arXiv subjects

Rodney Martinez Alonso

Publications and source records attributed to Rodney Martinez Alonso.

9 recordsLinked to original sources

arXiv2026

Depthwise Separable CNN for D-MIMO Indoor Localization with Data Reduction

Indoor localization using Distributed Multiple-Input Multiple-Output (D-MIMO) and machine learning (ML) achieves sub-centimeter accuracy but faces midhaul capacity bottlenecks when transmitting raw Channel State Information (CSI) in Open Radio Access Networks (O-RAN) architectures. To address this, we propose a lightweight, distributed ML framework that shifts initial processing to the network edge. By deploying localized models as dApps on Distributed Units (DUs), each requiring just 1.39 MB of memory and 1.96 MFLOPs, the system performs CSI feature extraction and reduction on the edge. The reduced low-dimensional features are transmitted to the Central Unit (CU), where another dApp is deployed for location estimation. Evaluated on a high-density dataset, this framework reduces midhaul traffic by 100x while maintaining an average error of 8.5 mm, even with half the deployed Radio Units (RUs), providing a scalable blueprint for practical D-MIMO localization.

eess.SP↗

arXiv2026

Low Complexity Neural Network Digital Predistortion of Wideband Power Amplifiers through Feature Selection

Due to the continuous increase in communication bandwidth and the use of highly efficient yet nonlinear power amplifiers, Digital Predistortion (DPD) algorithms are becoming increasingly complex. In particular, neural network (NN) based DPD approaches using Phase-Normalized NN architectures often incur substantially higher computational costs than widely deployed polynomial-based methods, such as the Memory Polynomial (MP) and Generalized Memory Polynomial (GMP) models. To bridge this gap between research performance and practical implementation, we propose a low-complexity Feature Selection NN DPD architecture. The proposed method employs an offline feature-engineering pipeline based on the Least Absolute Shrinkage and Selection Operator (LASSO) and the Minimum Redundancy Maximum Relevance (MRMR) algorithm to construct a compact and informative input representation. Using measured wideband FR3 power amplifier datasets that are publicly released with this work, we demonstrate up to 30% reduction in computational complexity while maintaining comparable linearization performance.

eess.SP↗

arXiv2026

LITE: Lightweight Channel Gain Estimation with Reduced X-Haul CSI Signaling in O-RAN

Cell-Free Massive Multiple-Input Multiple-Output (CF-MaMIMO) in Open Radio Access Network (O-RAN) promises high spectral efficiency but is limited by frequent Channel State Information (CSI) exchanges, which strain fronthaul/midhaul/backhaul (X-haul) bandwidth and exceed the capabilities of existing approaches relying on uncompressed CSI or heavy predictors. To overcome these constraints, we propose LITE, a lightweight pipeline combining a 1-D convolutional Autoencoder (AE) at the O-RAN Distributed Unit (O-DU) with a Squeeze-and-Excitation (SE)-enhanced Bidirectional Long Short-Term Memory (BiLSTM) predictor at the Near-Real-Time RAN Intelligent Controller (Near-RT-RIC), enabling short-horizon trajectory-unaware forecasting under strict transport and processing budgets. LITE applies 50% CSI compression and an asymmetric SE-BiLSTM, reducing model complexity by 83.39% while improving accuracy by 5% relative to a baseline BiLSTM. With compression-aware training, the Lightweight Intelligent Trajectory Estimator (LITE) incurs only 6% accuracy loss versus the BiLSTM baseline, outperforming independent and end-to-end strategies. A TensorRT-optimized implementation achieves 147k Queries per Second (QPS), a 4.6x throughput gain. These results demonstrate that LITE delivers X-haul-efficient, low-latency, and deployment-ready channel-gain prediction compatible with O-RAN splits.

cs.NI↗

arXiv2026

Efficient Channel Autoencoders for Wideband Communications leveraging Walsh-Hadamard interleaving

This paper investigates how end-to-end (E2E) channel autoencoders (AEs) can achieve energy-efficient wideband communications by leveraging Walsh-Hadamard (WH) interleaved converters. WH interleaving enables high sampling rate analog-digital conversion with reduced power consumption using an analog WH transformation. We demonstrate that E2E-trained neural coded modulation can transparently adapt to the WH-transceiver hardware without requiring algorithmic redesign. Focusing on the short block length regime, we train WH-domain AEs and benchmark them against standard neural and conventional baselines, including 5G Polar codes. We quantify the system-level energy tradeoffs among baseband compute, channel signal-to-noise ratio (SNR), and analog converter power. Our analysis shows that the proposed WH-AE system can approach conventional Polar code SNR performance within 0.14dB while consuming comparable or lower system power. Compared to the best neural baseline, WH-AE achieves, on average, 29% higher energy efficiency (in bit/J) for the same reliability. These findings establish WH-domain learning as a viable path to energy-efficient, high-throughput wideband communications by explicitly balancing compute complexity, SNR, and analog power consumption.

cs.IT↗

arXiv2026

Inter-Cell Interference Rejection Based on Ultrawideband Walsh-Domain Wireless Autoencoding

This paper proposes a novel technique for rejecting partial-in-band inter-cell interference (ICI) in ultrawideband communication systems. We present the design of an end-to-end wireless autoencoder architecture that jointly optimizes the transmitter and receiver encoding/decoding in the Walsh domain to mitigate interference from coexisting narrower-band 5G base stations. By exploiting the orthogonality and self-inverse properties of Walsh functions, the system distributes and learns to encode bit-words across parallel Walsh branches. Through analytical modeling and simulation, we characterize how 5G CPOFDM interference maps into the Walsh domain and identify optimal ratios of transmission frequencies and sampling rate where the end-to-end autoencoder achieves the highest rejection. Experimental results show that the proposed autoencoder achieves up to 12 dB of ICI rejection while maintaining a low block error rate (BLER) for the same baseline channel noise, i.e., baseline Signal-to-Noise-Ratio (SNR) without the interference.

eess.SP↗

arXiv2024

Multi-objective Optimization of Cognitive Radio Networks

New generation networks, based on Cognitive Radio technology, allow dynamic allocation of the spectrum, alleviating spectrum scarcity. These networks also have a resilient potential for dynamic operation for energy saving. In this paper, we present a novel wireless network optimization algorithm for cognitive radio networks based on a cloud sharing-decision mechanism. Three Key Performance Indicators (KPIs) were optimized: spectrum usage, power consumption, and exposure of human beings. For a realistic suburban scenario in Ghent city, Belgium, we determine the optimality among the KPIs. Compared to a traditional Cognitive Radio network design, our optimization algorithm for the cloud-based architecture reduced the network power consumption by 27.5%, the average global exposure by 34.3%, and spectrum usage by 34.5% at the same time. Even for the worst optimization case, our solution performs better than the traditional architecture by 4.8% in terms of network power consumption, 7.3% in terms of spectrum usage and 4.3% in terms of global exposure.

cs.NI↗

arXiv2024

TV White Space and LTE Network Optimization towards Energy Efficiency in Suburban and Rural Scenarios

The radio spectrum is a limited resource. Demand for wireless communication services is increasing exponentially, stressing the availability of radio spectrum to accommodate new services. TV White Space (TVWS) technologies allow a dynamic usage of the spectrum. These technologies provide wireless connectivity, in the channels of the Very High Frequency (VHF) and Ultra High Frequency (UHF) television broadcasting bands. In this paper, we investigate and compare the coverage range, network capacity, and network energy efficiency for TVWS technologies and LTE. We consider Ghent, Belgium and Boyeros, Havana, Cuba to evaluate a realistic outdoor suburban and rural area, respectively. The comparison shows that TVWS networks have an energy efficiency 9-12 times higher than LTE networks.

cs.NI↗

arXiv2024

Electric Field Evaluation of Reconfigurable Intelligent Surface in Wireless Networks

Reconfigurable intelligent surface (RIS) used as infrastructure in wireless networks has been a trend, thanks to its low cost and high flexibility. Working in many ways including reflective mirrors and phase-shifted surfaces, RIS is able to enhance the coverage in communications and provide more degrees of freedom for sensing. However, the key issue lies in how to place RIS in accordance with the regulations for electromagnetic field (EMF) exposure, which requires refined evaluations. In this paper, we first investigate the regulations in terms of E-field. Then, relevant deployment characteristics are evaluated jointly: the minimum distance from the base station (BS) to the RIS, and the minimum height of the RIS are given for a given BS power limit and as function of the number of RIS elements. The ray-tracing simulations verify the correctness of our analysis. Besides, different frequency ranges (FRs) and radiation patterns of RIS elements are investigated. The results show that the EMF exposure risk is negligible when RIS works in the reflective-only (RO) mode. However, when it works in the beamforming (BO) mode, its placement should be well specified based on our analytical framework to comply with the regulations of E-field limit in general public scenarios. Finally, we provide an E-field measurement methodology and low-cost solutions in terms of general wireless networks and 5G standalone networks, which pave the way for real-world evaluation in future work.

eess.SY↗

arXiv2024

Walsh-domain Neural Network for Power Amplifier Behavioral Modelling and Digital Predistortion

This paper investigates the use of Neural Network (NN) nonlinear modelling for Power Amplifier (PA) linearization in the Walsh-Hadamard transceiver architecture. This novel architecture has recently been proposed for ultra-high bandwidth systems to reduce the transceiver power consumption by extensive parallelization of the digital baseband hardware. The parallelization is achieved by replacing two-dimensional quadrature modulation with multi-dimensional Walsh-Hadamard modulation. The open research question for this architecture is whether conventional baseband signal processing algorithms can be similarly parallelized while retaining their performance. A key baseband algorithm, digital predistortion using NN models for PA linearization, will be adapted to the parallel Walsh architecture. A straighforward parallelization of the state-of-the-art NN architecture is extended with a cross-domain Knowledge Distillation pre-training method to achieve linearization performance on par with the quadrature implementation. This result paves the way for the entire baseband processing chain to be adapted into ultra-high bandwidth, low-power Walsh transceivers.

eess.SP↗