Hubert Cecotti is an Associate Professor in the department of Computer Science at
the College of Science and Mathematics at Fresno State, Fresno, CA, USA. HC received
the MSc and PhD degrees in computer science from the University of Lorraine, Lorraine,
France, in 2002 and 2005, respectively. He was a Lecturer in computer science with
the University Henri Poincare and ESIAL, Nancy, France, in 2006 and 2007. From 2008
to 2009, he was a Research Scientist with the Institute of Automation, Bremen University,
Bremen, Germany, where he conducted research on brain-computer interfaces (BCIs) and
proposed convolutional neural networks to process EEG signal for the detection of
event-related potentials and steady state visual evoked potentials. In 2010, he was
a researcher at the Gipsa-Lab CNRS, Grenoble, France, where he worked on sensor selection
and spatial filtering for the P300 speller that allows severely disabled people to
communicate through the detection of the P300 event related potential component. From
2011 to 2013, he was at the University of California Santa Barbara, Santa Barbara,
CA, USA, where he was involved in electroencephalography signal processing and machine
learning in projects related to the study of attention in dual-task paradigms and
in rapid serial visual presentation tasks. He was a Lecturer with the School of Computing
and Intelligent Systems, Ulster University, Londonderry, UK, from 2014 to 2017, where
he conducted research about magnetoencephalography, electroencephalography signal
processing and human-computer interface using eye-tracking, and co-supervised three
PhD students. His current research interests include pattern recognition, human-computer
interaction, and brain-computer interfaces.
Research Interests:
-
Pattern Recognition & Machine Learning
-
Neural Networks (Conv nets, Deep nets, ELM)
-
Image and Signal Processing
-
Human-Computer Interaction
-
Neural engineering
Applications:
-
Brain Computer Interface (non-invasive): Event-related potentials: P300 speller and
Rapid Serial Visual Presentation tasks; Steady-State Visual Evoked Potentials (SSVEP);
Motor imagery (ERD/ERS)
-
EEG/MEG signal processing: Spatial and temporal filtering, Single-trial detection
(classification) with linear and non-linear classifiers, deep learning.
-
Document Analysis and handwritten character recognition: Indian (Bangla, Oriya, Devnagari),
Arabic, Lampung, Farsi; Optical Character Recognition (OCR) combination (e.g., ancient
documents, technical maps)
-
Eye-trackers and multi-modal interfaces: Virtual keyboards (Latin script, Hindi script)
-
Virtual reality: Symbol recognition in immersive virtual reality (HTC Vive); Educational
applications (Astronomy, Art History, Medical Imaging)
