A5076787107- Recommender Systems and Techniques
- Data Mining Algorithms and Applications
- Music and Audio Processing
- E-Learning and Knowledge Management
- Educational Technology in Learning
- Software Engineering Research
- Image Retrieval and Classification Techniques
- Higher Education Teaching and Evaluation
- Sentiment Analysis and Opinion Mining
- Semantic Web and Ontologies
- Engineering and Information Technology
- Text and Document Classification Technologies
- Video Analysis and Summarization
- Data Management and Algorithms
- Multi-Agent Systems and Negotiation
- Topic Modeling
- Advanced Text Analysis Techniques
- Advanced Database Systems and Queries
- Software Engineering Techniques and Practices
- Service-Oriented Architecture and Web Services
- Imbalanced Data Classification Techniques
- Rough Sets and Fuzzy Logic
- Anomaly Detection Techniques and Applications
- Natural Language Processing Techniques
- Software Reliability and Analysis Research
Universidad de Salamanca
2015-2024
Research Institute Hospital 12 de Octubre
2024
Instituto de Investigación Sanitaria del Hospital Clínico San Carlos
2023
Hospital Clínico San Carlos
2023
Robert Bosch (Germany)
2023
Corporación para Investigaciones Biológicas
1999-2008
Indiana University School of Medicine
2007
Indiana University – Purdue University Indianapolis
2007
Universitat Politècnica de Catalunya
2004
Universidad de Antioquia
1993
The study of public opinion can provide us with valuable information. analysis sentiment on social networks, such as Twitter or Facebook, has become a powerful means learning about the users' opinions and wide range applications. However, efficiency accuracy is being hindered by challenges encountered in natural language processing (NLP). In recent years, it been demonstrated that deep models are promising solution to NLP. This paper reviews latest studies have employed solve problems,...
Sentiment analysis on public opinion expressed in social networks, such as Twitter or Facebook, has been developed into a wide range of applications, but there are still many challenges to be addressed. Hybrid techniques have shown potential models for reducing sentiment errors increasingly complex training data. This paper aims test the reliability several hybrid various datasets different domains. Our research questions aimed at determining whether it is possible produce that outperform...
Recommender systems have been applied in a wide range of domains such as e-commerce, media, banking, and utilities. This kind system provides personalized suggestions based on large amounts data to increase user satisfaction. These help client select products, while organizations can the consumption product. In case social data, sentiment analysis gain better understanding user’s attitudes, opinions emotions, which is beneficial integrate recommender for achieving higher recommendation...
The design of recommendation algorithms aware the user’s context has been subject great interest in scientific community, especially music domain where contextual factors have a significant impact on recommendations. In this type system, information can come from different sources such as specific time day, physical activity, and geolocation, among many others. This is generally obtained by electronic devices used user to listen smartphones other secondary wearables Internet Things (IoT)...
In many application domains such as medicine, information retrieval, cybersecurity, social media, etc., datasets used for inducing classification models often have an unequal distribution of the instances each class. This situation, known imbalanced data classification, causes low predictive performance minority class examples. Thus, prediction model is unreliable although overall accuracy can be acceptable. Oversampling and undersampling techniques are well-known strategies to deal with...
Abstract Neurons in the rostral raphe pallidus (rRP) have been proposed to mediate experimental stress‐induced tachycardia and fever rats, projections from dorsomedial hypothalamus (DMH) may signal their activation these settings. Thus, we examined c‐fos expression evoked by air jet/restraint stress restraint or systemic administration of lipopolysaccharide (10 µg/kg 100 µg/kg) as well distribution neuronal nitric oxide synthase (nNOS) neurons retrogradely labeled with cholera toxin B key...
The current methods for diagnosing Alzheimer’s Disease using Magnetic Resonance Imaging (MRI) have significant limitations. Many previous studies used 2D Transformers to analyze individual brain slices independently, potentially losing critical 3D contextual information. Region of interest-based models often focus on only a few regions despite affecting multiple areas. Additionally, most classification rely single test, whereas requires multifaceted approach integrating diverse data sources...
Despite the existence of different methods, including data mining techniques, available to be used in recommender systems, such systems still contain numerous limitations. They are a constant need for personalization order make effective suggestions and provide valuable information items available. A way reach is by means an alternative technique called classification based on association, which uses association rules prediction perspective. In this work we propose hybrid methodology...
This paper presents a hybrid algorithm that combines Fuzzy Logic Controller (FLC) and Genetic Algorithms (GAs) its application on traffic signal system. FLCs have been widely used in many applications diverse areas, such as control system, pattern recognition, processing, forecasting. They are, essentially, rule-based systems, which the definition of these rules fuzzy membership functions is generally based verbally formulated overlap through parameter space. great influence over performance...
Recent research in the field of recommender systems focuses on incorporation social information into collaborative filtering methods to improve reliability recommendations. Social networks enclose valuable data regarding user behavior and connections that can be exploited this area infer knowledge about preferences influence. The fact streaming music platforms have some functionalities also allows type used for recommendation. In work, we take advantage friendship structure address a...
Online streaming services have become the most popular way of listening to music. The majority these are endowed with recommendation mechanisms that help users discover songs and artists may interest them from vast amount music available. However, many not reliable as they take into account contextual aspects or ever-evolving user behavior. Therefore, it is necessary develop systems consider aspects. In field music, time one important factors influencing preferences managing its effects,...
Recommender systems are being used in streaming service platforms to provide users with personalized suggestions increase user satisfaction. These recommendations primarily based on data about the interaction of system; however, other information from large amounts media can be exploited improve their reliability. In case social data, sentiment analysis opinions expressed by users, together properties items they consume, help gain a better understanding preferences. this study, we present...
In this article a formal model applying REST architectural principles to the description of semantic web services is introduced, including discussion its syntax and operational semantics. RESTful resources are described using concept tuple spaces being manipulated by HTTP methods that related classical space operations. On other hand, creation, destruction dynamic aspects distributed computations involving coordination between agents modeled process calculus style named channels message...
This work presents a monitoring system for the environmental conditions of rose flower-cultivation in greenhouses. Its main objective is to improve quality crops while regulating production time. To this end, consisting autonomous quadruped vehicles connected with wireless sensor network (WSN) developed, which supports decision-making on type action be carried out greenhouse maintain appropriate cultivation. A data analysis process was out, aimed at designing an in-situ intelligent able make...
Recommender Systems (RSs) are used to provide users with personalized item recommendations and help them overcome the problem of information overload. Currently, recommendation methods based on deep learning gaining ground over traditional such as matrix factorization due their ability represent complex relationships between items incorporate additional information. The fact that these data have a graph structure greater capability Graph Neural Networks (GNNs) learn from structures has led...
A Mediterranean diet (MedDiet)-based intervention reduces the rate of immediate postpartum maternal metabolic disorders. Whether these effects persist long-term remains to be determined. total 2526 normoglycemic women were randomized before 12th gestational week (GW). IG followed a MedDiet with extra virgin olive oil (EVOO) (>40 mL/day) and handful nuts daily, whereas CG had restrict all kinds dietary fat. At 3 months postpartum, motivational lifestyle interview was held. The endpoint...