Francisco López de la Rosa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Francisco López de la Rosa has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Antonio Fernández-Caballero
Departamento de Sistemas Informáticos, Universidad de Castilla-La Mancha, Albacete, Spain
15 shared publications - José L. Gómez Sirvent
Universidad de Castilla-La Mancha
14 shared publications - Rafael Morales
Instituto de Investigación en Informática (I3A), Universidad de Castilla-La Mancha, 02071 Albacete, Spain
12 shared publications - Roberto Sánchez-Reolid
Universidad de Castilla-La Mancha
9 shared publications Antonio Fernández-Caballero
Neurocognition and Emotion Unit, Instituto de Investigación en Informática de Albacete, Albacete, Spain
5 shared publications- Lidia Maria Belmonte
Escuela Técnica Superior de Ingeniería Industrial de Albacete, Universidad de Castilla-La Mancha, 02071 Albacete, Spain
4 shared publications
Latest Publications
- 29 May 2026
- Published by Springer Nature
- p. 323-332
Exploring Whisper’s Latent Space for Emotion Recognition from Vocal Bursts
- 29 May 2026
- Published by Springer Nature
- p. 323-332
Exploring Whisper’s Latent Space for Emotion Recognition from Vocal Bursts
- Open Access
Model-Centric or Data-Centric Approach? A Case Study on the Classification of Surface Defects in Steel Hot Rolling Using Convolutional Neural Networks
Any industrial application that uses convolutional neural networks (CNNs) requires initial data and resources in order to train the models. However, the selection of models must be appropriate to the quality and quantity of the available data and computational resources. This study analyses the influence of data quantity and quality on the performance of CNN models of different complexity. Image preprocessing and image transformation data augmentation techniques are applied to generate different amounts of synthetic data with which to train the aforementioned models, shedding light on the following question: does the quality and quantity of the data or the depth of the model have more influence? Different experiments are performed using the Northeastern University (NEU) Steel Surface Defects Database, which contains surface defects found in hot-rolled steel. After analyzing the results, the authors conclude that data quality and quantity have a much greater influence than model choice. As resources and time are often limited in industry and the ultimate goal is to maximize profit by increasing efficiency, the authors encourage researchers to carefully consider the industrial application at hand and analyze the available data and resources before selecting CNN models.
Open AccessModel-Centric or Data-Centric Approach? A Case Study on the Classification of Surface Defects in Steel Hot Rolling Using Convolutional Neural Networks
Any industrial application that uses convolutional neural networks (CNNs) requires initial data and resources in order to train the models. However, the selection of models must be appropriate to the quality and quantity of the available data and computational resources. This study analyses the influence of data quantity and quality on the performance of CNN models of different complexity. Image preprocessing and image transformation data augmentation techniques are applied to generate different amounts of synthetic data with which to train the aforementioned models, shedding light on the following question: does the quality and quantity of the data or the depth of the model have more influence? Different experiments are performed using the Northeastern University (NEU) Steel Surface Defects Database, which contains surface defects found in hot-rolled steel. After analyzing the results, the authors conclude that data quality and quantity have a much greater influence than model choice. As resources and time are often limited in industry and the ultimate goal is to maximize profit by increasing efficiency, the authors encourage researchers to carefully consider the industrial application at hand and analyze the available data and resources before selecting CNN models.
- 15 January 2026
- Published by Springer Nature
- p. 71-80
Augmented Virtuality to Bridge the Gap Between the Real and Virtual Worlds in Neuroarchitecture
- 15 January 2026
- Published by Springer Nature
- p. 71-80
Augmented Virtuality to Bridge the Gap Between the Real and Virtual Worlds in Neuroarchitecture
- Open Access
Digital Tech Integration in Industrial Engineer Training via Affordable Academic Tools
The rapid advancement of Industry 4.0 and digital transformation is significantly impacting various sectors. Enabling digital technologies, such as big data, machine learning, and the Internet of Things, is becoming increasingly prevalent in industry. However, engineering curricula often fail to keep pace with these swift changes. This study, grounded in Kolb’s experiential learning theory, investigates the integration of enabling digital technologies into final academic projects for industrial engineering students to enhance their competencies through practical experience with affordable technologies. It presents a case study on the design of access control systems using Android, NFC, and Arduino. To demonstrate the potential of this approach, two projects are highlighted: one implementing an integrated parking access control system with NFC payment, and the other focusing on appointment management for access to services. A total of 50 industrial engineering students evaluated both projects, showing a high level of interest and a desire for similar future implementations. The findings indicate that integrating Industry 4.0 technologies into final academic projects effectively bridges the gap between industry requirements and engineering education, enhancing students’ technical skills through experiential learning.
Open AccessDigital Tech Integration in Industrial Engineer Training via Affordable Academic Tools
The rapid advancement of Industry 4.0 and digital transformation is significantly impacting various sectors. Enabling digital technologies, such as big data, machine learning, and the Internet of Things, is becoming increasingly prevalent in industry. However, engineering curricula often fail to keep pace with these swift changes. This study, grounded in Kolb’s experiential learning theory, investigates the integration of enabling digital technologies into final academic projects for industrial engineering students to enhance their competencies through practical experience with affordable technologies. It presents a case study on the design of access control systems using Android, NFC, and Arduino. To demonstrate the potential of this approach, two projects are highlighted: one implementing an integrated parking access control system with NFC payment, and the other focusing on appointment management for access to services. A total of 50 industrial engineering students evaluated both projects, showing a high level of interest and a desire for similar future implementations. The findings indicate that integrating Industry 4.0 technologies into final academic projects effectively bridges the gap between industry requirements and engineering education, enhancing students’ technical skills through experiential learning.
- 1 October 2025
- Published by Springer Nature
- p. 459-470
Expression Recognition in Faces Partially Occluded by Head-Mounted Displays
- 1 October 2025
- Published by Springer Nature
- p. 459-470
Expression Recognition in Faces Partially Occluded by Head-Mounted Displays
- Open Access
- 10 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 7730
Small Language Models for Speech Emotion Recognition in Text and Audio Modalities
Speech emotion recognition has become increasingly important in a wide range of applications, driven by the development of large transformer-based natural language processing models. However, the large size of these architectures limits their usability, which has led to a growing interest in smaller models. In this paper, we evaluate nineteen of the most popular small language models for the text and audio modalities for speech emotion recognition on the IEMOCAP dataset. Based on their cross-validation accuracy, the best architectures were selected to create ensemble models to evaluate the effect of combining audio and text, as well as the effect of incorporating contextual information on model performance. The experiments conducted showed a significant increase in accuracy with the inclusion of contextual information and the combination of modalities. The results obtained were highly competitive, outperforming numerous recent approaches. The proposed ensemble model achieved an accuracy of 82.12% on the IEMOCAP dataset, outperforming several recent approaches. These results demonstrate the effectiveness of ensemble methods for improving speech emotion recognition performance, and highlight the feasibility of training multiple small language models on consumer-grade computers.
- 10 July 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (14) , 7730
Open AccessSmall Language Models for Speech Emotion Recognition in Text and Audio Modalities
Speech emotion recognition has become increasingly important in a wide range of applications, driven by the development of large transformer-based natural language processing models. However, the large size of these architectures limits their usability, which has led to a growing interest in smaller models. In this paper, we evaluate nineteen of the most popular small language models for the text and audio modalities for speech emotion recognition on the IEMOCAP dataset. Based on their cross-validation accuracy, the best architectures were selected to create ensemble models to evaluate the effect of combining audio and text, as well as the effect of incorporating contextual information on model performance. The experiments conducted showed a significant increase in accuracy with the inclusion of contextual information and the combination of modalities. The results obtained were highly competitive, outperforming numerous recent approaches. The proposed ensemble model achieved an accuracy of 82.12% on the IEMOCAP dataset, outperforming several recent approaches. These results demonstrate the effectiveness of ensemble methods for improving speech emotion recognition performance, and highlight the feasibility of training multiple small language models on consumer-grade computers.
- 28 November 2024
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 41 (16) , 10143-10162
Musical Instruments in Extended Reality: A Systematic Review
- 28 November 2024
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 41 (16) , 10143-10162
Musical Instruments in Extended Reality: A Systematic Review
- 8 May 2024
- Published by Taylor & Francis in Building Research & Information
- Vol. 52 (7) , 765-780
Exploring the impact of windows on musicians’ experience: a neuroarchitecture perspective
- 8 May 2024
- Published by Taylor & Francis in Building Research & Information
- Vol. 52 (7) , 765-780
Exploring the impact of windows on musicians’ experience: a neuroarchitecture perspective
- 22 April 2024
- Published by Springer Nature
- p. 99-116
Automated Classification of Semiconductor Defect Density SEM Images Using Deep Learning
- 22 April 2024
- Published by Springer Nature
- p. 99-116
Automated Classification of Semiconductor Defect Density SEM Images Using Deep Learning
- 1 October 2023
- Published by Springer Nature
- p. 217-228
Artificial Vision Technique to Detect and Classify Cocoa Beans
- 1 October 2023
- Published by Springer Nature
- p. 217-228
Artificial Vision Technique to Detect and Classify Cocoa Beans