基于支持向量多分类机的多类复杂手操作EEG信号模式识别

针对用于服务机器人的脑机接口系统中脑电信号模式识别精度不高,不能满足机器人多任务要求的问题,提出一种基于C-支持向量多分类机的多类复杂手操作EEG信号模式识别方法,并将其应用到复杂手操作的EEG信号模式识别试验中,实现一个4类复杂手操作的模式识别,实验结果表明,与之前用BP神经网络进行识别相比,识别率由85%提高到了90%。

Artefact detection and removal algorithms for EEG diagnostic systems

The electroencephalogram (EEG) is a medical technology that is used in the monitoring of the brain and in the diagnosis of many neurological illnesses. Although coarse in its precision, the EEG is a non-invasive tool that requires minimal set-up times, and is suitably unobtrusive and mobile to allow continuous monitoring of the patient, either in clinical or domestic environments. Consequently, the EEG is the current tool-of-choice with which to continuously monitor the brain where temporal resolution, ease-of- use and mobility are important. Traditionally, EEG data are examined by a trained clinician who identifies neurological events of interest. However, recent advances in signal processing and machine learning techniques have allowed the automated detection of neurological events for many medical applications. In doing so, the burden of work on the clinician has been significantly reduced, improving the response time to illness, and allowing the relevant medical treatment to be administered within minutes rather than hours. However, as typical EEG signals are of the order of microvolts (μV ), contamination by signals arising from sources other than the brain is frequent. These extra-cerebral sources, known as artefacts, can significantly distort the EEG signal, making its interpretation difficult, and can dramatically disimprove automatic neurological event detection classification performance. This thesis therefore, contributes to the further improvement of auto- mated neurological event detection systems, by identifying some of the major obstacles in deploying these EEG systems in ambulatory and clinical environments so that the EEG technologies can emerge from the laboratory towards real-world settings, where they can have a real-impact on the lives of patients. In this context, the thesis tackles three major problems in EEG monitoring, namely: (i) the problem of head-movement artefacts in ambulatory EEG, (ii) the high numbers of false detections in state-of-the-art, automated, epileptiform activity detection systems and (iii) false detections in state-of-the-art, automated neonatal seizure detection systems. To accomplish this, the thesis employs a wide range of statistical, signal processing and machine learning techniques drawn from mathematics, engineering and computer science. The first body of work outlined in this thesis proposes a system to automatically detect head-movement artefacts in ambulatory EEG and utilises supervised machine learning classifiers to do so. The resulting head-movement artefact detection system is the first of its kind and offers accurate detection of head-movement artefacts in ambulatory EEG. Subsequently, addtional physiological signals, in the form of gyroscopes, are used to detect head-movements and in doing so, bring additional information to the head- movement artefact detection task. A framework for combining EEG and gyroscope signals is then developed, offering improved head-movement arte- fact detection. The artefact detection methods developed for ambulatory EEG are subsequently adapted for use in an automated epileptiform activity detection system. Information from support vector machines classifiers used to detect epileptiform activity is fused with information from artefact-specific detection classifiers in order to significantly reduce the number of false detections in the epileptiform activity detection system. By this means, epileptiform activity detection which compares favourably with other state-of-the-art systems is achieved. Finally, the problem of false detections in automated neonatal seizure detection is approached in an alternative manner; blind source separation techniques, complimented with information from additional physiological signals are used to remove respiration artefact from the EEG. In utilising these methods, some encouraging advances have been made in detecting and removing respiration artefacts from the neonatal EEG, and in doing so, the performance of the underlying diagnostic technology is improved, bringing its deployment in the real-world, clinical domain one step closer.

Neonatal EEG classification using atomic decomposition

The electroencephalogram (EEG) is an important noninvasive tool used in the neonatal intensive care unit (NICU) for the neurologic evaluation of the sick newborn infant. It provides an excellent assessment of at-risk newborns and formulates a prognosis for long-term neurologic outcome.The automated analysis of neonatal EEG data in the NICU can provide valuable information to the clinician facilitating medical intervention. The aim of this thesis is to develop a system for automatic classification of neonatal EEG which can be mainly divided into two parts: (1) classification of neonatal EEG seizure from nonseizure, and (2) classifying neonatal background EEG into several grades based on the severity of the injury using atomic decomposition. Atomic decomposition techniques use redundant time-frequency dictionaries for sparse signal representations or approximations. The first novel contribution of this thesis is the development of a novel time-frequency dictionary coherent with the neonatal EEG seizure states. This dictionary was able to track the time-varying nature of the EEG signal. It was shown that by using atomic decomposition and the proposed novel dictionary, the neonatal EEG transition from nonseizure to seizure states could be detected efficiently. The second novel contribution of this thesis is the development of a neonatal seizure detection algorithm using several time-frequency features from the proposed novel dictionary. It was shown that the time-frequency features obtained from the atoms in the novel dictionary improved the seizure detection accuracy when compared to that obtained from the raw EEG signal. With the assistance of a supervised multiclass SVM classifier and several timefrequency features, several methods to automatically grade EEG were explored. In summary, the novel techniques proposed in this thesis contribute to the application of advanced signal processing techniques for automatic assessment of neonatal EEG recordings.

Frontal EEG/ERP correlates of attentional processes, cortisol and motivational states in adolescents from lower and higher socioeconomic status

Event-related potentials (ERPs) and other electroencephalographic (EEG) evidence show that frontal brain areas of higher and lower socioeconomic status (SES) children are recruited differently during selective attention tasks. We assessed whether multiple variables related to self-regulation (perceived mental effort) emotional states (e.g., anxiety, stress, etc.) and motivational states (e.g., boredom, engagement, etc.) may co-occur or interact with frontal attentional processing probed in two matched-samples of fourteen lower-SES and higher-SES adolescents. ERP and EEG activation were measured during a task probing selective attention to sequences of tones. Pre- and post-task salivary cortisol and self-reported emotional states were also measured. At similar behavioural performance level, the higher-SES group showed a greater ERP differentiation between attended (relevant) and unattended (irrelevant) tones than the lower-SES group. EEG power analysis revealed a cross-over interaction, specifically, lower-SES adolescents showed significantly higher theta power when ignoring rather than attending to tones, whereas, higher-SES adolescents showed the opposite pattern. Significant theta asymmetry differences were also found at midfrontal electrodes indicating left hypo-activity in lower-SES adolescents. The attended vs. unattended difference in right midfrontal theta increased with individual SES rank, and (independently from SES) with lower cortisol task reactivity and higher boredom. Results suggest lower-SES children used additional compensatory resources to monitor/control response inhibition to distracters, perceiving also more mental effort, as compared to higher-SES counterparts. Nevertheless, stress, boredom and other task-related perceived states were unrelated to SES. Ruling out presumed confounds, this study confirms the midfrontal mechanisms responsible for the SES effects on selective attention reported previously and here reflect genuine cognitive differences.

Cognitive and task-related EEG correlates of arithmetic performance in adolescents

Cognitive and neurophysiological correlates of arithmetic calculation, concepts, and applications were examined in 41 adolescents, ages 12-15 years. Psychological and task-related EEG measures which correctly distinguished children who scored low vs. high (using a median split) in each arithmetic subarea were interpreted as indicative of processes involved. Calculation was related to visual-motor sequencing, spatial visualization, theta activity measured during visual-perceptual and verbal tasks at right- and left-hemisphere locations, and right-hemisphere alpha activity measured during a verbal task. Performance on arithmetic word problems was related to spatial visualization and perception, vocabulary, and right-hemisphere alpha activity measured during a verbal task. Results suggest a complex interplay of spatial and sequential operations in arithmetic performance, consistent with processing model concepts of lateralized brain function.

EEG decoding of semantic category reveals distributed representations for single concepts

Achieving a clearer picture of categorial distinctions in the brain is essential for our understanding of the conceptual lexicon, but much more fine-grained investigations are required in order for this evidence to contribute to lexical research. Here we present a collection of advanced data-mining techniques that allows the category of individual concepts to be decoded from single trials of EEG data. Neural activity was recorded while participants silently named images of mammals and tools, and category could be detected in single trials with an accuracy well above chance, both when considering data from single participants, and when group-training across participants. By aggregating across all trials, single concepts could be correctly assigned to their category with an accuracy of 98%. The pattern of classifications made by the algorithm confirmed that the neural patterns identified are due to conceptual category, and not any of a series of processing-related confounds. The time intervals, frequency bands and scalp locations that proved most informative for prediction permit physiological interpretation: the widespread activation shortly after appearance of the stimulus (from 100. ms) is consistent both with accounts of multi-pass processing, and distributed representations of categories. These methods provide an alternative to fMRI for fine-grained, large-scale investigations of the conceptual lexicon. © 2010 Elsevier Inc.

Análise da sonolência na condução rodoviária a partir de sinais EEG

A Sociedade Europeia de Pesquisa do Sono realizou muito recentemente um estudo, onde mostrou que a prevalência média de adormecimento ao volante nos últimos 2 anos foi de 17%. Além disto, tem sido provado por todo o mundo que a sonolência durante a condução é uma das principais causas de acidentes de trânsito. Torna-se assim conveniente, o desenvolvimento de sistemas que analisem a suscetibilidade de um determinado condutor para adormecer no trânsito, bem como de ferramentas que monitorem em tempo real o estado físico e mental do condutor, para alertarem nos momentos críticos. Apesar do estudo do sono se ter iniciado há vários anos, a maioria das investigações focaram-se no ciclo normal do sono, estudando os indivíduos de forma relaxada e de olhos fechados. Só mais recentemente, têm surgido os estudos que se focam nas situações de sonolência em atividade, como _e o caso da condução. Uma grande parte Dos estudos da sonolência em condução têm utilizado a eletroencefalografia (EEG), de forma a perceber se existem alterações nas diferentes bandas de frequência desta, que possam indicar o estado de sonolência do condutor. Além disso, a evolução da sonolência a partir de alterações no piscar dos olhos (que podem ser vistas nos sinais EEG) também tem sido alvo de grande pesquisa, tendo vindo a revelar resultados bastante promissores. Neste contexto e em parceria com a empresa HealthyRoad, esta tese está integrada no projeto HealthyDrive, que visa o desenvolvimento de um sistema de alerta e deteção de sinais de fadiga e sonolência nos condutores de veículos automóveis. A contribuição desta tese no projeto prendeu-se com o estudo da sonolência dos indivíduos em condução a partir de sinais EEG, para desta forma investigar possíveis indicadores dos diferentes níveis desta que possam ser utilizados pela empresa no projeto. Foram recolhidos e analisados 17 sinais EEG de indivíduos em simulação de condução. Além disso foram desenvolvidos dois métodos de análise destes sinais: O primeiro para a deteção e análise dos piscar de olhos a partir de EEG, o segundo para análise do espetro de potência. Ambos os métodos foram utilizados para analisar os sinais recolhidos e investigar que tipo de relação existe entre a sonolência do condutor e as alterações nos piscares dos olhos, bem como as alterações do espetro do EEG. Os resultados mostraram uma correlação entre a duração do piscar de olhos e a sonolência do condutor. Com o aumento da sonolência velicou-se um aumento da duração do piscar, desencadeado principalmente pelo aumento na duração de fecho, que chegou aos 51.2%. Em relação ao espectro de potência, os resultados sugerem que a potência relativa de todas as bandas analisadas fornecem informações relevantes sobre a sonolência do condutor. Além disso, o parâmetro (_+_)/_ demostrou estar relacionado com variações da sonolência, diminuindo com o seu avanço e aumentando significativamente (111%) no instante em que os condutores adormeceram.