A5057025835- Text and Document Classification Technologies
- Spam and Phishing Detection
- Machine Learning and Data Classification
- Image Retrieval and Classification Techniques
- Advanced Text Analysis Techniques
- Web Data Mining and Analysis
- Algorithms and Data Compression
- Neural Networks and Applications
- Machine Learning and Algorithms
- Topic Modeling
- Rough Sets and Fuzzy Logic
- Recommender Systems and Techniques
- Congenital Heart Disease Studies
- Genetic and phenotypic traits in livestock
- Data Mining Algorithms and Applications
- Natural Language Processing Techniques
- Innovative Teaching and Learning Methods
- Pelvic floor disorders treatments
- Student Assessment and Feedback
- Energy Load and Power Forecasting
- Spectroscopy and Chemometric Analyses
- Thermodynamic and Exergetic Analyses of Power and Cooling Systems
- Online and Blended Learning
- Refrigeration and Air Conditioning Technologies
- Advanced Thermodynamic Systems and Engines
Universidad de Oviedo
2011-2024
Research Institute Hospital 12 de Octubre
2021-2022
Great Ormond Street Hospital for Children NHS Foundation Trust
2021
SRI International
2003-2014
Hospital Universitario 12 De Octubre
2014
University College London
2010
Servicio Regional de Investigación y Desarrollo Agroalimentario
2010
Waste heat recovery is a proven process to improve efficiency on engines and meets current necessities of the maritime industry. Since January 1, 2023, already built vessels must meet energy indicators known as EEXI CII. Aiming reduce fuel consumption mitigate pollution emissions, novel waste system composed steam Rankine cycle, organic thermoelectric harvesters desalination presented. High, medium low-grade from exhaust gas, jacket water, lubricating oil engine block radiation are targeted...
This work presents an analysis of environmentally friendly organic Rankine cycle (ORC) fluids and their application in a marine waste heat recovery system (WHRS) to reduce the utilization fuel, thus reducing emission harmful pollutants. The proposed WHRS consists four subsystems: steam Rankine, Seebeck effect electricity conversion desalination. Among 80 ORC working analyzed, R1233zd(E), Novec 649 SES36 exhibit best overall performance terms power output, efficiency, safety environmental...
Text categorization, which consists of automatically assigning documents to a set categories, usually involves the management huge number features. Most them are irrelevant and others introduce noise could mislead classifiers. Thus, feature reduction is often performed in order increase efficiency effectiveness classification. In this paper, we propose select relevant features by means family linear filtering measures simpler than usual applied for purpose. We carry out experiments over two...
We propose a set of (machine learning) ML-based scoring measures for conducting feature selection. We've tested these on documents from two well-known corpora, comparing them with other previously applied this purpose. In particular, we've analyzed which measure obtains the best overall classification performance in terms properties such as precision and recall, emphasizing to what extent some statistical corpus affects performance. The results show that our outperform traditional certain situations.
Abstract Text Categorization is the process of assigning documents to a set previously fixed categories. A lot research going on with goal automating this time‐consuming task. Several different algorithms have been applied, and Support Vector Machines (SVM) shown very good results. In report, we try prove that previous filtering words used by SVM in classification can improve overall performance. This hypothesis systematically tested three measures word relevance, two corpus (one them...
Objective Hypertrophic cardiomyopathy (HCM) is an important predictor of long-term outcomes in Friedreich’s ataxia (FA), but the clinical spectrum and survival childhood poorly described. This study aimed to describe characteristics children with FA-HCM. Design setting Retrospective, longitudinal cohort FA-HCM from UK. Patients 78 (<18 years) diagnosed over four decades. Intervention Anonymised retrospective demographic data were collected baseline evaluation follow-up. Main outcome...
This study presents a review of the recent advances in performing inference probabilistic classifier chains for multilabel classification. The interest such arises an attempt improving performance approach based on greedy search (the well‐known CC method) and simultaneously reducing computational cost exhaustive PCC method). Unlike as , techniques do not explore all possible solutions, but they increase sometimes reaching optimal solution terms subset 0/1 loss, does. ε ‐approximate...
In Hyperparameter Optimization (HPO), only the hyperparameter configuration with best performance is chosen after performing several trials, then, discarding effort of training all models every trial and an ensemble them. This consists simply averaging model predictions or weighting by a certain probability. Recently, other more sophisticated strategies, such as Caruana method stacking strategy has been proposed. On one hand, performs well in HPO ensemble, since it not affected effects...
This research arises from the need to predict amount of air pollutants in meteorological stations. Air pollution depends on location stations (weather conditions and activities surroundings). Frequently, surrounding information is not considered learning process. known beforehand absence unobserved weather remains constant for same station. Considering as side facilitates generalization predicting new stations, leading a zero-shot regression scenario. Available methods typically lean towards...