Now I work in the project 5GEOSiS for the European Space Agency where I help define
and prototype a
versatile satellite payload offering onboard processing with high-performance
multicore and FPGA with signal processing and AI capabilities, as well as a 5G direct-to-ground user link.
In the winter semesters 2022 and 2023 I taught a course of Data Science to the
ProITD master students of the University of Applied Sciences (HTW) Berlin,
Germany.
From 2019 I worked in quantum computing projects, with a main focus on
quantum annealing and QUBO as a way to accelerate industrial optimization.
From 2017 I worked again in projects applying machine learning in network
anomaly detection and network optimization, for a telecom equipment
manufacturer and for the European Space Agency.
From 2015 to 2016 I have applied machine learning and computer vision to
fish farming in Norway - observational non-contact camera based fish weight
estimation.
Between 2013 and 2014 I have applied machine learning and signal
processing applied to robotic surgery (high intensity focused ultrasound
minimal invasive surgery).
Previously, while at Fraunhofer Institute FIRST, I was working from 2010 to
2012 on
ECG recording with small embedded
devices and on wireless-based indoor localization.
From January 2009 to March 2010 I worked in the ReMIND team, accelerating machine learning based network intrusion detection and prevention systems with the aim of making them fit for real-time processing of the network traffic.
From Nov 2007 to Dec 2008 I worked as postdoctoral researcher for the Marie Curie Excellence Team grant “BRAIN2ROBOT”.
From 1995 to 2006 I taught at the University of Bucharest's Faculty of Mathematics and Computer Science, having the position of lecturer in 2006.
You might be interested in my Bristle sensors
(dry electrodes for EEG)
work.
"Correlates of spreading depolarization in human scalp
electroencephalography"
,
Christoph Drenckhahn,
Maren K. L. Winkler,
Sebastian Major,
Michael Scheel,
Eun-Jeung Kang,
Alexandra Pinczolits,
Cristian Grozea,
Jed A. Hartings,
Johannes Woitzik and
Jens P. Dreier
for the COSBID study group,
in Brain (2012) 135 (3): 853-868. doi:10.1093/brain/aws010Open access
full-text article[PDF][BibTex]
The Encoplot Similarity Measure for Automatic Detection of Plagiarism -
Notebook for PAN at CLEF 2011.
in CLEF 2011 Labs and Workshop, Notebook Papers, 19-22 September
2011, Amsterdam, The Netherlands
PDF[BibTex]
"Bristle-sensors - Low-cost Flexible Passive Dry EEG
Electrodes for Neurofeedback and BCI Applications",
C.Grozea, C.D.Voinescu, and S.Fazli,
J. Neural Eng. 8 (2011) 025008.preprint [PDF]
"Single-subject classification of schizophrenia by event-related potentials
during selective attention",
A. Neuhaus, F. Popescu, C. Grozea, E. Hahn, C. Hahn, C. Opgen-Rhein, C.
Urbanek, M. Dettling,
NeuroImage Volume 55, Issue 2, 15 March 2011, Pages 514-521.
DOI
10.1016/j.neuroimage.2010.12.038
"Who's the Thief? Automatic Detection
of the Direction of Plagiarism",
C. Grozea and M. Popescu,Lecture Notes in Computer Science, Vol.
Volume 6008/2010, book "Computational Linguistics and Intelligent Text
Processing", pp. 700-710, DOI 10.1007/978-3-642-12116-6, 2010.
[PDF][Bibtex]Link to
the source on the website of Springer
"ENCOPLOT: Pairwise Sequence Matching in Linear Time Applied to Plagiarism Detection", C.Grozea, C.Gehl, and M.Popescu
- In Proceedings of 3rd PAN workshop. Uncovering Plagiarism, Authorship and Social Software Misuse.
pag. 10-18, 2009.
[PDF][Bibtex]
"Subject independent EEG-based BCI decoding", S.Fazli, C.Grozea, M.Danoczy, B.Blankertz, F.Popescu, K.-R.Muller - in Advances in Neural Information Processing Systems 22 edited by Y. Bengio, D. Schuurmans, J. Lafferty, C. K. I. Williams and A. Culotta, (2009), pag. 513-521
[PDF][Bibtex]
"Subject-independent mental state classification in single trials", S.Fazli, F.Popescu, M.Danóczy, B.Blankertz, K.-R.Müller and C.Grozea - Neural Networks, 2009, Vol 22, Issue 9, Pages 1305-1312.
doi:10.1016/j.neunet.2009.06.003[PDF][Bibtex]
"A method for predicting the success of a BCI training session based on the classification of the CSP filters", C.Grozea, S.Fazli, G.Nolte, M.Danoczy, F.Popescu – In Proceedings of the 4rd International Brain-Computer Interface Workshop and Training Course 2008. Verlag der Technischen Universität Graz, 2008
[post-publication updated PDF][Bibtex]
"Finding optimal parameter settings for high performance word sense disambiguation", C.Grozea
- In Proceedings of Senseval 3 - Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, July 2004 (editors Rada Mihalcea and Phil Edmonds), pag. 125-128
[PDF]
"NP Predicates Computable in the Weakest Level of the Grzegorczyck Hierarchy",
C.Grozea - Journal of Automata, Languages and Combinatorics, 2004, Vol 9, Issue 2/3, pag. 269-279
[post publication updated PDF]