Single-channel EEG Recordings Research Articles

Discriminating rapid eye movement sleep from wakefulness by analyzing high frequencies from single-channel EEG recordings in mice

Rapid eye movement sleep (REMS) is characterized by the appearance of fast, desynchronized rhythms in the cortical electroencephalogram (EEG), similar to wakefulness. The low electromyogram (EMG) amplitude during REMS distinguishes it from wakefulness; therefore, recording EMG signal seems to be imperative for discriminating between the two states. The present study evaluated the high frequency components of the EEG signal from mice (80–500 Hz) to support REMS detection during sleep scoring without an EMG signal and found a strong positive correlation between waking and the average power of 80–120 Hz, 120–200 Hz, 200–350 Hz and 350–500 Hz. A highly negative correlation was observed with REMS. Furthermore, our machine learning approach demonstrated that simple EEG time-series features are enough to discriminate REMS from wakefulness with sensitivity of roughly 98 percent and specificity of around 92 percent. Interestingly, assessing only the higher frequency bands (200–350 Hz as well as 350–500 Hz) gives significantly greater predictive power than assessing only the lower end of the EEG frequency spectrum. This paper proposes an approach that can detect subtle changes in REMS reliably, and future unsupervised sleep-scoring approaches could greatly benefit from it.

Detection of sleep apnea from single-channel electroencephalogram (EEG) using an explainable convolutional neural network (CNN).

Sleep apnea (SA) is a common disorder involving the cessation of breathing during sleep. It can cause daytime hypersomnia, accidents, and, if allowed to progress, serious, chronic conditions. Continuous positive airway pressure is an effective SA treatment. However, long waitlists impede timely diagnosis; overnight sleep studies involve trained technicians scoring a polysomnograph, which comprises multiple physiological signals including multi-channel electroencephalography (EEG). Therefore, it is important to develop simplified and automated approaches to detect SA. In the present study, we have developed an explainable convolutional neural network (CNN) to detect SA events from single-channel EEG recordings which generalizes across subjects. The network architecture consisted of three convolutional layers. We tuned hyperparameters using the Hyperband algorithm, optimized parameters using Adam, and quantified network performance with subjectwise 10-fold cross-validation. Our CNN performed with an accuracy of 69.9%, and a Matthews correlation coefficient (MCC) of 0.38. To explain the mechanisms of our trained network, we used critical-band masking (CBM): after training, we added bandlimited noise to test recordings; we parametrically varied the noise band center frequency and noise intensity, quantifying the deleterious effect on performance. We reconciled the effects of CBM with lesioning, wherein we zeroed the trained network’s 1st-layer filter kernels in turn, quantifying the deleterious effect on performance. These analyses indicated that the network learned frequency-band information consistent with known SA biomarkers, specifically, delta and beta band activity. Our results indicate single-channel EEG may have clinical potential for SA diagnosis.

Get rid of the beat in mobile EEG applications: A framework towards automated cardiogenic artifact detection and removal in single-channel EEG

Brain activity recordings outside clinical or laboratory settings using mobile EEG systems have gained popular interest allowing for realistic long-term monitoring and eventually leading to identification of possible biomarkers for diseases. The less obtrusive, minimized systems (e.g., single-channel EEG, no ECG reference) have the drawback of artifact contamination with varying intensity that are particularly difficult to identify and remove. We developed brMEGA, the first open-source algorithm for automated detection and removal of cardiogenic artifacts using non-linear time-frequency analysis and machine learning to (1) detect whether and where cardiogenic artifacts exist, and (2) remove those artifacts. We compare our algorithm against visual artifact identification and a previously established approach and validate it in one real and semi-real datasets. We demonstrated that brMEGA successfully identifies and substantially removes cardiogenic artifacts in single-channel EEG recordings. Moreover, recovery of cardiogenic artifacts, if present, gives the opportunity for future extraction of heart rate features without ECG measurement.

Comb filters for the removal of transcranial current stimulation artifacts from single channel EEG recordings

Abstract The combination of transcranial alternating current stimulation (tACS) and electroencephalogram (EEG) for mobile and home-based interventions offers the potential for control and adaptation of stimulation parameters. Yet, during stimulation, the EEG is heavily affected by stimulation artifacts. Spatial filters are often unsuited because too few channels are recorded and hardware capabilities are limited. Due to their speed and as they can be used for single channels, we explore the performance of single-channel weighted comb filters on artifact removal. At any given time point t, the recording r(t) is a superposition of a neurophysiological signal n(t), the stimulation artifact a(t) and noise e(t). Now, we can estimate the artifact a(t) based on the recording from an earlier (or later) time-point shifted by the artifacts period. A weighted estimate based on multiple time points has the potential to improve the signal recovery. Therefore, we explored several approaches and evaluated their performance on simulated and real data. The comb kernel filters were implemented in Matlab (https://github.com/agricolab/ARtACS) and Python (https://github.com/agricolab/pyARtACS), and the code is open access under an X11-license. We found that independent of the weighting function, all comb filters exhibit similarity in their suppression of the DC component, the artifacts frequency, and its harmonics. Yet, different weighting functions exhibit different pass-band performance, evident as ringing and amplification, and their induction of time-domain echoes. Interestingly, we note that a causal uniform filter is comparable to more complex approaches, while offering the option for real-time filtering. Comb filters are able to remove tACS artifacts even if only a single channel is available. As comb filters require no assumptions about the shape of the artifact, they might also be useful for filtering of non-sinusoidal, e.g. pulsed or saw-tooth, transcranial current stimulation.

Validation of an EEG seizure detection paradigm optimized for clinical use in a chronically implanted subcutaneous device

BackgroundMany electroencephalography (EEG) based seizure detection paradigms have been developed and validated over the last two decades. The majority of clinical approaches use scalp or intracranial EEG electrodes. Scalp EEG is limited by patient discomfort and short duration of useful EEG signals. Intracranial EEG involves an invasive surgical procedure associated with significant risk making it unsuitable for widespread use as a practical clinical biometric. A less invasive EEG monitoring approach, that is between invasive intracranial procedures and noninvasive methods, would fill the need of a safe, accurate, chronic (ultra-long term) and objective seizure detection method. We present validation of a continuous EEG seizure detection paradigm using human single-channel EEG recordings from subcutaneously placed electrodes that could be used to fulfill this need. MethodsTen-minute long sleep, awake and ictal EEG epochs obtained from 21 human subjects with subscalp electrodes and validated against simultaneous iEEG recordings were analyzed by three experienced clinical neurophysiologists. The 201subscalp EEG time series epochs where classified as diagnostic for awake, asleep, or seizure by the clinicians who were blinded to all other information. Seventy of the epochs were classified in this way as representing seizure activity. A subject specific seizure detection algorithm was trained and then evaluated offline for each patient in the data set using the expert consensus classification as the gold standard. ResultsThe average seizure detection performance of the algorithm across 21 subjects exceeded 90 % accuracy: 97 % sensitivity, 91 % specificity, and 93 % accuracy. For 19 of 21 patient datasets the algorithm achieved 100 % sensitivity. For 15 of 21 patients, the algorithm achieved 100 % specificity. For 13 of 21 patients the algorithm achieved 100 % accuracy. ComparisonNo comparable published methods are available for subgaleal EEG seizure detection. ConclusionsThese findings suggest that a simple seizure detection algorithm using subcutaneous EEG signals could provide sufficient accuracy and clinical utility for use in a low power, long-term subcutaneous brain monitoring device. Such a device would fill a need for a large number of people with epilepsy who currently have no means for accurately quantifying their seizures thereby providing important information to healthcare providers not currently available.

A Biometric System Based on Single-channel EEG Recording in One-second

In recent years, there are great research interests in using the Electroencephalogram (EEG) signals in biometrics applications. The strength of EEG signals as a biometric comes from its major fraud prevention capability. However, EEG signals are so sensitive, and many factors affect its usage as a biometric; two of these factors are the number of channels, and the required time for acquiring the signal; these factors affect the convenience and practicality. This study proposes a novel approach for EEG-based biometrics that optimizes the channels of acquiring data to only one channel. And the time to only one second. The results are compared against five commonly used classifiers named: KNN, Random Forest (RF), Support Vector Machine (SVM), Decision Tables (DT), and Naïve Bayes (NB). We test the approach on the public Texas data repository. The results prove the constancy of the approach for the eight minutes. The best result of the eyes-closed scenario is Average True Positive Rate (TPR) 99.1% and 98.2% for the eyes-opened. And it reaches 100% for multiple subjects.

Classification of emotions induced by horror and relaxing movies using single-channel EEG recordings

It has been observed from recent studies that corticolimbic Theta rhythm from EEG recordings perceived as fear or threatening scene during neural processing of visual stimuli. In additions, neural oscillations' patterns in Theta, Alpha and Beta sub-bands also play important role in brain's emotional processing. Inspired from these findings, in this paper we attempt to classify two different emotional states by analyzing single-channel EEG recordings. A video clip that can evoke 3 different emotional states: neutral, relaxation and scary is shown to 19 college-aged subjects and they were asked to score their emotional outcome by giving a number between 0 to 10 (where 0 means not scary at all and 10 means the most scary). First, recorded EEG data were preprocessed by stationary wavelet transform (SWT) based artifact removal algorithm. Then power distribution in simultaneous time-frequency domain was analyzed using short-time Fourier transform (STFT) followed by calculating the average power during each 0.2s time-segment for each brain sub-band. Finally, 46 features, as the mean power of frequency bands between 4 and 50 Hz during each time-segment, containing 689 instances\textemdash for each subject \textemdash were collected for classification. We found that relaxation and fear emotions evoked during watching scary and relaxing movies can be classified with average classification rate of 94.208\% using K-NN by applying methods and materials proposed in this paper. We also classified the dataset using SVM and we found out that K-NN classifier (when \begin{math} k=1 \end{math}) outperforms SVM in classifying EEG dynamics induced by horror and relaxing movies, however, for \begin{math} K >1 \end{math} in K-NN, SVM has better average classification rate.

0575 Sleep Monitoring with a Single Channel EEG Recorder in Patients with Psychiatric Disorders

Abstract Introduction The gold standard of sleep measurement has been laboratory polysomnography (PSG). However, electrodes and cables can cause discomfort, and exposure to an unfamiliar environment can cause the “first-night effect.” Difficulty falling asleep or maintaining sleep, poor sleep quality, and nightmares are some of the key clinical symptoms observed among individuals with psychiatric disorders. Those suffering from sleep disorders often present with symptoms of discontent with regard to sleep quality, timing, and quantity, and these symptoms have an adverse impact on function and quality of life. A minimally invasive technique would be preferable in patients with psychiatric disorders, who tend to be sensitive to environmental change. Accordingly, we evaluated the performance of a single-channel electroencephalography (EEG)-based sleep monitoring system in patients with psychiatric disorders. Methods Fifty-nine patients undergoing PSG were enrolled in this study. Single-channel EEG sleep monitoring was performed simultaneously with PSG. PSG and the EEG recordings were used to evaluate sleep parameters, such as total sleep time (TST), sleep efficiency, rapid eye movement (REM) sleep, light sleep (stages N1 and N2), and deep sleep (stage N3). Correlation analysis was used to evaluate the agreement on sleep parameters and attributing factors to the inaccuracies of the single-channel EEG recording. Results TST, sleep efficiency, REM sleep duration, and non-REM sleep duration of the single-channel EEG-based sleep monitoring showed a significant correlation with those of PSG. Lower sleep efficiency, a decrease in REM sleep, and increases in waking after sleep onset, arousal index, and apnea/hypopnea index were associated with the difference of sleep parameters between the two methods. Conclusion Among patients with psychiatric disorders who are sensitive to environmental change single-channel EEG sleep monitoring would be a useful technique to objectively evaluate sleep quality. Support Collaboration study with The KAITEKI Institute, Inc.

Removal of EOG artifacts from single channel EEG – An efficient model combining overlap segmented ASSA and ANC

Electroencephalogram (EEG) signals are mostly interfered by electrooculogram (EOG) artifacts. These artifacts degrade the performance of portable or wearable EEG recording systems. In this work, overlap segmented adaptive singular spectrum analysis (Ov-ASSA) combined with adaptive noise canceler (ANC) technique is presented for removal of EOG artifacts. Depending on the amplitude of the EEG signal, the first one or two reconstructed components of Ov-SSA technique are adaptively grouped and considered as a reference EOG signal for ANC in a single channel EEG recording system. In order to demonstrate the performance of the proposed technique, Matlab simulations are done on both synthetic and real EEG data. The synthetic EEG data is derived using the Markov Process Amplitude (MPA) EEG model. The performance metrics namely, RRMSE (relative root mean square error) and MAE (Mean Absolute Error) of proposed Ov-ASSA-ANC model outperformed the existing techniques. In addition to the removal of EOG artifacts, the proposed Ov-ASSA-ANC technique was also applied for seizure detection and an average accuracy of 98.05% was achieved.

Neonatal sleep stage identification using long short-term memory learning system.

Neonatal sleep analysis at the neonatal intensive care units (NICU) is critical for the diagnosis of any brain growth risks during the early stages of life. In this paper, an investigation is carried out on the use of a long short-term memory (LSTM) learning system in automatic sleep stage scoring in neonates. The developed algorithm automatically classifies sleep stages based on inputs from a single channel EEG recording. Up to this date, only a single study have developed an approach for automatic sleep stage scoring in neonatal sleep signals using deep neural network (DNN). A total of 5095 sleep stages signals acquired from EEG recordings of the University of Pittsburgh are used in this study. The sleep stages are annotated by a medical doctor from the Pediatric Neurology Department of Case Western Reserve University for three neonatal sleep stages including the awake (W), active sleep (AS), and quiet sleep (QS) stages on every 60-s epoch. The signals are pre-processed through normalization and filtering. The resulted signals are divided following 4-, 6-, and 10-fold cross-validation schemes. The training and classification process is done using a bi-directional LSTM network classifier built with pre-defined training parameters. At the end, the developed algorithm is evaluated along with a complete summary table that reports the results of this study and other state-of-the-art studies. The current study achieved high levels of Cohen's kappa (κ), accuracy, and F1 score with 91.37%, 96.81%, and 94.43%, respectively. Based on the confusion matrix, the overall true positives percentage reached 95.21%. The developed algorithm gave promising results in automatic sleep stage scoring in neonatal sleep signals. Future work include LSTM architecture and training parameters improvements to enhance the overall accuracy of the classifier.

Removal of muscle artefacts from few‐channel EEG recordings based on multivariate empirical mode decomposition and independent vector analysis

Electroencephalography (EEG) recordings are often contaminated by muscle artefacts. To address the problem, various methods have been proposed to suppress muscle artefacts from either multichannel or single-channel EEG recordings. However, there exist few studies for muscle artefact removal from few-channel EEG recordings. An effective solution for the few-channel situation by combining multivariate empirical mode decomposition (MEMD) with independent vector analysis (IVA), termed as MEMD-IVA, is proposed. The proposed method consists of two steps. MEMD is first utilised to decompose a few-channel EEG recording into intrinsic mode functions (IMFs) and then IVA is applied on the IMFs to separate sources related to muscle activity. The performance of the proposed method on simulated and real-life data is evaluated. The results demonstrated that MEMD-IVA outperforms other possible existing methods in a few-channel situation.

Automatic correction of short‐duration artefacts in single‐channel EEG recording: a group‐sparse signal denoising algorithm

A new algorithm for correcting short-duration artefacts in single-channel EEG recording is proposed here. A short-duration artefact has the characteristics of a group-sparse (GS) signal, i.e. a sparse signal in which its non-zero entries tend to concentrate in groups. Therefore, the problem of extracting a short-duration artefact from a recorded EEG data is formulated in the proposed algorithm as a denoising optimisation problem in which a penalty term is utilised to encourage the group sparsity of the estimated artefact. A quadratic penalty term is utilised in the proposed algorithm, and, hence, a closed-form solution is obtained in each iteration of the algorithm. In addition, a technique for automatic selection of the regularisation parameter, which controls the trade-off between the sparsity of the estimated artefact and its closeness to the measured EEG data, is also proposed. Simulation results on real and simulated EEG data show that the proposed algorithm can be successfully utilised to correct different kinds of short-duration artefacts in both single-channel and multichannel recordings. In addition, the proposed algorithm is also shown to produce significantly improved results compared to existing techniques used for performing similar tasks.

A preliminary study of muscular artifact cancellation in single-channel EEG.

Electroencephalogram (EEG) recordings are often contaminated with muscular artifacts that strongly obscure the EEG signals and complicates their analysis. For the conventional case, where the EEG recordings are obtained simultaneously over many EEG channels, there exists a considerable range of methods for removing muscular artifacts. In recent years, there has been an increasing trend to use EEG information in ambulatory healthcare and related physiological signal monitoring systems. For practical reasons, a single EEG channel system must be used in these situations. Unfortunately, there exist few studies for muscular artifact cancellation in single-channel EEG recordings. To address this issue, in this preliminary study, we propose a simple, yet effective, method to achieve the muscular artifact cancellation for the single-channel EEG case. This method is a combination of the ensemble empirical mode decomposition (EEMD) and the joint blind source separation (JBSS) techniques. We also conduct a study that compares and investigates all possible single-channel solutions and demonstrate the performance of these methods using numerical simulations and real-life applications. The proposed method is shown to significantly outperform all other methods. It can successfully remove muscular artifacts without altering the underlying EEG activity. It is thus a promising tool for use in ambulatory healthcare systems.

A low computational cost algorithm for REM sleep detection using single channel EEG.

The push towards low-power and wearable sleep systems requires using minimum number of recording channels to enhance battery life, keep processing load small and be more comfortable for the user. Since most sleep stages can be identified using EEG traces, enormous power savings could be achieved by using a single channel of EEG. However, detection of REM sleep from one channel EEG is challenging due to its electroencephalographic similarities with N1 and Wake stages. In this paper we investigate a novel feature in sleep EEG that demonstrates high discriminatory ability for detecting REM phases. We then use this feature, that is based on spectral edge frequency (SEF) in the 8–16 Hz frequency band, together with the absolute power and the relative power of the signal, to develop a simple REM detection algorithm. We evaluate the performance of this proposed algorithm with overnight single channel EEG recordings of 5 training and 15 independent test subjects. Our algorithm achieved sensitivity of 83%, specificity of 89% and selectivity of 61% on a test database consisting of 2221 REM epochs. It also achieved sensitivity and selectivity of 81 and 75% on PhysioNet Sleep-EDF database consisting of 8 subjects. These results demonstrate that SEF can be a useful feature for automatic detection of REM stages of sleep from a single channel EEG.Electronic supplementary materialThe online version of this article (doi:10.1007/s10439-014-1085-6) contains supplementary material, which is available to authorized users.

Removal of Muscle Artifacts from Single-Channel EEG Based on Ensemble Empirical Mode Decomposition and Multiset Canonical Correlation Analysis

Electroencephalogram (EEG) recordings are often contaminated with muscle artifacts. This disturbing muscular activity strongly affects the visual analysis of EEG and impairs the results of EEG signal processing such as brain connectivity analysis. If multichannel EEG recordings are available, then there exist a considerable range of methods which can remove or to some extent suppress the distorting effect of such artifacts. Yet to our knowledge, there is no existing means to remove muscle artifacts from single-channel EEG recordings. Moreover, considering the recently increasing need for biomedical signal processing in ambulatory situations, it is crucially important to develop single-channel techniques. In this work, we propose a simple, yet effective method to achieve the muscle artifact removal from single-channel EEG, by combining ensemble empirical mode decomposition (EEMD) with multiset canonical correlation analysis (MCCA). We demonstrate the performance of the proposed method through numerical simulations and application to real EEG recordings contaminated with muscle artifacts. The proposed method can successfully remove muscle artifacts without altering the recorded underlying EEG activity. It is a promising tool for real-world biomedical signal processing applications.

Hypnotic assessment based on the Recurrence Quantification Analysis of EEG recorded in the ordinary state of consciousness

The cerebral cortical correlates of the susceptibility to hypnosis in the ordinary states of consciousness have not been clarified. Aim of the study was to characterize the EEG dynamics of subjects with high (highs) and low hypnotisability (lows) through the non-linear method of Recurrence Quantification Analysis (RQA). The EEG of 16 males – 8 highs and 8 lows – was monitored for 1min without instructions other than keeping the eyes closed, being silent and avoiding movements (short resting), and during 15min of simple relaxation, that is with the instruction to relax at their best. Highs and lows were compared on the RQA measures of Determinism (DET) and Entropy (ENT), which are related to the signal determinism and complexity. In the short resting condition discriminant analysis could classify highs and lows on the basis of DET and ENT values at temporo-parietal sites. Many differences in DET and all differences in ENT disappeared during simple relaxation, although DET still separated the two groups in the earliest 6min of relaxation at temporo-parietal sites. Our RQA based approach allows to develop computer-based methods of hypnotic assessment using short-lasting, single channel EEG recordings analyzed through standard mathematical methods.

An algebraic method for eye blink artifacts detection in single channel EEG recordings

Event Abstract Back to Event An algebraic method for eye blink artifacts detection in single channel EEG recordings Zoran Tiganj1*, Mamadou Mboup2, Christophe Pouzat3 and Lotfi Belkoura4 1 Nord Europe, Projcet ALIEN, INRIA Lille , France 2 Université Paris Descartes, UFR Math-Info, France 3 Université Paris Descartes, Laboratoire de Physiologie Cérébral (CNRS UMR 8118), , France 4 Université des Sciences et Technologies de Lille, LAGIS (CNRS, UMR 8146) and Project Alien, INRIA Lille - Nord Europe, France Single-channel EEG systems are very useful in EEG based applications where real time processing, low computational complexity and low cumbersomeness are critical constrains. These include brain-computer-interface and biofeedback devices and also some clinical applications such as EEG recording on babies or Alzheimer's disease recognition. In this paper we address the problem of eye blink artifacts detection in such systems. We study an algebraic approach based on numerical differentiation, which is recently introduced from operational calculus. The occurrence of an artifact is modeled as an irregularity which appears explicitly in the time (generalized) derivative of the EEG signal as a delay. Manipulating such delay is easy with the operational calculus and it leads to a simple joint detection and localization algorithm. While the algorithm is devised based on continuous-time arguments, the final implementation step is fully realized in a discrete-time context, using very classical discrete-time FIR filters. The proposed approach is compared with three other approaches: (1) the very basic threshold approach, (2) the approach that combines the use of median filter, matched filter and nonlinear energy operator (NEO) and (3) the wavelet based approach. Comparison is done on: (a) the artificially created signal where the eye activity is synthesized from real EEG recordings and (b) the real single-channel EEG recordings from 32 different brain locations. Results are presented with Receiver Operating Characteristics curves. The results show that the proposed approach compares to the other approaches better or as good as, while having lower computational complexity with simple real time implementation. Comparison of the results on artificially created and real signal leads to conclusions that with detection techniques based on derivative estimation we are able to detect not only eye blink artifacts, but also any spike shaped artifact, even if it is very low in amplitude. Conference: Biomag 2010 - 17th International Conference on Biomagnetism , Dubrovnik, Croatia, 28 Mar - 1 Apr, 2010. Presentation Type: Poster Presentation Topic: MEG Modeling Citation: Tiganj Z, Mboup M, Pouzat C and Belkoura L (2010). An algebraic method for eye blink artifacts detection in single channel EEG recordings. Front. Neurosci. Conference Abstract: Biomag 2010 - 17th International Conference on Biomagnetism . doi: 10.3389/conf.fnins.2010.06.00064 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 22 Mar 2010; Published Online: 22 Mar 2010. * Correspondence: Zoran Tiganj, Nord Europe, Projcet ALIEN, INRIA Lille, Villeneuve d'Ascq, France, zoran.tiganj@gmail.com Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Zoran Tiganj Mamadou Mboup Christophe Pouzat Lotfi Belkoura Google Zoran Tiganj Mamadou Mboup Christophe Pouzat Lotfi Belkoura Google Scholar Zoran Tiganj Mamadou Mboup Christophe Pouzat Lotfi Belkoura PubMed Zoran Tiganj Mamadou Mboup Christophe Pouzat Lotfi Belkoura Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

Is your patient sleeping?

Is your patient sleeping?

KPCA denoising and the pre-image problem revisited

Kernel principal component analysis (KPCA) is widely used in classification, feature extraction and denoising applications. In the latter it is unavoidable to deal with the pre-image problem which constitutes the most complex step in the whole processing chain. One of the methods to tackle this problem is an iterative solution based on a fixed-point algorithm. An alternative strategy considers an algebraic approach that relies on the solution of an under-determined system of equations. In this work we present a method that uses this algebraic approach to estimate a good starting point to the fixed-point iteration. We will demonstrate that this hybrid solution for the pre-image shows better performance than the other two methods. Further we extend the applicability of KPCA to one-dimensional signals which occur in many signal processing applications. We show that artefact removal from such data can be treated on the same footing as denoising. We finally apply the algorithm to denoise the famous USPS data set and to extract EOG interferences from single channel EEG recordings.

Comparison of EEG monitoring techniques: An evaluation during cardiac surgery

A single channel EEG recording was made in 25 patients undergoing cardiac surgery and analysed using 5 different techniques — amplitude, cerebral function monitor, Fourier, Hjorth, and zero-crossing analyses. The results of the analyses were plotted as trend information on paper. These trends were studied for changes in the EEG during surgery. In the majority of cases changes were noted simultaneously by all 5 techniques. There were, however, some cases in which an amplitude-only technique showed no changes while frequency contributions were changing, and a frequency-only technique showed no changes while amplitudes were changing. The conclusion drawn is that major EEG changes are observed with any of the techniques studied, but that for improved sensitivity a technique analysing both frequency and amplitude information should be used.