arXiv subjects

Sinem Coleri

Publications and source records attributed to Sinem Coleri.

At least 55 records · Page 3Linked to original sources

arXiv2023

Vehicular Visible Light Positioning for Collision Avoidance and Platooning: A Survey

Relative vehicle positioning methods can contribute to safer and more efficient autonomous driving by enabling collision avoidance and platooning applications. For full automation, these applications require cm-level positioning accuracy and greater than 50 Hz update rate. Since sensor-based methods (e.g., LIDAR, cameras) have not been able to reliably satisfy these requirements under all conditions so far, complementary methods are sought. Recently, positioning based on visible light communication signals from vehicle head/tail LED lights (VLP) has shown significant promise as a complementary method attaining cm-level accuracy and near-kHz rate in realistic driving scenarios. Vehicular VLP methods measure relative bearing (angle) or range (distance) of transmitters (i.e., head/tail lights) based on received signals from on-board photodiodes and estimate transmitter relative positions based on those measurements. In this survey, we first review existing vehicular VLP methods and propose a new method that advances the state-of-the-art in positioning performance. Next, we analyze the theoretical and simulated performance of all methods in realistic driving scenarios under challenging noise and weather conditions, real asymmetric light beam patterns and different vehicle dimensions and light placements. Our simulation results show that the newly proposed VLP method is the overall best performer, and can indeed satisfy the accuracy and rate requirements for localization in collision avoidance and platooning applications within practical constraints. Finally, we discuss remaining open challenges that are faced for the deployment of VLP solutions in the automotive sector and further research questions.

eess.SP↗

arXiv2023

Statistical Analysis of Geometric Algorithms in Vehicular Visible Light Positioning

Vehicular visible light positioning (VLP) methods find relative locations of vehicles by estimating the positions of intensity-modulated head/tail lights of one vehicle (target) with respect to another (ego). Estimation is done in two steps: 1) relative bearing or range of the transmitter-receiver link is measured over the received signal on the ego side, and 2) target position is estimated based on those measurements using a geometric algorithm that expresses position coordinates in terms of the bearing-range parameters. The primary source of statistical error for these non-linear algorithms is the channel noise on the received signals that contaminates parameter measurements with varying levels of sensitivity. In this paper, we present two such geometric vehicular VLP algorithms that were previously unexplored, compare their performance with state-of-the-art algorithms over simulations, and analyze theoretical performance of all algorithms against statistical channel noise by deriving the respective Cramer-Rao lower bounds. The two newly explored algorithms do not outperform existing state-of-the-art, but we present them alongside the statistical analyses for the sake of completeness and to motivate further research in vehicular VLP. Our main finding is that direct bearing-based algorithms provide higher accuracy against noise for estimating lateral position coordinates, and range-based algorithms provide higher accuracy in the longitudinal axis due to the non-linearity of the respective geometric algorithms.

eess.SP↗

arXiv2022

Vehicular Networks for Combating a Worldwide Pandemic: Preventing the Spread of COVID-19

As a worldwide pandemic, the coronavirus disease-19 (COVID-19) has caused serious restrictions in people's social life, along with the loss of lives, the collapse of economies and the disruption of humanitarian aids. Despite the advance of technological developments, we, as researchers, have witnessed that several issues need further investigation for a better response to a pandemic outbreak. Therefore, researchers recently started developing ideas to stop or at least reduce the spread of the pandemic. While there have been some prior works on wireless networks for combating a pandemic scenario, vehicular networks and their potential bottlenecks have not yet been fully examined. Furthermore, the vehicular scenarios can be identified as the locations, where the social distancing is mostly violated. With this motivation, this article provides an extensive discussion on vehicular networking for combating a pandemic. We provide the major applications of vehicular networking for combating COVID-19 in public transportation, in-vehicle diagnosis, border patrol and social distance monitoring. Next, we identify the unique characteristics of the collected data in terms of privacy, flexibility and coverage, then highlight corresponding future directions in privacy preservation, resource allocation, data caching and data routing. We believe that this work paves the way for the development of new products and algorithms that can facilitate the social life and help controlling the spread of the pandemic.

eess.SP↗

arXiv2022

Federated Learning in Vehicular Networks

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 transmission 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.

eess.SP↗

arXiv2022

A Hybrid Architecture for Federated and Centralized Learning

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.

cs.LG↗

arXiv2022

Federated Channel Learning for Intelligent Reflecting Surfaces With Fewer Pilot Signals

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 IRS-assisted 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.

eess.SP↗

arXiv2021

Measurement Based Non-Line-Of-Sight Vehicular Visible Light Communication Channel Characterization

Vehicular visible light communication (V-VLC) aims to provide secure complementary vehicle to everything communications (V2X) to increase road safety and traffic efficiency. V-VLC provides directional transmissions, mainly enabling line-of-sight (LoS) communications. However, reflections due to nearby objects enable non-line-of-sight (NLoS) transmissions, extending the usage scenarios beyond LoS. In this paper, we propose a wide-band measurement-based NLoS channel characterization and evaluate the performance of direct current biased optical orthogonal frequency division multiplexing (DCO-OFDM) V-VLC scheme for NLoS channel. We propose a distance-based NLoS V-VLC channel path loss model considering reflection surface characteristics and NLoS V-VLC channel impulse response (CIR) incorporating the temporal broadening effect due to vehicle reflections through weighted double gamma function. The proposed path loss model yields higher accuracy up to 14 dB when compared to the single order reflection model whereas the CIR model estimates the full width at half maximum up to 2 ns accuracy. We further demonstrate that the target bit-error-rate of 10^-3 can be achieved up to 7.86 m, 9.79 m, and 17.62 m distances for black, orange, and white vehicle reflection induced measured NLoS V-VLC channels for DCO-OFDM transmissions.

eess.SP↗

arXiv2021

Vehicular Visible Light Communications Noise Analysis and Autoencoder Based Denoising

Vehicular visible light communications (V-VLC) is a promising intelligent transportation systems (ITS) technology for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications with the utilization of light-emitting diodes (LEDs). The main degrading factor for the performance of V-VLC systems is noise. Unlike traditional radio frequency (RF) based systems, V-VLC systems include many noise sources: solar radiation, background lighting from vehicles, streets, parking garages, and tunnel lights. Traditional V-VLC system noise modeling is based on the additive white Gaussian noise assumption in the form of shot and thermal noise. In this paper, to investigate both time-correlated and white noise components of the V-VLC channel, we propose a noise analysis based on Allan variance (AVAR), which provides a time-series analysis method to identify noise from the data. We also propose a generalized Wiener process-based V-VLC channel noise synthesis methodology to generate different noise components. We further propose a convolutional autoencoder(CAE) based denoising scheme to reduce V-VLC signal noise, which achieves reconstruction root mean square error (RMSE) of 0.0442 and 0.0474 for indoor and outdoor channels, respectively.

eess.SP↗

arXiv2021

Vehicular Visible Light Communications for Automated Valet Parking

Visible light communication (VLC) is a promising Optical Wireless Communications (OWC) scheme that is demonstrated to provide secure, line-of-sight (LoS), and short-distance vehicle-to-vehicle (V2V) and vehicle-to-infrastructure(V2I) communications. Recently, automated driving applications, supported by V2I links are proposed to increase the reliability of the autonomous vehicles. To this regard, we propose a VLCbased V2I scheme to increase the V2I communication redundancy of autonomous valet parking (AVP) applications, through jam-free and location-based characteristics of VLC. In this paper, we demonstrate a novel architecture to support indoor parking-garage online-map update with vehicle on-board data transmissions and location-based map update dissemination through bidirectional VLC communications. The proposed system yields error-free LoS transmissions with Direct Current Biased Optical OFDM (DCO-OFDM) up to 33 m transmitter-receiver distance enabling vehicle CAN Bus data, infrastructure camera video, and LIDAR point cloud data sharing in an indoor parking garage.

cs.NI↗

arXiv2021

Federated Learning for Channel Estimation in Conventional and RIS-Assisted Massive MIMO

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.

eess.SP↗

arXiv2021

Hybrid Federated and Centralized Learning

Many of the machine learning (ML) tasks are focused on centralized learning (CL), which requires the transmission of local datasets from the clients to a parameter server (PS) leading to a huge communication overhead. Federated learning (FL) overcomes this issue by allowing the clients to send only the model updates to the PS instead of the whole dataset. In this way, FL brings the learning to edge level, wherein powerful computational resources are required on the client side. This requirement may not always be satisfied because of diverse computational capabilities of edge devices. We address this through a novel hybrid federated and centralized learning (HFCL) framework to effectively train a learning model by exploiting the computational capability of the clients. In HFCL, only the clients who have sufficient resources employ FL; the remaining clients resort to CL by transmitting their local dataset to PS. This allows all the clients to collaborate on the learning process regardless of their computational resources. We also propose a sequential data transmission approach with HFCL (HFCL-SDT) to reduce the training duration. The proposed HFCL frameworks outperform previously proposed non-hybrid FL (CL) based schemes in terms of learning accuracy (communication overhead) since all the clients collaborate on the learning process with their datasets regardless of their computational resources.

cs.LG↗

arXiv2021

Federated Dropout Learning for Hybrid Beamforming With Spatial Path Index Modulation In Multi-User mmWave-MIMO Systems

Millimeter wave multiple-input multiple-output (mmWave-MIMO) systems with small number of radio-frequency (RF) chains have limited multiplexing gain. Spatial path index modulation (SPIM) is helpful in improving this gain by utilizing additional signal bits modulated by the indices of spatial paths. In this paper, we introduce model-based and model-free frameworks for beamformer design in multi-user SPIM-MIMO systems. We first design the beamformers via model-based manifold optimization algorithm. Then, we leverage federated learning (FL) with dropout learning (DL) to train a learning model on the local dataset of users, who estimate the beamformers by feeding the model with their channel data. The DL randomly selects different set of model parameters during training, thereby further reducing the transmission overhead compared to conventional FL. Numerical experiments show that the proposed framework exhibits higher spectral efficiency than the state-of-the-art SPIM-MIMO methods and mmWave-MIMO, which relies on the strongest propagation path. Furthermore, the proposed FL approach provides at least 10 times lower transmission overhead than the centralized learning techniques.

eess.SP↗

arXiv2021

Visible Light Communication based Vehicle Localization for Collision Avoidance and Platooning

Collision avoidance and platooning applications require vehicle localization at cm-level accuracy and at least 50 Hz rate for full autonomy. The RADAR/LIDAR and camera based methods currently used for vehicle localization do not satisfy these requirements, necessitating complementary technologies. Visible light positioning (VLP) is a highly suitable complementary technology due to its high accuracy and high rate, exploiting the line-of-sight propagation feature of the visible light communication (VLC) signals from LED head/tail lights. However, existing vehicular VLP algorithms impose restrictive requirements, e.g., use of high-bandwidth circuits, road-side lights and certain VLC modulation strategies, and work for limited relative vehicle orientations, thus, are not feasible for general use. This paper proposes a VLC-based vehicle localization method that eliminates these restrictive requirements by a novel VLC receiver design and associated vehicular VLP algorithm. The VLC receiver, named QRX, is low-cost/size, and enables high-rate VLC and high-accuracy angle-of-arrival (AoA) measurement, simultaneously, via the usage of a quadrant photodiode. The VLP algorithm estimates the positions of two head/tail light VLC transmitters (TX) on a neighbouring vehicle by using AoA measurements from two QRXs for localization. The algorithm is theoretically analyzed by deriving its Cramer-Rao lower bound on positioning accuracy, and simulated localization performance is evaluated under realistic platooning and collision avoidance scenarios. Results demonstrate that the proposed method performs at cm-level accuracy and up to 250 Hz rate within a 10 m range under realistic harsh road and channel conditions, demonstrating its eligibility for collision avoidance and safe platooning.

eess.SP↗

arXiv2021

Minimum Length Scheduling for Multi-cell Full Duplex Wireless Powered Communication Networks

In this paper, we investigate a novel minimum length scheduling problem to determine the optimal power control, and scheduling for constant and continuous rate models, while considering concurrent transmission of users, energy causality, maximum transmit power and traffic demand constraints. The formulated optimization problems are shown to be non-convex and combinatorial in nature, thus, difficult to solve for the global optimum. As a solution strategy, first, we propose optimal polynomial time algorithms for the power control problem considering constant and continuous rate models based on the evaluation of Perron-Frobenius conditions and usage of bisection method, respectively. Then, the proposed optimal power control solutions are used to determine the optimal transmission time for a subset of users that will be scheduled by the scheduling algorithms. For the constant rate scheduling problem, we propose a heuristic algorithm that aims to maximize the number of concurrently transmitting users by maximizing the allowable interference on each user without violating the signal-to-noise-ratio (SNR) requirements. For the continuous rate scheduling problem, we define a penalty function representing the advantage of concurrent transmission over individual transmission of the users. Following the optimality analysis of the penalty metric and demonstration of the equivalence between schedule length minimization and minimization of the sum of penalties, we propose a heuristic algorithm based on the allocation of the concurrently transmitting users with the goal of minimizing the sum penalties over the schedule. Through extensive simulations, we demonstrate that the proposed algorithm outperforms the successive transmission and concurrent transmission of randomly selected users for different HAP transmit powers, network densities and network size.

eess.SP↗

arXiv2020

Federated Learning for Hybrid Beamforming in mm-Wave Massive MIMO

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.

eess.SP↗

arXiv2020

Minimum Length Scheduling for Full Duplex Time-Critical Wireless Powered Communication Networks

Radio frequency (RF) energy harvesting is key in attaining perpetual lifetime for time-critical wireless powered communication networks due to full control on energy transfer, far field region, small and low-cost circuitry. In this paper, we propose a novel minimum length scheduling problem to determine the optimal power control, time allocation and transmission schedule subject to data, energy causality and maximum transmit power constraints in a full-duplex wireless powered communication network. We first formulate the problem as a mixed integer non-linear programming problem and conjecture that the problem is NP-hard. As a solution strategy, we demonstrate that the power control and time allocation, and scheduling problems can be solved separately in the optimal solution. For the power control and time allocation problem, we derive the optimal solution by using Karush-Kuhn-Tucker conditions. For the scheduling, we introduce a penalty function allowing reformulation as a sum penalty minimization problem. Upon derivation of the optimality conditions based on the characteristics of the penalty function, we propose two polynomial-time heuristic algorithms and a reduced-complexity exact algorithm employing smart pruning techniques. Via extensive simulations, we illustrate that the proposed heuristic schemes outperform the previously proposed schemes for predetermined transmission order of users and achieve close-to-optimal solutions.

eess.SP↗

arXiv2020

Minimum Length Scheduling for Discrete-Rate Full-Duplex Wireless Powered Communication Networks

In this paper, we consider a wireless powered communication network where multiple users with RF energy harvesting capabilities communicate to a hybrid energy and information access point (HAP) in full-duplex mode. Each user has to transmit a certain amount of data with a transmission rate from a finite set of discrete rate levels, using the energy initially available in its battery and the energy it can harvest until the end of its transmission. Considering this model, we propose a novel discrete rate based minimum length scheduling problem to determine the optimal power control, rate adaptation and transmission schedule subject to data, energy causality and maximum transmit power constraints. The proposed optimization problem is proven to be NP-hard which requires exponential-time algorithms to solve for the global optimum. As a solution strategy, first, we demonstrate that the power control and rate adaptation, and scheduling problems can be solved separately in the optimal solution. For the power control and rate adaptation problem, we derive the optimal solution based on the proposed minimum length scheduling slot definition. For the scheduling, we classify the problem based on the distribution of minimum length scheduling slots of the users over time. For the non-overlapping slots scenario, we present the optimal scheduling algorithm. For the overlapping scenario, we propose a polynomial-time heuristic scheduling algorithm.

eess.SP↗

arXiv2020

Optimal On-Off Transmission Schemes for Full Duplex Wireless Powered Communication Networks

In this paper, we consider a full duplex wireless powered communication network where multiple users with radio frequency energy harvesting capability communicate to an energy broadcasting hybrid access point. We investigate the minimum length scheduling and sum throughput maximization problems considering on-off transmission scheme in which users either transmit at a constant power or remain silent. For minimum length scheduling problem, we propose a polynomial-time optimal scheduling algorithm. For sum throughput maximization, we first derive the characteristics of an optimal schedule and then to avoid intractable complexity, we propose a polynomial-time heuristic algorithm which is illustrated to perform nearly optimal through numerical analysis.

eess.SY↗