Pedro Javier Navarro
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Pedro Javier Navarro has a total of 111 co-authors. Here are the top co-authors by number of shared publications:
- Carlos Fernández
División de Sistemas e Ingeniería Electrónica (DSIE), Campus Muralla del Mar, s/n, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
12 shared publications - Marcos Egea-Cortines
Instituto de Biotecnología Vegetal, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
11 shared publications - Francisca Rosique
División de Sistemas e Ingeniería Electrónica (DSIE), Campus Muralla del Mar, s/n, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
10 shared publications - Andrés Iborra
Universidad Politécnica de Cartagena
9 shared publications - Juan Suardíaz
División of Innovation in Telematic Systems and Electronic Technology (DINTEL), Technical University of Cartagena, Campus Muralla del Mar, s/n, E-30202 Cartagena, Spain
9 shared publications - Leanne Miller
División de Sistemas e Ingeniería Electrónica (DSIE), Campus Muralla del Mar, s/n, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
9 shared publications
Latest Publications
- 6 November 2026
- Published by Springer Nature
- p. 447-459
Improving Music Collaboration Recommendations Using TikTok Social Connections
- 6 November 2026
- Published by Springer Nature
- p. 447-459
Improving Music Collaboration Recommendations Using TikTok Social Connections
- Open Access
Large-scale forward genetics reveals genetically separable components of plant cell proliferative capacity
Summary: Plant cell cultures underpin regeneration, transformation and emerging applications in biotechnology and plant cell agriculture, yet the genetic determinants of proliferative performance remain poorly characterized. Here, we combined large-scale forward genetics with automated image-based phenotyping to quantify 27,648 calli representing 2,880 Arabidopsis thaliana T-DNA insertion lines. Of these, 2,456 lines produced calli smaller than the WT population mean, whereas only 190 produced larger calli, revealing a strongly asymmetric phenotypic distribution. Enhanced callus growth was not consistently associated with increased vegetative growth, indicating that these traits can be genetically uncoupled. Validation of selected high-growth mutants in suspension culture identified lines with enhanced biomass accumulation, while serial propagation revealed independent variation in sustained proliferative capacity. Thus, callus growth, whole-plant growth, short-term suspension biomass accumulation and sustained proliferation represent distinct, not necessarily coupled components of proliferative performance. These findings establish a scalable framework for identifying genetic determinants relevant to the development of improved plant cell production lines. Highlights: Established a high-throughput platform for quantitative phenotyping of plant callus growth. Screened 2,880 Arabidopsis T-DNA lines, revealing extensive genetic variation in callus proliferative capacity. Identified mutants with enhanced biomass accumulation or sustained proliferative capacity in suspension culture. Established a framework for the genetic improvement of plant cell production platforms. Graphical Overwiew of the study. Image created with Biorender.
Open AccessLarge-scale forward genetics reveals genetically separable components of plant cell proliferative capacity
Summary: Plant cell cultures underpin regeneration, transformation and emerging applications in biotechnology and plant cell agriculture, yet the genetic determinants of proliferative performance remain poorly characterized. Here, we combined large-scale forward genetics with automated image-based phenotyping to quantify 27,648 calli representing 2,880 Arabidopsis thaliana T-DNA insertion lines. Of these, 2,456 lines produced calli smaller than the WT population mean, whereas only 190 produced larger calli, revealing a strongly asymmetric phenotypic distribution. Enhanced callus growth was not consistently associated with increased vegetative growth, indicating that these traits can be genetically uncoupled. Validation of selected high-growth mutants in suspension culture identified lines with enhanced biomass accumulation, while serial propagation revealed independent variation in sustained proliferative capacity. Thus, callus growth, whole-plant growth, short-term suspension biomass accumulation and sustained proliferation represent distinct, not necessarily coupled components of proliferative performance. These findings establish a scalable framework for identifying genetic determinants relevant to the development of improved plant cell production lines. Highlights: Established a high-throughput platform for quantitative phenotyping of plant callus growth. Screened 2,880 Arabidopsis T-DNA lines, revealing extensive genetic variation in callus proliferative capacity. Identified mutants with enhanced biomass accumulation or sustained proliferative capacity in suspension culture. Established a framework for the genetic improvement of plant cell production platforms. Graphical Overwiew of the study. Image created with Biorender.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Vehicular Technology Magazine
- p. 2-11
Edge-AI Passenger Counting for Urban Bus Operations: Real-Time Doorway Sensing
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Vehicular Technology Magazine
- p. 2-11
Open AccessEdge-AI Passenger Counting for Urban Bus Operations: Real-Time Doorway Sensing
- Open Access
- 6 November 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (16) , 1-18
An end-to-end distributed deep learning system for real-time passenger flow measurement in transport interchanges
As urban populations continue to grow, managing and optimizing urban mobility has become increasingly complex, especially in multimodal transport interchanges. Accurate passenger flow measurement has therefore become essential for operators to mitigate congestion and improve service efficiency. This work proposes a scalable and flexible end-to-end system designed to accurately measure and track passenger flow in real-time. The system integrates a distributed network of Edge-AI sensor nodes with deep learning algorithms for local passenger detection and tracking, while a central processing server aggregates node outputs to derive flow counts. This approach overcomes the limitations of traditional single-sensor solutions by effectively handling occlusion and complex spatial configurations across multiple access points. Validated in a high-transited transport hub, results show that the system achieves accuracy rates between 94.03% and 99.30% even under crowded conditions with flow rates of 100 persons per minute, demonstrating its robustness and practical applicability in dynamic, high-density environments.
- 6 November 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (16) , 1-18
Open AccessAn end-to-end distributed deep learning system for real-time passenger flow measurement in transport interchanges
As urban populations continue to grow, managing and optimizing urban mobility has become increasingly complex, especially in multimodal transport interchanges. Accurate passenger flow measurement has therefore become essential for operators to mitigate congestion and improve service efficiency. This work proposes a scalable and flexible end-to-end system designed to accurately measure and track passenger flow in real-time. The system integrates a distributed network of Edge-AI sensor nodes with deep learning algorithms for local passenger detection and tracking, while a central processing server aggregates node outputs to derive flow counts. This approach overcomes the limitations of traditional single-sensor solutions by effectively handling occlusion and complex spatial configurations across multiple access points. Validated in a high-transited transport hub, results show that the system achieves accuracy rates between 94.03% and 99.30% even under crowded conditions with flow rates of 100 persons per minute, demonstrating its robustness and practical applicability in dynamic, high-density environments.
- Open Access
EdgeNet: An End-to-End Deep Neural Network Pretrained with Synthetic Data for a Real-World Autonomous Driving Application
This paper presents a novel end-to-end architecture based on edge detection for autonomous driving. The architecture has been designed to bridge the domain gap between synthetic and real-world images for end-to-end autonomous driving applications and includes custom edge detection layers before the Efficient Net convolutional module. To train the architecture, RGB and depth images were used together with inertial data as inputs to predict the driving speed and steering wheel angle. To pretrain the architecture, a synthetic multimodal dataset for autonomous driving applications was created. The dataset includes driving data from 100 diverse weather and traffic scenarios, gathered from multiple sensors including cameras and an IMU as well as from vehicle control variables. The results show that including edge detection layers in the architecture improves performance for transfer learning when using synthetic and real-world data. In addition, pretraining with synthetic data reduces training time and enhances model performance when using real-world data.
Open AccessEdgeNet: An End-to-End Deep Neural Network Pretrained with Synthetic Data for a Real-World Autonomous Driving Application
This paper presents a novel end-to-end architecture based on edge detection for autonomous driving. The architecture has been designed to bridge the domain gap between synthetic and real-world images for end-to-end autonomous driving applications and includes custom edge detection layers before the Efficient Net convolutional module. To train the architecture, RGB and depth images were used together with inertial data as inputs to predict the driving speed and steering wheel angle. To pretrain the architecture, a synthetic multimodal dataset for autonomous driving applications was created. The dataset includes driving data from 100 diverse weather and traffic scenarios, gathered from multiple sensors including cameras and an IMU as well as from vehicle control variables. The results show that including edge detection layers in the architecture improves performance for transfer learning when using synthetic and real-world data. In addition, pretraining with synthetic data reduces training time and enhances model performance when using real-world data.
- Open Access
- 14 November 2024
- Published by MDPI AG in Preprints.org
EdgeNet: An End-to-End Deep Neural Network pretrained with Synthetic Data for a Real-World Autonomous Driving Application
This study presents a novel end-to-end architecture based on edge detection for autonomous driving. The architecture has been designed to bridge the domain gap between synthetic and real-world images for end-to-end autonomous driving applications and includes custom edge detection layers before the Efficient Net convolutional module. To train the architecture, RGB and depth images were used together with inertial data as inputs to predict the driving speed and steering wheel angle. To pretrain the architecture, a synthetic multimodal dataset for autonomous driving applications was created. The dataset includes driving data from 100 diverse weather and traffic scenarios, gathered from multiple sensors including cameras and an IMU as well as vehicle control variables. The results show that including edge detection layers in the architecture improves performance for transfer learning when using synthetic and real-world data. In addition, pretraining with synthetic data reduces training time and enhances model performance when using real-world data.
- 14 November 2024
- Published by MDPI AG in Preprints.org
Open AccessEdgeNet: An End-to-End Deep Neural Network pretrained with Synthetic Data for a Real-World Autonomous Driving Application
This study presents a novel end-to-end architecture based on edge detection for autonomous driving. The architecture has been designed to bridge the domain gap between synthetic and real-world images for end-to-end autonomous driving applications and includes custom edge detection layers before the Efficient Net convolutional module. To train the architecture, RGB and depth images were used together with inertial data as inputs to predict the driving speed and steering wheel angle. To pretrain the architecture, a synthetic multimodal dataset for autonomous driving applications was created. The dataset includes driving data from 100 diverse weather and traffic scenarios, gathered from multiple sensors including cameras and an IMU as well as vehicle control variables. The results show that including edge detection layers in the architecture improves performance for transfer learning when using synthetic and real-world data. In addition, pretraining with synthetic data reduces training time and enhances model performance when using real-world data.
- Open Access
- 26 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on AgriFood Electronics
- Vol. 3 (1) , 56-68
Fruit Monitoring and Harvest Date Prediction Using On-Tree Automatic Image Tracking
Fruit harvest date prediction is crucial to optimize resource management, maximize quality, and minimize waste of this food. For this purpose, it is necessary to monitor the fruit ripening stage. However, current measurement procedures pose drawbacks for widespread field deployment: laboratory trials are manual, destructive and expensive; measurements with hand-held portable equipment in the field are very time consuming; and the use of remote sensing mobile platforms has a high operating cost. In this article, a low-cost autonomous fixed sensor for continuous on-tree monitoring of pomegranates is proposed. It is based on a computer vision system able to extract reliable fruit color and size estimations automatically. In addition, an empirical quantitative and qualitative study on the effectiveness of using image-based monitoring in comparison with in situ manual and lab-based measurements for pomegranates is provided in this work. Another contribution of this article is a harvest date prediction model that employs the fruit information collected from the images. Furthermore, a thorough quantitative evaluation of the proposed prediction model for the fruit harvest date was performed, being the median error of the best model of 3.5 days.
- 26 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on AgriFood Electronics
- Vol. 3 (1) , 56-68
Open AccessFruit Monitoring and Harvest Date Prediction Using On-Tree Automatic Image Tracking
Fruit harvest date prediction is crucial to optimize resource management, maximize quality, and minimize waste of this food. For this purpose, it is necessary to monitor the fruit ripening stage. However, current measurement procedures pose drawbacks for widespread field deployment: laboratory trials are manual, destructive and expensive; measurements with hand-held portable equipment in the field are very time consuming; and the use of remote sensing mobile platforms has a high operating cost. In this article, a low-cost autonomous fixed sensor for continuous on-tree monitoring of pomegranates is proposed. It is based on a computer vision system able to extract reliable fruit color and size estimations automatically. In addition, an empirical quantitative and qualitative study on the effectiveness of using image-based monitoring in comparison with in situ manual and lab-based measurements for pomegranates is provided in this work. Another contribution of this article is a harvest date prediction model that employs the fruit information collected from the images. Furthermore, a thorough quantitative evaluation of the proposed prediction model for the fruit harvest date was performed, being the median error of the best model of 3.5 days.
- Open Access
- 17 May 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (6-7) , 5461-5476
Various tomato infection discrimination using spectroscopy
Diagnosing plant diseases is a difficult task, but it could be made easier with the use of advanced instrumentation and the latest machine learning techniques. This paper is a further development of a previous authors study by the authors, which has been extended to provide the classification method for tomato diseases and to indicate the spectral ranges of greatest importance for this process. As tomatoes are one of the most popular and consumed vegetables, and diseases of this crop even reduce yields by up to 80% every year, their detection is a vague topic. This manuscript describes research in which spectroscopy was used to develop methods for discriminating between selected tomato diseases. The following, frequently occurring diseases were investigated for this research: anthracnose, bacterial speck, early blight, late blight, and Septoria Leaf Spot. The study used a dataset consisting of 3877 measurements taken with the ASD FieldSpec 4 Hi-Res spectroradiometer in the 350–2500 nm range from 2019/09/10 to 2019/12/20. The highest classification efficiency ( $$F_1$$ score) of 0.896 was obtained for the logistic regression based model which was evaluated on Septoria Leaf Spot disease records.- 17 May 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (6-7) , 5461-5476
Open AccessVarious tomato infection discrimination using spectroscopy
Diagnosing plant diseases is a difficult task, but it could be made easier with the use of advanced instrumentation and the latest machine learning techniques. This paper is a further development of a previous authors study by the authors, which has been extended to provide the classification method for tomato diseases and to indicate the spectral ranges of greatest importance for this process. As tomatoes are one of the most popular and consumed vegetables, and diseases of this crop even reduce yields by up to 80% every year, their detection is a vague topic. This manuscript describes research in which spectroscopy was used to develop methods for discriminating between selected tomato diseases. The following, frequently occurring diseases were investigated for this research: anthracnose, bacterial speck, early blight, late blight, and Septoria Leaf Spot. The study used a dataset consisting of 3877 measurements taken with the ASD FieldSpec 4 Hi-Res spectroradiometer in the 350–2500 nm range from 2019/09/10 to 2019/12/20. The highest classification efficiency ( $$F_1$$ score) of 0.896 was obtained for the logistic regression based model which was evaluated on Septoria Leaf Spot disease records. - 17 March 2023
- Published by Elsevier
- p. 355-373
Algorithms validation