EEG-based Automatic Detection of Drowsy State
01 Jan 2015-pp 65-72
TL;DR: This paper focuses on finding the relation between EEG signal and human drowsiness, for which it requires efficient algorithms to identify the drowsy signal sample from given input samples.
Abstract: Electrical signal generated by the brain represents not only the brain function but also the status of the whole body. This paper focuses on finding the relation between EEG signal and human drowsiness, for which we require efficient algorithms. In the drowsiness state, a decrease of vigilance is generally observed. Identification was done by giving the preprocessed signal to a trained ANN to identify correctly the sleep condition of the person under observation. Different back-propagation algorithms are used for the study and the best one chosen by using the MSE estimation. Then using this system, classification is done and the drowsy signal sample is identified from given input samples.
TL;DR: A computationally simple and novel methodology Normalized Spatial Pseudo Codec (n-SPC) to compress MCEEG signals to detect sleep spindle was proposed and results indicate that the algorithm exhibits good storage efficiency and decompressed signal quality.
Abstract: Widespread use of Multichannel Electroencephalograph (MCEEG) in diversified fields ranging from clinical studies to Brain Computer Interface (BCI) application, has put in a lot of thrust in data pr...
TL;DR: A computationally simple and novel coding scheme named spatial pseudo codec (SPC) is proposed, to achieve lossy to near lossless compression of multichannel EEG (MCEEG) signals and validated the feasibility of the proposed compression scheme for practical MCEEG recording, archiving and brain computer interfacing systems.
Abstract: Popularisation of electroencephalograph (EEG) signals in diversified fields have increased the need for devices capable of operating at lower power and storage requirements. This has led to a great deal of research in data compression, that can address (a) low latency in the coding of the signal, (b) reduced hardware and software dependencies, (c) quantify the system anomalies, and (d) effectively reconstruct the compressed signal. This paper proposes a computationally simple and novel coding scheme named spatial pseudo codec (SPC), to achieve lossy to near lossless compression of multichannel EEG (MCEEG). In the proposed system, MCEEG signals are initially normalized, followed by two parallel processes: one operating on integer part and the other, on fractional part of the normalized data. The redundancies in integer part are exploited using spatial domain encoder, and the fractional part is coded as pseudo integers. The proposed method has been tested on a wide range of databases having variable sampling rates and resolutions. Results indicate that the algorithm has a good recovery performance with an average percentage root mean square deviation (PRD) of 2.72 for an average compression ratio (CR) of 3.16. Furthermore, the algorithm has a complexity of only O(n) with an average encoding and decoding time per sample of 0.3 ms and 0.04 ms respectively. The performance of the algorithm is comparable with recent methods like fast discrete cosine transform (fDCT) and tensor decomposition methods. The results validated the feasibility of the proposed compression scheme for practical MCEEG recording, archiving and brain computer interfacing systems.
••03 Mar 2016
TL;DR: The method uses one-dimensional EEG signal to detect presence of spindles occurring in EEG signal with the help of Karhunen-Loeve transform to detect sleep spindle detection.
Abstract: Automatic detection of sleep and its analysis have significant applications in clinical and driver fatigue detection. The method proposed here is aimed at detecting sleep spindles which are hallmark of beginning stage of sleep. The method uses one-dimensional EEG signal to detect presence of spindles occurring in EEG signal with the help of Karhunen-Loeve transform. The transform represents sampled EEG signal in terms of a basis which carries transient characteristics of sleep spindle. Projecting an EEG signal onto the spindle basis generates transform coefficients whose magnitude will decide whether input contains spindle or not. This method is simple and very easy to execute with a sensitivity of 86.9% and specificity of 93.5%.
TL;DR: A simple and novel method for compression of multichannel EEG (MCEEG) signal is proposed that is able to achieve good signal compression without degrading the signal quality.
Abstract: Extensive use of electroencephalogram (EEG) signals in diversified fields has put in a lot of thrust in research for devices capable of operating at constrained power and storage levels. In this paper, a simple and novel method for compression of multichannel EEG (MCEEG) signal is proposed. Here, wave atom transform of MCEEG data followed by quantization, thresholding, and arithmetic coding of context adaptive residuals and threshold coefficients is performed to achieve compression with good signal quality. The proposed method has been tested on a wide range of publicly available databases and results indicate that the algorithm is able to achieve good signal compression without degrading the signal quality. The proposed system provides an average compression ratio of 14.01 with a percentage root mean square difference of 1.91% across different data sets.
TL;DR: The basic theory and applications of ICA are presented, and the goal is to find a linear representation of non-Gaussian data so that the components are statistically independent, or as independent as possible.
11 Sep 2007
TL;DR: This book discusses their applications to medical data, using graphs and topographic images to show simulation results that assess the efficacy of the methods, and provides expansive coverage of algorithms and tools from the field of digital signal processing.
Abstract: Electroencephalograms (EEGs) are becoming increasingly important measurements of brain activity and they have great potential for the diagnosis and treatment of mental and brain diseases and abnormalities. With appropriate interpretation methods they are emerging as a key methodology to satisfy the increasing global demand for more affordable and effective clinical and healthcare services. Developing and understanding advanced signal processing techniques for the analysis of EEG signals is crucial in the area of biomedical research. This book focuses on these techniques, providing expansive coverage of algorithms and tools from the field of digital signal processing. It discusses their applications to medical data, using graphs and topographic images to show simulation results that assess the efficacy of the methods. Additionally, expect to find: explanations of the significance of EEG signal analysis and processing (with examples) and a useful theoretical and mathematical background for the analysis and processing of EEG signals; an exploration of normal and abnormal EEGs, neurological symptoms and diagnostic information, and representations of the EEGs; reviews of theoretical approaches in EEG modelling, such as restoration, enhancement, segmentation, and the removal of different internal and external artefacts from the EEG and ERP (event-related potential) signals; coverage of major abnormalities such as seizure, and mental illnesses such as dementia, schizophrenia, and Alzheimer's disease, together with their mathematical interpretations from the EEG and ERP signals and sleep phenomenon; descriptions of nonlinear and adaptive digital signal processing techniques for abnormality detection, source localization and brain-computer interfacing using multi-channel EEG data with emphasis on non-invasive techniques, together with future topics for research in the area of EEG signal processing. © 2007 by John Wiley & Sons Ltd,. All Rights Reserved.
TL;DR: In this article, a fast fixed-point type algorithm that is capable of separating complex valued, linearly mixed source signals is presented and its computational efficiency is shown by simulations and the local consistency of the estimator given by the algorithm is proved.
Abstract: Separation of complex valued signals is a frequently arising problem in signal processing. For example, separation of convolutively mixed source signals involves computations on complex valued signals. In this article, it is assumed that the original, complex valued source signals are mutually statistically independent, and the problem is solved by the independent component analysis (ICA) model. ICA is a statistical method for transforming an observed multidimensional random vector into components that are mutually as independent as possible. In this article, a fast xed-point type algorithm that is capable of separating complex valued, linearly mixed source signals is presented and its computational eciency is shown by simulations. Also, the local consistency of the estimator given by the algorithm is proved.
TL;DR: It is concluded that ongoing 0.01–0.1 Hz EEG fluctuations are prominent and functionally significant during execution of cognitive tasks, suggesting that the infraslow fluctuations reflect the excitability dynamics of cortical networks.
Abstract: Our ability to perceive weak signals is correlated among consecutive trials and fluctuates slowly over time. Although this "streaking effect" has been known for decades, the underlying neural network phenomena have remained largely unidentified. We examined the dynamics of human behavioral performance and its correlation with infraslow (0.01-0.1 Hz) fluctuations in ongoing brain activity. Full-band electroencephalography revealed prominent infraslow fluctuations during the execution of a somatosensory detection task. Similar fluctuations were predominant also in the dynamics of behavioral performance. The subjects' ability to detect the sensory stimuli was strongly correlated with the phase, but not with the amplitude of the infraslow EEG fluctuations. These data thus reveal a direct electrophysiological correlate for the slow fluctuations in human psychophysical performance. We then examined the correlation between the phase of infraslow EEG fluctuations and the amplitude of 1-40 Hz neuronal oscillations in six frequency bands. Like the behavioral performance, the amplitudes in these frequency bands were robustly correlated with the phase of the infraslow fluctuations. These data hence suggest that the infraslow fluctuations reflect the excitability dynamics of cortical networks. We conclude that ongoing 0.01-0.1 Hz EEG fluctuations are prominent and functionally significant during execution of cognitive tasks.
TL;DR: The LVQ neural network gives the best classification compared with the linear network that uses WH algorithm (the worst), and the non-linear network trained with the LM rule, and it is shown that the automatic recognition algorithm is applicable for distinguishing between alert and drowsy state in recordings that have not been used for the training.