Computerization of Fujimori's method of waveform recognition. A review and methodological considerations for its application to all-night sleep EEG

EEG Waveform Analysis of P300 ERP with Applications to Brain Computer Interfaces

The Electroencephalography (EEG) is not just a mere clinical tool anymore. It has become the de-facto mobile, portable, non-invasive brain imaging sensor to harness brain information in real time. It is now being used to translate or decode brain signals, to diagnose diseases or to implement Brain Computer Interface (BCI) devices. The automatic decoding is mainly implemented by using quantitative algorithms to detect the cloaked information buried in the signal. However, clinical EEG is based intensively on waveforms and the structure of signal plots. Hence, the purpose of this work is to establish a bridge to fill this gap by reviewing and describing the procedures that have been used to detect patterns in the electroencephalographic waveforms, benchmarking them on a controlled pseudo-real dataset of a P300-Based BCI Speller and verifying their performance on a public dataset of a BCI Competition.

Automated sleep staging of OSAs based on ICA preprocessing and consolidation of temporal correlations

An automated sleep staging based on analyzing long-range time correlations in EEG is proposed. These correlations, indicating time-scale invariant property or self-similarity at different time scales, are known to be salient dynamical characteristics of stage succession for a sleeping brain even when the subject suffers a destructive disorder such as Obstructive Sleep Apnea (OSA). The goal is to extract a set of complementary features from cerebral sources mapped onto the scalp electrodes or from a number of denoised EEG channels. For this purpose, source localization/extraction and noise reduction approaches based on Independent Component Analysis were used prior to correlation analysis. Feature extracted segments were then classified in one of the five classes including WAKE, STAGE1, STAGE2, SWS and REM via an ensemble neuro-fuzzy classifier. Some techniques were employed to improve the classifier's performance including Scaled Conjugate Gradient Method to speed up learning the ANFIS classifiers, a pruning algorithm to eliminate irrelevant fuzzy rules and the 10-fold cross-validation technique to train and test the system more efficiently. The performance of classification for two strategies including (1) feature extraction from effective cerebral sources and (2) feature extraction from selected channels of denoised EEG signals was compared and contrasted in terms of training errors and test accuracies. The first and second strategies achieved 92.23 and 88.74% agreement with human expert respectively which indicates the effectiveness of the staging system based on cerebral sources of activity. Our results further indicate that the misclassification rates were almost below 10%. The proposed automated sleep staging system is reliable due to the fact that it is based on the underlying dynamics of sleep staging which is less likely to be affected by sleep fragmentations occurred repeatedly in OSA.

A computer method for identifying patterns in electroencephalogram signals

A computer method is developed for identifying patterns in electroencephalogram (EEG) signals. An EEG numerical signal is transformed into a symbolic series. The simple transformation used here studies the variations between two successive values of the signal. Then, this series is analysed with a symbolic correlation function based on probabilities without bias. The use of large windows, e.g. 1 hour, allows the identification of weak signals hidden by the specific ones. An application of this method to the sleep analysis of a healthy adult shows a periodicity modulo 10 in all derivations. A possible neurophysiological meaning is presented in the discussion.

Automated sleep stage scoring using hybrid rule- and case-based reasoning

We propose an automated method for sleep stage scoring using hybrid rule- and case-based reasoning. The system first performs rule-based sleep stage scoring, according to the Rechtschaffen and Kale's sleep-scoring rule (1968), and then supplements the scoring with case-based reasoning. This method comprises signal processing unit, rule-based scoring unit, and case-based scoring unit. We applied this methodology to three recordings of normal sleep and three recordings of obstructive sleep apnea (OSA). Average agreement rate in normal recordings was 87.5% and case-based scoring enhanced the agreement rate by 5.6%. This architecture showed several advantages over the other analytical approaches in sleep scoring: high performance on sleep disordered recordings, the explanation facility, and the learning ability. The results suggest that combination of rule-based reasoning and case-based reasoning is promising for an automated sleep scoring and it is also considered to be a good model of the cognitive scoring process.

A comparison of period amplitude analysis and FFT power spectral analysis of all-night human sleep EEG

Zero-cross and zero-derivative period amplitude analysis (PAA) data were compared with power spectral analysis (PSA) data obtained with the fast Fourier transform in all-night sleep EEG from 10 subjects. Although PAA zero-cross-integrated amplitude showed good agreement with PSA power in 0.3-2 Hz, zero-cross analysis appears relatively ineffective in measuring 2-4 Hz and above waves. However, PAA zero-derivative measures of peak-trough amplitude correlated well with PSA power in 2-4 Hz. Thus, while PAA appears able to measure the entire EEG spectrum, the analytic technique should be changed from zero cross to zero derivative at about 2 Hz in human sleep EEG. PAA and PSA both demonstrate robust and interrelated across-night oscillations in three frequency bands: delta (0.3-4 Hz); sigma (12-16 Hz); and fast beta (20-10 Hz). The frequencies between delta and sigma, and between sigma and fast beta, did not show clear across-night oscillations using either method, and the two methods showed lower epoch-to-epoch agreement in these intermediate bands. The causes of this reduced agreement are not immediately clear, nor is it obvious which method gives more valid results. We believe that the three strongly oscillating frequency bands represent fundamental properties of the human sleep EEG that provide important clues to underlying physiological mechanisms. These mechanisms are more likely to be understood if their dynamic properties are preserved and measured naturalistically rather than being forced into arbitrary sleep stages or procrustean models. Both PAA and PSA can be employed for such naturalistic studies. PSA has the advantages of applying the same analytic method across the EEG spectrum and rests on more fully developed theory. Combined zero-cross and zero-derivative PAA demonstrates EEG oscillations that closely parallel those observed with spectral power, and the PAA measures do not rely on assumptions about the spectral composition of the signal. In addition, both PAA techniques can measure the relative contributions of wave amplitude and incidence to total power: These waveform characteristics represent different biological processes and respond differentially to a wide range of experimental conditions.

Alpha-delta sleep in a case with non-24 h sleep-wake syndrome: quantitative electroencephalogram analysis of alpha and delta band waves

Four all-night polysomnograms of a 39-year-old male patient with non-24 h sleep-wake syndrome were recorded. We analysed electroencephalograms (EEG) with the power spectrum method and the wave pattern recognition analysis of Fujimori. The EEG of the rest waking condition showed normal patterns. High-voltage diffuse alpha band waves were observed in sleep stages 2, 3 and 4. The integrated area of the alpha band waves in the analysis epochs showed a strong positive correlation to the delta band components in the power spectrum of the same epoch during sleep (correlation coefficients r = 0.762-0.815). Alpha band waves during sleep were clearly different from the alpha waves in the rest waking condition, with respect to slower peak frequency and the frontal dominant voltage distribution.

Past and future of computer-assisted sleep analysis and drowsiness assessment

The development of computerized sleep analysis has been very much technology-driven by both mathematical tools and available hardware but, additionally and unfortunately, by the almost-30-year-old standard used for manual sleep stage scoring of paper recordings. There are no technical restrictions in terms of computing power, storage space, and costs anymore. However, the standards of visual sleep stage scoring have proven insufficient and ambiguous, and their utilization evidently provides misleading and erroneous information. The low temporal resolution provided by the one-page epoch, the crude division of the sleep processes into a few discrete stages, and the total ignorance of spatial information are the major drawbacks. It is meaningless to try to improve the computerised systems if the algorithms are based on erroneous concepts. Instead, the focus should be changed to studies dealing with the identification and modelling of true biological sleep-related processes. This work cannot be performed without the successful application of computerized methods, some of which have been used in related fields but have not yet been applied to sleep studies. It is extremely important that basic findings are confirmed with a wide variety of methods in several laboratories. The use of predetermined, fixed criteria for methods, waveforms, and states too early is scientifically erroneous and hazardous. Instead standards should describe the minimum requirements for the recording and analysis of the signals in terms of sampling rate, dynamic range, linearity, and documentation of the methods used. With the development of better technology, these standards ought to be constantly reevaluated and modified. The development toward more open commercial digital systems, including standardized programming methods and data formats, would have great positive impact to the field. These trends have long been established in many other fields of industry.