Papers by Ezequiel López-Rubio
CRC Press eBooks, Feb 7, 2022
CRC Press eBooks, Feb 7, 2022
Integrated Computer-aided Engineering, May 10, 2023
Video feeds from traffic cameras can be useful for many purposes, the most critical of which are ... more Video feeds from traffic cameras can be useful for many purposes, the most critical of which are related to monitoring road safety. Vehicle trajectory is a key element in dangerous behavior and traffic accidents. In this respect, it is crucial to detect those anomalous vehicle trajectories, that is, trajectories that depart from usual paths. In this work, a model is proposed to automatically address that by using video sequences from traffic cameras. The proposal detects vehicles frame by frame, tracks their trajectories across frames, estimates velocity vectors, and compares them to velocity vectors from other spatially adjacent trajectories. From the comparison of velocity vectors, trajectories that are very different (anomalous) from neighboring trajectories can be detected. In practical terms, this strategy can detect vehicles in wrong-way trajectories. Some components of the model are off-the-shelf, such as the detection provided by recent deep learning approaches; however, several different options are considered and analyzed for vehicle tracking. The performance of the system has been tested with a wide range of real and synthetic traffic videos.
Integrated Computer-aided Engineering, May 10, 2023
Video feeds from traffic cameras can be useful for many purposes, the most critical of which are ... more Video feeds from traffic cameras can be useful for many purposes, the most critical of which are related to monitoring road safety. Vehicle trajectory is a key element in dangerous behavior and traffic accidents. In this respect, it is crucial to detect those anomalous vehicle trajectories, that is, trajectories that depart from usual paths. In this work, a model is proposed to automatically address that by using video sequences from traffic cameras. The proposal detects vehicles frame by frame, tracks their trajectories across frames, estimates velocity vectors, and compares them to velocity vectors from other spatially adjacent trajectories. From the comparison of velocity vectors, trajectories that are very different (anomalous) from neighboring trajectories can be detected. In practical terms, this strategy can detect vehicles in wrong-way trajectories. Some components of the model are off-the-shelf, such as the detection provided by recent deep learning approaches; however, several different options are considered and analyzed for vehicle tracking. The performance of the system has been tested with a wide range of real and synthetic traffic videos.
Springer eBooks, 2022
Image classification has undergone a revolution in recent years due to the high performance of ne... more Image classification has undergone a revolution in recent years due to the high performance of new deep learning models. However, severe security issues may impact the performance of these systems. In particular, adversarial attacks are based on modifying input images in a way that is imperceptible for human vision, so that deep learning image classifiers are deceived. This work proposes a new deep neural network model composed of an encoder and a Generative Adversarial Network (GAN). The former encodes a possibly malformed input image into a latent vector, while the latter generates a reconstructed image from the latent vector. Then the reconstructed image can be reliably classified because our model removes the deleterious effects of the attack. The experiments carried out were designed to test the proposed approach against the Fast Gradient Signed Method attack. The obtained results demonstrate the suitability of our approach in terms of an excellent balance between classification accuracy and computational cost.
Springer eBooks, Sep 22, 2021
The evaluation methods employed in a course are the most important point for the students, above ... more The evaluation methods employed in a course are the most important point for the students, above any other learning aspect. For teachers, this task is arduous when the number of students is high. Traditional evaluation requires the teacher to grade all the assignments and exams, while peer assessments have become a valuable tool to involve students effectively in the correction of exercises. This paper applied and analyzes the evaluation through peer review in a course of Computer Sciences Engineering. A total of six assignments and a mid-term exam were evaluated by both teachers (individually) and students (cooperatively), and the differences were discussed to extract conclusions about the viability of this evaluation model.
Springer eBooks, 2022
Image classification has undergone a revolution in recent years due to the high performance of ne... more Image classification has undergone a revolution in recent years due to the high performance of new deep learning models. However, severe security issues may impact the performance of these systems. In particular, adversarial attacks are based on modifying input images in a way that is imperceptible for human vision, so that deep learning image classifiers are deceived. This work proposes a new deep neural network model composed of an encoder and a Generative Adversarial Network (GAN). The former encodes a possibly malformed input image into a latent vector, while the latter generates a reconstructed image from the latent vector. Then the reconstructed image can be reliably classified because our model removes the deleterious effects of the attack. The experiments carried out were designed to test the proposed approach against the Fast Gradient Signed Method attack. The obtained results demonstrate the suitability of our approach in terms of an excellent balance between classification accuracy and computational cost.
Neural Networks, Dec 1, 2009
The original Kohonen's Self-Organizing Map model has been extende... more The original Kohonen's Self-Organizing Map model has been extended by several authors to incorporate an underlying probability distribution. These proposals assume mixtures of Gaussian probability densities. Here we present a new self-organizing model which is based on a mixture of multivariate Student-t components. This improves the robustness of the map against outliers, while it includes the Gaussians as a limit case. It is based on the stochastic approximation framework. The 'degrees of freedom' parameter for each mixture component is estimated within the learning procedure. Hence it does not need to be tuned manually. Experimental results are presented to show the behavior of our proposal in presence of outliers, and its performance in adaptive filtering and classification problems.
The reduction of energy consumption in buildings is one of the goals to improve energy efficiency... more The reduction of energy consumption in buildings is one of the goals to improve energy efficiency. One way to achieve energy savings in buildings is to develop intelligent control strategies for heating systems that are able to reduce power consumption without affecting the thermal comfort. An intelligent control system must be able to predict the temperature of the building in order to manage the heating system. In this paper, we present a rule-based model that is able to predict the indoor temperature for different values of k (hours ahead in time). The model has been learned with FRULER, a genetic fuzzy system that generates accurate and simple knowledge bases. Our approach has been validated with real data from a residential college.
Springer eBooks, Sep 22, 2021
The evaluation methods employed in a course are the most important point for the students, above ... more The evaluation methods employed in a course are the most important point for the students, above any other learning aspect. For teachers, this task is arduous when the number of students is high. Traditional evaluation requires the teacher to grade all the assignments and exams, while peer assessments have become a valuable tool to involve students effectively in the correction of exercises. This paper applied and analyzes the evaluation through peer review in a course of Computer Sciences Engineering. A total of six assignments and a mid-term exam were evaluated by both teachers (individually) and students (cooperatively), and the differences were discussed to extract conclusions about the viability of this evaluation model.
Foreground object detection algorithms should be insensitive to noise present in the analyzed vid... more Foreground object detection algorithms should be insensitive to noise present in the analyzed video sequences. In this work, a study of a type of non-supervised deep learning network, called autoencoder, is performed. They are suited to reduce input dimensionality and capture the most relevant information present in a region or image. Therefore, different types of autoencoders, deterministic and variational, with different architectures, activation functions and number of layers, are analyzed. This neural network is combined with a probabilistic mixture model which attempts to classify each video frame region as background and foreground.
Information Sciences, Mar 1, 2015
Most current nonparametric approaches to probability density function estimation are based on the... more Most current nonparametric approaches to probability density function estimation are based on the kernel density estimator, also known as the Parzen window estimator. A usual alternative is the multivariate histogram, which features a low computational complexity. Multivariate frequency polygons have often been neglected, even though they share many of the advantages of the histograms, while they are continuous unlike the histograms. Here we build on our previous work on histograms in order to propose a new probability density estimator which is based on averaging multivariate frequency polygons. The convergence of the estimator is formally proved. Experiments are carried out with synthetic and real machine learning datasets. Finally, image denoising and object tracking applications are also considered.
Springer eBooks, 2022
Labeled medical datasets may include a limited number of observations for each class, while unlab... more Labeled medical datasets may include a limited number of observations for each class, while unlabeled datasets may include observations from patients with pathologies other than those observed in the labeled dataset. This negatively influences the performance of the prediction algorithms. Including out-of-distribution data in the unlabeled dataset can lead to varying degrees of performance degradation, or even improvement, by using a distance to measure how out-of-distribution a piece of data is. This work aims to propose an approach that allows estimating the predictive uncertainty of supervised algorithms, improving the behaviour when atypical samples are presented to the distribution of the dataset. In particular, we have used this approach to mammograms X-ray images applied to binary classification tasks. The proposal makes use of Feature Density, which consists of estimating the density of features from the calculation of a histogram. The obtained results report slight differences when different neural network architectures and uncertainty estimators are used.
Springer eBooks, 2022
This paper explores the effect of using different pipelines to compute connectomes (matrices repr... more This paper explores the effect of using different pipelines to compute connectomes (matrices representing brain connections) and use them to train machine learning models with the goal of diagnosing Autism Spectrum Disorder. Five different pipelines are used to train six different ML models, splitting the data into female, male and all subsets so we can also research the effect of considering male and female patients separately. Our results conclude that pipeline and model choice impact results, along with using general or specific models.
European Conference on Artificial Intelligence, Aug 22, 2004
One of the best known techniques for multidimensional data analysis is the Principal Components A... more One of the best known techniques for multidimensional data analysis is the Principal Components Analysis (PCA). A number of local PCA neural models have been proposed to partition an input distribution into meaningful clusters. Each neuron of these models uses a certain number of basis vectors to represent the principal directions of a particular cluster. Most of these neural networks are unable to learn the number of basis vectors, which is specified a priori as a fixed parameter. This leads to poor adaptation to input data. Here we develop a method where the number of basis vectors of each neuron is learned. Then we apply this method to a well known local PCA neural model. Finally, experimental results are presented where the original and modified versions of the neural model are compared.
Lecture Notes in Computer Science, 2021
Lecture Notes in Computer Science, 2021
Neural Processing Letters, Oct 3, 2020
In this paper, a new self-organizing artificial neural network called growing hierarchical neural... more In this paper, a new self-organizing artificial neural network called growing hierarchical neural forest (GHNF) is proposed. The GHNF is a hierarchical model based on the growing neural forest, which is a tree-based model that learns a set of trees (forest) instead of a general graph so that the forest can grow in size. This way, the GHNF faces three important limitations regarding the self-organizing map: fixed size, fixed topology, and lack of hierarchical representation for input data. Hence, the GHNF is especially amenable to datasets containing clusters where each cluster has a hierarchical structure since each tree of the GHNF forest can adapt to one of the clusters. Experimental results show the goodness of our proposal in terms of self-organization and clustering capabilities. In particular, it has been applied to text mining of tweets as a typical exploratory data analysis application, where a hierarchical representation of concepts present in tweets has been obtained. Moreover, it has been applied to foreground detection in video sequences, outperforming several methods specialized in foreground detection.
Advances in intelligent systems and computing, Apr 28, 2019
Evaluation is an important task in the classroom and it conditions the effort of the students. Mo... more Evaluation is an important task in the classroom and it conditions the effort of the students. Moreover, their marks are usually the main goal of the students. The traditional methodology about exams and the subsequent average of them to calculate the grade of the students is not the most suitable way in order to aim different facets like a significant learning or a critical thinking. Nowadays, several methods are indicated to improve this aspects among others, even the students attitude. Another evaluation methodology by cooperative assessment is shown in this paper.
Uploads
Papers by Ezequiel López-Rubio