A5074475841- Autonomous Vehicle Technology and Safety
- Semantic Web and Ontologies
- Biomedical Text Mining and Ontologies
- Spam and Phishing Detection
- Text and Document Classification Technologies
- Web Data Mining and Analysis
- Anomaly Detection Techniques and Applications
- Traffic control and management
- Traffic Prediction and Management Techniques
- Advanced Radiotherapy Techniques
- Melanoma and MAPK Pathways
- Automated Road and Building Extraction
- E-Learning and Knowledge Management
- Journalism and Media Studies
- ECG Monitoring and Analysis
- Data Quality and Management
- Prostate Cancer Diagnosis and Treatment
- Traffic and Road Safety
- 3D Surveying and Cultural Heritage
- Artificial Intelligence in Healthcare
- Radiopharmaceutical Chemistry and Applications
- Vehicular Ad Hoc Networks (VANETs)
- Image and Object Detection Techniques
- Network Security and Intrusion Detection
- Intravenous Infusion Technology and Safety
Universidad Europea
2014-2024
Hospital Universitario Dexeus
2021-2024
Universidad Europea
2004-2022
Hospital Quirónsalud Barcelona
2013-2021
Complexo Hospitalario Universitario A Coruña
2017
University Frères Mentouri Constantine 1
2017
Vall d'Hebron Hospital Universitari
2012
Universitat Autònoma de Barcelona
2012
In the recent years, we have witnessed a dramatic increment in volume of spam email. Other related forms are increasingly revealing as problem importance, specially on Instant Messaging services (the so called SPIM), and Short Message Service (SMS) or mobile spam.Like email spam, SMS can be approached with legal, economic technical measures. Among wide range measures, Bayesian filters playing key role stopping spam. this paper, analyze to what extent filtering techniques used block applied...
We consider the problem of content-based spam filtering for short text messages that arise in three contexts: mobile (SMS) communication, blog comments, and email summary information such as might be displayed by a low-bandwidth client. Short often consist only few words, therefore present challenge to traditional bag-of-words based filters. Using corpora message fields derived from real SMS, blog, messages, we evaluate feature-based compression-model-based observe filters can improved...
Mobile spam in an increasing threat that may be addressed using filtering systems like those employed against email spam. We believe techniques require some adaptation to reach good levels of performance on SMS spam, especially regarding message representation. In order test this assumption, we have performed experiments top performing filters mobile messages a suitable feature representation, with results supporting our hypothesis.
Navigating roundabouts is a complex driving scenario for both manual and autonomous vehicles. This paper proposes an approach based on the use of Q-learning algorithm to train vehicle agent learn how appropriately navigate roundabouts. The proposed learning implemented using CARLA simulation environment. Several simulations are performed in two scenarios: navigating roundabout with without surrounding traffic. results illustrate that Q-learning-algorithm-based able smooth efficient perform...
This article presents a machine learning-based technique to build predictive model and generate rules of action allow autonomous vehicles perform roundabout maneuvers. The approach consists building vehicle speeds steering angles based on collected data related driver-vehicle interactions other aggregated intrinsic the traffic environment, such as geometry number lanes obtained from Open-Street-Maps offline video processing. study systematically generates regarding speed angle required for...
Among the reasons for traffic accidents, distractions are most common. Although there many signs on road that contribute to safety, variable message (VMSs) require special attention, which is transformed into distraction. ADAS (advanced driver assistance system) devices advanced systems perceive environment and provide his comfort or safety. This project aims develop a prototype of VMS (variable sign) reading system using machine learning techniques, still not used, especially in this...
Many head‐and‐neck cancer (HNC) patients treated with radiotherapy suffer significant anatomical changes due to tumor shrinkage or weight loss. The purpose of this study was assess dose over target volumes and organs at risk during intensity‐modulated for HNC patients. Sixteen IMRT patients, all requiring bilateral neck irradiation, were enrolled in the study. A performed initial distribution calculated. During treatment, two subsequent CTs 15th 25th fractions acquired. plan calculated on ,...
Traffic accidents constitutes the first cause of death and injury in many developed countries. However, traffic information data provided by public organisms can be exploited to classify these according their type severity, consequently try build predictive model. Detecting identifying severity real time is primordial for speeding post-accidents protocols as well developing general road safety policies. This article presents a case study classification prediction Spain. Raw are from Spanish...
Spam filtering is a text categorization task that shows especial features make it interesting and difficult.First, the has been performed traditionally using heuristics from domain.Second, cost model required to avoid misclassification of legitimate messages.We present comparative evaluation several machine learning algorithms applied spam filtering, considering messages set for task.Cost-oriented biasing performed.
S. Martinez-Requejo 1E. Jimenez García 1S. Redondo Duarte 2J. Ruiz Lázaro Puertas Sanz 1G. Mariscal Vivas 1
This publication presents a dataset of Spanish roundabouts aerial images taken from UAV, along with annotations in PASCAL VOC XML files that indicate the position vehicles within them. Additionally, CSV file is attached containing information related to location and characteristics captured roundabouts. work details process followed obtain them: image capture, processing, labeling. The consists 985,260 total instances: 947,400 cars, 19,596 cycles, 2262 trucks, 7008 buses, 2208 empty 61,896...
// Maria Gonzalez-Cao 1 , Aram Boada 2 Cristina Teixidó 1,10 María Teresa Fernandez-Figueras 3 Clara Mayo Francesc Tresserra 4 Jean Bustamante 5 Santiago Viteri Enrique Puertas 6 Mariacarmela Santarpia 7 Aldo Riso Feliciano Barron 8 Niki Karachaliou Rafael Rosell 1,9 Translational Cancer Research Unit, Instituto Oncológico Dr Rosell, Dexeus University Hospital-Quirónsalud Group, Barcelona, Spain Dermatology Department, Hospital Universitari Germans Trias i Pujol,...
Urinary flow measurement and colorimetry are vital medical indicators for critically ill patients in intensive care units. However, there is a clinical need low-cost, continuous urinary monitoring devices that can automatically real-time measure urine flow. This led to the development of non-invasive device easy use does not require proprietary disposables. The operates by detecting using an infrared barrier returns unequivocal pattern, it capable measuring volume liquid real-time, storing...
The aging population and economic crisis specially in developed countries have as a consequence the reduction funds dedicated to health care; it is then desirable optimize costs of public private healthcare systems, reducing affluence chronic dependent people care centers; promoting healthy lifestyle activities can allow avoid diseases for example hypertension. In this article, we describe system an active recommend with guidelines valuable information about their habits. proposed being...
Abstract Background Encorafenib plus binimetinib (EB) is a standard-of-care treatment for advanced BRAFV600-mutant melanoma. We assessed the efficacy and safety of encorafenib in patients with melanoma brain metastasis (BM) explored if radiotherapy improves duration response. Methods E-BRAIN/GEM1802 was prospective, multicenter, single-arm, phase II trial that enrolled BM. Patients received 450 mg once daily 45 BID, those who achieved partial response or stable disease at first tumor...
Learning from human driver’s strategies for undertaking complex traffic scenarios has the potential to improve decision-making methods designing ADAS systems, as well design self-driving rules automated vehicles. This paper proposes a human-like algorithm built up drivers experiential naturalistic driving. The approach of this work consists exploring two main techniques. Firstly, use “think aloud protocol” build dataset based on driving, capturing intentions. Afterwards, technique decision...
In this paper we present a novel contribution work, describing system that helps to detect urban areas with high density of incidents or risk situations. Our has perception and pre-collision feed an expert aimed at detecting dangerous All gathered by the vehicles are sent global repository, its data is processed for hotspots where very high. That information can be useful city councils, allowing them address these concentration