Simon O' Regan

PhD researcher with Biomedical Signal Processing Group at University College Cork, Ireland

Location: Ireland
Industry: Research

As a LinkedIn member, you'll join 225 million other professionals who are sharing connections, ideas, and opportunities.

See who you and Simon O' Regan know in common
Get introduced to Simon O' Regan
Contact Simon O' Regan directly

View Simon's full profile

Simon O' Regan's Overview

Current

PhD researcher in Biomedical Signal Processing at University College Cork, Ireland

Past

Visiting researcher with Machine Learning Group at TU Berlin
Research Assistant with Photonic Systems Group at Tyndall National Institute
DAC Applications Co-op at Analog Devices

Education

University College Cork
Christian Brothers College

Connections

205 connections

Websites

Specialties

Biomedical Signal Processing, Neural Engineering, Machine Learning, Artefact Detection in EEG

PhD researcher in Biomedical Signal Processing

University College Cork, Ireland

Educational Institution; Higher Education industry

October 2008 – Present (4 years 8 months)

Developed Machine Learning and Signal Processing techniques for the detection and removal of EEG artefacts for use in neonatal and epileptic seizure detection systems.

Visiting researcher with Machine Learning Group

TU Berlin

Educational Institution; 1001-5000 employees; Research industry

2011 – 2011 (less than a year)

Investigated the use of Stationary Subspace Analysis and Stationary Common Spatial Patterns in removing EEG artefacts in an automated Epileptiform activity detection system

Research Assistant with Photonic Systems Group

Tyndall National Institute

Educational Institution; 201-500 employees; Research industry

June 2008 – September 2008 (4 months) Cork

Design and implementation of clock and data recovery (CDR) unit for 25 GHz and 50 GHz optical communications systems. As many high bit rate serial data streams are transmitted without a clock component, the CDR unit is used to reconstruct a clock signal from the approximate frequency reference, and then phase-align to the transitions in the transmitted data stream with a phase-locked loop (PLL). The clock recovery unit was implemented as an electrical PLL; consisting of voltage controlled oscillator (VCO), phase detector (PD), and loop controller. The design was simulated in C++ and Pspice, before implementing on a PCB.

DAC Applications Co-op

Analog Devices

Public Company; 5001-10,000 employees; ADI; Semiconductors industry

March 2007 – September 2007 (7 months) Limerick

Design of blood glucose measuring device.

Automatic detection of EEG artefacts arising from head movements
- In Proceedings of the IEEE Engineering in Medicine and Biology Conference (EMBC), Buenos Aires, Argentina, 2010.
- September 1, 2010
Authors: Simon O' Regan, Stephen Faul, Liam Marnane

The need for reliable detection of artefacts in raw and processed EEG is widely acknowledged. In this paper, we present the results of an investigation into appropriate features for artefact detection in the REACT ambulatory EEG system. The study focuses on EEG artefacts arising from head movement. The use of one generalised movement artefact class to detect movement artefacts is proposed. Temporal, frequency, and entropy-based features are evaluated using Kolmogorov-Smirnov and Wilcoxon rank-sum non-parametric tests, Mutual Information Evaluation Function and Linear Discriminant Analysis. Results indicate good separation between normal EEG and artefacts arising from head movement, providing a strong argument for treating these head movement artefacts as one generalised class rather than treating their component signals individually.
Automatic detection of EEG artefacts arising from head movements using gyroscopes
- In Proceedings of the 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies (ISABEL), Rome, Italy, 2010
- November 1, 2010
Authors: Simon O' Regan, Stephen Faul, Liam Marnane

The need for reliable detection of head movement artefacts in an ambulatory EEG system has been demonstrated in previous work. In this paper we propose the use of gyroscopes in detecting artefacts in EEG. A collection of features are extracted from the gyroscope signals and ranked using Mutual Information Evaluation Function. Linear Discriminant Analysis is subsequently used as a means of seperating between normal EEG and artefacts. A Support Vector Machine classifier is also applied to the gyroscope feature signals. Results indicate good separation between gyroscope features extracted from normal EEG and those extracted from artefacts arising from head movement, providing a strong argument for including gyroscope signals as features in the classification of head movement artefacts.
Parallel artefact rejection for epileptiform activity detection in routine EEG
- In Proceedings of the IEEE Engineering in Medicine and Biology Conference (EMBC), Boston, U.S.A., pages 7953– 7956. IEEE, 2011.
- September 1, 2011
Authors: Simon O' Regan, Daniel Kelleher, Andrey Temko, Brian McNamara, Derek Nash, Daniel Costello, Liam Marnane

The EEG signal is very often contaminated by electrical activity external to the brain. These artefacts make the accurate detection of epileptiform activity more difficult. A scheme developed to improve the detection of these artefacts (and hence epileptiform event detection) is introduced. A structure of parallel Support Vector Machine classifiers is assembled, one classifier tuned to perform the identification of epileptiform activity, the remainder trained for the detection of ocular and movement-related artefacts. This strategy enables an absolute reduction in false detection rate of 21.6% with the constraint of ensuring all epileptic events are recognized. Such a scheme is desirable given that sections of data which are heavily contaminated with artefact need not be excluded from analysis.
Automatic detection of EEG artefacts arising from head movements using EEG and gyroscope signals
- Medical Engineering and Physics
- September 27, 2012
Authors: Simon O' Regan

Contamination of EEG signals by artefacts arising from head movements has been a serious obstacle in the deployment of automatic neurological event detection systems in ambulatory EEG. In this paper, we present work on categorizing these head-movement artefacts as one distinct class and on using support vector machines to automatically detect their presence. The use of additional physical signals in detecting head-movement artefacts is also investigated by means of support vector machines classifiers implemented with gyroscope waveforms. Finally, the combination of features extracted from EEG and gyroscope signals is explored in order to design an algorithm which incorporates both physical and physiological signals in accurately detecting artefacts arising from head-movements.