Persona:
Herrera Caro, Pedro Javier

Foto de perfil
Dirección de correo electrónico
ORCID
0000-0001-8679-6617
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Herrera Caro
Nombre de pila
Pedro Javier
Nombre

Filtros

2023 - 20253
Restablecer filtros

Ajustes

Resultados de la búsqueda

Mostrando 1 - 3 de 3
  • Miniatura
    Publicación
    On the Supervision of Peer Assessment Tasks: An Efficient Instructor Guidance Technique
    (Institute of Electrical and Electronics Engineers (IEEE), 2023-12) Hernández González, Jerónimo; Herrera Caro, Pedro Javier
    In peer assessment, students assess a task done by their peers, provide feedback and usually a grade. The extent to which these peer grades can be used to formally grade the task is unclear, with doubts often arising regarding their validity. The instructor could supervise the peer assessments, but would not then benefit from workload reduction, one of the most appealing features of peer assessment for instructors. Our proposal uses a probabilistic model to estimate a grade for each test, accounting for the degree of precision and bias of grading peers. The grade that the instructor would assign to a test can help enhance the model. Our main hypothesis is that guiding the instructor through supervision of a peer-assessed task by pointing out to them which test to evaluate next can lead to improvement in the validity of the model-estimated grades at an early stage. Moreover, the instructor can decide how many tests to grade based on their own criteria of tolerable uncertainty, as measured by the model. We validate the method using both synthetically generated data and real data collected in an actual class. Models that link the roles of the student as grading peer and as test-taker appear to better exploit available information, although simpler models are more appropriate in specific conditions. The best performing technique for guiding the instructor is that which selects the test with the highest expected entropy reduction. In general, empirical results are in line with the hypothesis of this study.
  • Miniatura
    Publicación
    Recognition of Egyptian hieroglyphic texts through focused generic segmentation and cross-validation voting
    (ELSEVIER, 2025-03) Fuentes Ferrer, Raúl; Duque Domingo, Jaime; Herrera Caro, Pedro Javier
    Ancient Egyptian hieroglyphs form part of a complex language that has attracted the attention of Egyptologists, historians, and amateurs for centuries. In use for more than 3000 years, they consist of hundreds of symbols that can be transcribed into their Latin phonemes. Although there have been some previous works on the recognition of hieroglyphs through computer vision, this is a study of unprecedented depths and presents several unique contributions. On the one hand, we have created the largest and most complete dataset of existing Egyptian hieroglyphs to date, covering all the main symbols used on stelae. On the other, we have carried out a systematic analysis of detection, segmentation, and classification methods, focusing our research on a composite method of focused generic segmentation and classification with an ensemble model of ConvNeXt backbones using Cross-Validation Voting (CVV). Our trained model has been evaluated against several carved or painted stone stelae, obtaining excellent results. To the best of our knowledge, there is currently no other methodology capable of obtaining the classification results presented in this paper, and the method and the dataset presented represent a very significant advancement in the development of automated methods for reading Egyptian hieroglyphic texts.
  • Miniatura
    Publicación
    A Combined Model Based on Recurrent Neural Networks and Graph Convolutional Networks for Financial Time Series Forecasting
    (MDPI, 2023-01-02) Lazcano, Ana; Herrera Caro, Pedro Javier; Monge, Manuel
    Accurate and real-time forecasting of the price of oil plays an important role in the world economy. Research interest in forecasting this type of time series has increased considerably in recent decades, since, due to the characteristics of the time series, it was a complicated task with inaccurate results. Concretely, deep learning models such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have appeared in this field with promising results compared to traditional approaches. To improve the performance of existing networks in time series forecasting, in this work two types of neural networks are brought together, combining the characteristics of a Graph Convolutional Network (GCN) and a Bidirectional Long Short-Term Memory (BiLSTM) network. This is a novel evolution that improves existing results in the literature and provides new possibilities in the analysis of time series. The results confirm a better performance of the combined BiLSTM-GCN approach compared to the BiLSTM and GCN models separately, as well as to the traditional models, with a lower error in all the error metrics used: the Root Mean Squared Error (RMSE), the Mean Squared Error (MSE), the Mean Absolute Percentage Error (MAPE) and the R-squared (R2). These results represent a smaller difference between the result returned by the model and the real value and, therefore, a greater precision in the predictions of this model.