Arif Ullah

The growing complexity of modern wireless systems, especially for 5G, 6G, and IoT applications, demands efficient and intelligent design approaches for both radio frequency (RF) circuits and antenna systems. Artificial intelligence (AI) has emerged as a powerful enabler that offers data-driven techniques for modeling, optimization, and synthesis of communication hardware. In this paper, we discuss a unified perspective of AI-aided techniques used for RF circuits and antenna design. These techniques mainly encompass a broad range of learning methods, such as supervised learning, deep neural networks, evolutionary algorithms, reinforcement learning, and generative models. The survey highlights their roles in performance prediction, layout optimization, inverse design, and co-design strategies. Unlike existing works that specifically address the RF or antenna domains in terms of isolation, this paper integrates both domains and emphasizes on their joint optimization to meet system-level performance requirements. Comparative analysis, categorized summaries, and a focused discussion on current challenges are discussed that include limited datasets, lack of interpretability, and the gap between simulation and hardware implementation. Furthermore, this paper aims to provide a guide for researchers working on the development of intelligent, scalable, and physically aware AI frameworks for next-generation communication systems.

Holographic MIMO (HMIMO) antennas are emerging as a transformative technology for next-generation wireless networks, offering unprecedented control over EM wave propagation through continuous aperture modulation and intelligent surface integration. Based on the principles of EM holography, HMIMO systems enable dynamic beamforming, high spatial multiplexing, and real-time reconfiguration, surpassing the capabilities of conventional and massive MIMO systems. This review provides a comprehensive overview of HMIMO technologies, with an emphasis on their physical realizations, including metasurface-based designs, holographic leaky-wave antennas (HLWAs), dynamic metasurface antennas (DMAs), and liquid crystal-based reconfigurable architectures. The paper also explores advanced system-level integrations, such as hybrid beamforming, near-field (NF) propagation models, and photonic-assisted processing. By synthesizing recent advancements, we highlight the role of HMIMO in the realization of programmable, energy efficient, and scalable communication environments for 6G and beyond, including applications in smart cities, space-air-ground-sea (SAGS) networks, and secure defense systems. Finally, this review identifies critical challenges in hardware scalability, material limitations, environmental robustness, and system calibration, offering strategic insights and research directions toward the practical deployment of HMIMO-enabled intelligent wireless infrastructures.

The next generation of mobile networks is predicted to deliver high data speeds, lower latency, and increase the spectral and energy efficiency of wireless communication systems. Several technologies are being investigated for usage in 5G networks. Massive multiple-input multiple-output (mMIMO) systems are one of the most promising technologies for enabling 5G. Even after the recent advancements and research, numerous challenges still exist for channel estimation for mMIMO systems. In the context of pilot contamination and feedback overhead, this study tracks the most recent developments in research on mMIMO system difficulties. The primary goals of this study are to identify the problems with channel estimation, provide a summary of the cutting-edge solutions suggested in the literature, and then discuss newly emerging open research issues that must be taken into account for the implementation of beyond-5G networks.

This study examines a single-fed, self-isolated, dual-band, 8-element multiple-input multiple-output (MIMO) antenna system for fifth-generation (5G) and beyond-5G (B5G) handsets. The proposed antenna is designed by an innovative composition of two F-shaped slots backed by a slotted ground plane, enabling a dual-band operation in the sub-6 GHz (4.7 to 4.9 GHz, n79) and millimeter wave (mmWave) (28 to 29 GHz, n257) frequency bands. High isolation of >14.4 dB and >25 dB and a high diversity gain of >9.9 dB were achieved at the respective frequency bands without using additional decoupling techniques, exhibiting an efficiency of approximately 90% with high gains of 4.9 and 7.2 dBi at the n79 and n257 bands, respectively. The antenna demonstrates excellent MIMO performance regarding very low envelope correlation coefficient (<0.001), total active reflection coefficients (<10 dB and -24 dB), and mean effective gain (< -7.3 dB and -7 dB). In addition to the safety evaluations, the performance is verified in a realistic mobile device to ensure practical feasibility. The evaluations showed promising results, demonstrating that the proposed design is a suitable, compact, and highly effective MIMO solution for 5G and B5G handsets.

The rapid advancements in wireless technologies have led to numerous research studies that provide evidence of the successful utilization of wireless signals, particularly, WiFi signals for human activity sensing in the indoor environment. As a promising technology, WiFi-based human sensing can be utilized for a variety of applications such as smart healthcare, smart homes, security, industry, office indoor environments etc., due to the availability of rich infrastructure. Furthermore, compared to other radio frequency (RF) based systems such as radio detection and ranging (RADAR) and radio frequency identification (RFID), WiFi is non-invasive, has low-cost, and provides ubiquitous coverage in the indoor setup. However, due to the limited accuracy and high complexity of the model-based approaches for human sensing, the systems empowered by the deep learning (DL) techniques have achieved remarkable performance gains and showed more robustness in dealing with complicated human sensing tasks. The article explores the physical layer parameters used in WiFi sensing such as received signal strength indicator (RSSI) and channel state information (CSI), the estimated parameters such as angle-of-arrival (AoA) and Doppler shift (DS) along with frequency modulated continuous wave (FMCW) RADAR technology. Moreover, the preliminary signal processing stages that are applied to the received WiFi signals in the DL assisted systems are discussed. This article provides a comprehensive literature survey on the recent advances in DL-empowered WiFi sensing focusing on human activity recognition and movement tracking followed by fall detection, single task-multi task classification, crowd monitoring and sensing, indoor localization, gaits recognition, and pose estimation. Furthermore, the paper highlight the challenges in the existing literature and discusses the possible future research directions in WiFi-based human sensing assisted by DL techniques.

The multiple-input-multiple-output-orthogonal frequency division multiplexing (MIMO-OFDM) receiver aims to softly decode the transmitted information from the observed received signal. However, soft-output detection requires additional computation and leads to higher overall detection complexity in high-dimensional MIMO and higher-order modulation. Therefore, accurate and low-complexity soft-output detection is a challenging task in such systems. The conventional likelihood ascent search (LAS) detectors perform well in large antenna setups, however, multiple symbol updates and the soft-output estimation using brute force search further boost its complexity. In this paper, we propose a model-based soft-output LAS detector to jointly detect and precisely estimate the soft output in MIMO-OFDM systems. Furthermore, we propose a data-driven deep-LAS (Deep LAS) architecture for MIMO detection which is a multi-layer perception (MLP), and a gated recurrent unit (GRU)-based hybrid trainable learning framework to unfold the proposed two-stage LAS algorithm by directly learning the soft output from the received equalized signals. Numerical results demonstrate that the proposed two-stage soft-output LAS detector precisely computes the log-likelihood ratio (LLR) and provides better performance than the conventional LAS detector. Alternatively, the proposed Deep LAS efficiently estimates the LLR values by achieving a performance gain of 2.55 dB and 3 dB compared to the conventional LAS algorithm. Furthermore, the proposed Deep LAS outperforms the counterpart model-based and standalone data-driven learning schemes and provides a comparable signal-to-noise ratio (SNR) gap of 0.4 dB and 1.2 dB with the optimal soft output sphere decoding (SD) to achieve a BER of $ \text{10}^{\text{-5}}$ for 4-QAM and 16-QAM, respectively.

Intelligent recommendation applications in smart cities require the precise location of the users. The traditional global positioning system (GPS) uses satellite signals for the precise positioning of the user but is vulnerable to signal blockage in the complex indoor environment. The unforeseeable propagation losses due to multi-path effects as well as the permittivity and permeability difference of the materials lead to non-linear attenuation in the electromagnetic (EM) beam generated by the beacon devices in the indoor environment. Therefore, a robust indoor localization algorithm is required to precisely localize the users in the indoor environment with severe EM blockages. In this paper, we propose a novel hybrid RS-DeepNet framework that uses received signal strength (RSS) from WiFi devices for indoor localization of users. The proposed RS-DeepNet is a deep learning architecture that utilizes multiple gated recurrent layers (GRU) and a K-nearest neighbors (KNN) classifier to estimate the precise location of the user in the indoor setup. Simulation results show that the proposed RS-DeepNet outperforms the state-of-theart approaches and efficiently localizes the users in two indoor scenarios and achieves a lowest mean absolute error of 4.81 and 1.68 meters, respectively.