Mohammed Imamul Hassan Bhuiyan

Detection of Seizure and Epilepsy Using Higher Order Statistics in the EMD Domain

In this paper, a method using higher order statistical moments of EEG signals calculated in the empirical mode decomposition (EMD) domain is proposed for detecting seizure and epilepsy. The appropriateness of these moments in distinguishing the EEG signals is investigated through an extensive analysis in the EMD domain. An artificial neural network is employed as the classifier of the EEG signals wherein these moments are used as features. The performance of the proposed method is studied using a publicly available benchmark database for various classification cases that include healthy, interictal (seizure-free interval) and ictal (seizure), healthy and seizure, nonseizure and seizure, and interictal and ictal, and compared with that of several recent methods based on time-frequency analysis and statistical moments. It is shown that the proposed method can provide, in almost all the cases, 100% accuracy, sensitivity, and specificity, especially in the case of discriminating seizure activities from the nonseizure ones for patients with epilepsy while being much faster as compared to the time-frequency analysis-based techniques.

Spatially Adaptive Wavelet-Based Method Using the Cauchy Prior for Denoising the SAR Images

The speckle noise complicates the human and automatic interpretation of synthetic aperture radar (SAR) images. Thus, the reduction of speckle is critical in various SAR image processing tasks. In this paper, we introduce a new spatially adaptive wavelet-based Bayesian method for despeckling the SAR images. The wavelet coefficients of the logarithmically transformed reflectance and speckle noise are modeled using the zero-location Cauchy and zero-mean Gaussian distributions, respectively. These prior distributions are then exploited to develop a Bayesian minimum mean absolute error estimator as well as a maximum a posteriori estimator. A new context-based technique with a reduced complexity is proposed for incorporating the spatial dependency of the wavelet coefficients with the Bayesian estimation processes. Experiments are carried out using typical noise-free images corrupted with simulated speckle noise as well as real SAR images, and the results show that the proposed method performs favorably in comparison to some of the existing methods in terms of the peak signal-to-noise ratio, speckle statistics and structural similarity index, and in its ability to suppress the speckle in the homogeneous regions

Computer-aided sleep staging using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and bootstrap aggregating

Abstract Computer-aided sleep staging based on single channel electroencephalogram (EEG) is a prerequisite for a feasible low-power wearable sleep monitoring system. It can also eliminate the burden of the clinicians during analyzing a high volume of data by making sleep scoring less onerous, time-consuming and error-prone. Most of the prior studies focus on multichannel EEG based methods which hinder the aforementioned goals. Among the limited number of single-channel based methods, only a few yield good performance in automatic sleep staging. In this article, a single-channel EEG based method for sleep staging using recently introduced Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Bootstrap Aggregating (Bagging) is proposed. At first, EEG signal segments are decomposed into intrinsic mode functions. Higher order statistical moments computed from these functions are used as features. Bagged decision trees are then employed to classify sleep stages. This is the first time that CEEMDAN is employed for automatic sleep staging. Experiments are carried out using the well-known Sleep-EDF database and the results show that the proposed method is superior as compared to the state-of-the-art methods in terms of accuracy. In addition, the proposed scheme gives high detection accuracy for sleep stages S1 and REM.

A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral features

BACKGROUND Automatic sleep scoring is essential owing to the fact that conventionally a large volume of data have to be analyzed visually by the physicians which is onerous, time-consuming and error-prone. Therefore, there is a dire need of an automated sleep staging scheme. NEW METHOD In this work, we decompose sleep-EEG signal segments using tunable-Q factor wavelet transform (TQWT). Various spectral features are then computed from TQWT sub-bands. The performance of spectral features in the TQWT domain has been determined by intuitive and graphical analyses, statistical validation, and Fisher criteria. Random forest is used to perform classification. Optimal choices and the effects of TQWT and random forest parameters have been determined and expounded. RESULTS Experimental outcomes manifest the efficacy of our feature generation scheme in terms of p-values of ANOVA analysis and Fisher criteria. The proposed scheme yields 90.38%, 91.50%, 92.11%, 94.80%, 97.50% for 6-stage to 2-stage classification of sleep states on the benchmark Sleep-EDF data-set. In addition, its performance on DREAMS Subjects Data-set is also promising. COMPARISON WITH EXISTING METHODS The performance of the proposed method is significantly better than the existing ones in terms of accuracy and Cohens kappa coefficient. Additionally, the proposed scheme gives high detection accuracy for sleep stages non-REM 1 and REM. CONCLUSIONS Spectral features in the TQWT domain can discriminate sleep-EEG signals corresponding to various sleep states efficaciously. The proposed scheme will alleviate the burden of the physicians, speed-up sleep disorder diagnosis, and expedite sleep research.

On the classification of sleep states by means of statistical and spectral features from single channel Electroencephalogram

Traditional sleep scoring based on visual inspection of Electroencephalogram (EEG) signals is onerous for sleep scorers because of the gargantuan volume of data that have to be analyzed per examination. Computer-aided sleep staging can alleviate the onus of the sleep scorers. Again, most of the existing works on automatic sleep staging are multichannel based. Multichannel based sleep scoring is not pragmatic for the implementation of a wearable and portable sleep quality evaluation device. Due to all these factors, automatic sleep scoring based on single channel EEG is garnering increasing attention of sleep researchers. In this work, we propound a single channel based solution to sleep scoring. First, we decompose the EEG signals into segments. We then compute various statistical and spectral features from the signal segments. After performing statistical analyses, we perform classification using artificial neural network. Results of various experiments perspicuously manifest that the proposed scheme is superior to state-of-the-art ones in accuracy.

Automatic classification of sleep stages from single-channel electroencephalogram

A portable and wearable yet low-power sleep monitoring system necessitates an automatic sleep scoring algorithm with the use of minimum number of recording channels. Computer-aided sleep staging is also important to eradicate the onus of sleep scorers of analyzing an enormous volume of data. The existing works on sleep scoring are either multichannel based or yield poor performance. Therefore, an automatic sleep scoring algorithm based on single channel EEG signals is yet to emerge. In this work, we utilize spectral features to extract discriminatory information from EEG signal segments. We then perform statistical analyses to find out the efficacy and the discriminatory capability of the selected features for various sleep states. Afterwards, we employ Adaptive Boosting to perform classification. The experimental outcomes perspicuously manifest that the proposed scheme is superior to state-of-the-art ones in accuracy.

An automated method for sleep staging from EEG signals using normal inverse Gaussian parameters and adaptive boosting

Sleep stage screening based on visual inspection is burdensome, time-consuming, subjective, and error-prone owing to the large bulk of data which have to be screened. Consequently, automatic sleep scoring is essential for both sleep research and sleep disorder diagnosis. In this work, we present the application of newly proposed tunable-Q factor wavelet transform (TQWT) to devise a single channel EEG based computerized sleep staging algorithm. First, we decompose the sleep-EEG signal segments into TQWT sub-bands. Then we perform normal inverse Gaussian (NIG) pdf modeling of TQWT sub-bands wherein NIG parameters are used as features. The effects of various TQWT parameters are also studied. The suitability of NIG parameters in the TQWT domain is inspected. In this study, we employ adaptive boosting (AdaBoost) for sleep stage classification. To assess the performance of the classification model and to determine the optimal choices of AdaBoost parameters, 10 fold cross-validation is performed. The performance of the proposed scheme is promising in terms of sensitivity, specificity, accuracy, and Cohens Kappa co-efficient. Comparative analysis of performance suggests that the algorithmic performance of the proposed scheme, as opposed to that of the state-of-the-art ones is better. Further, the proposed algorithm also gives superior S1 and REM stage detection accuracy. The computerized sleep scoring scheme propounded herein can expedite sleep disorder diagnosis, contribute to the device implementation of a sleep monitoring system, and benefit sleep research.

Identification of motor imagery movements from EEG signals using Dual Tree Complex Wavelet Transform

In this paper, Dual Tree Complex Wavelet Transform (DTCWT) domain based feature extraction method has been proposed to identify left and right hand motor imagery movements from electroencephalogram (EEG) signals. After first performing auto-correlation of the EEG signals to enhance the weak brain signals and reduce noise, the EEG signals are decomposed into several bands of real and imaginary coefficients using DTCWT. The energy of the coefficients from relevant bands have been extracted as features and from the one way ANOVA analysis, scatter plots, box plots and histograms, this features are shown to be promising to distinguish various kinds of EEG signals. Publicly available benchmark BCI-competition 2003 Graz motor imagery dataset is used for this experiment. Among different types of classifiers developed such as support vector machine (SVM), probabilistic neural network (PNN), adaptive neuro fuzzy inference system (ANFIS) and K-nearest neighbor (KNN), KNN classifiers have been shown to provide a good mean accuracy of 91.07% which is better than several existing techniques.

Wavelet-Based Despeckling of Medical Ultrasound Images with the Symmetric Normal Inverse Gaussian Prior

A major problem in medical ultrasonography is the inherent corruption of ultrasound images with speckle noise that severely hampers the diagnosis and automatic image processing tasks. In this paper, an efficient wavelet-based method is proposed for despeckling medical ultrasound images. A closed-form Bayesian wavelet-based maximum a posteriori denoiser is developed in a homomorphic framework, based on modelling the wavelet coefficients of the log-transform of the reflectivity with a symmetric normal inverse Gaussian (SNIG) prior. A simple method is presented for obtaining the parameters of the SNIG prior using local neighbors. Thus, the proposed method is spatially adaptive. Experiments are carried out using synthetically speckled and real ultrasound images, and the results show that the proposed method performs better than several other existing methods in terms of the signal-to-noise ratio and visual quality.

Low complexity iris recognition using curvelet transform

In this paper, a low complexity technique is proposed for iris recognition in the curvelet transform domain. The proposed method does not require the detection of outer boundary and decreases unwanted artefacts such as the eyelid and eyelash. Thus, the time required for preprocessing of an iris image is significantly reduced. The zero-crossings of the transform coefficients are used to generate the iris codes. Since only the coefficients from approximation subbands are used, it reduces the length of the code. The iris codes are matched employing the correlation coefficient. Extensive experiments are carried out using a number of standard databases such as CASIA- V3, UBIRIS.v1 and UPOL. The results reveal that the proposed method using the curvelet transform provides a very high degree of accuracy (about 100%) over a wide range of images with a low equal error rate (EER) and a significant reduction in the computational time, as compared to those of the state-of-the-art techniques.