F. Novoa - Academia.edu (original) (raw)
Papers by F. Novoa
Proceedings
While traditional network security methods have been proven useful until now, the flexibility of ... more While traditional network security methods have been proven useful until now, the flexibility of machine learning techniques makes them a solid candidate in the current scene of our networks. In this paper, we assess how well the latter are capable of detecting security threats in a corporative network. To that end, we configure and compare several models to find the one which fits better with our needs. Furthermore, we distribute the computational load and storage so we can handle extensive volumes of data. The algorithms that we use to create our models, Random Forest, Naive Bayes, and Deep Neural Networks (DNN), are both divergent and tested in other papers in order to make our comparison richer. For the distribution phase, we operate with Apache Structured Streaming, PySpark, and MLlib. As for the results, it is relevant to mention that our dataset has been found to be effectively modelable with just a reduced number of features. Finally, given the outcomes obtained, we find thi...
Journal of Medical Internet Research
Background: Major depressive disorder (MDD) or depression is among the most prevalent psychiatric... more Background: Major depressive disorder (MDD) or depression is among the most prevalent psychiatric disorders, affecting more than 300 million people globally. Early detection is critical for rapid intervention, which can potentially reduce the escalation of the disorder. Objective: This study used data from social media networks to explore various methods of early detection of MDDs based on machine learning. We performed a thorough analysis of the dataset to characterize the subjects' behavior based on different aspects of their writings: textual spreading, time gap, and time span. Methods: We proposed 2 different approaches based on machine learning singleton and dual. The former uses 1 random forest (RF) classifier with 2 threshold functions, whereas the latter uses 2 independent RF classifiers, one to detect depressed subjects and another to identify nondepressed individuals. In both cases, features are defined from textual, semantic, and writing similarities. Results: The evaluation follows a time-aware approach that rewards early detections and penalizes late detections. The results show how a dual model performs significantly better than the singleton model and is able to improve current state-of-the-art detection models by more than 10%. Conclusions: Given the results, we consider that this study can help in the development of new solutions to deal with the early detection of depression on social networks.
Proceedings
Communication network data has been growing in the last decades and with the generalisation of th... more Communication network data has been growing in the last decades and with the generalisation of the Internet of Things (IoT) its growth has increased. The number of attacks to this kind of infrastructures have also increased due to the relevance they are gaining. As a result, it is vital to guarantee an adequate level of security and to detect threats as soon as possible. Classical methods emphasise in detection but not taking into account the number of records needed to successfully identify an attack. To achieve this, time-aware techniques both for detection and measure may be used. In this work, well-known machine learning methods will be explored to detect attacks based on public datasets. In order to obtain the performance, classic metrics will be used but also the number of elements processed will be taken into account in order to determine a time-aware performance of the method.
Proceedings
Nowadays, a wide variety of computer systems use authentication protocols based on several factor... more Nowadays, a wide variety of computer systems use authentication protocols based on several factors in order to enhance security. In this work, the viability of a second-phase authentication scheme based on users’ mouse behavior is analyzed by means of classical Artificial Intelligence techniques, such as the Support Vector Machines or Multi-Layer Perceptrons. Such methods were found to perform particularly well, demonstrating the feasibility of mouse behavior analytics as a second-phase authentication mechanism. In addition, in the current stage of the experiments, the classification techniques were found to be very stable for the extracted features.
The purpose of this work is to present the design and implementation of a secure web framework th... more The purpose of this work is to present the design and implementation of a secure web framework that allows the creation and application of customized metric systems related to diagnoses based on medical images. The image studies are obtained from a Picture Archiving and Communications System (PACS) that was developed at the Medical Informatics and Radiological Diagnosis Centre (IMEDIR Research Centre); the web application is designed with the architectonic design pattern Model View Controller (MVC); and we opted for Java Server Pages (JSP), Servlets and Java DataBase Connectivity (JDBC) as implementation technology and deployment platform. Extensible MarkUp Language (XML) is used to store the information related to the composition of the metrics, and to save the results of the application of these metrics to each image. The X-Rays were selected at random and proceed from patients at the Orthopedic Surgery Service of the Juan Canalejo Hospital and the Modelo Hospital at A Coruña. The system was validated by a comparative study, in which we used our tool, as well as an already validated software application, to apply the same metric system to a series of 29 digitalized total hip X-Rays.By testing our framework against previously validated methods, we obtain a measurement method that is not only in concordance with preceding software tools, but presents the advantages of secure access through the web, flexibility in the development of new metric systems, and integration with a PACS.
Current Pharmaceutical Design, 2010
The complex diseases in the field of Neurology, Cardiology and Oncology have the most important i... more The complex diseases in the field of Neurology, Cardiology and Oncology have the most important impact on our society. The theoretical methods are fast and they involve some efficient tools aimed at discovering new active drugs specially designed for these diseases. The ontology of all the items that are linked with the molecule metabolism and the treatment of these diseases gives us the possibility to correlate information from different levels and to discover new relationships between complex diseases such as common drug targets and disease patterns. This review presents the ontologies used to process drug discovery and design in the most common complex diseases.
Wseas Transactions on Computers, Dec 17, 2004
Recent progress in digital medical imaging has ineluctably created a need for efficient managemen... more Recent progress in digital medical imaging has ineluctably created a need for efficient management, for a mechanism that is able to gather and store all the modalities of medical images, regardless of the device that generated them. The DICOM standard defines a protocol for the communication between such devices. This article presents a software server that communicates with DICOM compatible machines and stores their studies. It has been validated and tested in real environments.
Concepts, Methodologies, Tools and Applications, 2011
Heart-related pathologies are among the most frequent health problems in western society. Symptom... more Heart-related pathologies are among the most frequent health problems in western society. Symptoms that point towards cardiovascular diseases are usually diagnosed with angiographies, which allow the medical expert to observe the bloodflow in the coronary arteries and detect severe narrowing (stenosis). According to the severity, extension, and location of these narrowings, the expert pronounces a diagnosis, defines a treatment, and establishes a prognosis. The current modus operandi is for clinical experts to observe the image sequences and take decisions on the basis of their empirical knowledge. Various techniques and segmentation strategies now aim at objectivizing this process by extracting quantitative and qualitative information from the angiographies.
Lecture Notes in Computer Science, 2013
With increasingly complex and heterogeneous systems in pervasive service computing, it becomes mo... more With increasingly complex and heterogeneous systems in pervasive service computing, it becomes more and more important to provide self-protected services to end users. In order to achieve selfprotection, the corresponding security should be provided in an optimized manner considering the constraints of heterogeneous devices and networks. In this paper, we present a Genetic Algorithms-based approach for obtaining optimized security configurations at run time, supported by a set of security OWL ontologies and an event-driven framework. This approach has been realized as a prototype for self-protection in the Hydra middleware, and is integrated with a framework for enforcing the computed solution at run time using security obligations. The experiments with the prototype on configuring security strategies for a pervasive service middleware show that this approach has acceptable performance, and could be used to automatically adapt security strategies in the middleware.
Telemedicine and e-Health, 2007
The field of Medical Informatics is currently experiencing increasing demands for new models of t... more The field of Medical Informatics is currently experiencing increasing demands for new models of the Picture Archiving and Communication Systems (PACS) and Digital Imaging and Communications in Medicine (DICOM) protocols. Despite of the considerable advantages of current systems, implementation in hospitals is remarkably slow, due primarily to difficulties in integration and relatively high costs. Even though the success of DICOM standards has greatly contributed to the development of PACS, many hospitals remain unable to support it or to make full use of its potential because various imaging modalities in use at these sites generate images that cannot be stored in the PACS and cannot be managed in a centralized manner without DICOM standardization modules. Furthermore, the imaging modalities being used in such smaller centers are expensive and unlikely to be replaced, making DICOM compliance untenable. With this in mind, this paper describes the design, development, and implementation of a management system for medical diagnostic imaging, based on the DICOM standard and adapted to the needs of a small hospital. The system is currently being implemented in the San Rafael Hospital at A Coruna in Spain, and integrated with the existing hospital information system (HIS). We have studied the networking infrastructure of the hospital and its available image generation devices, and have subsequently carried out a series of measurements including transmission times, image file size, compression ratios, and many others that allow us to analyze the behavior of the system. Results obtained from these investigations demonstrate both the flexibility of using such a…
International Journal of Computer Assisted Radiology and Surgery, 2006
Current Pharmaceutical Design, 2010
The complex diseases in the field of Neurology, Cardiology and Oncology have the most important i... more The complex diseases in the field of Neurology, Cardiology and Oncology have the most important impact on our society. The theoretical methods are fast and they involve some efficient tools aimed at discovering new active drugs specially designed for these diseases. The ontology of all the items that are linked with the molecule metabolism and the treatment of these diseases gives us the possibility to correlate information from different levels and to discover new relationships between complex diseases such as common drug targets and disease patterns. This review presents the ontologies used to process drug discovery and design in the most common complex diseases.
Current Bioinformatics, 2011
1Centre of Medical Informatics and Radiological Diagnosis (IMEDIR), Faculty of Science Health and... more 1Centre of Medical Informatics and Radiological Diagnosis (IMEDIR), Faculty of Science Health and Computer Science, University of A Coruña, A Coruña, Spain; 2College of Computing, Georgia Institute of Technology, Atlanta, Georgia, USA; 3Interventional Cardiology Unit, Complejo ...
Proceedings
While traditional network security methods have been proven useful until now, the flexibility of ... more While traditional network security methods have been proven useful until now, the flexibility of machine learning techniques makes them a solid candidate in the current scene of our networks. In this paper, we assess how well the latter are capable of detecting security threats in a corporative network. To that end, we configure and compare several models to find the one which fits better with our needs. Furthermore, we distribute the computational load and storage so we can handle extensive volumes of data. The algorithms that we use to create our models, Random Forest, Naive Bayes, and Deep Neural Networks (DNN), are both divergent and tested in other papers in order to make our comparison richer. For the distribution phase, we operate with Apache Structured Streaming, PySpark, and MLlib. As for the results, it is relevant to mention that our dataset has been found to be effectively modelable with just a reduced number of features. Finally, given the outcomes obtained, we find thi...
Journal of Medical Internet Research
Background: Major depressive disorder (MDD) or depression is among the most prevalent psychiatric... more Background: Major depressive disorder (MDD) or depression is among the most prevalent psychiatric disorders, affecting more than 300 million people globally. Early detection is critical for rapid intervention, which can potentially reduce the escalation of the disorder. Objective: This study used data from social media networks to explore various methods of early detection of MDDs based on machine learning. We performed a thorough analysis of the dataset to characterize the subjects' behavior based on different aspects of their writings: textual spreading, time gap, and time span. Methods: We proposed 2 different approaches based on machine learning singleton and dual. The former uses 1 random forest (RF) classifier with 2 threshold functions, whereas the latter uses 2 independent RF classifiers, one to detect depressed subjects and another to identify nondepressed individuals. In both cases, features are defined from textual, semantic, and writing similarities. Results: The evaluation follows a time-aware approach that rewards early detections and penalizes late detections. The results show how a dual model performs significantly better than the singleton model and is able to improve current state-of-the-art detection models by more than 10%. Conclusions: Given the results, we consider that this study can help in the development of new solutions to deal with the early detection of depression on social networks.
Proceedings
Communication network data has been growing in the last decades and with the generalisation of th... more Communication network data has been growing in the last decades and with the generalisation of the Internet of Things (IoT) its growth has increased. The number of attacks to this kind of infrastructures have also increased due to the relevance they are gaining. As a result, it is vital to guarantee an adequate level of security and to detect threats as soon as possible. Classical methods emphasise in detection but not taking into account the number of records needed to successfully identify an attack. To achieve this, time-aware techniques both for detection and measure may be used. In this work, well-known machine learning methods will be explored to detect attacks based on public datasets. In order to obtain the performance, classic metrics will be used but also the number of elements processed will be taken into account in order to determine a time-aware performance of the method.
Proceedings
Nowadays, a wide variety of computer systems use authentication protocols based on several factor... more Nowadays, a wide variety of computer systems use authentication protocols based on several factors in order to enhance security. In this work, the viability of a second-phase authentication scheme based on users’ mouse behavior is analyzed by means of classical Artificial Intelligence techniques, such as the Support Vector Machines or Multi-Layer Perceptrons. Such methods were found to perform particularly well, demonstrating the feasibility of mouse behavior analytics as a second-phase authentication mechanism. In addition, in the current stage of the experiments, the classification techniques were found to be very stable for the extracted features.
The purpose of this work is to present the design and implementation of a secure web framework th... more The purpose of this work is to present the design and implementation of a secure web framework that allows the creation and application of customized metric systems related to diagnoses based on medical images. The image studies are obtained from a Picture Archiving and Communications System (PACS) that was developed at the Medical Informatics and Radiological Diagnosis Centre (IMEDIR Research Centre); the web application is designed with the architectonic design pattern Model View Controller (MVC); and we opted for Java Server Pages (JSP), Servlets and Java DataBase Connectivity (JDBC) as implementation technology and deployment platform. Extensible MarkUp Language (XML) is used to store the information related to the composition of the metrics, and to save the results of the application of these metrics to each image. The X-Rays were selected at random and proceed from patients at the Orthopedic Surgery Service of the Juan Canalejo Hospital and the Modelo Hospital at A Coruña. The system was validated by a comparative study, in which we used our tool, as well as an already validated software application, to apply the same metric system to a series of 29 digitalized total hip X-Rays.By testing our framework against previously validated methods, we obtain a measurement method that is not only in concordance with preceding software tools, but presents the advantages of secure access through the web, flexibility in the development of new metric systems, and integration with a PACS.
Current Pharmaceutical Design, 2010
The complex diseases in the field of Neurology, Cardiology and Oncology have the most important i... more The complex diseases in the field of Neurology, Cardiology and Oncology have the most important impact on our society. The theoretical methods are fast and they involve some efficient tools aimed at discovering new active drugs specially designed for these diseases. The ontology of all the items that are linked with the molecule metabolism and the treatment of these diseases gives us the possibility to correlate information from different levels and to discover new relationships between complex diseases such as common drug targets and disease patterns. This review presents the ontologies used to process drug discovery and design in the most common complex diseases.
Wseas Transactions on Computers, Dec 17, 2004
Recent progress in digital medical imaging has ineluctably created a need for efficient managemen... more Recent progress in digital medical imaging has ineluctably created a need for efficient management, for a mechanism that is able to gather and store all the modalities of medical images, regardless of the device that generated them. The DICOM standard defines a protocol for the communication between such devices. This article presents a software server that communicates with DICOM compatible machines and stores their studies. It has been validated and tested in real environments.
Concepts, Methodologies, Tools and Applications, 2011
Heart-related pathologies are among the most frequent health problems in western society. Symptom... more Heart-related pathologies are among the most frequent health problems in western society. Symptoms that point towards cardiovascular diseases are usually diagnosed with angiographies, which allow the medical expert to observe the bloodflow in the coronary arteries and detect severe narrowing (stenosis). According to the severity, extension, and location of these narrowings, the expert pronounces a diagnosis, defines a treatment, and establishes a prognosis. The current modus operandi is for clinical experts to observe the image sequences and take decisions on the basis of their empirical knowledge. Various techniques and segmentation strategies now aim at objectivizing this process by extracting quantitative and qualitative information from the angiographies.
Lecture Notes in Computer Science, 2013
With increasingly complex and heterogeneous systems in pervasive service computing, it becomes mo... more With increasingly complex and heterogeneous systems in pervasive service computing, it becomes more and more important to provide self-protected services to end users. In order to achieve selfprotection, the corresponding security should be provided in an optimized manner considering the constraints of heterogeneous devices and networks. In this paper, we present a Genetic Algorithms-based approach for obtaining optimized security configurations at run time, supported by a set of security OWL ontologies and an event-driven framework. This approach has been realized as a prototype for self-protection in the Hydra middleware, and is integrated with a framework for enforcing the computed solution at run time using security obligations. The experiments with the prototype on configuring security strategies for a pervasive service middleware show that this approach has acceptable performance, and could be used to automatically adapt security strategies in the middleware.
Telemedicine and e-Health, 2007
The field of Medical Informatics is currently experiencing increasing demands for new models of t... more The field of Medical Informatics is currently experiencing increasing demands for new models of the Picture Archiving and Communication Systems (PACS) and Digital Imaging and Communications in Medicine (DICOM) protocols. Despite of the considerable advantages of current systems, implementation in hospitals is remarkably slow, due primarily to difficulties in integration and relatively high costs. Even though the success of DICOM standards has greatly contributed to the development of PACS, many hospitals remain unable to support it or to make full use of its potential because various imaging modalities in use at these sites generate images that cannot be stored in the PACS and cannot be managed in a centralized manner without DICOM standardization modules. Furthermore, the imaging modalities being used in such smaller centers are expensive and unlikely to be replaced, making DICOM compliance untenable. With this in mind, this paper describes the design, development, and implementation of a management system for medical diagnostic imaging, based on the DICOM standard and adapted to the needs of a small hospital. The system is currently being implemented in the San Rafael Hospital at A Coruna in Spain, and integrated with the existing hospital information system (HIS). We have studied the networking infrastructure of the hospital and its available image generation devices, and have subsequently carried out a series of measurements including transmission times, image file size, compression ratios, and many others that allow us to analyze the behavior of the system. Results obtained from these investigations demonstrate both the flexibility of using such a…
International Journal of Computer Assisted Radiology and Surgery, 2006
Current Pharmaceutical Design, 2010
The complex diseases in the field of Neurology, Cardiology and Oncology have the most important i... more The complex diseases in the field of Neurology, Cardiology and Oncology have the most important impact on our society. The theoretical methods are fast and they involve some efficient tools aimed at discovering new active drugs specially designed for these diseases. The ontology of all the items that are linked with the molecule metabolism and the treatment of these diseases gives us the possibility to correlate information from different levels and to discover new relationships between complex diseases such as common drug targets and disease patterns. This review presents the ontologies used to process drug discovery and design in the most common complex diseases.
Current Bioinformatics, 2011
1Centre of Medical Informatics and Radiological Diagnosis (IMEDIR), Faculty of Science Health and... more 1Centre of Medical Informatics and Radiological Diagnosis (IMEDIR), Faculty of Science Health and Computer Science, University of A Coruña, A Coruña, Spain; 2College of Computing, Georgia Institute of Technology, Atlanta, Georgia, USA; 3Interventional Cardiology Unit, Complejo ...