Training Program - Doctoral Meeting

Training Program

Our biennial training programme is designed to complement the training of our research staff. The current programme, based on the principles for innovative doctoral training promoted by the EU, is divided into the following thematic areas:
The Doctoral Meeting (DM) is a CiTIUS initiative aimed at developing and stimulating the communication, argumentation and scientific criticism skills of young CiTIUS researchers, providing them with an opportunity to present the development of the research carried out in their doctoral thesis in an informal atmosphere that favors an open and productive discussion.

Testing the private mode of web browsers. Are you sure it is private?

Multiple 0bject visual tracking through deep convolutional networks
Argumentative counterfactual explanation generation for enhancing human-machine interaction
Techniques for the extraction of spatial and spectral information in the supervised classification of hyperspectral imagery for land-cover applications
Five-year prediction of glucose changes with missing data in a Reproducing Kernel Hilbert Space
Deep learning for predictive process monitoring based on change characterization and detection
Doctoral meeting: 'Process-to-Text: A Framework for the Description of Processes in Natural Language'
Doctoral meeting: 'Ultra-low power CMOS circuit design for energy harvesting applications'
Fuzzy Quantified Protoforms for Data-To-Text Systems: a new model with applications

Efficient registration of hyperspectral images on GPU
RoI Feature Propagation for Video Object Detection
Development of a 'glocal' and continuous machine learning strategy applicable to devices
Understanding complex processes through frequent and infrequent behaviour
Structural change detection on process models

Processing of airborne LiDAR Data: power line detection and search of optimal routes
Efficient query over large datasets of analytical chemistry
Next Generation Edge and Federation Large-scale Data Analytics: the scalability and security concerns
In-Pixel Analog Processing Elements of the HO-PBAS Algorithm for Background Subtraction
Using hardware counter data to model performance and energy usage in NUMA systems
Automatic dental age calculation from significant parameters extracted automatically from orthopantomographies

Line-based Structure-from-Motion
Corpus-based Construction of Polarity Lexicon

Ensemble and choice modelling for recommending items
Efficient object classification from airborne LiDAR
Micro-energy harvesting on CMOS chips
Deep Learning Based Classification Techniques for hyperspectral imagery in real time

Efficient techniques for change detection in multitemporal hyperspectral images
Nanodevice simulations: tools and insights

Motion planning and controller learning in robotics
Approaching Big Data technologies to scientific applications
Automatic Learning of Simple and Accurate Fuzzy Rule Systems for Regression
Semantic Virtual Integration of Observation Data through Sensor Observation Services
Improving Design Smell Detection for Adoption in Industry
Data Mining Algorithms for Discovering Exception and Deviation Patterns in Temporal Databases
Time-of-Flight sensors in standard CMOS technologies
Efficient optimization techniques for automatic composition of Web services

Simultaneous characterization of deterministic and stochastic components in Heart Rate Variability
Spatial Observation Data Acquisition and Declarative AnalyticalProcessing
Efficient Segmentation and Classification of n-dimensional Images in GPU for Real Time Processing
Classifiers for biosignal interpretation? Not beyond toy examples...
Development of tools to improve the efficiency of amorphous silicon solar cells
Automatic Characterization of Thoracic Aortic Aneurysms from CT Images
ProDiGen: mining complete, precise and minimal structure process models with a genetic algorithm
Computing With Perceptions for the linguistic description of complex processes through time series data analysis
Ordinal classification and time series segmentation: Potential applications

Context-based adaptive QRS clustering in real-time
Advanced visualization and interaction applied to virtual scenarios
Graph-based semantic annotation for enriching documents with linked data
Discovering metric temporal constraint networks on temporal databases
Semantic Relation Extraction. Resources, Tools and Strategies
Hardware Counters Based Methods for the Analysis of Shared Memory Parallel Codes
Scale and Rotation Invariant Feature Detectors on CMOS-3D Technologies for Low Power Vision Systems
3D diagnonis in Orthodontics: Clinical and research applications
Development of simulation tools for devices based on magnetic semiconductors
Development, deployment and validation of an oceanographic virtual laboratory based on Grid computing
Time and space scale adaptive whitening as visual dynamic attentional mechanism
Development of GPU-efficient visualization and segmentation algorithms for 3D medical datas
Fuzzy Syllogistic Reasoning with Generalized Quantifiers

Self-organized multi-camera system for a fast and easy deployment of service robots in unknown environments
Combining retrieval, learning and NLP to estimate polarity in social media