields hefty performance gains in downstream physical layer tasks compared to using scarce data alone or stochastic channels.

cs.IT↗

arXiv2025

Data-Driven Deployment of Reconfigurable Intelligent Surfaces in Cellular Networks

This paper presents a fully automated, data-driven framework for the large-scale deployment of reconfigurable intelligent surfaces (RISs) in cellular networks. Leveraging physically consistent ray tracing and empirical data from a commercial deployment in the UK, the proposed method jointly optimizes RIS placement, orientation, configuration, and base station beamforming in dense urban environments across frequency bands (corresponding to 4G, 5G, and a hypothetical 6G system). Candidate RIS locations are identified via reflection- and scattering-based heuristics using calibrated electromagnetic models within the Sionna Ray Tracing (RT) engine. Outage users are clustered to reduce deployment complexity, and the tradeoff between coverage gains and infrastructure cost is systematically evaluated. It is shown that achieving meaningful coverage improvement in urban areas requires a dense deployment of large-aperture RIS units, raising questions about cost-effectiveness. To facilitate reproducibility and future research, the complete simulation framework and RIS deployment algorithms are provided as open-source software.

cs.IT↗

arXiv2025

Site-Specific RIS Deployment in Cellular Networks via Calibrated Ray Tracing

This work introduces a fully-automated RIS deployment strategy validated through a digital twin, powered by Sionna ray tracing, of a UK city. On a scene calibrated with measured data, the method jointly optimizes RIS placement, orientation, configuration, and BS beamforming across 4G, 5G, and hypothetical 6G frequencies. Candidate RIS sites are identified via scattering-based rays, while user clustering reduces deployment overhead. Results show that meaningful coverage enhancement requires dense, large-aperture RIS deployments, raising questions about the practicality and cost of large-scale RIS adoption.

cs.IT↗

arXiv2025

Evaluating the Performance of Reconfigurable Intelligent Base Stations through Ray Tracing

Massive multiple-input multiple-output (mMIMO) is a key capacity-boosting technology in 5G wireless systems. To reduce the number of radio frequency (RF) chains needed in such systems, a novel approach has recently been introduced involving an antenna array supported by a reconfigurable intelligent surface. This arrangement, known as a reconfigurable intelligent base station (RIBS), offers performance comparable to that of a traditional mMIMO array, but with significantly fewer RF chains. Given the growing importance of precise, location-specific performance prediction, this paper evaluates the performance of an RIBS system by means of the SIONNA ray-tracing module. That performance is contrasted against results derived from a statistical 3GPP-compliant channel model, optimizing power and RIS configuration to maximize the sum spectral efficiency. Ray tracing predicts better performance than the statistical model in the evaluated scenario, suggesting the potential of site-specific modeling. However, empirical validation is needed to confirm this advantage.

cs.IT↗

arXiv2023

Deep Learning Framework for the Design of Orbital Angular Momentum Generators Enabled by Leaky-wave Holograms

In this paper, we present a novel approach for the design of leaky-wave holographic antennas that generates OAM-carrying electromagnetic waves by combining Flat Optics (FO) and machine learning (ML) techniques. To improve the performance of our system, we use a machine learning technique to discover a mathematical function that can effectively control the entire radiation pattern, i.e., decrease the side lobe level (SLL) while simultaneously increasing the central null depth of the radiation pattern. Precise tuning of the parameters of the impedance equation based on holographic theory is necessary to achieve optimal results in a variety of scenarios. In this research, we applied machine learning to determine the approximate values of the parameters. We can determine the optimal values for each parameter, resulting in the desired radiation pattern, using a total of 77,000 generated datasets. Furthermore, the use of ML not only saves time, but also yields more precise and accurate results than manual parameter tuning and conventional optimization methods.

physics.optics↗

arXiv2021

A deep learning approach for inverse design of the metasurface for dual-polarized waves

Compared to the conventional metasurface design, machine learning-based methods have recently created an inspiring platform for an inverse realization of the metasurfaces. Here, we have used the Deep Neural Network (DNN) for the generation of desired output unit cell structures in an ultra-wide working frequency band for both TE and TM polarized waves. To automatically generate metasurfaces in a wide range of working frequencies from 4 to 45 GHz, we deliberately design an 8 ring-shaped pattern in such a way that the unit-cells generated in the dataset can produce single or multiple notches in the desired working frequency band. Compared to the general approach, whereby the final metasurface structure may be formed by any randomly distributed "0" and "1", we propose here a restricted output structure. By restricting the output, the number of calculations will be reduced and the learning speed will be increased. Moreover, we have shown that the accuracy of the network reaches 91\%. Obtaining the final unit cell directly without any time-consuming optimization algorithms for both TE and TM polarized waves, and high average accuracy, promises an effective strategy for the metasurface design; thus, the designer is required only to focus on the design goal.

cs.LG↗

arXiv2021

Deep neural network-based automatic metasurface design with a wide frequency range

Beyond the scope of conventional metasurface which necessitates plenty of computational resources and time, an inverse design approach using machine learning algorithms promises an effective way for metasurfaces design. In this paper, benefiting from Deep Neural Network (DNN), an inverse design procedure of a metasurface in an ultra-wide working frequency band is presented where the output unit cell structure can be directly computed by a specified design target. To reach the highest working frequency, for training the DNN, we consider 8 ring-shaped patterns to generate resonant notches at a wide range of working frequencies from 4 to 45 GHz. We propose two network architectures. In one architecture, we restricted the output of the DNN, so the network can only generate the metasurface structure from the input of 8 ring-shaped patterns. This approach drastically reduces the computational time, while keeping the network's accuracy above 91\%. We show that our model based on DNN can satisfactorily generate the output metasurface structure with an average accuracy of over 90\% in both network architectures. Determination of the metasurface structure directly without time-consuming optimization procedures, having an ultra-wide working frequency, and high average accuracy equip an inspiring platform for engineering projects without the need for complex electromagnetic theory.

eess.SP↗

arXiv2021

Implementation of conformal digital metasurfaces for THz polarimetric sensing

Monitoring and controlling the state of polarization of electromagnetic waves is of significant interest for various basic and practical applications such as linear position sensing and medical imaging. Here, we propose the first conformal digital metamaterial absorber to detect the polarization state of THz incident waves. The proposed polarimeter is capable of characterizing four independent polarization states of (TE, TM, $\pm {45^\circ}$ linear, and RCP/LCP) by observing the reflectivity of the structure with respect to the x- and y-direction. Besides, the proposed structure displays a strong absorptivity above 90\% up to the incidence angle of $50^{\circ}$ for oblique incident waves with different polarizations. By mere changing the bias voltage of two orthogonal VO2 microwires via two independent computer-programmed multichannel DC network, distinct conditions for reflected waves occurs under excitations of different polarizations, whereby the polarization state of the incident wave may readily be estimated. We believe that the proposed metasurface-based polarimeter can pave the way for polarization detection applications on curved surfaces.

physics.optics↗

arXiv2020

Reconfigurable honeycomb metamaterial absorber having incident angular stability

Ultrawide-angle electromagnetic wave absorbers with excellent mechanical properties are required in many diverse applications such as sensing, and stealth technologies. Here, a novel 3D reconfigurable metamaterial absorber (MMA) consisting of honeycomb and VO2 films is proposed. The proposed MMA exhibits a strong absorptivity above 90\% in the widest incident angle up to $87^\circ$ for TM- and TE- polarized oblique incidences for THz wave propagating in yoz-plane. According to simulation results, under normal incidence, when VO2 films are in the insulating state, the proposed absorber exhibits high absorptivity in the frequency band of 1-4 THz. By increasing the temperature of the whole structure, the structural transformation of VO2 occurs and turns into the metallic phase. We have shown that under oblique incidence, the ohmic losses of VO2 films especially those parallel to the direction of the incident electric field are the most important absorption principles of the proposed MMA. Furthermore, to understand the physical mechanism of absorption, the induced electric field as well as the power loss density of the proposed structure are investigated. In addition, it is shown that the presented VO2 based honeycomb absorber retains its full-coverage incident angle characteristics for TM-polarized incidences propagating in the xoz-plane. Due to the ultra wide-angle absorption (angular stability) and mechanical performance, it is expected that the presented MMA may find potential applications, such as camouflage technologies, electromagnetic interference, imaging, and sensing. To the best knowledge of authors, the proposed MMA configuration exhibits the absorptivity in the widest incident angle ever reported.

physics.app-ph↗

arXiv2019

Ultrafast reprogrammable multifunctional vanadium-dioxide-assisted metasurface for dynamic THz wavefront engineering

In this paper, for the first time, a new generation of ultrafast reprogrammable multi-mission bias encoded metasurface is proposed for dynamic THz wavefront engineering by employing VO2 reversible and fast monoclinic to tetragonal phase transition. The multi-functionality of our designed VO2 based coding metasurface (VBCM) was guaranteed by elaborately designed meta-atom comprising three-patterned VO2 thin films whose operational statuses can be dynamically tuned among four states of "00"- "11" by merely changing the biasing voltage controlled by an external FPGA platform. Capitalizing on such meta-atom design and by driving VBCM with different spiral-like and spiral-parabola-like coding sequences, single vortex beam and focused vortex beam with interchangeable OAM modes were satisfactorily generated respectively. Additionally, by adopting superposition theorem and convolution operation, symmetric/asymmetric multiple beams and arbitrarily-oriented multiple vortex beams in pre-demined directions with different topological charges are realized. The versatility of our designed VBCM also has equipped a platform to focus the incident THz wavefront into a pre-determined point which can be dynamically altered. Several illustrative examples successfully have clarified that proposed VBCM is a promising candidate for solving crucial THz challenges such as high data rate wireless communication where ultrafast switching between several missions is required.

physics.app-ph↗