Research Group on High Performance and Intelligent Systems

Description

The team works in four main related and simultaneously complementary research lines:
- Pattern Recognition Techniques, Computer Vision and its applications for different problems, mainly content-based image search, distance learning and emotion detection from video sequences.
- Processing of different types of signals, particularly audio and video ones. Group works in this research line include capture, analysis and synthesis of acoustic signals, as well as analysis of video signals, all acting in coordination with the Computer Vision line.
- Design of Intelligent Tutoring Systems (ITSs) with affective capacities. Part of the results obtained from the first and second line of work are used to detect emotions from videos filmed with low-cost hardware by applying techniques specific to the fields of Signal Processing and Computer Vision.
- High-performance and high-availability computer systems offering a fundamental tool for all the previously mentioned fields (pattern recognition, intelligent systems and signal processing) by providing the necessary power in real time whenever required from application areas or in case of high system availability requirements. In this regard, the latest trends focus on distributed systems, the handling of Big Data and the so-called “cloud computing”: three fundamental aspects in the context of group investigation.

Goals CT

Application of pattern recognition techniques and computer vision in different research fields.
Application of signal processing techniques in the analysis and synthesis of acoustic signals.
Quality improvement of Intelligent Tutoring Systems (ITSs) through customisation and use of affective computing.
Problem resolution requiring high performance and / or Big Data processing.
Improvement of different aspects of existing distributed platforms: safety, availability, service quality and experience.

Research lines

Pattern Recognition and Computer Vision
Recognition and machine learning techniques applied to linear and nonlinear models. Continuous Distance Learning. Heterogeneous and multi-dimensional data mining, with special emphasis on image analysis and recovery and the processing of audio and video signals.
Intelligent Tutoring Systems
We are currently working on forms of knowledge representation that allow the supervision of the students tasks resolution, as well as the incorporation of affective support through the detection of emotions by means of typical techniques within the field of computer vision
Networks and Telecommunication Systems
This line of research focuses on the development of new network architectures and protocols, as well as on the creation of advanced telecommunication systems to improve communications between users. This work includes the development and implementation of our new services, technologies and network architectures centred on enhancing the quality of the final user’s experience.
Parallel computing and Distributed systems
The line focuses on the application of high performance computing techniques, and the development and optimisation of distributed platforms within the cloud computing paradigm, for Big Data, multimedia applications and intelligent systems problem solving.
Signal processing (Sound)
Advanced methods for the capture, analysis and synthesis of acoustic signals, including musical and voice processes, acoustic simulation of rooms, 3D reproduction methods and intelligent monitoring of acoustic environments.

Management

AREVALILLO HERRAEZ, MIGUEL
PDI-Catedratic/a d'Universitat
Coordinador/a Curs

Research Group on High Performance and Intelligent Systems - HiPIS