Inverse design of frequency reconfigurable antenna arrays using machine learning

A novel ultrathin reconfigurable metamaterial antenna with dual CSRR-DGS for wireless body area networks and adaptive medical telemetry in the 2.2–2.4 GHz ISM band: a 16-state PIN diode implementation

Switchable meander-strip enabled frequency and pattern reconfigurable monopole antenna based on AlGaAs PIN diode

This paper presents a compact, reconfigurable sub-6GHz MIMO antenna array integrated with a solar panel, targeting energy-efficient and sustainable 5G communication networks. The proposed design addresses the critical challenges of antenna performance degradation and mutual coupling that typically arise when antennas are integrated with photovoltaic structures. To overcome these limitations, the antenna employs a metamaterial (MTM) radiating patch composed of a 5 × 3 Hilbert-curve split-ring resonator (SRR) array, which enhances impedance bandwidth and gain through plasmonic resonance behavior. Additionally, a defected electromagnetic band-gap (EMBG) ground plane is introduced to suppress surface waves and back radiation, thereby improving radiation efficiency and isolation. A novel composite right/left-handed (CRLH) isolation wall is incorporated between antenna elements to achieve strong mutual coupling reduction within an ultra-compact footprint. Frequency reconfigurability is realized using PIN diodes, enabling dynamic control of the operating bands and radiation characteristics. The proposed two-element MIMO configuration is mounted beneath a solar panel, demonstrating negligible impact on photovoltaic I-V characteristics, while simultaneously providing a gain enhancement due to constructive electromagnetic interaction. The antenna operates over a wide frequency range between 2.7 and 6.0GHz and beyond, with resonances around 3 and 5GHz, achieving a maximum gain of approximately 7.3 dBi.

This study introduces a new design for a reconfigurable open-slot antenna tailored for LTE smartphone applications. The antenna is engineered to efficiently cover two broad frequency ranges: 698-960MHz and 1710-2690MHz. To minimize the used space, the slot is positioned at the top of the smartphone's printed circuit board (PCB) and by incorporating switches loaded with lumped components, the design effectively tunes into the lower frequency bands while keeping the antenna compact. The working mechanism of the antenna was carefully analyzed, with the final version optimized, fabricated, and tested. Simulated and measured results show that the antenna consistently provides a great performance across all target frequency bands. This makes it a strong and practical solution for modern LTE smartphones and similar handheld devices.

This article presents a compact, pattern-reconfigurable leaky-wave antenna (LWA) realized on a dual-path spoof surface plasmon polariton (SSPP) transmission structure, wherein two PIN diode switches control the active propagation path to enable three independently configurable radiation modes. In Mode 1 (S1 ON, S2 OFF), the upper SSPP branch operates alone and produces a right-handed circularly polarized (RHCP) beam scanning over a 22◦ range within 8.3–9.0 GHz with an average gain of approximately 7.5 dBi and a radiation efficiency exceeding 92%. In Mode 2 (S1 OFF, S2 ON), the structurally symmetric lower branch is activated instead, yielding an identical scanning performance with left-handed circular polarization (LHCP). In Mode 3 (S1 ON, S2 ON), both branches are simultaneously energized, producing a linearly polarized (LP) beam that scans over a wider 78◦ angular span within 8.3–10.3 GHz and achieves a peak gain of 10.3 dBi together with a total efficiency greater than 70%. Sidelobe levels are suppressed below −10 dB across all three modes by means of a tapered arrangement of elliptical patches loaded periodically along the transmission line. The antenna operates over a broadband range of 5–15 GHz and occupies a compact footprint of 216 × 40 mm2. The proposed design offers an attractive combination of wide-bandwidth operation, high gain, low sidelobe levels, and flexible polarization switching that is well-suited to radar sensing, satellite communication, and next-generation wireless systems. Index Terms—Spoof surface plasmon polariton (SSPP), leaky-wave antenna (LWA), reconfigurable antenna, beam steering, PIN diode switching, low sidelobe level (SLL), circular polarization, linear polarization.

A MetaFractal cell-based reconfigurable Vivaldi antenna for non-invasive detection of malignant skin tissues

ABSTRACT This letter presents a butterfly‐shaped pattern‐reconfigurable antenna featuring unidirectional/bidirectional (U/B) radiation patterns and broadband stable gain. This paper innovatively utilizes the coupling effect between two reflective elements to achieve impedance matching for the antenna's bidirectional radiation pattern. Pattern reconfiguration is realized by controlling two pairs of PIN diodes integrated onto parallel twin lines via dedicated DC control circuits. The bidirectional pattern occurs when two driving units are fed with equal‐amplitude and anti‐phase currents, which are spaced at 0.5λ 0 apart (at 4.5 GHz). This feeding configuration, combined with coupling effects between reflective elements, enables the bidirectional pattern. The stable gain stems primarily from the director and reflector units. A prototype was fabricated and measured, yielding an overall antenna size of 0.87λ 0 ×0.87λ 0 ×0.015λ 0 at 4.5 GHz. The measured overlapping impedance bandwidths for the three patterns are 16.5% (4.34–5.12 GHz). The measured overlapping 0.5‐dB stable gain bandwidths for the three patterns are 14.9% (4.34–5.04 GHz). This coverage encompasses the 5 G n86 (4.4–4.9 GHz) and n90 (4.9–5.0 GHz) bands, enabling flexible deployment in high‐density scenarios like urban areas and stadiums.

The rapid evolution of wireless communication systems across sub-6 GHz and millimeter Wave bands has intensified the demand for Frequency Reconfigurable Antennas (FRAs) capable of adaptive, multi-standard operation. This review presents a comprehensive performance-driven synthesis of reconfigurable patch antenna architectures developed from 1963 to 2026, with emphasis on recent advances after 2020. Reconfiguration techniques are systematically classified into electrical, mechanical, and metamaterial-based approaches and evaluated based on key performance parameters including tuning range, radiation efficiency, switching speed, biasing complexity, and structural footprint. Electrical methods employing PIN diodes, varactors, and RF-MEMS switches are analyzed alongside mechanical actuators, liquid-metal and phase-change materials, magneto-dielectric substrates, and metasurface-based mechanisms to establish critical trade-offs between actuation latency, power handling, and integration feasibility. A unified benchmarking framework incorporating comparative performance mapping and response-time frontiers is introduced to support informed design selection. Additionally, the emerging role of machine learning in reducing simulation overhead and enabling predictive optimization is discussed as a transformative paradigm in antenna engineering. The review concludes by outlining research challenges and hybrid strategies essential for 5G and future 6G adaptive communication systems.

This paper presents a compact, wideband, and frequency-reconfigurable Magneto-Electric Dipole (MED) antenna designed for sub-6GHz 5G New Radio (NR) and Industrial, Scientific, and Medical (ISM)/ Wireless Local Area Network (WLAN) applications. The proposed antenna utilizes an aperture-coupled excitation mechanism integrated within a multilayer FR4 structure, featuring complementary electric and magnetic dipole elements that are optimized through a four-step evolutionary design process. The final configuration achieves a simulated broad Impedance Bandwidth (IBW) of 2.24-4.55GHz in the all-diodes-off state, while maintaining stable broadside radiation, a peak gain of over 7.7 dBi, and a radiation efficiency of up to 94.2%. Frequency reconfigurability is achieved through the use of six strategically placed PIN diodes, which selectively modify the current distribution on the microstrip feed line by coupling six rectangular stubs. Multiple diode-controlled switching states enable wide tunability from 1.79GHz to 4.41GHz, providing support for more than twelve major 5G NR bands, including n7, n30, n34, n38, n40, n41, n48, n53, n65, n77, n78, n90, n95, and n97, as well as ISM/WLAN services. Simulated and measured results exhibit strong agreement across all states, with peak gains ranging from 7.06 to 7.82 dBi and radiation efficiencies between 65.6% and 96.1% (see Table3), confirming the robustness of the aperture-coupled and diode-integrated MED architecture. Compared to recent state-of-the-art MED and reconfigurable MED antennas, the proposed design demonstrates a wider tuning range, competitive gain, and reduced structural complexity while maintaining a compact volume of 0.48λ₀ × 0.48λ₀ × 0.11λ₀ at 3.5GHz. These characteristics highlight its suitability for compact 5G terminals, small-cell base stations, reconfigurable wireless systems, and multi-standard communication platforms.

Presented in this paper are operational principles of MIMO radar systems and their future development trends in terms of achieving high angular resolution and enhancing their energy potential under constrained size and weight conditions. A comparative analysis has proved that transition to microwave photonic beamforming devices based on Radio-over-Fiber and frequency-independent delay line technologies ensures wideband beamforming and makes it possible to create distributed coherent systems. This paper also presents the results of a comprehensive analysis of the capabilities and limitations of available components to be used for beamforming in such systems. It is shown that further development of microwave photonic MIMO radars entails the need for overcoming significant limitations in operational range and distribution network length of the system. Key areas for improving such systems have been identified including the use of programmable photonic integrated circuits, linearization of the microwave photonic channel, and application of hybrid orthogonalization methods. The findings may be useful for development of new generations of wideband short- and medium-range radars with reconfigurable distributed antenna systems.

Reconfigurable antennas play a central role in next-generation wireless communication systems by enabling dynamic adaptation of operating frequency, radiation pattern, and polarization. Tunable metasurfaces have emerged as a powerful and compact approach to antenna reconfiguration, allowing electromagnetic wave manipulation through engineered, planar structures whose properties can be dynamically controlled. By embedding active devices or tunable materials within metasurface unit cells, antenna characteristics can be modified without altering the antenna geometry. This review provides a comprehensive overview of reconfigurable antennas enabled by tunable metasurfaces. We adopt a functionality-based classification that focuses on operating frequency, radiation pattern, polarization, and multifunction reconfiguration. An overview of major tunability technologies, including PIN diodes, varactors, MEMS, graphene and two-dimensional materials, and liquid crystal (LC) or phase-change materials, is first presented. Subsequently, metasurface-based reconfiguration strategies are discussed and compared for each antenna functionality, highlighting design principles, practical trade-offs, and limitations. The review concludes with an assessment of challenges and future research directions relevant to next-generation wireless communications and beyond.

Abstract This paper presents the design and experimental validation of an interlocked frequency-switchable multiple-input multiple-output (MIMO) antenna. The proposed reconfigurable antenna is based on an ultra-wideband (UWB) radiator consisting of a circular patch integrated with a four-armed floral slot resonator and extended slotted stubs. The main radiator achieves a reflection coefficient bandwidth from 3 to 10.6 GHz, thereby covering the entire UWB frequency range. To enable a high-performance narrowband mode centered at 3.5 GHz, a compact low-pass filter (LPF) using a butterfly-shaped resonator with a 4 GHz cut-off frequency is integrated adjacent to the radiator. A feed selection network with PIN diodes allows seamless switching between UWB and narrowband operations. The antenna element, with an electrical size of 0.24 λ 0 × 0.16 λ 0 ( λ 0 = 100 mm at 3 GHz), is extended into a 4 × 4 MIMO antenna using an interlocked layout to achieve frequency reconfiguration and pattern diversity. A fabricated prototype shows good agreement with simulations with a gain above 4.2 dBi, radiation efficiency over 85%, and diversity metrics such as envelope correlation coefficient, diversity gain, and channel capacity loss are well within acceptable limits. The dual-mode operation between UWB and 3.5 GHz makes the antenna desirable for next-generation wireless networks, 5G sub-6 GHz communications, IoT and short-range high-speed data links.

ABSTRACT Programmable metasurfaces enable various novel functionalities, including real‐time beam steering, high‐resolution imaging, adaptive wireless communications, and so on, by dynamically tuning electromagnetic wavefronts. These capabilities hold significant promise for transformative applications in reconfigurable antennas, smart sensing systems, and encrypted data transmission within emerging 5G/6G networks. In this article, we provide a comprehensive review of recent advances in microwave and terahertz programmable metasurfaces, encompassing various control mechanisms including electrical, thermal, optical and mechanical tuning. We begin by discussing electrically controlled metasurfaces based on Positive‐Intrinsic‐Negative(PIN) diodes or varactor diodes, highlighting their reconfigurable applications in beam scanning, imaging, and wireless communications. The review then explores the distinct advantages of liquid crystals and graphene in achieving dynamic electromagnetic control, along with representative devices. Additionally, we analyze thermally controlled metasurfaces that utilize and chalcogenide phase‐change materials, as well as optically controlled metasurfaces driven by structured light and laser excitation. Programmable metasurfaces based on micro‐electro‐mechanical systems are also discussed. Finally, the review summarizes the practical applications of programmable metasurfaces and addresses current challenges such as response speed, power consumption, and integration density. We conclude this review by presenting perspectives on the existing challenges and future directions in this fast‐growing research field.

Remotely Controlled Compact Hybrid Reconfigurable Dual-Element MIMO Antenna for Next-Generation Wireless Communication Systems

ABSTRACT In modern communication networks, optimizing radiation patterns is essential for ensuring high‐quality signal transmission, directional beamforming, and efficient spectrum utilization. Traditional methods often struggle with nonlinearity, high dimensionality, and limited adaptability to dynamic and complex beam requirements. Therefore, this research proposes a novel model of enhancing antenna array performance through hybrid deep learning for accurate beam coefficient prediction in complex communication networks (AAP‐HybDL‐BCP). Here, complex communication networks refer to a dynamic 5G/6G environment with rapid beam switching, interference, and varying user conditions—not a complex antenna structure. While a simple 4 × 4 isotropic array is adopted for evaluation, the proposed model is designed to effectively deal with the challenges in such real‐world network scenarios. These radiation pattern images are provided as input to a hybrid deep learning framework composed of finite element interpolated neural network (FEINN) for phase prediction and the multi‐anchor space‐aware temporal convolutional neural network (MSATCNN) for amplitude prediction. This dual‐network approach significantly enhances the reliability and precision of beam coefficient prediction for next‐generation reconfigurable antenna systems. Then, the proposed AAP‐HybDL‐BCP is implemented and the performance metrics like root‐mean‐square error (RMSE), R ‐square, peak signal‐to‐noise ratio (PSNR), structural similarity index measure (SSIM), and peak beam great circle distance (GCD) are examined. Finally, the proposed AAP‐HybDL‐BCP method achieves a lower MSE of 0.0312 and a higher PSNR of 19.57 compared with existing approaches such as CNN‐ANFP‐SM, SB‐DNN‐CBFA, and LC‐ML‐MWBP, demonstrating its superior prediction accuracy.

A novel generalized regression model (GRM) is proposed to characterize the relationship between the activation states of reconfigurable units or their combinations on a reconfigurable partially reflective surface (PRS) and the multi-objective electromagnetic performance metrics of antennas. The GRM framework integrates a forward prediction process and an inverse design process. In the forward process, three parallel generalized regression neural network (GRNN) subnetworks are utilized to model critical electromagnetic performance metrics, including the return loss (S-parameter), gain, and radiation patterns. To improve prediction accuracy and robustness, each GRNN subnetwork is optimized with multiobjective particle swarm optimization (MOPSO) and refined using a recursive correction method. The inverse process integrates the forward predictions to construct an enumeration-based inverse mapping that identifies reconfigurable unit configurations satisfying predefined performance constraints. The efficacy of the model is validated through cross-validation on a liquid-based reconfigurable Fabry-Perot (FP) antenna, demonstrating its ability to significantly accelerate the performance optimization of reconfigurable antenna systems.

Antennas are significant in wireless communication systems, and with advancing technology, there's a rising demand for lightweight, low-profile antennas with broad coverage and versatile applications. The main aim of this research is to evaluate the performance of Evaluation of Reconfigurable Antennas for wireless communication. In this research the final design achieved dual-band operation at 3.21 GHz, 4.0 GHz, and 5.32 GHz with gains up to 6.77 dBi and efficiency exceeding 70%, enabling pattern tilts of +30° and 30°. Advantages include high efficiency, simplified design, and versatile functionality, while drawbacks involve larger dimensions, fabrication discrepancies, and limitations of the FR-4 substrate. This design, suitable for wireless communication and WLAN, balances performance and complexity, with potential for future miniaturization and material optimization.

Abstract This study presents a UWB antenna for spectrum sensing and a reconfigurable communication antenna with dynamic frequency selection designed for cognitive radio applications. The UWB antenna (ANT1) is used for spectrum sensing while the PIN diode-integrated frequency-reconfigurable antenna (ANT2) is used for communication. The antenna is designed on a FR-4-based dielectric material with dimensions of 25 × 35 × 1.6 mm 3 (0.175 λ ₀ × 0.245 λ ₀ × 0.011 λ ₀) and sized at the wavelength ( λ ₀) corresponding to the lowest resonant frequency in free space. The UWB antenna (ANT1) operates at a bandwidth of 2.1–12 GHz and the communication antenna (ANT2) operates at 3.8–6.3 GHz and 2.4–3.5 GHz; 8.6–12 GHz, respectively, depending on the pin diode off/on states. To increase the isolation between the antenna components and the impedance bandwidth, a T-shaped extension is integrated into the ground plane, which significantly enhances the isolation levels. The proposed antenna structure is transformed into a 4 × 4 8-port MIMO antenna architecture. A total of four PIN diodes are integrated into the MIMO antenna structure to provide frequency reconfigurability. The simulated and fabricated antenna structures are comprehensively evaluated in terms of MIMO performance parameters, including mutual coupling, diversity gain (DG), and envelope correlation coefficient (ECC).

The research work introduces a compact, frequency reconfigurable trident-shaped antenna suitable for cognitive radio (CR) applications. The antenna features a compact dimension of 30 × 30 × 1.6 mm3 and incorporates four PIN diodes, namely S 1 t , S 2 t , S 3 t and S 4 t to toggle between various operational frequency bands. This innovative design supports multiple states, enabling both wide-band (WB) sensing and narrowband communication modes across the spectrum. In the ON state, the PIN diodes exhibit low inductance and resistance, allowing current to flow with minimal impedance. In the OFF state, they demonstrate high resistance and low capacitance, effectively acting as insulators. When all four PIN diodes are activated, the antenna achieves a wide operational frequency range from 3.6 GHz to 12.8 GHz as wideband spectrum. By varying the switching combinations of all four diodes, the antenna can dynamically reconfigure to support 16 possible states with 23 different narrowband and wideband frequencies, providing full spectral coverage.