Chih-Sheng Huang

A Spatial–Contextual Support Vector Machine for Remotely Sensed Image Classification

Recent studies show that hyperspectral image classification techniques that use both spectral and spatial information are more suitable, effective, and robust than those that use only spectral information. Using a spatial-contextual term, this study modifies the decision function and constraints of a support vector machine (SVM) and proposes two kinds of spatial-contextual SVMs for hyperspectral image classification. One machine, which is based on the concept of Markov random fields (MRFs), uses the spatial information in the original space (SCSVM). The other machine uses the spatial information in the feature space (SCSVMF), i.e., the nearest neighbors in the feature space. The SCSVM is better able to classify pixels of different class labels with similar spectral values and deal with data that have no clear numerical interpretation. To evaluate the effectiveness of SCSVM, the experiments in this study compare the performances of other classifiers: an SVM, a context-sensitive semisupervised SVM, a maximum likelihood (ML) classifier, a Bayesian contextual classifier based on MRFs (ML_MRF), and nearest neighbor classifier. Experimental results show that the proposed method achieves good classification performance on famous hyperspectral images (the Indian Pine site (IPS) and the Washington, DC mall data sets). The overall classification accuracy of the hyperspectral image of the IPS data set with 16 classes is 95.5%. The kappa accuracy is up to 94.9%, and the average accuracy of each class is up to 94.2%.

Knowledge-based identification of sleep stages based on two forehead electroencephalogram channels

Sleep quality is important, especially given the considerable number of sleep-related pathologies. The distribution of sleep stages is a highly effective and objective way of quantifying sleep quality. As a standard multi-channel recording used in the study of sleep, polysomnography (PSG) is a widely used diagnostic scheme in sleep medicine. However, the standard process of sleep clinical test, including PSG recording and manual scoring, is complex, uncomfortable, and time-consuming. This process is difficult to implement when taking the whole PSG measurements at home for general healthcare purposes. This work presents a novel sleep stage classification system, based on features from the two forehead EEG channels FP1 and FP2. By recording EEG from forehead, where there is no hair, the proposed system can monitor physiological changes during sleep in a more practical way than previous systems. Through a headband or self-adhesive technology, the necessary sensors can be applied easily by users at home. Analysis results demonstrate that classification performance of the proposed system overcomes the individual differences between different participants in terms of automatically classifying sleep stages. Additionally, the proposed sleep stage classification system can identify kernel sleep features extracted from forehead EEG, which are closely related with sleep clinicians expert knowledge. Moreover, forehead EEG features are classified into five sleep stages by using the relevance vector machine. In a leave-one-subject-out cross validation analysis, we found our system to correctly classify five sleep stages at an average accuracy of 76.7 ± 4.0 (SD) % [average kappa 0.68 ± 0.06 (SD)]. Importantly, the proposed sleep stage classification system using forehead EEG features is a viable alternative for measuring EEG signals at home easily and conveniently to evaluate sleep quality reliably, ultimately improving public healthcare.

An EEG-based perceptual function integration network for application to drowsy driving

Drowsy driving is among the most critical causes of fatal crashes. Thus, the development of an effective algorithm for detecting a drivers cognitive state demands immediate attention. For decades, studies have observed clear evidence using electroencephalography that the brains rhythmic activities fluctuate from alertness to drowsiness. Recognition of this physiological signal is the major consideration of neural engineering for designing a feasible countermeasure. This study proposed a perceptual function integration system which used spectral features from multiple independent brain sources for application to recognize the drivers vigilance state. The analysis of brain spectral dynamics demonstrated physiological evidenced that the activities of the multiple cortical sources were highly related to the changes of the vigilance state. The system performances showed a robust and improved accuracy as much as 88% higher than any of results performed by a single-source approach.

A hierarchical classification system for sleep stage scoring via forehead EEG signals

The study adopts the structure of hierarchical classification to develop an automatic sleep stage classification system using forehead (Fpl and Fp2) EEG signals. The hierarchical classification consists of a preliminary wake detection rule, a novel feature extraction method based on American Academy of Sleep Medicine (AASM) scoring manual, feature selection methods and SVM. After estimating the preliminary sleep stages, two adaptive adjustment schemes are applied to adjust the preliminary sleep stages and provide the final estimation of sleep stages. Clinical testing reveals that the proposed automatic sleep stage classification system is about 77% accuracy and 67% kappa for individual 10 normal subjects. This system could provide the possibility of long term sleep monitoring at home and provide a preliminary result of sleep stages so that doctor could decide if a patient needs to have a detailed diagnosis using Polysomnography (PSG) system in a sleep laboratory of hospital.

Identifying changes in EEG information transfer during drowsy driving by transfer entropy

Drowsy driving is a major cause of automobile accidents. Previous studies used neuroimaging based approaches such as analysis of electroencephalogram (EEG) activities to understand the brain dynamics of different cortical regions during drowsy driving. However, the coupling between brain regions responding to this vigilance change is still unclear. To have a comprehensive understanding of neural mechanisms underlying drowsy driving, in this study we use transfer entropy, a model-free measure of effective connectivity based on information theory. We investigate the pattern of information transfer between brain regions when the vigilance level, which is derived from the driving performance, changes from alertness to drowsiness. Results show that the couplings between pairs of frontal, central, and parietal areas increased at the intermediate level of vigilance, which suggests that an enhancement of the cortico-cortical interaction is necessary to maintain the task performance and prevent behavioral lapses. Additionally, the occipital-related connectivity magnitudes monotonically decreases as the vigilance level declines, which further supports the cortical gating of sensory stimuli during drowsiness. Neurophysiological evidence of mutual relationships between brain regions measured by transfer entropy might enhance the understanding of cortico-cortical communication during drowsy driving.

A nonparametric contextual classification based on Markov random fields

In this paper a nonparametric contextual classification using both spectral and spatial information will be proposed for hyperspectral image classification. Essentially, among the classification, spatial information is acquired on the basis of Markov random field (MRF) and then joined with the nonparametric density estimation. Two MRF-based nonparametric contextual classifications based on kNN and Parzen density estimation will be introduced. We expect this combination could strengthen the capability for classifying pixels of different class labels with similar spectral values and dealing with data that has no clear numerical interpretation.

Spatial information based support vector machine for hyperspectral image classification

In this study, a novel spatial information based support vector machine for hyperspectral image classification, named spatial-contextual semi-supervised support vector machine (SC3SVM), is proposed. This approach modifies the SVM algorithm by using the spectral information and spatial-contextual information. The concept of SC3SVM is to utilize other information, obtain from the pixels of a neighborhood system in the spatial domain, to modify the effective of each patterns. Experimental results show a sound performance of classification on the famous hyperspectral images, Indian Pine site. Especially, the overall classification accuracy of whole hyperspectral image (Indian Pine site with 16 classes) is up to 96.4%, the kappa accuracy is up to 95.9%.

Real-time assessment of vigilance level using an innovative Mindo4 wireless EEG system

Monitoring the neurophysiological activities of driver in an operational environment poses a severe measurement challenge using a current laboratory-oriented biosensor technology. The aims of this research are to 1) introduce a dry and wireless EEG system used for conveniently recording EEG signals from forehead regions, 2) propose an effective system for processing EEG recordings and translating them into the vigilance level, and 3) implement the proposed system with a JAVA-based graphical user interface (GUI) for online analysis. To validate the performance of the proposed system, this study recruited eight voluntary subjects to participate a 90-min sustained-attention driving task in a virtual-realistic driving environment. Physiological evidence obtained from the power spectral analysis showed that the dry EEG system could distinguish an alert EEG from a drowsy EEG by evaluating the spectral dynamics of delta and alpha activities. Furthermore, the experimental result of the comparison of the prediction performance using four forehead electrode sites (AF8, FP2, FP1, and AF7) implied that a single-electrode EEG signal used in the mobile and wireless EEG system is able to obtain a high prediction accuracy (~93%). Taken together, the proposed system applied a dry-EEG device combined with an effective algorithm can be a promising technology for real driving applications.

A vectorcardiogram-based classification system for the detection of Myocardial infarction

Myocardial infarction (MI), generally known as a heart attack, is one of the top leading causes of mortality in the world. In clinical diagnosis, cardiologists generally utilize 12-lead ECG system to classify patients into MI symptoms: 1. ST segment elevation, 2. ST segment depression or T wave inversion. However unstable ischemic syndromes have rapidly changing supply versus demand characteristics that is one of the several limitations of 12-lead ECG system for MI detection. In addition, the ECG sensor placements of 12-lead system is not easily donned and doffed for tele-healthcare monitoring at home. Vectorcardiogram (VCG) system in clinic is another type of diagnosis plot which represents the magnitude and direction of the electrical potential in the form of a vector loop during cardiac electric activity. The VCG system can easily acquire three ECG waves from X, Y, Z directions to composite vector signal in space and the VCG signals can be transferred to 12-lead ECG signal through Dower transformation and vice versa. Hence, this study attempts to develop a VCG-based classification system for the detection of Myocardial infarction. In the experiment results, the proposed system can select the proper ECG features based on cardiologists knowledge and proposed principal moments of QRS complex. The classification performance of MI detection can be reached to 99.89% of sensitivity, 92.51% of specificity, 95.35% of positive predictive value, and 96.96% overall accuracy with maximum-likelihood classifier (MLC).

Mapping Information Flow of Independent Source to Predict Conscious Level: A Granger Causality Based Brain-Computer Interface

Recent studies have shown that the various brain networks over different cognitive states. In contrast to measure a physiological change over a single region, the information flows between brain regions described by effective connectivity provides an informative dynamic over the whole brain. In this study, we proposed a source information flow network based on the combination of Granger causality and support vector regression to predict drivers conscious level. This work provides the first application of using brain network to develop a brain-computer interface and obtain a sound result of performance.