VTC 2025 Spring Conference’s Shorts

Transfer Learning for VLC-based indoor Localization: Addressing Environmental Variability

Accurate indoor localization is crucial in industrial environments. Visible Light Communication (VLC) has emerged as a promising solution, offering high accuracy, energy efficiency, and minimal electromagnetic interference. However, VLC-based indoor localization faces challenges due to environmental variability, such as lighting fluctuations and obstacles. To address these challenges, we propose a Transfer Learning (TL)-based approach for VLC-based indoor localization. Using real-world data collected at a BOSCH factory, the TL framework integrates a deep neural network (DNN) to improve localization accuracy by 47%, reduce energy consumption by 32%, and decrease computational time by 40% compared to the conventional models. The proposed solution is highly adaptable under varying environmental conditions and achieves similar accuracy with only 30% of the dataset, making it a cost-efficient and scalable option for industrial applications in Industry 4.0.Transfer Learning for VLC-based indoor Localization: Addressing Environmental VariabilityMasood Jan, Institut supérieur d'électronique de Paris (ISEP); Wafa Njima, ISEP; Xun Zhang, Institut suprieur d’lectronique de Paris; Alexander Artemenko, Robert Bosch GmbH, Stuttgart, Germany

Mixed-Field Localization for Range-Angle Migration with Low Complexity in Automotive MIMO ...

In this paper, we present a direction of arrival (DOA) estimation method for multiple-input and multiple-output frequency-modulated continuous wave radar systems considering range-angle migration and piecewise sub-array model. In general, DOA estimation methods based on an exact wavefront model can achieve highly accurate results. However, the methods also entail considerable computational complexity, hindering real-time radar data processing in automotive driving. To reduce the computational complexity caused from the nonlinearity of wavefront curvature, we use a piecewise sub-array model and FFT-based methods in both the range and angle domains. The proposed method combines the advantages of far-field-based methods and near-field-based methods, thereby offering enhanced resolution at a reduced computational cost. We confirm that the DOA spectrum generated by the proposed method achieves higher resolution compared to conventional far-field-based methods and demonstrates approximately four times greater computational efficiency (in terms of FLOPs) than the back-projection algorithm.Mixed-Field Localization for Range-Angle Migration with Low Complexity in Automotive MIMO Radar SystemsGunhwi Moon, Seoul National University

LiDAR based Landmark and Odometry fusion for precise rail localization without additional ...

This paper addresses the need for precise train localization within rail networks. Traditional methods face challenges such as high costs, imprecision, and vulnerabilities to disruptions. To overcome these issues, we propose a localization approach without additional infrastructure, i.e., using only existing infrastructure landmarks, specifically catenary poles, using a Deep Neural Network (DNN) within the 3D point cloud captured by a LiDAR sensor. By matching these landmarks to a precomputed two-dimensional HD Map and fusing this information with a state-of-the art LiDAR odometry algorithm, our proof of concept demonstrates the ability to achieve sub-meter precision for electrified rail segments.LiDAR based Landmark and Odometry fusion for precise rail localization without additional infrastructureJohannes Wortmann, Fraunhofer Institute for Open Communication Systems (FOKUS); Florian Wulff, Fraunhofer Institute for Open Communication Technologies (FOKUS); Bernd Schäufele, Daimler Center for Automotive IT Innovations (DCAITI); Ilja Radusch, Daimler Center for Automotive IT Innovations

Improving GNSS Localization in IoT Applications with Machine Learning and 3D Map Integrati...

In Internet of Things (IoT) applications, ultra-low-power GNSS receivers combined with cloud-based positioning engines often rely on a single-epoch positioning framework with a limited set of raw measurements. As redundancy and prior estimates cannot be leveraged for signal selection, these approaches pose significant challenges when it comes to GNSS degraded environments. To address these limitations, we propose a novel approach that integrates Machine Learning (ML) techniques with 3D map data to enhance the accuracy and robustness of GNSS localization in complex urban environments. Our method leverages a Long Short-Term Memory Neural Network (LSTM-NN) to predict pseudorange error magnitudes, while a simplified ray-tracing algorithm is used to derive map-based features. The predicted error magnitudes are utilized to weight measurements within the positioning engine, enabling reliable single-epoch positioning even when working with a limited set of signals. Real-world experiments demonstrate the effectiveness of our approach, showcasing strong performance in low-connectivity contexts. Furthermore, the methodology shows promise for extension to alternative signals such as Narrowband-IoT (NB-IoT) and 5G.Improving GNSS Localization in IoT Applications with Machine Learning and 3D Map IntegrationMarion Jeamart, CEA - Leti Grenoble; Ibrahim Sbeity, CEA Grenoble, ETIS, CY Cergy Paris Université, ENSEA, CNRS; Christophe Villien, CEA-Leti

RRAM-based nonlinear precoding with linear complexity and quantization analysis

In multi-user communication systems, nonlinear precoding generally exhibits higher throughput than linear precoding, however at the cost of higher computation complexity. With the increasing number of antennas and users, the realization of nonlinear precoder at the base station is even more challenging. To address this issue, we propose a new system architecture that employs resistive random-access memory (RRAM) circuits to reduce the computation complexity of the nonlinear Tomlinson-Harashima precoding (THP) to a linear scale. We present a computation-constraints principle for designing RRAM circuits to perform nonlinear operations and construct an LQ decomposition RRAM circuit. Since the conductance of memristor is quantized, we perform the bit precision analysis and derive the lower bound of the Signal to Interference plus Noise Ratio (SINR). Our analysis indicates that at a high Signal to Noise Ratio (SNR) or with a large number of antennas, each 1 bit increase in bit precision brings a 6 dB improvement in SINR. Simulation demonstrates the feasibility and accuracy of the RRAM-based circuit and our theoretical results. Our work proves that the RRAM array holds significant potential for implementing high-complexity nonlinear precoding algorithms and may offer a promising solution to meet the demands of future communication.RRAM-based nonlinear precoding with linear complexity and quantization analysisYuhao Zhang, Huazhong University of science and technology; Haifan Yin, Tao Wang, Jindiao Huang, Huazhong University of Science and Technology

Robust DWMMSE Framework for Energy-Efficient Relay-Assisted Carrier Aggregation (RACA) in ...

Extended Reality (XR) applications demanding high data rates pose significant challenges for uplink transmissions from user equipment (UE) with limited power and antenna resources. Recently, relay-assisted carrier aggregation (RACA) systems have been proposed to enhance data rates by transmitting data across two frequency bands. This paper addresses the practical issues of power-constrained XR devices and imperfect channel state information (CSI) in RACA systems. We propose a robust Dinkelbach’s-transformed weighted minimum mean square error (DWMMSE) framework to maximize energy efficiency (EE) and minimize mean square error (MSE) under Gaussian CSI errors. The framework adapts to content-intensive, power-constrained, and reliability-critical XR scenarios through specific alternating optimization settings. Simulation results demonstrate that DWMMSE achieves superior EE with a 92% reduction in complexity compared to baseline methods. Moreover, it delivers lower MSE and bit error rate (BER) than non-robust schemes.Robust DWMMSE Framework for Energy-Efficient Relay-Assisted Carrier Aggregation (RACA) in Power-Constrained XR SystemsChi-Wei Chen, National Taiwan University

Next Generation Reference Signal Design Using Non-Orthogonal Space-Time Codes

In this paper, we propose a Reference Signal (RS) framework potentially for next generation wireless systems, which targets to systematical RS construction with non-orthogonal Space-Time Code (STC) designs. In particular, we embed parametrized non-orthogonal STCs into the RS design, by exploiting the properties of so-called ABBA STCs or its diagonal variants, where the diagonality is imposed by use of appropriate precoding and postcoding. The transformations of the ABBA coding vectors can be resolved at the receiver. The transformed matrices are used to enhance channel estimation quality with the aid of inherent power gain, self-interference mitigation, and diversity gain. The proposed framework can be flexibly integrated to existing RS sequences, defined in 5G New Radio (NR). In effect, this leads to parameterizable code space and controllable self-interference. The proposed RS construction can be easily extended to support 2𝑀× 2𝑀 STC systems for 𝑀≥2, and can be used to track the channel response with up to 2𝑀 spatial links in parallel.Next Generation Reference Signal Design Using Non-Orthogonal Space-Time CodesYejian Chen, Bell Labs, Nokia; Ari Hottinen, Nokia Technologies

Near-Field Channel Estimation via Dynamic Grids and Bayesian Inference

In this paper, we propose a dynamic grid sparse Bayesian inference (DGSBI) method for near-field channel estimation in extremely large-scale multiple-input multiple-output (XL-MIMO) systems. To address the off-grid problem of scatterers in the polar-domain channel, we represent the polar-domain dictionary dynamically using angle and distance offsets and provide a sparse representation of the channel within this dynamic dictionary. By updating the grid through angle and distance offset variables, the proposed method significantly improves signal recovery performance in the sparse polar domain. The dictionary update process is modeled as a linear-quadratic (LQ) optimization problem, and we derive an analytical solution for the update. Simulation results demonstrate that our method outperforms benchmark approaches in terms of estimation accuracy.Near-Field Channel Estimation via Dynamic Grids and Bayesian InferenceZhongmin Ma, Xi'an Jiaotong University, China; Wang Jianwei, ZTE Corporation; Qinghe Du, Yuhao Zhang, Xi'an Jiaotong University; Yunsheng Zhang, School of International Exchange and Cooperation; Chen Lu, Shenzhen Institute of Information Technology

BER Prediction of Distributed MISO Systems using Beamsteering with Phase Compensation in m...

This paper presents theoretical derivations for predicting the bit error rate (BER) of distributed antenna systems (DAS) in 3GPP clustered delay line channels with partial blockage accounting for typical millimeter wave (mmWave) propagation conditions. Assuming that the receiver equalizer is not updated during sudden blockage events, a statistical analysis is led to provide the probability density functions for received symbols under such blockage conditions. Three beamforming techniques—maximum ratio transmission (MRT), beamsteering (BS), and a proposed combination of BS with phase compensation (PC)—are considered in line-of-sight scenarios. Analytical BER predictions of the proposed PC-BS are validated through simulations, offering insights for optimizing DAS in mmWave environments. In particular, we conclude that PC-BS performs very close to MRT while being much simpler to implement and much more suited to mmWave electronics.BER Prediction of Distributed MISO Systems using Beamsteering with Phase Compensation in mmWave ChannelsThibaut Rolland, Orange Innovation of Rennes, France; Matthieu Crussière, IETR of Rennes; Marie Le Bot, Orange Innovation of Rennes

Performance of Cell-Sweeping Using 256-QAM, 3D Antennas and SU-MIMO in 3GPP LTE

Ensuring robust and uniform network coverage is crucial for mobile network operators, particularly at the cell edges, where interference remains a persistent challenge. Traditional solutions such as network densification are complex, costly, and prone to increased interference. This paper presents the performance of recently proposed Cell-Sweeping base stations deployment in a typical 4G LTE network with Single User-Multiple Input Multiple Output (SU-MIMO) operation, use of higher-order modulation schemes, i.e. 256-Quadrature Amplitude Modulation (256-QAM), as well as using 3D antenna radiation patterns. By dynamically sweeping the antenna radiation patterns, cell-sweeping aims to significantly enhance the cell-edge performance while at the same time also harmonises the distribution of throughput in the whole cell. System-level simulations conducted using the 3rd Generation Partnership Project (3GPP) configurations reveal significant performance gain of cell-sweeping of up to 147% improvement in cell-edge throughput observed under open-loop spatial multiplexing, i.e. Transmission Mode 3 (TM3) in 3GPP LTE compared to conventional (i.e. non cell-sweeping) cellular network deployment. The results demonstrate that integrating cell-sweeping with advanced modulation and MIMO configurations is feasible and significantly improves Signal-to-Interference-plus-Noise Ratio (SINR), throughput, and Channel Quality Indicators (CQI) distribution, particularly in dense urban environments. These findings highlight the potential of cell-sweeping as an effective and simpler deployment strategy for future radio access networks.Performance of Cell-Sweeping Using 256-QAM, 3D Antennas and SU-MIMO in 3GPP LTEAli Alnaqeeb, Atta Quddus, Chuan Heng Foh, Rahim Tafazolli, University of Surrey