M ultichannel A nalysis of the N ewborn EEG D ata Vaclav Gerla*, Lenka Lhotska*, Member, IEEE, Vladimir Krajca**, Karel Paul*** * Czech Technical University.

Slides:



Advertisements
Similar presentations
Copyright Compumedics Limited
Advertisements

Air Force Technical Applications Center 1 Subspace Based Three- Component Array Processing Gregory Wagner Nuclear Treaty Monitoring Geophysics Division.
Detection, segmentation and classification of heart sounds
An Approach to ECG Delineation using Wavelet Analysis and Hidden Markov Models Maarten Vaessen (FdAW/Master Operations Research) Iwan de Jong (IDEE/MI)
Classification of Sleep EEG Václav Gerla cvut
Semi-invasive biopotential & activity in rodents.
Visualization of dynamic power and synchrony changes in high density EEG A. Alba 1, T. Harmony2, J.L. Marroquín 2, E. Arce 1 1 Facultad de Ciencias, UASLP.
Supervised Learning Recap
D ECOUPLING THE C ORTICAL P OWER S PECTRUM Real-Time Representation of Finger Movements 1.
Introduction The aim the project is to analyse non real time EEG (Electroencephalogram) signal using different mathematical models in Matlab to predict.
Pre-processing for EEG and MEG
Artifact (artefact) reduction in EEG – and a bit of ERP basics CNC, 19 November 2014 Jakob Heinzle Translational Neuromodeling Unit.
Accelerometer-based Transportation Mode Detection on Smartphones
Multiple Criteria for Evaluating Land Cover Classification Algorithms Summary of a paper by R.S. DeFries and Jonathan Cheung-Wai Chan April, 2000 Remote.
“Real-time” Transient Detection Algorithms Dr. Kang Hyeun Ji, Thomas Herring MIT.
Standard electrode arrays for recording EEG are placed on the surface of the brain. Detection of High Frequency Oscillations Using Support Vector Machines:
Automatic Annotation of Actigraphy Data for Sleep Disorders Diagnosis Purposes 32nd Annual International Conference of the IEEE Engineering in Medicine.
Body Sensor Networks to Evaluate Standing Balance: Interpreting Muscular Activities Based on Intertial Sensors Rohith Ramachandran Lakshmish Ramanna Hassan.
Speaker Adaptation for Vowel Classification
A commonly used feature to discriminate between hand and foot movements is the variance of the EEG signal at certain electrodes. To this end, one calculates.
Artificial Intelligence Techniques
Dan Simon Cleveland State University
1 QRS Detection Section Linda Henriksson BRU/LTL.
Final Project Classification of Sleep data Akane Sano Affective Computing Group Media Lab.
EE513 Audio Signals and Systems Statistical Pattern Classification Kevin D. Donohue Electrical and Computer Engineering University of Kentucky.
ERP DATA ACQUISITION & PREPROCESSING EEG Acquisition: 256 scalp sites; vertex recording reference (Geodesic Sensor Net)..01 Hz to 100 Hz analogue filter;
TIME SERIES by H.V.S. DE SILVA DEPARTMENT OF MATHEMATICS
1 Methods for detection of hidden changes in the EEG H. Hinrikus*, M.Bachmann*, J.Kalda**, M.Säkki**, J.Lass*, R.Tomson* *Biomedical Engineering Center.
Automatic Ballistocardiogram (BCG) Beat Detection Using a Template Matching Approach Adviser: Ji-Jer Huang Presenter: Zhe-Lin Cai Date:2014/12/24 30th.
Department of Computer and Electrical Engineering A Study of Time-based Features and Regularity of Manipulation to Improve the Detection of Eating Activity.
Experimental Results ■ Observations:  Overall detection accuracy increases as the length of observation window increases.  An observation window of 100.
Functional Brain Signal Processing: EEG & fMRI Lesson 4
Quick EEG facts Physicians use the EEG to aid in the diagnosis of : epilepsy, cerebral tumors, encephalitis, and stroke EEG usage was first documented.
Authors: Sriram Ganapathy, Samuel Thomas, and Hynek Hermansky Temporal envelope compensation for robust phoneme recognition using modulation spectrum.
Ensemble Methods: Bagging and Boosting
ECE 8443 – Pattern Recognition LECTURE 10: HETEROSCEDASTIC LINEAR DISCRIMINANT ANALYSIS AND INDEPENDENT COMPONENT ANALYSIS Objectives: Generalization of.
Spam Detection Ethan Grefe December 13, 2013.
Analysis of Movement Related EEG Signal by Time Dependent Fractal Dimension and Neural Network for Brain Computer Interface NI NI SOE (D3) Fractal and.
Using Feed Forward NN for EEG Signal Classification Amin Fazel April 2006 Department of Computer Science and Electrical Engineering University of Missouri.
J.-Y. Yang, J.-S. Wang and Y.-P. Chena, Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural.
Boundary Detection in Tokenizing Network Application Payload for Anomaly Detection Rachna Vargiya and Philip Chan Department of Computer Sciences Florida.
Classification (slides adapted from Rob Schapire) Eran Segal Weizmann Institute.
Team Dogecoin: An Experience in Predicting Hospital Readmissions Acknowledgements The Problem Hospitals in the UK must keep track of which patients, once.
Dr. Galal Nadim.  The root-MUltiple SIgnal Classification (root- MUSIC) super resolution algorithm is used for indoor channel characterization (estimate.
Face Image-Based Gender Recognition Using Complex-Valued Neural Network Instructor :Dr. Dong-Chul Kim Indrani Gorripati.
Chapter 20 Classification and Estimation Classification – Feature selection Good feature have four characteristics: –Discrimination. Features.
Sleep Stage Identification Jessie Y. Shen February 17, 2004.
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition LECTURE 12: Advanced Discriminant Analysis Objectives:
Principal components analysis (PCA) as a tool for identifying EEG frequency bands: I. Methodological considerations and preliminary findings Jürgen Kayser,
Distinguishing humans from robots in web search logs preliminary results using query rates and intervals Omer Duskin Dror G. Feitelson School of Computer.
Abstract Automatic detection of sleep state is an important queue in accurate detection of sleep conditions. The analysis of EEGs is a difficult time-consuming.
Chapter 15: Classification of Time- Embedded EEG Using Short-Time Principal Component Analysis by Nguyen Duc Thang 5/2009.
Next, this study employed SVM to classify the emotion label for each EEG segment. The basic idea is to project input data onto a higher dimensional feature.
CLASSIFICATION OF ECG SIGNAL USING WAVELET ANALYSIS
A WEB PLATFORM FOR ANALYSIS OF MULTIVARIATE HETEROGENEOUS BIOMEDICAL TIME - SERIES - A PRELIMINARY REPORT Alan Jovic, Davor Kukolja, Kresimir Jozic, Marko.
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
Face Detection EE368 Final Project Group 14 Ping Hsin Lee
LECTURE 11: Advanced Discriminant Analysis
Fig. 1. proFIA approach for peak detection and quantification
QRS Detection Linda Henriksson 1.
Automatic Sleep Stage Classification using a Neural Network Algorithm
New approaches to sleep monitoring
Detecting Artifacts and Textures in Wavelet Coded Images
Blind Signal Separation using Principal Components Analysis
Volume 69, Issue 3, Pages (February 2011)
klinické neurofyziologie
AN ANALYSIS OF TWO COMMON REFERENCE POINTS FOR EEGS
Perceptual Echoes at 10 Hz in the Human Brain
EE513 Audio Signals and Systems
Machine Learning for Visual Scene Classification with EEG Data
Presentation transcript:

M ultichannel A nalysis of the N ewborn EEG D ata Vaclav Gerla*, Lenka Lhotska*, Member, IEEE, Vladimir Krajca**, Karel Paul*** * Czech Technical University - Department of Cybernetics, Prague - Czech Republic ** University Hospital Na Bulovce, Prague - Czech Republic *** Care of Mother and Child, Prague - Czech Republic

O ur R esearch P urpose Biological Signals Feature Extraction / Selection Classifier 1 Classifier N … Classifier 2 Visualisation Optimalization Classifiers Combining EEG, ECG, EOG, EMG, PNG Mainly FFT/Wavelets Various type of classifiers: Linear Models, Neural Networks, Kernel Methods, Mixture Models, … Weighted Average, Bagging, Boosting, Shafer approach, Fuzzy Integral, BKS * We solve problem of feature extraction and we compare various classifiers in this study Visualisation in all stages of this process

Motivation, approach usability online monitoring estimation of the newborn brain maturity In this study we use data: from 12 infants // 3 hours for each provided by the Institute for Care of Mother and Child in Prague Data are evaluated and scored by expert into 4 stages: quiet sleep active sleep wake movement artefact M otivation, U sed D ata proportion of these states is a significant indicator in clinical practice!

S ystem S tructure learning by EM PSD (band 0.5-3Hz) EEG, 8 channels PNG (respiration) measure of regularity ECG beat frequency EOG PSD (1-2Hz) EMG standart deviation 8 features HMM nearest neighbourcluster analysisdecision rules F1 F2 F3 features centering + Principal Component Analysis (12 features 3 features)

S egmentation EEG

EEG F eature E xtraction - classification obtained by doctor - record length = 85 minutes - features based on PSD - compute for each EEG channel - delta band is shown here (0.5 to 3Hz) - for subsequent processing we use these 8 characteristics - simple classification procedure example - used EEG signal only - based on proportion between activities in the different EEG channels (e.g.T3+T4/C3+C4)

EEG F eature E xtraction - PSD for other newborns signal - blue color = minimum & red color = maximum - maximum is in central electrodes (C3, C4)

R egularity of R espiration C urve - We utilize the strong regularity in quite sleep => autocorrelation analysis - clear difference in the magnitude of the second peak in the autocorrelation function - we use average breath duration for second peak position estimation

R egularity of R espiration C urve - characteristics for other newborns - it is no possible find one value for classification threshold - but it is good for doctors (as additional information )

E ye M ovements - we detect eye movements - derived from EOG signal Algorithm: 1. filter signal to freq. band 1-2Hz 2. compute STDs in small windows Utilized fact: In the quiet sleep there should not be any eye movements!

EMG A ctivity - obtained from chin EMG signal - computed STD of this signal - feature useful for movement artifact detection - we compute mean value for small window (removing peaks) and than we find maximum for bigger windows (trend enforcement) Utilized fact: Large majority of movement artifacts are present at EMG signal (characterized by the very high amplitude)

EMG A ctivity - muscles activity for other newborns - not present in quiet sleep

H eart R ate - derived from ECG - used standard method for QRS position detection based on first derivation - we detect maximum of R-peak The amplitude and the regularity of heart rate is changed during sleep!

H eart R ate - heart rate characteristics for other newborns - slow changes are visible - heart rate is lower in quiet sleep

P rincipal C omponent A nalysis reduce the number of dimensions without significant loss of information original features are very correlated -> PCA saves classification time PCA

H idden M arkov M odels in our case, HMMs allow us to describe relations between all features and hidden states (all sleep stages) we use the EM algorithm for finding the maximum-likelihood estimate of the parameters of HMMs choise of initial model is crucial - we compute it from the training data set mutual relations between individual hidden states

R esults Accuracy of classification: 2. We used data from 11 newborns for learning and data from remaining one newborn for testing. This procedure we repeated for all newborns and computed mean value. 1. We used all data from 12 newborns and cross-validation (10 group)

C onclusion our final accuracy obtained was about 70% on unknown data set compared with physician (evalution accuracy of physician is about 80%) very illustrative is to show final decision together with all described characteristics (we can see significant trends during sleep) during automated classification we have problem with clear separation of stages wake and active sleep. Now we try to find hidden information enabling this separation our designed technique can be applicable to other similar problem in medicine as well

in our further research we plan to develop methods for quantification that can help in evaluation of newborns brain maturity we expected increasing of accuracy and robustness by the combining all described classifiers. We plan use methods as bagging and boosting F uture W ork we plan to use similar methods for classification of sleep in adults we have developed hardware solution for on-line measuring of EEG (now we concentrate on the pda based analysis methods)

T hank you for your A ttention