Bertha Guijarro-Berdiñas

Bertha Guijarro-Berdiñas
University of A Coruña | UDC · Centre for Research of Information and Communication Technologies (CITIC)

PhD onc Computer Science

About

94
Publications
21,761
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,351
Citations

Publications

Publications (94)
Article
Full-text available
This paper presents an intuitive, robust and efficient One-Class Classification algorithm. The method developed is called OCENCH (One-class Classification via Expanded Non-Convex Hulls) and bases its operation on the construction of subdivisible and expandable non-convex hulls to represent the target class. The method begins by reducing the dimensi...
Preprint
Full-text available
This paper presents a novel, fast and privacy preserving implementation of deep autoencoders. DAEF (Deep Autoencoder for Federated learning), unlike traditional neural networks, trains a deep autoencoder network in a non-iterative way, which drastically reduces its training time. Its training can be carried out in a distributed way (several partiti...
Preprint
Full-text available
There are many contexts where dyadic data is present. Social networking is a well-known example, where transparency has grown on importance. In these contexts, pairs of items are linked building a network where interactions play a crucial role. Explaining why these relationships are established is core to address transparency. These explanations ar...
Article
Full-text available
In this study, we analyze the capability of several state of the art machine learning methods to predict whether patients diagnosed with CoVid-19 (CoronaVirus disease 2019) will need different levels of hospital care assistance (regular hospital admission or intensive care unit admission), during the course of their illness, using only demographic...
Chapter
Agent based models (ABM) are computational models employed for simulating the actions and interactions of autonomous agents with the objective of assessing their effects on the system as a whole. They have been extensively applied in social sciences because ABM simulations, under different running conditions, can help to test the implications of a...
Chapter
Deploying machine learning models at scale is still a major challenge; one reason is that performance degrades when they are put into production. It is therefore very important to ensure the maximum possible generalization capacity of the models and regularization plays a key role in avoiding overfitting. We describe Regularized One-Layer Artificia...
Article
Full-text available
Feature selection algorithms, such as ReliefF, are very important for processing high‐dimensionality data sets. However, widespread use of popular and effective such algorithms is limited by their computational cost. We describe an adaptation of the ReliefF algorithm that simplifies the costliest of its step by approximating the nearest neighbor gr...
Conference Paper
Due to the frequent use of anomaly detection systems in monitoring and the lack of methods capable of learning in real time, this research presents a new method that provides such online adaptability. The method developed is called OSHULL (Online and Subdivisible Distributed Scaled Convex Hull) and bases its operation on the properties of scaled co...
Article
The k -nearest-neighbors ( k NN) graph is a popular and powerful data structure that is used in various areas of Data Science, but the high computational cost of obtaining it hinders its use on large datasets. Approximate solutions have been described in the literature using diverse techniques, among which Locality-sensitive Hashing (LSH) is a prom...
Article
One‐class classification has gained interest as a solution to certain kinds of problems typical in a wide variety of real environments like anomaly or novelty detection. Autoencoder is the type of neural network that has been widely applied in these one‐class problems. In the Big Data era, new challenges have arisen, mainly related with the data vo...
Article
Full-text available
Anomaly detection is a sub-area of machine learning that deals with the development of methods to distinguish among normal and anomalous data. Due to the frequent use of anomaly-detection systems in monitoring and the lack of methods capable of learning in real time, this research presents a new method that provides such online adaptability. The me...
Article
Full-text available
Multiagent systems (MASs) allow facing complex, heterogeneous, distributed problems difficult to solve by only one software agent. The world of video games provides problems and suitable environments for the use of MAS. In the field of games, Unity is one of the most used engines and allows the development of intelligent agents in virtual environme...
Article
Full-text available
COVID-19 has brought a new normality in society. However, to avoid the situation, the virus must be stopped. There are several ways in which the governments of the world have taken action, from small measures like general cleaning up to large-scale measures like confinement. In this work, we present an agent-based tool that allows for simulating th...
Article
Full-text available
In this work, we propose an autonomous monitoring system for the daily routine of an elderly person. SARDAM (Service Assistant Robot for Daily Activity Monitoring), which is the name of this system, uses a humanoid robot as a key element that carries out a direct interaction with the user. The purpose of SARDAM is to keep the user active as long as...
Article
Full-text available
In a society in which information is a cornerstone the exploding of data is crucial. Thinking of the Internet of Things, we need systems able to learn from massive data and, at the same time, being inexpensive and of reduced size. Moreover, they should operate in a distributed manner making use of edge computing capabilities while preserving local...
Article
Full-text available
Gaining relevant insight from a dyadic dataset, which describes interactions between two entities, is an open problem that has sparked the interest of researchers and industry data scientists alike. However, the existing methods have poor explainability, a quality that is becoming essential in certain applications. We describe an explainable and sc...
Article
Full-text available
This work presents the ADMNC method, designed to tackle anomaly detection for large-scale problems with a mixture of categorical and numerical input variables. A flexible parametric probability measure is adjusted to input data, allowing low likelihood values to be tracked as anomalies. The main contribution of this method is that, to cope with the...
Article
Full-text available
Obtaining relevant information from the vast amount of data generated by interactions in a market or, in general, from a dyadic dataset, is a broad problem of great interest both for industry and academia. Also, the interpretability of machine learning algorithms is becoming increasingly relevant and even becoming a legal requirement, all of which...
Article
Free download before October 20, 2018 by clicking: https://authors.elsevier.com/c/1XekB5aecSVnxn In machine learning literature, and especially in the literature referring to artificial neural networks, most methods are iterative and operate in batch mode. However, many of the standard algorithms are not suitable for efficiently managing the emerg...
Article
Full-text available
Lately, derived from the explosion of high dimensionality, researchers in machine learning became interested not only in accuracy, but also in scalability. Although scalability of learning methods is a trending issue, scalability of feature selection methods has not received the same amount of attention. This research analyzes the scalability of st...
Article
Full-text available
In real applications learning algorithms have to address several issues such as, huge amount of data, samples which arrive continuously and underlying data generation processes that evolve over time. Classical learning is not always appropriate to work in these environments since independent and indentically distributed data are assumed. Taking int...
Article
In the scope of data analytics, the volume of a data set can be defined as a product of instance size and dimensionality of the data. In many real problems, data sets are mainly large only on one of these aspects. Machine learning methods proposed in the literature are able to efficiently learn in only one of these two situations, when the number o...
Conference Paper
In many applications, learning algorithms act in dynamic environments where data flows continuously. In those situations, the learning algorithms should be able to work in real time adjusting its controlling parameters, even its structures, when knowledge arrives. In a previous work, the authors proposed an online learning method for two-layer feed...
Article
Full-text available
This paper presents a novel distributed one-class classification approach based on an extension of the ν-SVM method, thus permitting its application to Big Data data sets. In our method we will consider several one-class classifiers, each one determined using a given local data partition on a processor, and the goal is to find a global model. The c...
Article
This paper presents the development of a novel automatic lineheating forming machine based on intensive application of the numerical simulation and artificial intelligence. The forming of certain parts of the shell of the ships can be done by heating forming or mechanical forming. Line heating forming is usually a more flexible process, and therefo...
Article
Full-text available
We propose an adaptive inverse control scheme, which employs a neural network for the system identification phase and updates its weights in online mode. The theoretical basis of the method is given and its performance is illustrated by means of its application to different control problems showing that our proposal is able to overcome the problems...
Article
Full-text available
Dry eye is a symptomatic disease which affects a wide range of population and has a negative impact on their daily activities. Its diagnosis can be achieved by analyzing the interference patterns of the tear film lipid layer and by classifying them into one of the Guillon categories. The manual process done by experts is not only affected by subjec...
Article
In the last few years, distributed learning has been the focus of much attention due to the explosion of big databases, in some cases distributed across different nodes. However, the great majority of current selection and classification algorithms are designed for centralized learning, i.e. they use the whole dataset at once. In this paper, a new...
Article
Many real problems in machine learning are of a dynamic nature. In those cases, the model used for the learning process should work in real time and have the ability to act and react by itself, adjusting its controlling parameters, even its structures, depending on the requirements of the process. In a previous work, the authors proposed an online...
Article
Many real scenarios in machine learning are of dynamic nature. Learning in these types of environments represents an important challenge for learning systems. In this context, the model used for learning should work in real time and have the ability to act and react by itself, adjusting its controlling parameters, even its structures, depending on...
Conference Paper
In this paper, we propose a novel distributed learning algorithm built upon the Frontier Vector Quantization based on Information Theory (FVQIT) method. The FVQIT is very effective in classification problems but it shows poor training time performance. Thus, distributed learning is appropriate here to speed up training. One of the most promising li...
Article
Until recently, the most common criterion in machine learning for evaluating the performance of algorithms was accuracy. However, the unrestrainable growth of the volume of data in recent years in fields such as bioinformatics, intrusion detection or engineering, has raised new challenges in machine learning not simply regarding accuracy but also s...
Conference Paper
Full-text available
En este trabajo se presentan las conclusiones extraídas tras evaluar los resultados académicos obtenidos por los estudiantes en la asignatura de Programación II, del primer curso del Grado en Ingeniería Informática en la Universidad de A Coruña. Los datos, pertenecientes al segundo año de implantación de la asignatura bajo las directrices del EEES,...
Article
In the past few years, the bottleneck for machine learning developers is not longer the limited data available but the algorithms inability to use all the data in the available time. For this reason, researches are now interested not only in the accuracy but also in the scalability of the machine learning algorithms. To deal with large-scale databa...
Conference Paper
In recent years, the unrestrainable growth of the volume of data has raised new challenges in machine learning regarding scalability. Scalability comprises not simply accuracy but several other measures regarding computational resources. In order to compare the scalability of algorithms it is necessary to establish a method allowing integrating all...
Article
Machine Learning (ML) addresses the problem of adjusting those mathematical models which can accurately predict a characteristic of interest from a given phenomenon. They achieve this by extracting information from regularities contained in a data set. From its beginnings two visions have always co-existed in ML: batch and online learning. The form...
Conference Paper
Full-text available
Dry eye is a symptomatic disease which affects a wide range of population and has a negative impact on their daily activities, such as driving or working with computers. Its diagnosis can be achieved by several clinical tests, one of which is the analysis of the interference pattern and its classification into one of the Guillon's categories. The m...
Article
This paper presents a novel approach for classifying sleep apneas into one of the three basic types: obstructive, central and mixed. The goal is to overcome the problems encountered in previous work and improve classification accuracy. The proposed model uses a new classification approach based on the characteristics that each type of apnea present...
Article
Full-text available
Traditionally, a bottleneck preventing the development of more intelligent systems was the limited amount of data available. Nowadays, the total amount of information is almost incalculable and automatic data analyzers are even more needed. However, the limiting factor is the inability of learning algorithms to use all the data to learn within a re...
Article
Full-text available
Researchers in machine learning are now interested not only in accuracy but also in scalability of methods. Although scalability of learning algorithms is a trending issue, scalability of feature selection methods has not received the same amount of attention. In this research, a preliminary attempt to study the scalability of three well-known filt...
Conference Paper
Advances in communication technologies have contributed to the proliferation of distributed datasets. The most effective approach to distributed learning is to learn locally and then combine the local models. In general, distributed algorithms assume that there is a single model that could be induced from the distributed datasets. Under this view,...
Conference Paper
The unrestrainable growth of data in many domains in which machine learning could be applied has brought a new field called largescale learning that intends to develop efficient and scalable algorithms with regard to requirements of computation, memory, time and communications. A promising line of research for large-scale learning is distributed le...
Conference Paper
Full-text available
The advent of high dimensionality problems has brought new challenges for machine learning researchers, who are now interested not only in the accuracy but also in the scalability of algorithms. In this context, machine learning can take advantage of feature selection methods to deal with large-scale databases. Feature selection is able to reduce t...
Conference Paper
Nowadays, machine learning applications deal most often with large and/or distributed datasets. In this context, distributed learning seems to be the most promising line of research to handle both situations since large datasets can be allocated across several locations. Moreover, the current trend of reducing the speed of processors in favor of mu...
Conference Paper
Traditionally, a bottleneck preventing the development of more intelligent systems was the limited amount of data available. However, nowadays in many domains of machine learning, the size of the datasets is so large that the limiting factor is the inability of learning algorithms to use all the data to learn with in a reasonable time. In order to...
Conference Paper
Computer systems are facing an increased number of security threats, specially regarding Intrusion detection (ID). From the point of view of Machine learning, ID presents many of the new cutting-edge challenges: tackle with massive databases, distributed learning and privacy-preserving classification. In this work, a new approach for ID capable of...
Conference Paper
Many real scenarios in machine learning are non-stationary. These challenges forces to develop new algorithms that are able to deal with changes in the underlying problem to be learnt. These changes can be gradual or abrupt. As the dynamics of the changes can be different, the existing machine learning algorithms exhibit difficulties to cope with t...
Article
This paper proposes a novel supervised learning method for single-layer feedforward neural networks. This approach uses an alternative objective function to that based on the MSE, which measures the errors before the neuron's nonlinear activation functions instead of after them. In this case, the solution can be easily obtained solving systems of l...
Conference Paper
The Sensitivity-Based Linear Learning Method (SBLLM) is a learning method for two-layer feedforward neural networks based on sensitivity analysis that calculates the weights by solving a linear system of equations. Therefore, there is an important saving in computational time which significantly enhances the behavior of this method as compared to o...
Conference Paper
Objective: The involuntary periodic repetition of respiratory pauses or apneas constitutes the sleep apnea-hypopnea syndrome (SAHS). This paper presents two novel approaches for sleep apnea classification in one of their three basic types: obstructive, central and mixed. The goal is to improve the classification accuracy obtained in previous works....
Conference Paper
In recent years, Machine Learning (ML) has witnessed a great increase of storage capacity of computer systems and an enormous growth of available information to work with thanks to the WWW. This has raised an opportunity for new real life applications of ML methods and also new cutting-edge ML challenges like: tackle with massive databases, Distrib...
Conference Paper
Full-text available
The Sensitivity-Based Linear Learning Method (SBLLM) is a learning method for two-layer feedforward neural networks based on sensitivity analysis, that calculates the weights by solving a linear system of equations. Therefore, there is an important saving in computational time which significantly enhances the behavior of this method compared to oth...
Article
Full-text available
We describe the design of a misuse detection agent, one of the distinct agents in a multi-agent-based intrusion detection system. This system is being implemented in JADE, a well-known multi-agent platform based in Java. The agent analyses the packets in the network connections using a packet sniffer and then creates a data model based on the infor...
Conference Paper
Full-text available
Evolutionary agents are flexible, agile, capable of learning, and appropriate for problems with changing conditions or where the correct solution cannot be known in advance. Evolutionary Multi-Agent systems, therefore, consist of populations of agents that learn through interactions with the environment and with other agents and which are periodica...
Conference Paper
Full-text available
The Sensitivity-Based Linear Learning Method (SBLLM) is a learning method for two-layer feedforward neural networks, based on sensitivity analysis, that calculates the weights by solving a system of lin- ear equations. Therefore, there is an important saving in computational time which significantly enhances the behavior of this method compared to...
Chapter
Functional networks are a generalization of neural networks, which is achieved by using multiargument and learnable functions, i.e., in these networks the transfer functions associated with neurons are not fixed but learned from data. In addition, there is no need to include parameters to weigh links among neurons since their effect is subsumed by...
Conference Paper
Training multilayer neural networks is typically carried out using gradient descent techniques. Ever since the brilliant backpropagation (BP), the first gradient-based algorithm proposed by Rumelhart et al., novel training algorithms have appeared to become better several facets of the learning process for feed-forward neural networks. Learning spe...
Conference Paper
Ever since the first gradient-based algorithm, the brilliant backpropagation proposed by Rumelhart, a variety of new training algorithms have emerged to improve different aspects of the learning process for feed-forward neural networks. One of these aspects is the learning speed. In this paper, we present a learning algorithm that combines linear-...
Conference Paper
In this article, two new implementations for behaviours in JADE are presented. These new behaviours, while being able to reproduce the functioning of the old JADE's behaviours, allow the user to define priorities. This fact is of vital importance for several multiagent applications. Finally, a test was developed to show that the performance of the...
Conference Paper
The sleep apnea syndrome (SAS) is a respiratory disorder suffered by people who stop breathing during their sleep. The most common method for the diagnosis of the SAS is based on nocturnal polysomnography. One the task for diagnosis comprises the classification of apneic events in order to distinguish among three basic types of respiratory disfunct...
Article
Full-text available
This paper introduces a learning method for two-layer feedforward neural networks based on sensitivity analysis, which uses a linear training algorithm for each of the two layers. First, random values are assigned to the outputs of the first layer; later, these initial values are updated based on sensitivity formulas, which use the weights in each...
Article
This paper presents a novel approach for sleep apnea classification. The goal is to classify each apnea in one of three basic types: obstructive, central and mixed. Three different supervised learning methods using a neural network were tested. The inputs of the neural network are the first level-5-detail coefficients obtained from a discrete wavel...
Conference Paper
Mozart/Oz is an advanced development platform for intelligent, distributed, powerful and highly functional applications, developed under the European ACCLAIM project. The platform at present lacks a tool for agent communications based on a standard such as ACL-FIPA or KQML. In this work, a tool for agent communication in Mozart/Oz based on KQML has...
Article
This paper presents a study of the influence of perturbations in the parameters of a functional network. A quantitative measure is introduced, related to the change in the mean squared error when noise is applied to the network parameters. This measure, based on statistical sensitivity, provides a fault tolerance estimate for a functional network a...
Article
Over the last two decades in southern Europe, more than 10 million hectares of forest have been damaged by fire. Due to the costs and complications of fire-fighting a number of technical developments in the field have been appeared in recent years. This paper describes a system developed for the region of Galicia in NW Spain, one of the regions of...
Conference Paper
In this paper a method for sleep apnea classification is proposed. The method is based on a feedforward neural network trained using a bayesian framework and a cross-entropy error function. The inputs of the neural network are the first level-5-detail coefficients obtained from a discrete wavelet transformation of the samples of the thoracic effort...
Conference Paper
In this work, a new supervised learning method for single layer neural networks based on a regularized cost function is presented. This method obtains the optimal weights and biases by solving a system of linear equations and therefore it is always guaranteed the global optimum solution. In order to verify the soundness of the proposed learning alg...
Conference Paper
Full-text available
The paper presents a method for times series prediction using a local dynamic modeling based on a three step process. In the first step the input data is embedded in a reconstruction space using a memory structure. The second step, implemented by a self-organizing map (SOM), derives a set of local models from data. The third step is accomplished by...
Conference Paper
The paper presents a method for time series prediction using local dynamic modeling. After embedding the input data in a reconstruction space using a memory structure, a self-organizing map (SOM) derives a set of local models from these data. Afterwards, a set of single layer neural networks, trained optimally with a system of linear equations, is...
Article
The article presents a method for learning the weights in one-layer feedforward neural networks minimizing either the sum of squared errors or the maximum absolute error, measured in the input scale. This leads to the existence of a global optimum that can be easily obtained solving linear systems of equations or linear programming problems, using...
Article
In obstetrics, cardiotocograph (CTG) and non-stress test readings are indispensable to antenatal monitoring and assessment. Difficulties in the interpretation of CTG records require methods for computer-assisted analysis. This article describes CAFE (Computer Aided Foetal Evaluator), an intelligent tightly coupled hybrid system developed to overcom...