Machine unlearning (MUL) is introduced as a means to achieve interference cancellation within artificial intelligence (AI)-enabled wireless systems. It is observed that interference cancellation with MUL demonstrates 30% improvement in a classification task accuracy in the presence of a corrupted AI model. Accordingly, the necessity for instantaneous channel state information for existing interference source is eliminated and a corrupted latent space with interference noise is cleansed with MUL algorithm, achieving this without the necessity for either retraining or dataset cleansing. A Membership Inference Attack (MIA) served as a benchmark for assessing the efficacy of MUL in mitigating interference within a neural network model. The advantage of the MUL algorithm was determined by evaluating both the probability of interference and the quantity of samples requiring retraining. In a simple signal-to-noise ratio classification task, the comprehensive improvement across various test cases in terms of accuracy demonstrates that MUL exhibits extensive capabilities and limitations, particularly in native AI applications.

This study investigates an experimental software defined radio (SDR) implementation on 180 GHz. The system model is presented to evaluate the performance and unveil hidden opportunities. Accordingly, rate scarcity and frequency sparsity are discussed as hardware bottlenecks. Multiple error metrics for the terahertz (THz) signal are acquired, and various case scenarios are subsequently compared, revealing that the SDR-THz testbed reaches 3.2 Mbps with$< 1^\circ$skew error. It is observed that the use of a reflector plate can fine-tune the frequency error and gain imbalance in the expense of at least 14.91 dB signal-to-noise ratio. The results demonstrate the complete feasibility of SDR-based baseband signal generation in THz communication, revealing abundant opportunities to overcome hardware limitations in experimental research.

A precise incident wave angle estimation in aerial communication is a key enabler in sixth-generation wireless communication network. With this goal, a generic 3-dimensional (3D) channel model is analyzed for air-to-air (A2A) networks under antenna misalignment, radio frequency impairments and polarization loss. The unique aspects of each aerial node are highlighted and the few-shot learning as a model agnostic meta-learning (MAML) classifier is proposed for learning-to-learn (L2L) incident wave angle estimation by utilizing the received signal strength (RSS). Additionally, a more computationally efficient technique, first order model agnostic meta-learning (FOMAML) is implemented. It has been observed that the proposed approach reaches up to 85% training accuracy and 75.4% evaluation accuracy with MAML. Regarding this, a convergence rate and accuracy trade-off have been established for several cases of MAML and FOMAML. For different L2L models trained with limited data, heuristic accuracy performance is determined by an upper bound of the probability of confidence.

Low Earth orbit (LEO) satellite mega-constellation networks aim to address the high connectivity demands with a projected 50,000 satellites in less than a decade. To fully utilize such a large-scale dynamic network, an air network composed of stratospheric nodes, specifically high altitude platform station (HAPS), can help significantly with a number of aspects including mobility management. HAPS-LEO network will be subject to time-varying conditions, and in this paper, we introduce an artificial intelligence (AI)-based approach for the unique channel estimation and synchronization problems. First, channel equalization and carrier frequency offset with residual Doppler effects are minimized by using the proposed convolutional neural networks based estimator. Then, the data rate is compounded by increasing spectral efficiency using non-orthogonal multiple access method. We observed that the proposed AI-empowered HAPS-LEO network provides not only a high data throughput per second but also higher service quality thanks to the agile signal reconstruction process.

This paper presents a unified outage probability (OP) performance analysis of two hybrid antenna selection (AS) schemes, transmit antenna selection (TAS) and maximal ratio combining (MRC), and joint transmit and receive antenna selection (JTRAS) in multiple-input multiple-output non-orthogonal multiple access based downlink amplify-and-forward (AF) relaying network with channel estimation error (CEE) and feedback delay (FD). Since the communications in the first and second hops are kinds of single-user and multi-user communications, respectively the AS is done as optimal TAS/MRC or JTRAS is applied in the first hop while the suboptimal majority-based TAS/MRC or JTRAS is employed in the second hop. For both TAS/MRC and JTRAS schemes, the OP expressions are derived in single closed-form over Nakagami-${m}$fading channels in the practical and ideal cases. Moreover, in the practical case, the lower bound OP expressions are found and at high signal-to-noise ratio (SNR) values, the OP reaches an error floor value, which means zero-diversity order. In the ideal case, asymptotic OP expressions are obtained in high SNR regime and demonstrate achievable non-zero diversity and array gains. Finally, through simulations and software-defined radio-based real-time tests, the accuracy of theoretical analysis is validated.