A5031471658- Hate Speech and Cyberbullying Detection
- Indoor and Outdoor Localization Technologies
- Semantic Web and Ontologies
- Sentiment Analysis and Opinion Mining
- Robotics and Sensor-Based Localization
- Handwritten Text Recognition Techniques
- Eating Disorders and Behaviors
- Image Processing and 3D Reconstruction
- UAV Applications and Optimization
- COVID-19 epidemiological studies
- Digital Communication and Language
- Mental Health via Writing
- Facility Location and Emergency Management
- Natural Language Processing Techniques
- Biomimetic flight and propulsion mechanisms
- Smart Grid Security and Resilience
- AI-based Problem Solving and Planning
- Caching and Content Delivery
- Advanced Aircraft Design and Technologies
- Network Security and Intrusion Detection
- Digital Transformation in Industry
- Asian Culture and Media Studies
- Distributed and Parallel Computing Systems
- Energy Efficient Wireless Sensor Networks
- COVID-19 Pandemic Impacts
Universidad de León
2010-2024
Universidad de León
2013
Eating disorders affect an increasing number of people. Social networks provide information that can help.We aimed to find machine learning models capable efficiently categorizing tweets about eating domain.We collected related disorders, for 3 consecutive months. After preprocessing, a subset 2000 was labeled: (1) messages written by people suffering from or not, (2) promoting (3) informative and (4) scientific nonscientific messages. Traditional deep were used classify tweets. We evaluated...
Abstract Localization Wireless Sensor Networks (WSN) represent a research topic with increasing interest due to their numerous applications. However, the viability of these systems is compromised by attained localization uncertainties once implemented, since network performance highly dependent on sensors location. The Node Location Problem (NLP) aims obtain optimal distribution for particular environment, problem already categorized as NP-Hard. Furthermore, WSN usually perform sensor...
With the growth that social networks have experienced in recent years, it is entirely impossible to moderate content manually. Thanks different existing techniques natural language processing, possible generate predictive models automatically classify texts into categories. However, a weakness has been detected concerning used train such models. This work aimed develop model based on BERT, capable of detecting racist and xenophobic messages tweets written Spanish. A comparison was made with...
Abstract Parkinson’s disease is easy to diagnose when it advanced, but very difficult in its early stages. Early diagnosis essential be able treat the symptoms. It impacts on daily activities and reduces quality of life both patients their families also second most prevalent neurodegenerative disorder after Alzheimer people over age 60. Most current studies prediction severity are carried out advanced stages disease. In this work, study analyzes a set variables that can easily extracted from...
Unmanned-Aerial-Vehicles (UAVs) represent an active research topic over multiple fields for performing inspection, delivery and surveillance applications among other operations. However, achieving the utmost efficiency requires drones to perform these tasks without need of human intervention, which demands a robust accurate localization system safe efficient autonomous navigation. Nevertheless, currently used satellite-based systems like GPS are insufficient high-precision applications,...
Eating disorders (ED) are among the most widespread mental illnesses in our society today. This research work presents study of deep learning models applied to domain eating disorders. For this purpose, a collection messages from social network Twitter was compiled using web scraping techniques. After collecting total amount 1,085,957 tweets, subset 2,000 tweets manually classified. classification made it possible differentiate written by people who suffer or have suffered an ED those not...
The efficient design of the aerodynamic surfaces in aircraft allows optimal performance vehicle and reduction fuel consumption. Among these surfaces, wing is main contributor to force which lifts enabling flight. However, application this out center gravity generates a moment that must be balanced through applied Horizontal-Tail-Plane (HTP) reaching longitudinal trim aircraft. Traditionally, HTP have been performed iteratively attaining suboptimal or time ineffective results. In paper, we...
Software Defined Networking (SDN) is an emerging field of study within computer networks research area that will, in a near future, play important role the design and development network infrastructures. The main idea behind SDN to separate control data planes are nowadays coupled traditional devices (routers, switches, etc). This separation plane from electronic performs actual packet switching tasks allows former be implemented physical different device also permits build strategies vendor...
Abstract This article presents an Off-line handwritten digit recognition approach based on neural networks. We define a numeric character as composition of vertical and horizontal strokes. After the preprocessing, we use dynamic zoning to retrieve positions where strokes – main — are joined These features recorded into representative string verified using custom matching pattern. Finally, multilayer perceptron network is fed with previous data raise learning process. The results gathered...