The Advanced Signal Processing Group (GTAS, in Spanish) is part of the Communications Engineering Department of the University of Cantabria. It is located at the E.T.S.I. Industriales y Telecomunicaciones, Avda Los Castros s/n. Santander 39005, SPAIN.

The GTAS conducts research in the development of digital signal processing algorithms for communications, as well as in machine-learning techniques and nonlinear modeling. Currently, the research activity of the GTAS is focused on the following topics:

  • Signal processing techniques for MIMO communication links.
    • CSI (Channel State Information) estimation techniques, synchronization, detection techniques,...
    • Capacity analysis of MIMO links.
    • Development of hardware MIMO testbeds and performance evaluation.
  • Machine-learning techniques and their applications.
    • Kernel methods, neural networks and adaptive information processing systems.
    • Multivariate statistical techniques: PCA, CCA and ICA.
    • Nonlinear modeling.



Paper accepted in IEEE Transactions on Emerging Topics in Computational Intelligence

The paper "Complex-valued Neural Networks with Non-parametric Activation Functions", co-authored by S. Scardapane, S. Van Vaerenbergh, A. Hussain, and A. Uncini, has been accepted for publication in the newly launched journal IEEE Transactions on Emerging Topics in Computational Intelligence.

Paper accepted in IEEE Transactions on Signal Processing

The paper "Testing Equality of Multiple Power Spectral Density Matrices", co-authored by D. Ramirez, D. Romero, J. Via, R. Lopez-Valcarce and I. Santamaría, has been accepted for publication in the IEEE Transactions on Signal Processing.

Paper presented at MLSP 2018

The paper "Recurrent Neural Networks With Flexible Gates Using Kernel Activation Functions" co-authored by S. Scardapane, S. Van Vaerenbergh, D. Comminiello, S. Totaro, and A. Uncini has been presented at the IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2018).

Paper presented at ITISE 2018

The paper "MoCap multichannel time series representation and relevance analysis by kernel adaptive filtering and multikernel learning oriented to action recognition tasks" co-authored by Juan Diego Pulgarin-Giraldo, Andres Marino Alvarez-Meza, Steven Van Vaerenbergh, Ignacio Santamaría and German Castellanos is being presented this week at the International Conference on Time Series and Forecasting (ITISE 2018).

Paper presented at EUSIPCO 2018

The paper "Improving Graph Convolutional Networks with Non-Parametric Activation Functions" co-authored by Simone Scardapane, Steven Van Vaerenbergh, Danilo Comminiello, and Aurelio Uncini was presented this week at the 26th European Signal Processing Conference (EUSIPCO 2018).


Subscribe to News
Subscribe to Grupo de Tratamiento Avanzado de Señal RSS