Pasar al contenido principal

COMUNICACIONES 6G Y SENSADO PARA REDES INALAMBRICAS DETERMINISTAS

PID2022-138648OB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 22
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Use of Attention Maps to Enrich Discriminability in Deep Learning Prediction Models Using Longitudinal Data from Electronic Health Records

  • Carrasco-Ribelles, Lucía Amalia|||0000-0001-9263-1747
  • Cabrera-Bean, Margarita|||0000-0001-9058-3825
  • Llanes-Jurado, Jose|||0000-0001-6778-5912
  • Violán, Concepció|||0000-0003-3309-5360
Featured Application: A better discrimination in a prediction model does not imply a better interpretability. In healthcare, where transparency is crucial, both discriminability and interpretability should be checked before stating that a new model is better. Background: In predictive modelling, particularly in fields such as healthcare, the importance of understanding the model's behaviour rivals, if not surpasses, that of discriminability. To this end, attention mechanisms have been included in deep learning models for years. However, when comparing different models, the one with the best discriminability is usually chosen without considering the clinical plausibility of their predictions. Objective: In this work several attention-based deep learning architectures with increasing degrees of complexity were designed and compared aiming to study the balance between discriminability and plausibility with architecture complexity when working with longitudinal data from Electronic Health Records (EHRs). Methods: We developed four deep learning-based architectures with attention mechanisms that were progressively more complex to handle longitudinal data from EHRs. We evaluated their discriminability and resulting attention maps and compared them amongst architectures and different input processing approaches. We trained them on 10 years of data from EHRs from Catalonia (Spain) and evaluated them using a 5-fold cross-validation to predict 1-year all-cause mortality in a subsample of 500,000 people over 65 years of age. Results: Generally, the simplest architectures led to the best overall discriminability, slightly decreasing with complexity by up to 8.7%. However, the attention maps resulting from the simpler architectures were less informative and less clinically plausible compared to those from more complex architectures. Moreover, the latter could give attention weights both in the time and feature domains. Conclusions: Our results suggest that discriminability and more informative and clinically plausible attention maps do not always go together. Given the preferences within the healthcare field for enhanced explainability, establishing a balance with discriminability is imperative.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Development of Attention-based Prediction Models for All-cause Mortality, Home Care Need, and Nursing Home Admission in Ageing Adults in Spain Using Longitudinal Electronic Health Record Data

  • Carrasco-Ribelles, Lucía A
  • Cabrera-Bean, Margarita|||0000-0001-9058-3825
  • Khalid, Sara|||0000-0002-2845-5731
  • Roso-Llorach, Albert|||0000-0002-9264-0405
  • Violán, Concepció|||0000-0003-3309-5360
The online version contains supplementary material available at 10.1007/s10916-024-02138-z.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Use of Attention Maps to Enrich Discriminability in Deep Learning Prediction Models Using Longitudinal Data from Electronic Health Records

  • Carrasco-Ribelles, Lucía Amalia
  • Cabrera-Bean, Margarita
  • Llanes-Jurado, José
  • Violán, Concepcion
[EN] Featured Application A better discrimination in a prediction model does not imply a better interpretability. In healthcare, where transparency is crucial, both discriminability and interpretability should be checked before stating that a new model is better.Abstract Background: In predictive modelling, particularly in fields such as healthcare, the importance of understanding the model's behaviour rivals, if not surpasses, that of discriminability. To this end, attention mechanisms have been included in deep learning models for years. However, when comparing different models, the one with the best discriminability is usually chosen without considering the clinical plausibility of their predictions. Objective: In this work several attention-based deep learning architectures with increasing degrees of complexity were designed and compared aiming to study the balance between discriminability and plausibility with architecture complexity when working with longitudinal data from Electronic Health Records (EHRs). Methods: We developed four deep learning-based architectures with attention mechanisms that were progressively more complex to handle longitudinal data from EHRs. We evaluated their discriminability and resulting attention maps and compared them amongst architectures and different input processing approaches. We trained them on 10 years of data from EHRs from Catalonia (Spain) and evaluated them using a 5-fold cross-validation to predict 1-year all-cause mortality in a subsample of 500,000 people over 65 years of age. Results: Generally, the simplest architectures led to the best overall discriminability, slightly decreasing with complexity by up to 8.7%. However, the attention maps resulting from the simpler architectures were less informative and less clinically plausible compared to those from more complex architectures. Moreover, the latter could give attention weights both in the time and feature domains. Conclusions: Our results suggest that discriminability and more informative and clinically plausible attention maps do not always go together. Given the preferences within the healthcare field for enhanced explainability, establishing a balance with discriminability is imperative., This work was supported by a research grant from the Carlos III Institute of Health, Ministry of Economy and Competitiveness (Spain), awarded on the 2019 call under the Health Strategy Action 2013-2016, within the National Research Programme oriented to Societal Challenge and the Technical, Scientific and Innovation Research National Plan 2013-2016, (reference PI19/00535), and the PFIS Grant FI20/00040, co-funded with European Union ERDF (European Regional Development Fund) funds. This work has also been funded through project 6-SENSES (PID2022-138648OB-I00) funded by MCIN/AEI/10.13039/501100011033 and "ERDF A way of making Europe", EU. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Deep learning-based UWB-IMU data fusion for indoor positioning in industrial scenario

  • Muthineni, Karthik|||0000-0002-8827-2013
  • Artemenko, Alexander
  • Vidal Manzano, José|||0000-0002-1985-2065
  • Nájar Martón, Montserrat|||0000-0003-3507-5689
  • Catalán Cid, Marisa
  • Paradells Aspas, Josep|||0000-0003-4185-2202
Accurate and precise wireless infrastructure-based positioning systems become crucial as industries move towards flexible, portable, and autonomous transportation systems such as Automated Guided Vehicles (AGVs). Multipath-dominant dynamic environments like industries present significant challenges for wireless signal propagation and affect wireless positioning accuracy due to the interplay of reflected signals from obstacles. The achievable indoor positioning accuracy of the target AGV can be enhanced by fusing the measurements from the wireless infrastructure with the target's onboard sensor data. Nevertheless, the lack of correspondence between the wireless infrastructure and the target's onboard sensors causes the measurements from these two systems to arrive at irregular time steps. Using asynchronous measurements in the data fusion process can degrade the overall positioning accuracy of the target AGV. This paper proposes a novel deep learning-based data fusion approach to deal with asynchronous measurements from the wireless infrastructure Ultra-Wideband (UWB) and the target's onboard Inertial Measurement Unit (IMU) sensor to achieve enhanced positioning accuracy of the target AGV. In particular, a two-stage cascaded Deep Neural Network (DNN) is proposed to deal with the asynchronized measurements from UWB and IMU sensors. The first stage of the DNN is used to obtain the initial position estimate of the AGV by processing the measurements from UWB. Subsequently, the second stage of the DNN fuses the initial position estimate of the AGV with the IMU sensor data to obtain the final enhanced position estimate. The proposed approach is validated with real-world experiments in an indoor industrial scenario using UWB technology in channel 2 (3.7-4.2 GHz) and an IMU sensor placed on an AGV. Moreover, the achievable positioning accuracy and the computational runtime to provide the position estimates with the proposed approach are analyzed. The experimental results show that the proposed approach achieves a mean absolute error of less than 10 cm, outperforming the considered baseline methods, Extended Kalman Filter (EKF) and Long Short-Term Memory (LSTM)., The work of Josep Paradells was supported in part by the Spanish MCIU/AEI/10.13039/501100011033/FEDER/UE through Project PID2023-146378NB-I00 and in part by the Secretaria d’Universitats i Recerca del departament d’Empresa i Coneixement de la Generalitat de Catalunya under Grant 2021 SGR 00330. This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Programme through the Marie Sklodowska-Curie under Grant 956670, in part by Project 6-SENSES under Grant PID2022-138648OB-I00 funded by MCIN/AEI/10.13039/501100011033, and in part by ERDF A way of making Europe., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Contactless acquisition and decoupling of respiratory and cardiac signals using a 122 GHz FMCW radar

  • Miró Mezquita, Laura|||0009-0000-1524-2940
  • Wu, Ruochen|||0000-0003-0852-424X
  • Aguasca Solé, Alberto|||0000-0003-2079-4322
  • Broquetas Ibars, Antoni|||0000-0001-9801-9145
  • Garcia Garcia, Cosme
  • Estrada Cuxart, Oriol
  • Nájar Martón, Montserrat|||0000-0003-3507-5689
This paper presents a contactless method for the simultaneous monitoring of heart rate (HR) and respiratory rate (RR) using a Frequency Modulated Continuous Wave (FMCW) radar operating at 122.5 GHz. To address the challenges posed by spectral overlap and interference between cardiac and respiratory components, we introduce a signal separation and estimation framework based on Maximum Likelihood Estimation (MLE) combined with an orthogonal projection technique. The approach models the thoracic displacement captured by the radar as the superposition of periodic sources and applies spectral projection to isolate the fundamental frequencies and their harmonics. Theoretical performance is assessed through the derivation of the Cramér-Rao Lower Bound (CRLB) and extensive Monte Carlo simulations under varying SNR and sample size conditions. Experimental validation was conducted on 23 healthy volunteers, each providing two 20 second recordings, using a clinical-grade reference monitor. The method achieves high estimation accuracy, with a mean absolute error of 0.69 bpm for HR and 0.33 bpm for RR. The algorithm is capable of reconstructing the cardiac pulse waveform while preserving key morphological features such as the systolic peak and dicrotic notch. Furthermore, the use of the projection technique further enhanced estimation accuracy under nonphysiological conditions, including both elevated and reduced rates. These findings demonstrate the potential of the proposed method as a reliable tool for contactless monitoring of vital signs and support its future integration into biomedical applications., This work was supported by the Industrial Doctorates Plan of the Department of Research and Universities of the Generalitat de Catalunya, and is part of the I+D+i project 6-SENSES (PID2022-138648OB-I00) funded by MICIU/AEI/10.13039/501100011033 and ERDF/EU. It is also supported by the Spanish MCIN project PID2020-117303GB-C21, funded by AEI/10.13039/501100011033, and by the China Scholarship Council (CSC) under Grant 202208390068., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

PosGNN: A graph neural network based multimodal data fusion for indoor positioning in industrial Non-Line-of-Sight scenarios

  • Muthineni, Karthik|||0000-0002-8827-2013
  • Artemenko, Alexander
  • Abode, Daniel
  • Vidal Manzano, José|||0000-0002-1985-2065
  • Nájar Martón, Montserrat|||0000-0003-3507-5689
In industrial environments, the wireless infrastructure is functional for offering services such as communication and positioning of industrial assets. However, the frequently occurring Non-Line-of-Sight (NLoS) conditions in industrial scenarios cause the wireless receiver to have positional information from a limited and varying number of wireless transmitters between consecutive time steps, leading to ambiguities in wireless infrastructure-based positioning. In this paper, we propose PosGNN, a novel data fusion solution based on the Graph Neural Network (GNN) approach that allows us to estimate the position of the User Equipment (UE) by fusing the positional information from the available wireless transmitters at each time step with the UE sensor technology. The performance of the proposed method is assessed using an experimental setup of Ultra-Wideband (UWB) technology as wireless infrastructure at 3.7-4.2GHz frequency band, the Inertial Measurement Unit (IMU) as UE-side sensor, and the Automated Guided Vehicle (AGV) as the target UE to be positioned. The experimental results demonstrate the exceptional performance of our approach over the conventional model-based approach, Extended Kalman Filter (EKF), and the data-driven approach, Deep Neural Network (DNN), achieving an average positioning error of less than 15cm in harsh industrial environments., This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Programme through the Marie Sklodowska-Curie under Grant Agreement 956670 and in part by MCIN/AEI/ 10.13039/501100011033 and ERDF A way of making Europe as part of Project 6-SENSES under Grant PID2022-138648OB-I00., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Robust design of reconfigurable intelligent surfaces for parameter estimation in MTC

  • Liesegang Maria, Sergi|||0000-0002-7806-4755
  • Pascual Iserte, Antonio|||0000-0001-5596-2029
  • Muñoz Medina, Olga|||0000-0002-8739-7068
This paper introduces a reconfigurable intelligent surface (RIS) to support parameter estimation in machine-type communications (MTC). We focus on a network where single-antenna sensors transmit spatially correlated measurements to a multiple-antenna collector node (CN) via non-orthogonal multiple access. We propose an estimation scheme based on the minimum mean square error (MMSE) criterion. We also integrate successive interference cancelation (SIC) at the receiver to mitigate communication failures in noisy and interference-prone channels under the finite blocklength (FBL) regime. Moreover, recognizing the importance of channel state information (CSI), we explore various methodologies for its acquisition at the CN. We statistically design the RIS configuration and SIC decoding order to minimize estimation error while accounting for channel temporal variations and short-packet lengths. To mirror practical systems, we incorporate the detrimental effects of FBL communication and imperfect CSI errors in our analysis. Simulations demonstrate that larger reflecting surfaces lead to smaller MSEs and underscore the importance of selecting an appropriate decoding order for accuracy and ultimate performance., This work was supported in part by the project 6-SENSES under the grant PID2022-138648OB-I00, funded by MCIN/ AEI/10.13039/501100011033 and FEDER-UE, ERDF-EU “A way of making Europe”; and the scholarship FPI under the grant BES-2017-079,994, funded by the Spanish Ministry of Science, Innovation, and Universities., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Use of attention maps to enrich discriminability in deep learning prediction models using longitudinal data from electronic health records

  • Carrasco Ribelles, Lucía Amalia|||0000-0001-9263-1747
  • Cabrera-Bean, Margarita|||0000-0001-9058-3825
  • Llanes Jurado, José
  • Violán Fors, Concepción
Background: In predictive modelling, particularly in fields such as healthcare, the importance of understanding the model’s behaviour rivals, if not surpasses, that of discriminability. To this end, attention mechanisms have been included in deep learning models for years. However, when comparing different models, the one with the best discriminability is usually chosen without considering the clinical plausibility of their predictions. Objective: In this work several attention-based deep learning architectures with increasing degrees of complexity were designed and compared aiming to study the balance between discriminability and plausibility with architecture complexity when working with longitudinal data from Electronic Health Records (EHRs). Methods: We developed four deep learning-based architectures with attention mechanisms that were progressively more complex to handle longitudinal data from EHRs. We evaluated their discriminability and resulting attention maps and compared them amongst architectures and different input processing approaches. We trained them on 10 years of data from EHRs from Catalonia (Spain) and evaluated them using a 5-fold cross-validation to predict 1-year all-cause mortality in a subsample of 500,000 people over 65 years of age. Results: Generally, the simplest architectures led to the best overall discriminability, slightly decreasing with complexity by up to 8.7%. However, the attention maps resulting from the simpler architectures were less informative and less clinically plausible compared to those from more complex architectures. Moreover, the latter could give attention weights both in the time and feature domains. Conclusions: Our results suggest that discriminability and more informative and clinically plausible attention maps do not always go together. Given the preferences within the healthcare field for enhanced explainability, establishing a balance with discriminability is imperative., This work was supported by a research grant from the Carlos III Institute of Health, Ministry of Economy and Competitiveness (Spain), awarded on the 2019 call under the Health Strategy Action 2013–2016, within the National Research Programme oriented to Societal Challenge and the Technical, Scientific and Innovation Research National Plan 2013–2016, (reference PI19/00535), and the PFIS Grant FI20/00040, co-funded with European Union ERDF (European Regional Development Fund) funds. This work has also been funded through project 6-SENSES (PID2022-138648OB-I00) funded by MCIN/AEI/10.13039/501100011033 and “ERDF A way of making Europe”, EU., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Development of attention-based prediction models for all-cause mortality, home care need, and nursing home admission in ageing adults in Spain using longitudinal electronic health record data

  • Carrasco Ribelles, Lucía Amalia|||0000-0001-9263-1747
  • Cabrera-Bean, Margarita|||0000-0001-9058-3825
  • Khalid, Sara
  • Roso Llorach, Albert
  • Violán Fors, Concepción
Predicting health-related outcomes can help with proactive healthcare planning and resource management. This is especially important on the older population, an age group growing in the coming decades. Considering longitudinal rather than cross-sectional information from primary care electronic health records (EHRs) can contribute to more informed predictions. In this work, we developed prediction models using longitudinal EHRs to inform resource allocation. In this study, we developed deep-learning-based prognostic models to predict 1-year and 5-year all-cause mortality, nursing home admission, and home care need in people over 65 years old using all the longitudinal information from EHRs. The models included attention mechanisms to increase their transparency. EHRs were drawn from SIDIAP (primary care, Catalonia (Spain)) from 2010-2019. Performance on the test set was compared to that from baseline models using cross-sectional one-year history only. Data from 1,456,052 individuals over 65 years old were considered. Cohen’s kappa obtained using longitudinal data was 3.4-fold (1-year all-cause mortality), 10.3-fold (5-year all-cause mortality), 1.1-fold (5-year nursing home admission), and 1.2-fold (5-year home care need) higher than that obtained by the one-year history baseline models. Our models performed better than those not considering longitudinal data, especially when predicting further into the future. However, nursing home admission and home care need in the long term were harder to predict, suggesting their dependence on more abrupt changes. The attention maps helped to understand the predictions, enhancing model transparency. These prediction models can contribute to improve resource allocation in the general population of aging adults., The project received a research grant from the Carlos III Institute of Health, Ministry of Economy and Competitiveness (Spain), awarded on the 2019 call under the Health Strategy Action 2013-2016, within the National Research Programme oriented to Societal Challenges, within the Technical, Scientific, and Innovation Research National Plan 2013-2016, (reference PI19/00535), and the PFIS Grant FI20/00040, co-funded with European Union ERDF (European Regional Development Fund) funds. This work has been funded through project 6-SENSES (PID2022-138648OB-I00) funded by MCIN/AEI/10.13039/501100011033 and “ERDF A way of making Europe”, EU. The funders had no role in the study design, data analysis, or writing of this work., Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Design of RIS-aided mMTC+ networks for rate maximization under the finite blocklength regime with imperfect channel knowledge

  • Liesegang, Sergi
  • Pascual Iserte, Antonio|||0000-0001-5596-2029
  • Muñoz Medina, Olga|||0000-0002-8739-7068
  • Zappone, Alessio
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Within the context of massive machine-type communications+, reconfigurable intelligent surfaces (RISs) represent a promising technology to boost system performance in scenarios with poor channel conditions. Considering single-antenna sensors transmitting short data packets to a multiple-antenna collector node, we introduce and design an RIS to maximize the weighted sum rate (WSR) of the system working in the finite blocklength regime. Due to the large number of reflecting elements and their passive nature, channel estimation errors may occur. In this letter, we then propose a robust RIS optimization to combat such a detrimental issue. Based on concave bounds and approximations, the nonconvex WSR problem for the RIS response is addressed via successive convex optimization (SCO). Numerical experiments validate the performance and complexity of the SCO solutions., The work of S. Liesegang, A. Pascual-Iserte, and O. Munoz is part of the I+D+i project 6-SENSES (PID2022-138648OB-I00), funded by MI- CIU/AEI/10.13039/501100011033 and ERDF/EU, Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Uplink and downlink slice-aware OFDMA resource allocation for smart factory networks

  • Ochonu, Regina
  • Vidal Manzano, José|||0000-0002-1985-2065
  • Bhatia, Gurjot Singh
  • Corre, Yoann
Smart factories require wireless networks capable of supporting diverse applications with stringent and heterogeneous quality of service (QoS) demands. Network slicing enables this by virtualizing resources into isolated slices optimized for specific service types. To effectively manage scarce radio resources and ensure seamless support for mixed-traffic industrial users, this paper proposes a suite of slice-aware resource allocation (RA) frameworks encompassing power and subchannel (SC) allocation for both uplink (UL) and downlink (DL) in industrial time-division duplexing (TDD)-orthogonal frequency division multiple access (OFDMA) networks. We transform diverse QoS constraints—latency, reliability, jitter, and throughput—into unified rate expressions enabling tractable convex optimization across three slice types: capacity limited (CL) for best-effort traffic, ultra-reliable low-latency communication (URLLC) for mission-critical control, and time sensitive (TS) for deterministic periodic traffic. The framework incorporates dynamic TDD adaptation for asymmetric traffic patterns and admission control to manage congestion. The effectiveness of the proposed algorithms in reducing energy consumption while guaranteeing slice-specific QoS is validated using realistic industrial ray-tracing channels and extensive simulations., This work was supported in part by the 5GSmartFact Project funded by European Union’s H2020 Research and Innovation Program through the Marie Skłodowska-Curie under Grant 956670 and in part by the Project 6-SENSES funded by MCIN/AEI/10.13039/501100011033 under Grant PID2022-138648OB-I00., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Robust biometric information sensing with mmWave radar system-on-chip

  • Wu, Ruochen|||0000-0003-0852-424X
  • Miró Mezquita, Laura|||0009-0000-1524-2940
  • Aguasca Solé, Alberto|||0000-0003-2079-4322
  • Nájar Martón, Montserrat|||0000-0003-3507-5689
  • Broquetas Ibars, Antoni|||0000-0001-9801-9145
Vital information wireless sensing is an interesting alternative to conventional techniques based on contact sensors. The evolution of radar technologies enables the proposal of cost-effective and compact radar sensors designed for diverse health monitoring, diagnostics, and Internet of Medical Things (IoMT) applications. It is possible to observe respiratory rate (RR), heart rate (HR), cardiac rhythm, blood pressure waveform (BPW), and emerging biometrics from the phase of radar echo signals. However, recognition and separation of the signals of interest from other interfering motion is a challenge, taking into account the diversity of signal patterns depending on subjects, health and observation conditions. In this context, we propose a novel wireless vital sensing system with a self-designed 120 GHz Frequency-Modulated Continuous Wave (FMCW) Radar. The developed sensor, based on a Radar System-on-Chip (RSoC), uses a real-time Repetitive Waveform Adaptive Matched Filter (RWAMF) maximizing Signal-to-Interference-plus-Noise Ratio (SINR) for reliable cardiac rhythm and BPW observations. The radar design has been optimized for vital sensing with a very short wavelength providing excellent sensitivity to micro-motion and a centimetric range and transversal resolutions to reject clutter and unwanted motions. The superior performance of our solution has been validated and evaluated experimentally on different subjects and measurement conditions with our own acquired vital signal database., This work was supported by the Spanish MCIN funds including Excelencia Maria de Maeztu MDM-2016-0600 and projects PID2020-117303GBC21, PID2022-138648OB-I00, and PID2024-161188OB-C21 funded by MCIN/AEI/10.13039/501100011033 and the European Regional Development Fund FEDER, UE, the China Scholarship Council (CSC) under Grant 202208390068, and the Industrial Doctorates Plan of the Department of Research and Universities of the Generalitat de Catalunya., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

RIS-assisted multiuser MISO transmission and the impact of imperfect channel estimation

  • Moreno Locubiche, Ainna Yue|||0009-0006-4237-7131
  • Vidal Manzano, José|||0000-0002-1985-2065
  • Pascual Iserte, Antonio|||0000-0001-5596-2029
  • Muñoz Medina, Olga|||0000-0002-8739-7068
This paper proposes the joint design of reconfigurable intelligent surfaces (RIS) and zeroforcing (ZF) precoding for the downlink (DL) multiuser multiple-input single-output (MU-MISO) setup in millimeter-wave (mmWave) bands, where ZF is particularly attractive due to its ability to suppress inter-user interference by exploiting the large antenna arrays and sparse directional channels characteristic of mmWave systems. This ensures efficient spatial multiplexing with manageable complexity, making ZF a practical and in modern 5G/6G deployments. However, a careful design is necessary to overcome potential rank deficiency in the channel matrix. For the MU-MISO case, rank deficiency may arise if users exhibit significantly different channel gains or if, being in far-field, they are aligned with the position of the transmitter. On the other hand, the deployment of a RIS introduces artificial scattering which can shape the radio environment to address those situations. We explore the joint design under perfect channel knowledge, assess the impact of imperfect channel estimation on the bit error rate (BER) and propose a robust design of pilot transmissions that equalizes multiuser interference across users in the presence of channel errors in the precoder design. This evaluation shows the advantages of optimized RIS-aided ZF MU-MISO communication for the DL of wireless systems., This work was supported by the Project 6-SENSES funded by MICIU/AEI/10.13039/501100011033 and ERDF/EU under Grant PID2022-138648OB-I00.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Use of attention maps to enrich discriminability in deep learning prediction models using longitudinal data from electronic health records

  • Carrasco Ribelles, Lucía Amalia
  • Cabrera-Bean, Margarita
  • Llanes Jurado, José
  • Violán Fors, Concepción
Background: In predictive modelling, particularly in fields such as healthcare, the importance of understanding the model’s behaviour rivals, if not surpasses, that of discriminability. To this end, attention mechanisms have been included in deep learning models for years. However, when comparing different models, the one with the best discriminability is usually chosen without considering the clinical plausibility of their predictions. Objective: In this work several attention-based deep learning architectures with increasing degrees of complexity were designed and compared aiming to study the balance between discriminability and plausibility with architecture complexity when working with longitudinal data from Electronic Health Records (EHRs). Methods: We developed four deep learning-based architectures with attention mechanisms that were progressively more complex to handle longitudinal data from EHRs. We evaluated their discriminability and resulting attention maps and compared them amongst architectures and different input processing approaches. We trained them on 10 years of data from EHRs from Catalonia (Spain) and evaluated them using a 5-fold cross-validation to predict 1-year all-cause mortality in a subsample of 500,000 people over 65 years of age. Results: Generally, the simplest architectures led to the best overall discriminability, slightly decreasing with complexity by up to 8.7%. However, the attention maps resulting from the simpler architectures were less informative and less clinically plausible compared to those from more complex architectures. Moreover, the latter could give attention weights both in the time and feature domains. Conclusions: Our results suggest that discriminability and more informative and clinically plausible attention maps do not always go together. Given the preferences within the healthcare field for enhanced explainability, establishing a balance with discriminability is imperative., This work was supported by a research grant from the Carlos III Institute of Health, Ministry of Economy and Competitiveness (Spain), awarded on the 2019 call under the Health Strategy Action 2013–2016, within the National Research Programme oriented to Societal Challenge and the Technical, Scientific and Innovation Research National Plan 2013–2016, (reference PI19/00535), and the PFIS Grant FI20/00040, co-funded with European Union ERDF (European Regional Development Fund) funds. This work has also been funded through project 6-SENSES (PID2022-138648OB-I00) funded by MCIN/AEI/10.13039/501100011033 and “ERDF A way of making Europe”, EU., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Uplink and downlink slice-aware OFDMA resource allocation for smart factory networks

  • Ochonu, Regina
  • Vidal Manzano, José
  • Bhatia, Gurjot Singh
  • Corre, Yoann
Smart factories require wireless networks capable of supporting diverse applications with stringent and heterogeneous quality of service (QoS) demands. Network slicing enables this by virtualizing resources into isolated slices optimized for specific service types. To effectively manage scarce radio resources and ensure seamless support for mixed-traffic industrial users, this paper proposes a suite of slice-aware resource allocation (RA) frameworks encompassing power and subchannel (SC) allocation for both uplink (UL) and downlink (DL) in industrial time-division duplexing (TDD)-orthogonal frequency division multiple access (OFDMA) networks. We transform diverse QoS constraints—latency, reliability, jitter, and throughput—into unified rate expressions enabling tractable convex optimization across three slice types: capacity limited (CL) for best-effort traffic, ultra-reliable low-latency communication (URLLC) for mission-critical control, and time sensitive (TS) for deterministic periodic traffic. The framework incorporates dynamic TDD adaptation for asymmetric traffic patterns and admission control to manage congestion. The effectiveness of the proposed algorithms in reducing energy consumption while guaranteeing slice-specific QoS is validated using realistic industrial ray-tracing channels and extensive simulations., This work was supported in part by the 5GSmartFact Project funded by European Union’s H2020 Research and Innovation Program through the Marie Skłodowska-Curie under Grant 956670 and in part by the Project 6-SENSES funded by MCIN/AEI/10.13039/501100011033 under Grant PID2022-138648OB-I00., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Development of attention-based prediction models for all-cause mortality, home care need, and nursing home admission in ageing adults in Spain using longitudinal electronic health record data

  • Carrasco Ribelles, Lucía Amalia
  • Cabrera-Bean, Margarita
  • Khalid, Sara
  • Roso Llorach, Albert
  • Violán Fors, Concepción
Predicting health-related outcomes can help with proactive healthcare planning and resource management. This is especially important on the older population, an age group growing in the coming decades. Considering longitudinal rather than cross-sectional information from primary care electronic health records (EHRs) can contribute to more informed predictions. In this work, we developed prediction models using longitudinal EHRs to inform resource allocation. In this study, we developed deep-learning-based prognostic models to predict 1-year and 5-year all-cause mortality, nursing home admission, and home care need in people over 65 years old using all the longitudinal information from EHRs. The models included attention mechanisms to increase their transparency. EHRs were drawn from SIDIAP (primary care, Catalonia (Spain)) from 2010-2019. Performance on the test set was compared to that from baseline models using cross-sectional one-year history only. Data from 1,456,052 individuals over 65 years old were considered. Cohen’s kappa obtained using longitudinal data was 3.4-fold (1-year all-cause mortality), 10.3-fold (5-year all-cause mortality), 1.1-fold (5-year nursing home admission), and 1.2-fold (5-year home care need) higher than that obtained by the one-year history baseline models. Our models performed better than those not considering longitudinal data, especially when predicting further into the future. However, nursing home admission and home care need in the long term were harder to predict, suggesting their dependence on more abrupt changes. The attention maps helped to understand the predictions, enhancing model transparency. These prediction models can contribute to improve resource allocation in the general population of aging adults., The project received a research grant from the Carlos III Institute of Health, Ministry of Economy and Competitiveness (Spain), awarded on the 2019 call under the Health Strategy Action 2013-2016, within the National Research Programme oriented to Societal Challenges, within the Technical, Scientific, and Innovation Research National Plan 2013-2016, (reference PI19/00535), and the PFIS Grant FI20/00040, co-funded with European Union ERDF (European Regional Development Fund) funds. This work has been funded through project 6-SENSES (PID2022-138648OB-I00) funded by MCIN/AEI/10.13039/501100011033 and “ERDF A way of making Europe”, EU. The funders had no role in the study design, data analysis, or writing of this work., Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

PosGNN: A graph neural network based multimodal data fusion for indoor positioning in industrial Non-Line-of-Sight scenarios

  • Muthineni, Karthik
  • Artemenko, Alexander
  • Abode, Daniel
  • Vidal Manzano, José
  • Nájar Martón, Montserrat
In industrial environments, the wireless infrastructure is functional for offering services such as communication and positioning of industrial assets. However, the frequently occurring Non-Line-of-Sight (NLoS) conditions in industrial scenarios cause the wireless receiver to have positional information from a limited and varying number of wireless transmitters between consecutive time steps, leading to ambiguities in wireless infrastructure-based positioning. In this paper, we propose PosGNN, a novel data fusion solution based on the Graph Neural Network (GNN) approach that allows us to estimate the position of the User Equipment (UE) by fusing the positional information from the available wireless transmitters at each time step with the UE sensor technology. The performance of the proposed method is assessed using an experimental setup of Ultra-Wideband (UWB) technology as wireless infrastructure at 3.7-4.2GHz frequency band, the Inertial Measurement Unit (IMU) as UE-side sensor, and the Automated Guided Vehicle (AGV) as the target UE to be positioned. The experimental results demonstrate the exceptional performance of our approach over the conventional model-based approach, Extended Kalman Filter (EKF), and the data-driven approach, Deep Neural Network (DNN), achieving an average positioning error of less than 15cm in harsh industrial environments., This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Programme through the Marie Sklodowska-Curie under Grant Agreement 956670 and in part by MCIN/AEI/ 10.13039/501100011033 and ERDF A way of making Europe as part of Project 6-SENSES under Grant PID2022-138648OB-I00., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Contactless acquisition and decoupling of respiratory and cardiac signals using a 122 GHz FMCW radar

  • Miró Mezquita, Laura
  • Wu, Ruochen
  • Aguasca Solé, Alberto
  • Broquetas Ibars, Antoni
  • Garcia Garcia, Cosme
  • Estrada Cuxart, Oriol
  • Nájar Martón, Montserrat
This paper presents a contactless method for the simultaneous monitoring of heart rate (HR) and respiratory rate (RR) using a Frequency Modulated Continuous Wave (FMCW) radar operating at 122.5 GHz. To address the challenges posed by spectral overlap and interference between cardiac and respiratory components, we introduce a signal separation and estimation framework based on Maximum Likelihood Estimation (MLE) combined with an orthogonal projection technique. The approach models the thoracic displacement captured by the radar as the superposition of periodic sources and applies spectral projection to isolate the fundamental frequencies and their harmonics. Theoretical performance is assessed through the derivation of the Cramér-Rao Lower Bound (CRLB) and extensive Monte Carlo simulations under varying SNR and sample size conditions. Experimental validation was conducted on 23 healthy volunteers, each providing two 20 second recordings, using a clinical-grade reference monitor. The method achieves high estimation accuracy, with a mean absolute error of 0.69 bpm for HR and 0.33 bpm for RR. The algorithm is capable of reconstructing the cardiac pulse waveform while preserving key morphological features such as the systolic peak and dicrotic notch. Furthermore, the use of the projection technique further enhanced estimation accuracy under nonphysiological conditions, including both elevated and reduced rates. These findings demonstrate the potential of the proposed method as a reliable tool for contactless monitoring of vital signs and support its future integration into biomedical applications., This work was supported by the Industrial Doctorates Plan of the Department of Research and Universities of the Generalitat de Catalunya, and is part of the I+D+i project 6-SENSES (PID2022-138648OB-I00) funded by MICIU/AEI/10.13039/501100011033 and ERDF/EU. It is also supported by the Spanish MCIN project PID2020-117303GB-C21, funded by AEI/10.13039/501100011033, and by the China Scholarship Council (CSC) under Grant 202208390068., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Robust biometric information sensing with mmWave radar system-on-chip

  • Wu, Ruochen
  • Miró Mezquita, Laura
  • Aguasca Solé, Alberto
  • Nájar Martón, Montserrat
  • Broquetas Ibars, Antoni
Vital information wireless sensing is an interesting alternative to conventional techniques based on contact sensors. The evolution of radar technologies enables the proposal of cost-effective and compact radar sensors designed for diverse health monitoring, diagnostics, and Internet of Medical Things (IoMT) applications. It is possible to observe respiratory rate (RR), heart rate (HR), cardiac rhythm, blood pressure waveform (BPW), and emerging biometrics from the phase of radar echo signals. However, recognition and separation of the signals of interest from other interfering motion is a challenge, taking into account the diversity of signal patterns depending on subjects, health and observation conditions. In this context, we propose a novel wireless vital sensing system with a self-designed 120 GHz Frequency-Modulated Continuous Wave (FMCW) Radar. The developed sensor, based on a Radar System-on-Chip (RSoC), uses a real-time Repetitive Waveform Adaptive Matched Filter (RWAMF) maximizing Signal-to-Interference-plus-Noise Ratio (SINR) for reliable cardiac rhythm and BPW observations. The radar design has been optimized for vital sensing with a very short wavelength providing excellent sensitivity to micro-motion and a centimetric range and transversal resolutions to reject clutter and unwanted motions. The superior performance of our solution has been validated and evaluated experimentally on different subjects and measurement conditions with our own acquired vital signal database., This work was supported by the Spanish MCIN funds including Excelencia Maria de Maeztu MDM-2016-0600 and projects PID2020-117303GBC21, PID2022-138648OB-I00, and PID2024-161188OB-C21 funded by MCIN/AEI/10.13039/501100011033 and the European Regional Development Fund FEDER, UE, the China Scholarship Council (CSC) under Grant 202208390068, and the Industrial Doctorates Plan of the Department of Research and Universities of the Generalitat de Catalunya., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Design of RIS-aided mMTC+ networks for rate maximization under the finite blocklength regime with imperfect channel knowledge

  • Liesegang, Sergi
  • Pascual Iserte, Antonio
  • Muñoz Medina, Olga
  • Zappone, Alessio
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Within the context of massive machine-type communications+, reconfigurable intelligent surfaces (RISs) represent a promising technology to boost system performance in scenarios with poor channel conditions. Considering single-antenna sensors transmitting short data packets to a multiple-antenna collector node, we introduce and design an RIS to maximize the weighted sum rate (WSR) of the system working in the finite blocklength regime. Due to the large number of reflecting elements and their passive nature, channel estimation errors may occur. In this letter, we then propose a robust RIS optimization to combat such a detrimental issue. Based on concave bounds and approximations, the nonconvex WSR problem for the RIS response is addressed via successive convex optimization (SCO). Numerical experiments validate the performance and complexity of the SCO solutions., The work of S. Liesegang, A. Pascual-Iserte, and O. Munoz is part of the I+D+i project 6-SENSES (PID2022-138648OB-I00), funded by MI- CIU/AEI/10.13039/501100011033 and ERDF/EU, Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Deep learning-based UWB-IMU data fusion for indoor positioning in industrial scenario

  • Muthineni, Karthik
  • Artemenko, Alexander
  • Vidal Manzano, José
  • Nájar Martón, Montserrat
  • Catalán Cid, Marisa
  • Paradells Aspas, Josep
Accurate and precise wireless infrastructure-based positioning systems become crucial as industries move towards flexible, portable, and autonomous transportation systems such as Automated Guided Vehicles (AGVs). Multipath-dominant dynamic environments like industries present significant challenges for wireless signal propagation and affect wireless positioning accuracy due to the interplay of reflected signals from obstacles. The achievable indoor positioning accuracy of the target AGV can be enhanced by fusing the measurements from the wireless infrastructure with the target's onboard sensor data. Nevertheless, the lack of correspondence between the wireless infrastructure and the target's onboard sensors causes the measurements from these two systems to arrive at irregular time steps. Using asynchronous measurements in the data fusion process can degrade the overall positioning accuracy of the target AGV. This paper proposes a novel deep learning-based data fusion approach to deal with asynchronous measurements from the wireless infrastructure Ultra-Wideband (UWB) and the target's onboard Inertial Measurement Unit (IMU) sensor to achieve enhanced positioning accuracy of the target AGV. In particular, a two-stage cascaded Deep Neural Network (DNN) is proposed to deal with the asynchronized measurements from UWB and IMU sensors. The first stage of the DNN is used to obtain the initial position estimate of the AGV by processing the measurements from UWB. Subsequently, the second stage of the DNN fuses the initial position estimate of the AGV with the IMU sensor data to obtain the final enhanced position estimate. The proposed approach is validated with real-world experiments in an indoor industrial scenario using UWB technology in channel 2 (3.7-4.2 GHz) and an IMU sensor placed on an AGV. Moreover, the achievable positioning accuracy and the computational runtime to provide the position estimates with the proposed approach are analyzed. The experimental results show that the proposed approach achieves a mean absolute error of less than 10 cm, outperforming the considered baseline methods, Extended Kalman Filter (EKF) and Long Short-Term Memory (LSTM)., The work of Josep Paradells was supported in part by the Spanish MCIU/AEI/10.13039/501100011033/FEDER/UE through Project PID2023-146378NB-I00 and in part by the Secretaria d’Universitats i Recerca del departament d’Empresa i Coneixement de la Generalitat de Catalunya under Grant 2021 SGR 00330. This work was supported in part by the European Union’s Horizon 2020 Research and Innovation Programme through the Marie Sklodowska-Curie under Grant 956670, in part by Project 6-SENSES under Grant PID2022-138648OB-I00 funded by MCIN/AEI/10.13039/501100011033, and in part by ERDF A way of making Europe., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Robust design of reconfigurable intelligent surfaces for parameter estimation in MTC

  • Liesegang Maria, Sergi
  • Pascual Iserte, Antonio
  • Muñoz Medina, Olga
This paper introduces a reconfigurable intelligent surface (RIS) to support parameter estimation in machine-type communications (MTC). We focus on a network where single-antenna sensors transmit spatially correlated measurements to a multiple-antenna collector node (CN) via non-orthogonal multiple access. We propose an estimation scheme based on the minimum mean square error (MMSE) criterion. We also integrate successive interference cancelation (SIC) at the receiver to mitigate communication failures in noisy and interference-prone channels under the finite blocklength (FBL) regime. Moreover, recognizing the importance of channel state information (CSI), we explore various methodologies for its acquisition at the CN. We statistically design the RIS configuration and SIC decoding order to minimize estimation error while accounting for channel temporal variations and short-packet lengths. To mirror practical systems, we incorporate the detrimental effects of FBL communication and imperfect CSI errors in our analysis. Simulations demonstrate that larger reflecting surfaces lead to smaller MSEs and underscore the importance of selecting an appropriate decoding order for accuracy and ultimate performance., This work was supported in part by the project 6-SENSES under the grant PID2022-138648OB-I00, funded by MCIN/ AEI/10.13039/501100011033 and FEDER-UE, ERDF-EU “A way of making Europe”; and the scholarship FPI under the grant BES-2017-079,994, funded by the Spanish Ministry of Science, Innovation, and Universities., Peer Reviewed, Postprint (published version)