Pablo Manglano-Redondo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Pablo Manglano-Redondo has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Alvaro Paricio-Garcia
Universidad de Alcala Department of Automatica
6 shared publications - Miguel Angel Lopez-Carmona
Universidad de Alcala Department of Automatica
4 shared publications Miguel A. Lopez-Carmona
2 shared publications- Sergio Sierra Arquero
Universidad de Alcala Department of Automatica
2 shared publications Sergio Sierra-Arquero
1 shared publication
Latest Publications
- 26 January 2026
- Published by Emerald Publishing in Engineering Computations
- Vol. 43 (8) , 1-50
Residual dynamic spatio-temporal graph attention network for enhanced urban traffic origin/destination demand calibration
Purpose: The purpose of this paper is to introduce the residual dynamic spatio-temporal graph attention network (RDSTGAT), a novel deep learning architecture designed to address traffic origin-destination (OD) flow calibration. The study aims to accurately estimate the temporal evolution of OD demand matrices using observed sensor data, addressing the limitations of traditional statistical and mathematical models and the lack of datasets for deep learning in this domain. Design/methodology/approach: The research employs a microscopic simulation environment (SUMO) as a digital twin to generate synthetic, empirically shaped datasets for training and validation, thereby overcoming the scarcity of real-world ground-truth OD data. The RDSTGAT architecture improves upon the dynamic spatio-temporal graph attention network (DSTGAT) by encapsulating residual logic within modular ResidualGATv2Conv blocks (integrating GATv2, skip connections and normalization) and replacing GRU layers with long short-term memory units to better capture long-range temporal dependencies. The model is trained using a stochastic demand generator to recover the underlying OD flows that generate observed sensor counts. The RDSTGAT model needs to be trained for each urban scenario, as it captures the structural internal capacity relationships of the city. Findings: RDSTGAT offers high efficiency in deciphering the spatio-temporal patterns in urban traffic flows and stands out by dynamically assessing the relevance of distinct road network segments and their temporal correlations through advanced graph attention mechanisms. RDSTGAT also reduces the impact of data noise, elevating the accuracy of traffic predictions. Experimental results from different urban scenarios and data-acquisition sensors demonstrated high robustness, with minimal error increase (less than 12%) even when up to 70% of traffic sensors were deactivated. Different prediction models and architectures were analyzed, and the baseline DSTGAT model was outperformed by 4.6%. Research limitations/implications: The study currently serves as an algorithmic validation within a controlled digital twin environment driven by synthetic demand profiles. While the demand is empirically shaped using official traffic statistics, external validation against real-world sensor networks and independent OD estimates is reserved for future research phases. In order to capture the internal structural capacity relationships of a city, the RDSTGAT model must be trained separately for each urban scenario. Practical implications: The proposed model enables urban planners and authorities to anticipate traffic demand patterns dynamically, which is essential for optimizing traffic signaling, managing lane preferences and designing efficient low-emission zones. The system is designed to function as an offline or near-real-time module within traffic management systems, ingesting data from existing sensor infrastructure. Social implications: By enabling more accurate traffic calibration and prediction, this research contributes to the development of sustainable, livable cities by mitigating congestion and its associated environmental impacts. Additionally, accurate flow prediction enhances road safety and facilitates more efficient emergency responses by ensuring the availability of effective evacuation routes. Originality/value: This work is original in its specific application of deep learning techniques to the traffic flow calibration problem (OD matrix estimation). Data limitations have been a significant limitation in previous works. The paper presents a reproducible methodology for building calibration models using microscopic simulation and introduces architectural innovations that provide more flexible, robust building blocks for deeper architectures. It provides a fundamental basis for designing urban digital twins.
- 26 January 2026
- Published by Emerald Publishing in Engineering Computations
- Vol. 43 (8) , 1-50
Residual dynamic spatio-temporal graph attention network for enhanced urban traffic origin/destination demand calibration
Purpose: The purpose of this paper is to introduce the residual dynamic spatio-temporal graph attention network (RDSTGAT), a novel deep learning architecture designed to address traffic origin-destination (OD) flow calibration. The study aims to accurately estimate the temporal evolution of OD demand matrices using observed sensor data, addressing the limitations of traditional statistical and mathematical models and the lack of datasets for deep learning in this domain. Design/methodology/approach: The research employs a microscopic simulation environment (SUMO) as a digital twin to generate synthetic, empirically shaped datasets for training and validation, thereby overcoming the scarcity of real-world ground-truth OD data. The RDSTGAT architecture improves upon the dynamic spatio-temporal graph attention network (DSTGAT) by encapsulating residual logic within modular ResidualGATv2Conv blocks (integrating GATv2, skip connections and normalization) and replacing GRU layers with long short-term memory units to better capture long-range temporal dependencies. The model is trained using a stochastic demand generator to recover the underlying OD flows that generate observed sensor counts. The RDSTGAT model needs to be trained for each urban scenario, as it captures the structural internal capacity relationships of the city. Findings: RDSTGAT offers high efficiency in deciphering the spatio-temporal patterns in urban traffic flows and stands out by dynamically assessing the relevance of distinct road network segments and their temporal correlations through advanced graph attention mechanisms. RDSTGAT also reduces the impact of data noise, elevating the accuracy of traffic predictions. Experimental results from different urban scenarios and data-acquisition sensors demonstrated high robustness, with minimal error increase (less than 12%) even when up to 70% of traffic sensors were deactivated. Different prediction models and architectures were analyzed, and the baseline DSTGAT model was outperformed by 4.6%. Research limitations/implications: The study currently serves as an algorithmic validation within a controlled digital twin environment driven by synthetic demand profiles. While the demand is empirically shaped using official traffic statistics, external validation against real-world sensor networks and independent OD estimates is reserved for future research phases. In order to capture the internal structural capacity relationships of a city, the RDSTGAT model must be trained separately for each urban scenario. Practical implications: The proposed model enables urban planners and authorities to anticipate traffic demand patterns dynamically, which is essential for optimizing traffic signaling, managing lane preferences and designing efficient low-emission zones. The system is designed to function as an offline or near-real-time module within traffic management systems, ingesting data from existing sensor infrastructure. Social implications: By enabling more accurate traffic calibration and prediction, this research contributes to the development of sustainable, livable cities by mitigating congestion and its associated environmental impacts. Additionally, accurate flow prediction enhances road safety and facilitates more efficient emergency responses by ensuring the availability of effective evacuation routes. Originality/value: This work is original in its specific application of deep learning techniques to the traffic flow calibration problem (OD matrix estimation). Data limitations have been a significant limitation in previous works. The paper presents a reproducible methodology for building calibration models using microscopic simulation and introduces architectural innovations that provide more flexible, robust building blocks for deeper architectures. It provides a fundamental basis for designing urban digital twins.
- 11 August 2025
- Published by Emerald Publishing in Engineering Computations
- Vol. 43 (7) , 2702-2726
Leveraging enhanced dimensionality reduction techniques for biometric profiling and verification: subspace-adaptive autoencoder vector (SAAV) systems
Purpose: Create extra-small biometrical footprints for face recognition, capable of being contained in low-density QR codes with high recognition accuracy. This would allow for validating connectionless physical assets with direct face image recognition without storing or connecting to external services. Design/methodology/approach: Design of a new architecture of clustered AI-based autoencoders that are trained with large face images datasets. New loss functions are designed using vectorized dimensions. Findings: (1) Accurate dimensionality reduction of face features up to four dimensions for enhanced low-density biometric QR codes; (2) a topology-aware AI-based novel architecture based on multiplexing autoencoders over clusterized data, applied to biometrical face recognition; (3) a case study based on biometrical QR recognition using the SAAV architecture; and (4) an experimental implementation of the case study using a large face dataset. Research limitations/implications: The results are solid, providing a compression rate of 80 times (1/80) over Google’s FaceNet architecture, with 89% of recognition success. It should recall attention not only from the academics but also from the real business as it is a solid improvement with practical application. Practical implications: The technology can be directly transferred to multiple business applications: – transport tickets (plane, train, etc.) – events tickets (concerts, festivals, etc.) – self-contained biometrical stickers for physical assets such as computers, cars, etc. – self-contained personal identifications for emergencies – personal transport cards for logistics and many more. Social implications: It could have a great implication when applied to emergency situations in refugee camps, or hospitals, to create self-identifying bracelets or cross-identifying bracelets for mom’s and babies. Originality/value: The techniques exposed are 100% original.
- 11 August 2025
- Published by Emerald Publishing in Engineering Computations
- Vol. 43 (7) , 2702-2726
Leveraging enhanced dimensionality reduction techniques for biometric profiling and verification: subspace-adaptive autoencoder vector (SAAV) systems
Purpose: Create extra-small biometrical footprints for face recognition, capable of being contained in low-density QR codes with high recognition accuracy. This would allow for validating connectionless physical assets with direct face image recognition without storing or connecting to external services. Design/methodology/approach: Design of a new architecture of clustered AI-based autoencoders that are trained with large face images datasets. New loss functions are designed using vectorized dimensions. Findings: (1) Accurate dimensionality reduction of face features up to four dimensions for enhanced low-density biometric QR codes; (2) a topology-aware AI-based novel architecture based on multiplexing autoencoders over clusterized data, applied to biometrical face recognition; (3) a case study based on biometrical QR recognition using the SAAV architecture; and (4) an experimental implementation of the case study using a large face dataset. Research limitations/implications: The results are solid, providing a compression rate of 80 times (1/80) over Google’s FaceNet architecture, with 89% of recognition success. It should recall attention not only from the academics but also from the real business as it is a solid improvement with practical application. Practical implications: The technology can be directly transferred to multiple business applications: – transport tickets (plane, train, etc.) – events tickets (concerts, festivals, etc.) – self-contained biometrical stickers for physical assets such as computers, cars, etc. – self-contained personal identifications for emergencies – personal transport cards for logistics and many more. Social implications: It could have a great implication when applied to emergency situations in refugee camps, or hospitals, to create self-identifying bracelets or cross-identifying bracelets for mom’s and babies. Originality/value: The techniques exposed are 100% original.
- Open Access
- 15 July 2025
- Published by TIB Open Publishing in SUMO Conference Proceedings
- Vol. 6, 33-50
Spatio-Temporal AI Modeling for Urban Traffic Calibration: A SUMO-Based Approach
Urban traffic management is a critical challenge in modern cities, necessitating innovative solutions to optimize traffic flow and reduce congestion. This research presents the development of an AI engine leveraging spatio-temporal learning techniques for urban traffic calibration. The proposed methodology leverages digital twin scenarios driven by microscopic simulations, which capture detailed vehicle behaviors—including interactions, lane changes, and driver dynamics to provide granular insights into urban traffic patterns. At the core of the AI engine is the Dynamic Spatio-Temporal Graph Attention Network (DSTGAT), a hybrid model that combines multi-head Graph Attention Networks (GATv2) with Long Short-Term Memory (LSTM) networks. DSTGAT exploits the joint spatio-temporal relationships inherent in traffic data by processing sequential snapshots of urban traffic, where each snapshot is represented as a graph with nodes indicating urban zones and edges carrying continuous flow values. The GATv2 layers, enhanced with residual connections and batch normalization, extract robust spatial embeddings, while the LSTM aggregates these embeddings over time to capture dynamic patterns and predict future traffic flows in real-time. The AI engine incorporates an iterative feedback loop that continuously refines the OD demand using synthetic scenarios, improving estimation accuracy across diverse urban environments. Preliminary results show that the DSTGAT‑based framework lowers OD‑estimation error on simulated data, suggesting its usefulness as an input to downstream traffic‑management strategies.
- 15 July 2025
- Published by TIB Open Publishing in SUMO Conference Proceedings
- Vol. 6, 33-50
Open AccessSpatio-Temporal AI Modeling for Urban Traffic Calibration: A SUMO-Based Approach
Urban traffic management is a critical challenge in modern cities, necessitating innovative solutions to optimize traffic flow and reduce congestion. This research presents the development of an AI engine leveraging spatio-temporal learning techniques for urban traffic calibration. The proposed methodology leverages digital twin scenarios driven by microscopic simulations, which capture detailed vehicle behaviors—including interactions, lane changes, and driver dynamics to provide granular insights into urban traffic patterns. At the core of the AI engine is the Dynamic Spatio-Temporal Graph Attention Network (DSTGAT), a hybrid model that combines multi-head Graph Attention Networks (GATv2) with Long Short-Term Memory (LSTM) networks. DSTGAT exploits the joint spatio-temporal relationships inherent in traffic data by processing sequential snapshots of urban traffic, where each snapshot is represented as a graph with nodes indicating urban zones and edges carrying continuous flow values. The GATv2 layers, enhanced with residual connections and batch normalization, extract robust spatial embeddings, while the LSTM aggregates these embeddings over time to capture dynamic patterns and predict future traffic flows in real-time. The AI engine incorporates an iterative feedback loop that continuously refines the OD demand using synthetic scenarios, improving estimation accuracy across diverse urban environments. Preliminary results show that the DSTGAT‑based framework lowers OD‑estimation error on simulated data, suggesting its usefulness as an input to downstream traffic‑management strategies.
- Open Access
- 7 March 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (6) , 2915
Dynamic Low-Emission Zones for Urban Mobility: A Systematic Review
Urban air pollution, particularly from vehicular emissions, poses a significant challenge to public health and environmental sustainability. Low-Emission Zones (LEZs) have emerged as a solution, reducing pollution in high-traffic areas by restricting access to high-emission vehicles. However, most LEZ implementations are static, failing to account for real-time changes in traffic and emissions. This review focuses on dynamic LEZ systems, which are adjusted based on real-time data to optimize emission reduction without disrupting traffic flow. By categorizing LEZ strategies into static, hybrid, and dynamic systems, this study highlights key case studies and technologies, such as traffic simulation tools and sensor networks, that enable these adaptive systems. The review also discusses the challenges and future opportunities in LEZ implementation, emphasizing the need for data-driven approaches to achieve both environmental and mobility goals. This study aims to provide insights for policymakers and researchers seeking to enhance urban air quality management through more flexible, efficient LEZ strategies.
- 7 March 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (6) , 2915
Open AccessDynamic Low-Emission Zones for Urban Mobility: A Systematic Review
Urban air pollution, particularly from vehicular emissions, poses a significant challenge to public health and environmental sustainability. Low-Emission Zones (LEZs) have emerged as a solution, reducing pollution in high-traffic areas by restricting access to high-emission vehicles. However, most LEZ implementations are static, failing to account for real-time changes in traffic and emissions. This review focuses on dynamic LEZ systems, which are adjusted based on real-time data to optimize emission reduction without disrupting traffic flow. By categorizing LEZ strategies into static, hybrid, and dynamic systems, this study highlights key case studies and technologies, such as traffic simulation tools and sensor networks, that enable these adaptive systems. The review also discusses the challenges and future opportunities in LEZ implementation, emphasizing the need for data-driven approaches to achieve both environmental and mobility goals. This study aims to provide insights for policymakers and researchers seeking to enhance urban air quality management through more flexible, efficient LEZ strategies.
- Open Access
- 22 February 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 172
Analysis and evaluation of autoencoder-driven dimensionality reduction for face recognition pipelines
- 22 February 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 172
Open AccessAnalysis and evaluation of autoencoder-driven dimensionality reduction for face recognition pipelines
- Open Access
- 17 July 2024
- Published by TIB Open Publishing in SUMO Conference Proceedings
- Vol. 5, 247-268
Optimized Design of Low Emission Zones in SUMO
Focusing on the critical challenge of air pollution in urban areas, primarily caused by vehicular emissions, this study proposes an innovative process for Low Emission Zones (LEZ) design within the Simulation of Urban Mobility (SUMO) framework. Our primary focus is on enhancing urban mobility through the strategic design of LEZs, while simultaneously maintaining or even improving emission levels. The novel aspect of the approach lies in the use of LEZs with minimal geometric boundaries, strategically designed to balance the reduction of CO2 emissions and the necessity of fluid urban transportation. LEZs are calculated using genetic algorithms that optimize a cost function balancing emissions and travel time while applying topological and specific constraints. Several experiments are simulated with SUMO to compare the efficiency of urban mobility under various LEZ configurations and different traffic demands. The results show the improvement of the approach in comparison with traditional LEZ design methodologies. The proposal not only preserves or even reduces the emission levels, but also actively improves urban mobility and traffic flow. This empirical evidence strongly supports the feasibility and effectiveness of the proposed solution in different urban scenarios. The design of the heuristic enables the possibility to create dynamic LEZs that may be changed depending on demand, weather, or any other varying conditions that affect traffic and emissions, preserving the mobility concerns of the users.
- 17 July 2024
- Published by TIB Open Publishing in SUMO Conference Proceedings
- Vol. 5, 247-268
Open AccessOptimized Design of Low Emission Zones in SUMO
Focusing on the critical challenge of air pollution in urban areas, primarily caused by vehicular emissions, this study proposes an innovative process for Low Emission Zones (LEZ) design within the Simulation of Urban Mobility (SUMO) framework. Our primary focus is on enhancing urban mobility through the strategic design of LEZs, while simultaneously maintaining or even improving emission levels. The novel aspect of the approach lies in the use of LEZs with minimal geometric boundaries, strategically designed to balance the reduction of CO2 emissions and the necessity of fluid urban transportation. LEZs are calculated using genetic algorithms that optimize a cost function balancing emissions and travel time while applying topological and specific constraints. Several experiments are simulated with SUMO to compare the efficiency of urban mobility under various LEZ configurations and different traffic demands. The results show the improvement of the approach in comparison with traditional LEZ design methodologies. The proposal not only preserves or even reduces the emission levels, but also actively improves urban mobility and traffic flow. This empirical evidence strongly supports the feasibility and effectiveness of the proposed solution in different urban scenarios. The design of the heuristic enables the possibility to create dynamic LEZs that may be changed depending on demand, weather, or any other varying conditions that affect traffic and emissions, preserving the mobility concerns of the users.