This paper presents a massive multiple-inputmultiple-output (mMIMO) system that utilizes spectrally efficient frequency division multiplexing (SEFDM) and integrates deep learning (DL) for improved channel estimation in the mMIMO-SEFDM. In contrast to the literature, this study utilizes the estimated channel feedback to dynamically adapt the SEFDM signal characteristics at the transmitter, which improves the system's agility. This enables the selection of the SEFDM signal's compression value and modulation order depending on the channel conditions, thus enhancing the symbol error rate (SER). The simulation findings demonstrate that using DLbased channel estimation and adaptive parameter selection for SEFDM leads to a better symbol error rate and improved spectral efficiency compared to orthogonal frequency division multiplexing (OFDM).

javascript:void(0) In this paper, simultaneous vortex and non-vortex based transmission is proposed to enhance capacity by covering multiple users. The system model proposes a cell scenario including new and legacy user equipments (UEs) for backward compatibility and a geometrical transceiver for uniform circular array (UCA) and uniform rectangular array (URA). The proposed scenarios are divided into two different types of transmissions; vortex based, non-vortex based and a simultaneous vortex and non-vortex based. The channel model is approximated by dominant transmission distance. Moreover, modified Bessel function is proposed to derive channel model giving fair divergence effect with elevation angle. The performance of simultaneous vortex and non-vortex based transmissions is derived and simulated in terms of the average capacity (AC), outage probability (OP), and throughput.

Ground control station (GCS) is a system for controlling and monitoring unmanned aerial vehicle (UAV). In current GCS, the device used are considered as complex environment. This paper proposes a video streaming and speech command control for supporting mixed reality based UAV GCS using Microsoft HoloLens. Video streaming will inform the UAV view and transmit the raw video to the HoloLens, while the HoloLens steers the UAV based on the displayed UAV field of view (FoV). Using the HoloLens Mixed Reality Tool-Kit (MRTK) speech input, UAV speech control from the HoloLens was successfully implemented. Finally, experimental results based on video streaming and speech command calculation of the throughput, round-time trip, latency and speech accuracy tests are discussed to demonstrate the feasibility of the proposed scheme.

This paper proposes a global positioning system (GPS)-aided visual simultaneous localization and mapping (SLAM) called GO-SLAM for adaptive UAV navigation. The proposed system offers a solution by the method to address the adaptive navigation challenge, wherein the navigation path needs to pass through an indoor area or outdoor area. GO-SLAM relies on a GPS receiver sensor and camera for visual SLAM to provide local positioning information for UAV navigation. Specifically, a transition system was designed by converting geocentric coordinates from the last coordinate and assigned goal position. The experimental result showed that the GO-SLAM is able to switch navigation, achieving lower travel time and lower computation memory.

In this paper, a novel index modulation (IM) for orbital angular momentum (OAM) communication is proposed by employing the phase offset (PO) state to enhance the capacity, called OAM-PO-IM. The uniform circular array (UCA) based OAM is exploited with PO. The UCA is divided into uniform circular sub-arrays (UCSAs) in the transmitter allocating additional index bits for the activation state of UCSA. In addition, the modified Bessel function of the first kind is used to derive the channel model for effective OAM mode combination under beam divergence. Simulation results are provided to compare with conventional schemes in terms of capacity and bit error rate (BER).

In this paper, an unsupervised federated quantum generative adversarial network (UF-QGAN) is proposed to handle optimization issues in wireless communications. The proposed UF-QGAN considers unsupervised learning so that it could work without labeling for the training dataset. By adopting the federated framework, the computational load could be distributed between the cloud and edge. As a representative example, the proposed UFQGAN is applied for non-orthogonal multiple access (NOMA). Achievable sum rate and complexity are investigated for the performance measure. Simulation results show that the UF-QGAN, which not requires data labeling, achieved a similar achievable sum rate compared to the supervised learning scheme

This study proposes the multiple reconfigurable intelligent surface (RIS) based index modulation (IM) called as MRB-IM, in order to improve the channel capacity by activating one or more RISs among multiple RIS (MRIS) and utilizing its number of combinations. The ergodic capacity analysis is derived to prove the validity of the simulation for the Rayleigh fading channel. Generally, MRIS suffers from inter-RIS interference (IRI) which is considered as the leverage of the secondary reflection amongst the MRIS. Despite having a larger capacity, the proposed MRB-IM has less of an impact on IRI because occurs among active MRIS. Simulation results demonstrate that the proposed system outperforms the existing MRIS in terms of capacity with and without IRI. In addition, bit error rates with different activation numbers of elements and RISs are shown. Here, the maximum likelihood on the receiver side is adopted to estimate the selected RIS index and information symbols in this study.

This study proposes quantum-based deep deterministic policy gradient (Q-DDPG) and quantum-based recurrent DDPG (Q-RDDPG) schemes for time-series optimization in UAV communications. Herein, Q-DDPG based actor-critic reinforcement learning is utilized to optimize action selections in a large state and continuous action space. In this scheme, quantum models are exploited to reduce computational complexity and training loss. As a particular case, Q-DDPG and Q-RDDPG are employed for trajectory optimization and dynamic resource allocation in UAV communications. Quantum circuits of the Q-DDPG schemes are described to showcase their implementation in noisy intermediate-scale quantum (NISQ) computers. The results demonstrate that Q-DDPG and Q-RDDPG schemes achieved higher rewards with lower training losses compared to classical DDPG.

Divergence intensity (DI) and mode combinations are proposed for multiple orbital angular momentum (OAM) users to enhance the sum capacity

In this study, a deep neural network (DNN) for a massive multiple-input-multiple-output (mMIMO) nonorthogonal multiple access (NOMA) system’s channel estimation and detection is presented. The proposed network applies deep learning (DL) to a discrete wavelet transform (DWT) based orthogonal frequency-division-multiplexing (OFDM) to reduce the noise and inter-channel interference (ICI) while maintaining compatibility with the existing networks. The transmission overhead is reduced because the presented network is trained to estimate and detect symbols with and without pilot signals. The results of this study demonstrate that our provided DL-based successive interference cancellation (SIC) method performs better than the conventional SIC-based signal detection in the mMIMONOMA network. The suggested wavelet-based mMIMO-NOMA is also compared to the traditional fast-Fourier-transform (FFT) based mMIMO-NOMA, particularly in terms of symbol error rate (SER).

In this paper, a novel image-based deep learning (DL) approach for channel estimation for future wireless communications is proposed. The time-frequency response of fast fading wireless channel is represented as a 2D image to estimate the unknown values of the channel response using known values at the pilot locations. With given images, both image superresolution (SR) and image restoration (IR), termed as super resolution and denoising network (SRDnN), are combined to estimate wireless channel. To show the effectiveness, the proposed SRDnN is applied to massive multiple-input multiple output (mMIMO) with non-orthogonal multiple access (NOMA). The enhanced performances of SRDnN are quantified in terms of mean square error (MSE) and symbol error rate (SER). In addition, the influence of pilot numbers on SRDnN performance for next generation mMIMO-NOMA networks is presented. The simulation results demonstrate that SRDnN is comparable to the level of maximum likelihood (ML) detection for both with and without complete channel state information (CSI) at the receiver with less number of pilots.

Reconfigurable intelligent surface (RIS) as a supportive technology for aiding downlink non-orthogonal multiple access (NOMA) can enhance the bit error rate (BER) performance. In this paper, a novel BER-aware reflecting elements allocation (REA) on an RIS is proposed to maintain the BER order among paired RIS-NOMA users. The RIS REA is useful for minimizing the average user BER, ompared with a system that allocates the same number of elements to all users. Additionally, the Ricean fading is considered instead of Rayleigh fading as it is more practical and general. Furthermore,an REA optimization objective function for equalizing the user BER is proposed. In order to solve the problem, a modified exhaustive search is proposed to reduce complexity. The distribution of the objective function is observed first; subsequently, the exhaustive search range is determined. Both the analytical and simulation results show that the proposed algorithm can minimize the average user BER.