Enrique Puertas | Universidad Europea de Madrid (original) (raw)

Papers by Enrique Puertas

Text Classification tasks are becoming increasingly popular in the field of Information Access. B... more Text Classification tasks are becoming increasingly popular in the field of Information Access. Being approached as Machine Learning problems, the definition of suitable attributes for each task is approached in an ad-hoc way. We believe that a more principled framework is required, and we present initial insights on attribute engineering for Text Classification, along with a software library that allows experiment definition and fast prototyping of classification systems. The library is currently being used and evaluated in Information Access projects in the biomedical domain.

In this paper we explore the potential of concept indexing with WordNet synsets for Text Categori... more In this paper we explore the potential of concept indexing with WordNet synsets for Text Categorization, in comparison with the traditional bag of words text representation model. We have performed a series of experiments in which we also test the possibility of using simple yet robust disambiguation methods for concept indexing, and the e#ectiveness of stoplist-filtering and stemming on the SemCor semantic concordance. Results are not conclusive yet promising.

In this paper, we describe Hermes, a multilingual news filtering service that sends its users a c... more In this paper, we describe Hermes, a multilingual news filtering service that sends its users a customized enewspaper by email through the use of several text classification techniques, including categorization, summarization and relevance feedback. Hermes is based on a user model far richer than most current newspapers personalization services. The prototype has been evaluated by final users reporting a high degree of satisfaction.

Abstract. On-line access to patient clinical records from pocket and hand-held or tablet computer... more Abstract. On-line access to patient clinical records from pocket and hand-held or tablet computers, will be an useful tool for health care professionals and a valuable complement to other medical applications if information delivery and access information systems are designed with handheld computers in mind. In this paper we present and discuss some partial results of two different research projects: SINAMED 1 and ISIS 2, both of them has as main goals the design of new text categorization and summarization algorithms applied to patient clinical records and associated medical information, and advanced, efficient user interfaces to mobile and on-line access to this results. Continued and new research is expected to improve additional handheld-based user interface design principles as well as guidelines for results organization and system performance and acceptation in a concrete public health institution. 1

2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)

Traffic accidents constitutes the first cause of death and injury in many developed countries. Ho... more Traffic accidents constitutes the first cause of death and injury in many developed countries. However, traffic accidents information and data provided by public organisms can be exploited to classify these accidents according to their type and severity, and consequently try to build predictive model. Detecting and identifying injury severity in traffic accidents in real time is primordial for speeding post-accidents protocols as well as developing general road safety policies. This article presents a case study of traffic accidents classification and severity prediction in Spain. Raw data are from Spanish traffic agency covering a period of six years ranging from 2011 to 2015. To this end, are compared three different machine learning classification techniques, such as Gradient Boosting Trees, Deep Learning and Naïve Bayes.

2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)

this article presents the development of a geographical information system (GIS). App to visualiz... more this article presents the development of a geographical information system (GIS). App to visualize hotspots in the road network inside the metropolitan area of Madrid. On the other hand, this App aims to warn drivers when approaching those spots. The App is fed by the open data provided by the City Hall of Madrid and the Spanish Traffic Agency (DGT), as well as by the data recorded in the on-board system of the vehicle. Firstly, this article presents the general structure of the system with comments on the sources and the nature of the data used. Secondly, it describes the process of data mining carried out for the generation of the structured data used by the App. Thirdly, some characteristics of the developed App are described.

17th International Conference on Information Fusion (FUSION), 2014

This paper describes a global database recorder architecture following a multi agent system philo... more This paper describes a global database recorder architecture following a multi agent system philosophy to provide a specific global database information service. The global database stores relevant vehicles information, related to trips data and risky situations occurred. Trip information and risky situations details (stored previously on vehicle's local databases) are gathered together and used to show traffic hotspots in a graphical representation. In our work, each vehicle has a local database managed by an on-board system. This local database is fed by a pre-collision system and a perception system that identify traffic hazards. The global database can automatically collect all vehicles' local databases and is then exploited for a novel report system that shows traffic hotspots as highlighted points in a geographic map.

Sensors (Basel, Switzerland), 2020

Understanding naturalistic driving in complex scenarios is an important step towards autonomous d... more Understanding naturalistic driving in complex scenarios is an important step towards autonomous driving, and several approaches have been adopted for modeling driver’s behaviors. This paper presents the methodology known as “Think Aloud Protocol” to model driving. This methodology is a data-gathering technique in which drivers are asked to verbalize their thoughts as they are driving which are then recorded, and the ensuing analysis of the audios and videos permits to derive driving rules. The goal of this paper is to show how think aloud methodology is applied in the naturalistic driving area, and to demonstrate the validity of the proposed approach to derive driving rules. The paper presents, firstly, the background of the think aloud methodology and then presents the application of this methodology to driving in roundabouts. The general deployment of this methodology consists of several stages: driver preparation, data collection, audio and video processing, generation of coded t...

In order of maintain the sustainability of the public health systems it is necessary to develop n... more In order of maintain the sustainability of the public health systems it is necessary to develop new medical applications to reduce the affluence of chronic and dependent people to care centers and enabling the management of chronic diseases outside institutions Recent advances in wireless sensors technology applied to e-health allow the development of “personal medicine” concept, whose main objective is to identify specific therapies that make safe and effective individualized treatment of patients based for example in remote monitoring. The volume of health information to manage, including data from medical and biological sensors make necessary to use Big Data and IoT concepts for an adequate treatment of this kind of information. In this paper we present a general approach for sensor’s information processing and analytics based on Big Data concepts.

2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)

Naturalistic Driving Studies (NDS) register data in real driving situations, trying to extract co... more Naturalistic Driving Studies (NDS) register data in real driving situations, trying to extract conclusions about how real drivers behave in specific situations, and for this purpose unobtrusive devices are used. In this paper, we present our work analyzing brain activity using Muse, a wearable electroencephalography (EEG) brain band, and an ad-hoc Android smartphone application. Our study is focuses in a specific maneuver: the roundabouts, and in the comparison between the brainwaves produced in that handling and in a straight section. For this purpose we made the same route in different moments of the day and under different weather conditions, and we isolate a specific stretch of six roundabouts and a straight one. Then we compare the beta and gamma brainwaves obtained in this two different maneuvers, which occurs in normal brain alert consciousness, attention or concentration states.

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

This article presents the development of an application (App) for mobile devices to visualize hot... more This article presents the development of an application (App) for mobile devices to visualize hotspots in the road network of Madrid metropolitan area, which is also aimed at warning drivers when approaching those hotspots. The paper describes, firstly, the nature of data used and their provenance, and then puts the focus on the Extraction, Transformation and Loading Process (or ETL Process) carried out for the generation of the structured data used by the App. Afterwards, the main features and functionalities of the developed App are also described.

Electronics

Navigating roundabouts is a complex driving scenario for both manual and autonomous vehicles. Thi... more Navigating roundabouts is a complex driving scenario for both manual and autonomous vehicles. This paper proposes an approach based on the use of the Q-learning algorithm to train an autonomous vehicle agent to learn how to appropriately navigate roundabouts. The proposed learning algorithm is implemented using the CARLA simulation environment. Several simulations are performed to train the algorithm in two scenarios: navigating a roundabout with and without surrounding traffic. The results illustrate that the Q-learning-algorithm-based vehicle agent is able to learn smooth and efficient driving to perform maneuvers within roundabouts.

Journal of Biomedical Informatics

AIM The aim of this study is to compare the utility of several supervised machine learning (ML) a... more AIM The aim of this study is to compare the utility of several supervised machine learning (ML) algorithms for predicting clinical events in terms of their internal validity and accuracy. The results, which were obtained using two statistical software platforms, were also compared. MATERIALS AND METHODS The data used in this research come from the open database of the Framingham Heart Study, which originated in 1948 in Framingham, Massachusetts as a prospective study of risk factors for cardiovascular disease. Through data mining processes, three data models were elaborated and a comparative methodological study between the different ML algorithms - decision tree, random forest, support vector machines, neural networks, and logistic regression - was carried out. The global selection criterium for choosing the right set of hyperparameters and the type of data manipulation was the area under a curve (AUC). The software tools used to analyze the data were R-Studio® and RapidMiner®. RESULTS The Framingham study open database contains 4240 observations. The algorithm that yielded the greatest AUC when analyzing the data in R-Studio was neural network applied to a model that excluded all observations in which there was at least one missing value (AUC = 0,71); when analyzing the data in RapidMiner and applying the same model, the best algorithm was support vector machines (AUC = 0,75). CONCLUSIONS ML algorithms can reinforce the diagnostic and prognostic capacity of traditional regression techniques. Differences between the applicability of those algorithms and the results obtained with them were a function of the software platforms used in the data analysis.

Sensors

This article presents a machine learning-based technique to build a predictive model and generate... more This article presents a machine learning-based technique to build a predictive model and generate rules of action to allow autonomous vehicles to perform roundabout maneuvers. The approach consists of building a predictive model of vehicle speeds and steering angles based on collected data related to driver–vehicle interactions and other aggregated data intrinsic to the traffic environment, such as roundabout geometry and the number of lanes obtained from Open-Street-Maps and offline video processing. The study systematically generates rules of action regarding the vehicle speed and steering angle required for autonomous vehicles to achieve complete roundabout maneuvers. Supervised learning algorithms like the support vector machine, linear regression, and deep learning are used to form the predictive models.

Lecture Notes in Computer Science, 2016

Recent advances in wireless sensors technology applied to e-health allow the development of “pers... more Recent advances in wireless sensors technology applied to e-health allow the development of “personal medicine” concept, whose main goal is to identify specific therapies that make safe and effective individualized treatment of patients based, for example, in health status remote monitoring. Also the existence of multiple sensor devices in Hospital Units like ICUs (Intensive Care Units) constitute a big source of data, increasing the volume of health information to be analyzed in order to detect or predict abnormal situations in patients. In order to process this huge volume of information it is necessary to use Big Data and IoT technologies. In this paper, we present a general approach for sensor’s information processing and analysis based on Big Data concepts and to describe the use of common tools and techniques for storing, filtering and processing data coming from sensors in an ICU using a distributed architecture based on cloud computing. The proposed system has been developed around Big Data paradigms using bio-signals sensors information and machine learning algorithms for prediction of outcomes.

2015 IEEE 18th International Conference on Intelligent Transportation Systems, 2015

2015 9th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, 2015

These last years developed countries and specially European countries are characterized by aging ... more These last years developed countries and specially European countries are characterized by aging population and economical crisis, as a consequence, the funds dedicated to social services has been diminished specially those dedicated to healthcare, is then desirable to optimize the costs of public and private healthcare systems reducing the affluence of chronic and dependant people to care centers and enabling the management of chronic diseases outside institutions. It is necessary to streamline the health system resources leading to the development of new medical services based on telemedicine and biomedical sensors. New health applications based on remote monitoring will significantly increasing the volume of health information to store, manage and analyze, including heterogeneous data coming from medical records and biomedical sensors. The Big Data and IoT concepts and techniques offer an integrated approach to develop a suitable architecture for an adequate treatment of this kind of information.

2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE)

2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)

17th International Conference on Information Fusion (FUSION), 2014

Sensors (Basel, Switzerland), 2020

2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

Electronics

Journal of Biomedical Informatics

Sensors

Lecture Notes in Computer Science, 2016

2015 IEEE 18th International Conference on Intelligent Transportation Systems, 2015

2015 9th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, 2015