Sibsambhu Kar

Functional network changes associated with sleep deprivation and fatigue during simulated driving: validation using blood biomarkers.

OBJECTIVE Network analysis of electroencephalograph (EEG) signals to study the effect of fatigue and sleep deprivation in human drivers and its validation using blood biochemical parameters. METHODS We present a new method of detection of human fatigue and sleepiness by studying the variation of functional interdependencies among EEG signals from various channels. An experiment has been designed to induce fatigue in 12 subjects through several stages over 36 h of sleep deprivation. The functional interdependency among the signals has been computed using synchronisation likelihood (SL), which measures the dynamical (both linear and non-linear) interdependency between two or more non-stationary time series. A network structure has been generated based on the likelihood values and is characterised by a number of standard network-characterising parameters at each stage. Finally, the trends in the network parameters have been validated using biochemical analysis of three blood parameters: glucose, blood urea and creatinine. RESULTS An increasing trend in the degree of connectivity and clustering coefficient and a decreasing trend in the characteristic path length have been observed in some bands of signals at successive stages of the experiment. CONCLUSIONS Synchronisation of specific bands of the EEG signals from different cortical areas has been observed along with variation in network parameters at increased levels of fatigue and sleep deprivation. SIGNIFICANCE The results indicate that the network parameters may be used to detect and quantify the level of fatigue and sleepiness.

Effect of Sleep Deprivation on Functional Connectivity of EEG Channels

This paper presents the functional interdependences among electroencephalograph (EEG) signals collected from human subjects undergoing a controlled experiment over a period of 36 h of sleep deprivation. The EEG signals were recorded from 19 electrodes spread all over the scalp. The interdependence among the signals was measured using synchronization likelihood (SL), which measures the dynamical (both linear and nonlinear) interdependence between two or more nonstationary time series. A network structure was evolved based on these SL values. The EEG signal being nonstationary, instead of the frequency bands, the connectivity was evaluated at various intrinsic modes known as intrinsic mode functions (IMFs). These IMFs were generated using empirical mode decomposition. It was observed that the connectivity of the networks exhibits definite patterns at specific IMFs with increase in sleep deprivation at successive stages of the experiment. The results were validated using subjective assessment and audiovisual response tests.

A novel drowsiness detection scheme based on speech analysis with validation using simultaneous EEG recordings

This paper uses voice response analysis of human subjects for assessing their level of fatigue. The results are simultaneously validated through Electroencephalography (EEG) based measurements. We have designed a 36-hour long experiment where the subjects are asked to repeat a particular sentence at different stages. The response is analyzed for computing various parameters such as voiced duration, unvoiced duration, and the response time. We have used Mel-Frequency-Cepstral-Coefficients (MFCC) as the features for the silence, voiced and unvoiced parts of speech. We have segregated these parts using a Gaussian Mixture Model (GMM) classifier. The results have been validated with an EEG based parameter i.e. relative energy of α band which increases with fatigue. A correlation between Speech and EEG based measurements is observed at various stages of the experiment.

Fatigue in human drivers: A study using ocular, Psychometric, physiological signals

Fatigue of human driver (operator) is a major concern as it is a significant cause of road accidents. This is not only applicable in transport industry, but also in aviation, heavy engineering industries etc. In the present work we have applied three objective methods for assessment of fatigue in human operator. These methods are based on Auditory Vigilance test (AVT) and Visual Response Test (VRT), facial image based measurement of fatigue, and Electroencephalographic (EEG) signal analysis. The present paper concludes that the human fatigue should be assessed by Meta-Analysis as it is a complex psycho-physiological phenomenon.

Complex brain networks using Visibility Graph synchronization

Coordination between brain areas has been extensively studied by analyzing the synchronization of EEG signals generated in these areas. This paper proposes a complex network structure of the brain using the Visibility Graph Similarity technique to study the change of connectivity among brain areas at various stages of an experiment involving sleep-deprived subjects. The parameters of the network have also been compared with that of a complex network with a randomly chosen degree of connectivity.

Phase synchronization based weighted networks for classifying levels of fatigue and sleepiness

This paper presents the variation of functional interdependency of electroencephalograph (EEG) signals from different cortical areas during a 36 hour long sleep deprived experiment using phase synchronization. Weighted undirected network structures have been constructed based on the magnitude of Phase Synchronization at various levels of wavelet decomposition. Various network parameters have been computed at each stages of the experiment to study the integration and segregation of different lobes. It has been found that few network parameters exhibit definite patterns in some frequency bands with increasing sleepiness and fatigue at successive stages of the experiment.

A fast method of fog and haze removal

Fog and haze degrade the quality of preview and captured image by reducing the contrast and saturation. As a result the visibility of scene or object degrades. The objective of the present work is to enhance the visibility, saturation, contrast and reduce the noise in a foggy image. We propose a method that uses single frame for enhancing foggy images using multilevel transmission map. The method is fast and free from noise or artifacts that generally arise in such enhancement techniques. A comparison with existing methods shows that the proposed method performs better in terms of both processing time and quality. The proposed method works in real time for VGA resolution. The proposed work also presents a scheme to remove fog, rain and snow in real-time.

Classification of brain states using principal components analysis of cortical EEG synchronization and HMM

The state of brain and its rapid transition from one state to the other is responsible for various activities and cognitive functions. These brain states are the result of balanced coordination between integrating and segregating activities of different lobes through rhythmic oscillations. Such coordination has been studied in recent times through synchronization of EEG signals generated from different lobes. In this paper, the authors have considered Synchronization Likelihood (SL) to measure the synchronization or integration between the lobes. The synchronization information is stored in SL matrix and the principal components of an SL matrix have been used to represent the state of brain at any instant. Finally, the time series of weight vectors corresponding to the principal components of SL matrices at each time point has been used to classify different states of brain at different stages of a sleep deprived experiment.

A new technique for removal of ocular artifacts from EEG signals using S-transform

A novel and robust technique is described for removing electroencephalogram (EEG) artifacts resulting from ocular muscles contraction during eye movements. We present a new method to remove ocular artifacts from raw EEG signals. This technique is based on the S-transform (ST), a mathematical operation that produces frequency content at each time point within a time-varying signal. The S-transform generates high magnitude S-coefficients at the instants of artifact generation in the signal. A statistical threshold function has been applied to filter out the artifacts in the S-domain. The major advantage of ST-filtering is that the artifacts may be removed within a narrow time frame, while preserving the frequency information at all other time points. It also preserves the absolutely referenced phase information of the signal after removing the artifacts.

Estimation of Fatigue in Drivers by Analysis of Brain Networks

Synchronization measures between Electro-Encephalogram (EEG) signals from different regions of the brain characterize the integration and segregation of brain areas during any mental and physical activity. EEG can reflect both the normal and abnormal activity of the brain and is widely used as a powerful tool in the field of clinical neurophysiology. Being sensitive to decreasing alertness and decline in vigilance, EEG can be used to predict performance degradation due to mental or physical fatigue. This paper studies the variation of fatigue levels in human drivers in a sleep-deprivation experiment by analyzing the synchronization between EEG recorded from brain areas. A Weighted Visibility Graph (WVG) technique has been proposed to quantify the synchronization between brain regions, which is then formulated in terms of a complex network. The change in the parameters of the network is analyzed to find the variation of connectivity and hence to trace the increase in fatigue levels of an individual.