DSpace Arşivi :: by Yazar "Elbir, Ahmet M." değerine göre listeleniyor

Yazar "Elbir, Ahmet M." seçeneğine göre listele

Listeleniyor 1 - 20 / 29

BSA-OMP: Beam-Split-Aware Orthogonal Matching Pursuit for THz Channel Estimation
(Institute of Electrical and Electronics Engineers Inc., 2023) Elbir, Ahmet M.; Chatzinotas, S.
Terahertz (THz)-band has been envisioned for the sixth generation wireless networks thanks to its ultra-wide bandwidth and very narrow beamwidth. Nevertheless, THz-band transmission faces several unique challenges, one of which is beam-split which occurs due to the usage of subcarrier-independent analog beamformers and causes the generated beams at different subcarriers split, and point to different directions. Unlike the prior works dealing with beam-split by employing additional complex hardware components, e.g., time-delayer networks, a beam-split-aware orthogonal matching pursuit (BSA-OMP) approach is introduced to efficiently estimate the THz channel and beamformer design without any additional hardware. Specifically, we design a BSA dictionary comprised of beam-split-corrected steering vectors which inherently include the effect of beam-split so that the proposed BSA-OMP solution automatically yields the beam-split-corrected physical channel directions. Numerical results demonstrate the superior performance of BSA-OMP approach against the existing state-of-the-art techniques. IEEE
CNN-Based Cognitive Radar Array Selection
(Ieee, 2019) Elbir, Ahmet M.; Mishra, Kumar Vijay; Eldar, Yonina C.
In cognitive radar, it may be desired to select an optimal subarray from a full antenna array in each scan to reduce the cost and computational complexity. Previous works on antenna selection rely on mostly optimization or greedy search methods. In this paper, we introduce a deep learning approach for antenna selection in a cognitive radar scenario. We design a deep convolutional neural network (CNN) to select the best subarray for direction-of-arrival estimation for each scan. The CNN accepts the array covariance matrix as its input and, unlike previous works, does not require prior knowledge about the target location. The performance of the proposed CNN approach is evaluated through numerical simulations. In particular, we show that it provides more accurate results than conventional support vector machines.
Cognitive Learning-Aided Multi-Antenna Communications
(Ieee-Inst Electrical Electronics Engineers Inc, 2022) Elbir, Ahmet M.; Mishra, Kumar Vijay
Cognitive communications have emerged as a promising solution to enhance, adapt, and invent new tools and capabilities that transcend conventional wireless networks. Deep learning (DL) is critical in enabling essential features of cognitive systems because of its fast prediction performance, adaptive behavior, and model-free structure. These features are especially significant for multi-antenna wireless communications systems, which generate and handle massive data. Multiple antennas may provide multiplexing, diversity, or antenna gains that improve the capacity, bit error rate, or the signal-to-interference-plus-noise ratio, respectively. In practice, multi-antenna cognitive communications encounter challenges in terms of data complexity and diversity, hardware complexity, and wireless channel dynamics. DL solutions such as federated learning, transfer learning, and online learning tackle these problems at various stages of communications processing, including multi-channel estimation, hybrid beamforming, user localization, and sparse array design. This article provides a synopsis of various DL-based methods to impart cognitive behavior to multi-antenna wireless communications for improved robustness and adaptation to the environmental changes while providing satisfactory spectral efficiency and computation times. We discuss DL design challenges from the perspective of data, learning and transceiver architectures. In particular, we suggest quantized learning models, data/model parallelization, and distributed learning methods to address the aforementioned challenges.
Cooperative RIS and STAR-RIS Assisted mMIMO Communication: Analysis and Optimization
(Ieee-Inst Electrical Electronics Engineers Inc, 2023) Papazafeiropoulos, Anastasios; Elbir, Ahmet M.; Kourtessis, Pandelis; Krikidis, Ioannis; Chatzinotas, Symeon
Reconfigurable intelligent surface (RIS) has emerged as a cost-effective and promising solution to extend the wireless signal coverage and improve the performance via passive signal reflection. Different from existing works which do not account for the cooperation between RISs or do not provide full space coverage, we propose the marriage of cooperative double-RIS with simultaneously transmitting and reflecting RIS (STAR-RIS) technologies denoted as RIS/STAR-RIS under correlated Rayleigh fading conditions to assist the communication in a massive multiple-input multiple-output (mMIMO) setup. The proposed architecture is superior since it enjoys the benefits of the individual designs. We introduce a channel estimation approach of the cascaded channels with reduced overhead. Also, we obtain the deterministic equivalent (DE) of the downlink achievable sum spectral efficiency (SE) in closed form based on large-scale statistics. Notably, relied on statistical channel state information (CSI), we optimise both surfaces by means of the projected gradient ascent method (PGAM), and obtain the gradients in closed form. The proposed optimization achieves to maximise the sum SE of such a complex system, and has low complexity and low overhead since it can be performed at every several coherence intervals. Numerical results show the benefit of the proposed architecture and verify the analytical framework. In particular, we show that the RIS/STAR-RIS architecture outperforms the conventional double-RIS or its single-RIS counterparts.
Deep Channel Learning for Large Intelligent Surfaces Aided mm-Wave Massive MIMO Systems
(Ieee-Inst Electrical Electronics Engineers Inc, 2020) Elbir, Ahmet M.; Papazafeiropoulos, Anastasios; Kourtessis, Pandelis; Chatzinotas, Symeon
This letter presents the first work introducing a deep learning (DL) framework for channel estimation in large intelligent surface (LIS) assisted massive MIMO (multiple-input multiple-output) systems. A twin convolutional neural network (CNN) architecture is designed and it is fed with the received pilot signals to estimate both direct and cascaded channels. In a multi-user scenario, each user has access to the CNN to estimate its own channel. The performance of the proposed DL approach is evaluated and compared with state-of-the-art DL-based techniques and its superior performance is demonstrated.
Deep Learning Design for Joint Antenna Selection and Hybrid Beamforming in Massive MIMO
(Ieee, 2019) Elbir, Ahmet M.; Mishra, Kumar Vijay
In this paper, we propose a deep-learning-based for joint antenna selection and hybrid beamformer design problem in mmWave massive MIMO systems. In this respect, we treat both problems as a classification problem. We design two convolutional neural networks (CNNs) which accept the input as the channel matrix and it yields the output as the optimum antenna subarray. The selected part of channel matrix is fed to the second CNN which gives the output as the analog and baseband beamformers. We evaluate the performance of the proposed approach through numerical simulations and show that our CNN framework provides significantly better performance as compared to the conventional techniques such as orthogonal matching pursuit.
Deep-Sparse Array Cognitive Radar
(Ieee, 2019) Elbir, Ahmet M.; Mulleti, Satish; Cohen, Regev; Fu, Rong; Eldar, Yonina C.
In antenna array based radar applications, it is often desirable to choose an optimum subarray from a full array to achieve a balance between hardware cost and resolution. Moreover, in a cognitive radar system, the sparse subarrays are chosen based on the target scenario at that instant. Recently, a deep-learning based antenna selection technique was proposed for a single target scenario. In this paper, we extend this approach to multiple targets and assess the performance of state-of-the-art direction of arrival estimation techniques in conjunction with the proposed antenna selection method. To optimally choose the subarrays based on the target DOAs, we design a convolutional neural network which accepts the array covariance matrix as an input and selects the best sparse subarray that minimizes the error. Once the optimum sparse subarray is obtained, the signals from the selected antennas are used to estimate the DOAs. We provide numerical simulations to validate the performance of the proposed cognitive array selection strategy. We show that the proposed approach outperforms random sparse antenna selection and it leads to a higher DOA estimation accuracy by 6 dB.
Evaluation of Reconfigurable Multiple and Compact Micro-Strip Antennas for MIMO Systems
(2018) Aslan, Batuhan; Dikmen, Osman; Kulaç, Selman; Elbir, Ahmet M.
In wireless communication systems, theimprovement of data rate and quality is a priority as a result ofusers' requests. During the improvement of these prioritysituations, there will also be a number of losses in the signals. It isknown that the techniques used in large systems to solve suchproblems are not efficient in small systems like modem. Therefore,when using a smaller system such as a modem, the recommendedtechniques will have to be different. Multimode antenna designswill be an important alternative for next generation wirelesscommunication systems especially for MIMO systems due to thephysical advantages of small antenna structures. In this study,MIMO channel structure is shown and performance analysis andtheories of compact micro-strip and reconfigurable multipleantenna designs used for the development of MIMOcommunication systems are mentioned.
A Family of Deep Learning Architectures for Channel Estimation and Hybrid Beamforming in Multi-Carrier mm-Wave Massive MIMO
(Ieee-Inst Electrical Electronics Engineers Inc, 2022) Elbir, Ahmet M.; Mishra, Kumar Vijay; Shankar, M. R. Bhavani; Ottersten, Bjorn
Hybrid analog and digital beamforming transceivers are instrumental in addressing the challenge of expensive hardware and high training overheads in the next generation millimeter-wave (mm-Wave) massive MIMO (multiple-input multiple-output) systems. However, lack of fully digital beamforming in hybrid architectures and short coherence times at mm-Wave impose additional constraints on the channel estimation. Prior works on addressing these challenges have focused largely on narrowband channels wherein optimization-based or greedy algorithms were employed to derive hybrid beamformers. In this paper, we introduce a deep learning (DL) approach for channel estimation and hybrid beamforming for frequency-selective, wideband mm-Wave systems. In particular, we consider a massive MIMO Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system and propose three different DL frameworks comprising convolutional neural networks (CNNs), which accept the raw data of received signal as input and yield channel estimates and the hybrid beamformers at the output. We also introduce both offline and online prediction schemes. Numerical experiments demonstrate that, compared to the current state-of-the-art optimization and DL methods, our approach provides higher spectral efficiency, lesser computational cost and fewer number of pilot signals, and higher tolerance against the deviations in the received pilot data, corrupted channel matrix, and propagation environment.
FEDERATED CHANNEL LEARNING FOR INTELLIGENT REFLECTING SURFACES WITH FEWER PILOT SIGNALS
(Ieee, 2022) Elbir, Ahmet M.; Cöleri, Sinem; Mishra, Kumar Vijay
Channel estimation is a critical task in intelligent reflecting surface (IRS)-assisted wireless systems due to the uncertainties imposed by environment dynamics and rapid changes in the IRS configuration. To deal with these uncertainties, deep learning (DL) approaches have been proposed. Previous works consider centralized learning (CL) approach for model training, which entails the collection of the whole training dataset from the users at the base station (BS), hence introducing huge transmission overhead for data collection. To address this challenge, this paper proposes a federated learning (FL) framework to jointly estimate both direct and cascaded channels in IRSassisted wireless systems. We design a single convolutional neural network trained on the local datasets of the users without sending them to the BS. We show that the proposed FL-based channel estimation approach requires approximately 60% fewer pilot signals and it exhibits 12 times lower transmission overhead than CL, while maintaining satisfactory performance close to CL. In addition, it provides lower estimation error than the state-of-the-art DL-based schemes.
Federated Learning for Channel Estimation in Conventional and RIS-Assisted Massive MIMO
(Ieee-Inst Electrical Electronics Engineers Inc, 2022) Elbir, Ahmet M.; Cöleri, Sinem
Machine learning (ML) has attracted a great research interest for physical layer design problems, such as channel estimation, thanks to its low complexity and robustness. Channel estimation via ML requires model training on a dataset, which usually includes the received pilot signals as input and channel data as output. In previous works, model training is mostly done via centralized learning (CL), where the whole training dataset is collected from the users at the base station (BS). This approach introduces huge communication overhead for data collection. In this paper, to address this challenge, we propose a federated learning (FL) framework for channel estimation. We design a convolutional neural network (CNN) trained on the local datasets of the users without sending them to the BS. We develop FL-based channel estimation schemes for both conventional and RIS (intelligent reflecting surface) assisted massive MIMO (multiple-input multiple-output) systems, where a single CNN is trained for two different datasets for both scenarios. We evaluate the performance for noisy and quantized model transmission and show that the proposed approach provides approximately 16 times lower overhead than CL, while maintaining satisfactory performance close to CL. Furthermore, the proposed architecture exhibits lower estimation error than the state-of-the-art ML-based schemes.
Federated Learning for DL-CSI Prediction in FDD Massive MIMO Systems
(Ieee-Inst Electrical Electronics Engineers Inc, 2021) Hou, Weihao; Sun, Jinlong; Gui, Guan; Ohtsuki, Tomoaki; Elbir, Ahmet M.; Gacanin, Haris; Sari, Hikmet
In frequency-division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems, deep learning for predicting the downlink channel state information (DL-CSI) has been extensively studied. However, in some small cellular base stations (SBSs), a small amount of training data is insufficient to produce an excellent model for CSI prediction. Traditional centralized learning (CL) based method brings all the data together for training, which can lead to overwhelming communication overheads. In this work, we introduce a federated learning (FL) based framework for DL-CSI prediction, where the global model is trained at the macro base station (MBS) by collecting the local models from the edge SBSs. We propose a novel model aggregation algorithm, which updates the global model twice by considering the local model weights and the local gradients, respectively. Numerical simulations show that the proposed aggregation algorithm can make the global model converge faster and perform better than the compared schemes. The performance of the FL architecture is close to that of the CL-based method, and the transmission overheads are much fewer.
Federated Learning for Hybrid Beamforming in mm-Wave Massive MIMO
(Ieee-Inst Electrical Electronics Engineers Inc, 2020) Elbir, Ahmet M.; Coleri, Sinem
Machine learning for hybrid beamforming has been extensively studied by using centralized machine learning (CML) techniques, which require the training of a global model with a large dataset collected from the users. However, the transmission of the whole dataset between the users and the base station (BS) is computationally prohibitive due to limited communication bandwidth and privacy concerns. In this work, we introduce a federated learning (FL) based framework for hybrid beamforming, where the model training is performed at the BS by collecting only the gradients from the users. We design a convolutional neural network, in which the input is the channel data, yielding the analog beamformers at the output. Via numerical simulations, FL is demonstrated to be more tolerant to the imperfections and corruptions in the channel data as well as having less transmission overhead than CML.
Federated Learning for Physical Layer Design
(Ieee-Inst Electrical Electronics Engineers Inc, 2021) Elbir, Ahmet M.; Papazafeiropoulos, Anastasios K.; Chatzinotas, Symeon
Model-free techniques, such as machine learning (ML), have recently attracted much interest toward the physical layer design (e.g., symbol detection, channel estimation, and beamforming). Most of these ML techniques employ centralized learning (CLK) schemes and assume the availability of datasets at a parameter server (PS), demanding the transmission of data from edge devices, such as mobile phones, to the PS. Exploiting the data generated at the edge, federated learning (FL) has been proposed recently as a distributed learning scheme, in which each device computes the model parameters and sends them to the PS for model aggregation, while the datasets are kept intact at the edge. Thus, FL is more communication-efficient and privacy-preserving than CL and applicable to the wireless communication scenarios, wherein the data are generated at the edge devices. This article presents the recent advances in FL-based training for physical layer design problems. Compared to CL, the effectiveness of FL is presented in terms of communication overhead with a slight performance loss in the learning accuracy. The design challenges, such as model, data, and hardware complexity, are also discussed in detail along with possible solutions.
Federated Learning in Vehicular Networks
(Institute of Electrical and Electronics Engineers Inc., 2022) Elbir, Ahmet M.; Soner, B.; Çöleri, S.; Gunduz, D.; Bennis, M.
Machine learning (ML) has recently been adopted in vehicular networks for applications such as autonomous driving, road safety prediction and vehicular object detection, due to its model-free characteristic, allowing adaptive fast response. However, most of these ML applications employ centralized learning (CL), which brings significant overhead for data trans-mission between the parameter server and vehicular edge devices. Federated learning (FL) framework has been recently introduced as an efficient tool with the goal of reducing transmission overhead while achieving privacy through the transmission of model updates instead of the whole dataset. In this paper, we investigate the usage of FL over CL in vehicular network applications to develop intelligent transportation systems. We provide a comprehensive analysis on the feasibility of FL for the ML based vehicular applications, as well as investigating object detection by utilizing image-based datasets as a case study. Then, we identify the major challenges from both learning perspective, i.e., data labeling and model training, and from the communications point of view, i.e., data rate, reliability, transmission overhead, privacy and resource management. Finally, we highlight related future research directions for FL in vehicular networks. © 2022 IEEE.
A Hybrid Architecture for Federated and Centralized Learning
(Ieee-Inst Electrical Electronics Engineers Inc, 2022) Elbir, Ahmet M.; Cöleri, Sinem; Papazafeiropoulos, Anastasios K.; Kourtessis, Pandelis; Chatzinotas, Symeon
Many of the machine learning tasks rely on centralized learning (CL), which requires the transmission of local datasets from the clients to a parameter server (PS) entailing huge communication overhead. To overcome this, federated learning (FL) has been suggested as a promising tool, wherein the clients send only the model updates to the PS instead of the whole dataset. However, FL demands powerful computational resources from the clients. In practice, not all the clients have sufficient computational resources to participate in training. To address this common scenario, we propose a more efficient approach called hybrid federated and centralized learning (HFCL), wherein only the clients with sufficient resources employ FL, while the remaining ones send their datasets to the PS, which computes the model on behalf of them. Then, the model parameters are aggregated at the PS. To improve the efficiency of dataset transmission, we propose two different techniques: i) increased computation-per-client and ii) sequential data transmission. Notably, the HFCL frameworks outperform FL with up to 20% improvement in the learning accuracy when only half of the clients perform FL while having 50% less communication overhead than CL since all the clients collaborate on the learning process with their datasets.
Hybrid Precoding Design for Two-Way Relay-Assisted Terahertz Massive MIMO Systems
(Ieee-Inst Electrical Electronics Engineers Inc, 2020) Mir, Talha; Waqas, Muhammad; Mir, Usama; Hussain, Syed Mudassir; Elbir, Ahmet M.; Tu, Shanshan
Hybrid precoding has emerged as a promising technique to reduce the hardware cost and complexity in millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems. However, due to the drastic increase in the number of user devices and higher data rate demand, new frequency bands (i.e., terahertz (THz) communications) are needed to explore. At THz frequencies, the precoding technique can provide a large beamforming gain, but still, the blockage and high path-loss remain a significant problem. To overcome the blockage problem, in this paper, we introduce the two-way relay design where the well-known two-way amplify-and-forward (AF) relay in THz-MIMO orthogonal frequency-division multiplexing (OFDM) systems is employed. The optimal two-way relay hybrid precoding problem is non-convex due to the practical hardware constraints (i.e., unit-modulus and block-diagonal constraints). To solve this problem, we first propose to use mathematical manipulations to remove the block-diagonal constraints from its analog part and then reformulate the original two-way relay hybrid precoding problem into a quadratic-convex problem with only power constraint. Finally, we obtain the closed-form solution for the two-way relay hybrid precoding problem. Simulation results reveal that our proposed solution can achieve better sum-rate and energy efficiency than existing hybrid schemes.
Hybrid Precoding for Multiuser Millimeter Wave Massive MIMO Systems: A Deep Learning Approach
(Ieee-Inst Electrical Electronics Engineers Inc, 2020) Elbir, Ahmet M.; Papazafeiropoulos, Anastasios K.
In multi-user millimeter wave (mmWave) multiple-input-multiple-output (MIMO) systems, hybrid precoding is a crucial task to lower the complexity and cost while achieving a sufficient sum-rate. Previous works on hybrid precoding were usually based on optimization or greedy approaches. These methods either provide higher complexity or have sub-optimum performance. Moreover, the performance of these methods mostly relies on the quality of the channel data. In this work, we propose a deep learning (DL) framework to improve the performance and provide less computation time as compared to conventional techniques. In fact, we design a convolutional neural network for MIMO (CNN-MIMO) that accepts as input an imperfect channel matrix and gives the analog precoder and combiners at the output. The procedure includes two main stages. First, we develop an exhaustive search algorithm to select the analog precoder and combiners from a predefined codebook maximizing the achievable sum-rate. Then, the selected precoder and combiners are used as output labels in the training stage of CNN-MIMO where the input-output pairs are obtained. We evaluate the performance of the proposed method through numerous and extensive simulations and show that the proposed DL framework outperforms conventional techniques. Overall, CNN-MIMO provides a robust hybrid precoding scheme in the presence of imperfections regarding the channel matrix. On top of this, the proposed approach exhibits less computation time with comparison to the optimization and codebook based approaches.
Joint Antenna Selection and Hybrid Beamformer Design Using Unquantized and Quantized Deep Learning Networks
(Ieee-Inst Electrical Electronics Engineers Inc, 2020) Elbir, Ahmet M.; Mishra, Kumar Vijay
In millimeter-wave communications, multiple-input-multiple-output (MIMO) systems use large antenna arrays to achieve high gain and spectral efficiency. These massive MIMO systems employ hybrid beamformers to reduce power consumption associated with fully digital beamforming in large arrays. Further savings in cost and power are possible through the use of subarrays. Unlike prior works that resort to large latency methods such as optimization and greedy search for subarray selection, we propose a deep-learning-based approach in order to overcome the complexity issue without causing significant performance loss. We formulate antenna selection and hybrid beamformer design as a classification/prediction problem for convolutional neural networks (CNNs). For antenna selection, the CNN accepts the channel matrix as input and outputs a subarray with optimal spectral efficiency. The resultant subarray channel matrix is then again fed to a CNN to obtain analog and baseband beamformers. We train the CNNs with several noisy channel matrices that have different channel statistics in order to achieve a robust performance at the network output. Numerical experiments show that our CNN framework provides an order better spectral efficiency and is 10 times faster than the conventional techniques. Further investigations with quantized-CNNs show that the proposed network, saved in no more than 5 bits, is also suited for digital mobile devices.
Low-Complexity Limited-Feedback Deep Hybrid Beamforming for Broadband Massive MIMO
(Ieee, 2020) Elbir, Ahmet M.; Mishra, Kumar Vijay
The broadband millimeter-wave (mm-Wave) systems use hybrid beamformers with common analog beamformer for the entire band while employing different baseband beamformers in different frequency sub-bands. Furthermore, the performance mostly relies on the perfectness of the channel information. In this paper, we propose a deep learning (DL) framework for hybrid beamformer design in broadband mmWave massive MIMO systems. We design a convolutional neural network (CNN) that accepts the channel matrix of all subcarriers as input and the output of CNN is the hybrid beamformers. The proposed CNN architecture is trained with imperfect channel matrices in order to provide robust performance against the deviations in the channel data. Hence, the proposed precoding scheme can handle the imperfect or limited feedback scenario where the full and exact knowledge of the channel is not available. We show that the proposed DL framework is more robust and computationally less complex than the conventional optimization and phase-extraction-based approaches.

Yazar "Elbir, Ahmet M." seçeneğine göre listele

Sayfa Başına Sonuç

Sıralama seçenekleri