Seizure detection using Bessel k-form parameters in the empirical mode decomposition domain

Automatic patient monitoring for cardiac diseases requires the detection of various abnormal electrical activities occurring in the heart. Pseudo-pacemaker activities by cardiac cells or non-standard electrical impulses in the atria or ventricle cause various types of arrhythmia. Atrial fibrillation (AF) is the most important irregularity that occurs due to electrical malfunctioning in the atria. Unsynchronized pumping of the atria and ventricle causes different volumes of blood flow at different rhythms. In this paper, a method for the automatic detection of AF in the empirical mode decomposition (EMD) domain is proposed. Being a completely data-adaptive technique, EMD can be applied to all kinds of electrocardiogram signals. Selective reconstruction eliminates the requirement of conventional preprocessing for denoising the raw data. A combination of temporal and statistical features is used to characterize abnormal rhythms. A novel SQ time deviation feature is introduced, which is proved to be a good choice for AF classification. A nonlinear-kernel-based support vector machine classifier is used for classification. Sensitivity, specificity, and accuracy comparable to those of previous works are achieved for the MIT-BIH Arrhythmia Database.

Sleep disorders has a vital effect on mental depression and many other diseases of human body. Diagnosing the sleep disorder in an early curable stage may help to provide better treatment and save the life. The EEG (Electroencephalogram) signal is one of the most uses bio signal for capturing brain activities to detect and diagnosis the sleep disorders. Empirical mode decomposition (EMD) is an efficient time-frequency data analysis technique for diagnosing disease by analyzing EEG signal. However, it is a challenging issue to select the optimal intrinsic mode functions (IMFs) of Empirical mode decomposition (EMD) for extracting discriminant properties of EEG signals to diagnosis the sleep disorder. From this point of view, this paper presents a model to select optimal IMF of EMD for diagnosing the sleep disorder using EEG brain signal. In this proposed model, EMD is applied to decompose and analyze EEG signal for extracting biomarker/feature of sleep disorders. During the EMD decomposition process, different levels of IMF are extracted and features, i.e., Shannon Entropy, Spectral Entropy, Standard deviation, Skewness and Kurtosis are calculated from those IMFs for detecting the sleep disorders. In identification process, the multiclass support vector machine (MC-SVM) classification algorithm is used and sleep disorders are classified based on trained knowledge. Finally, the performance of proposed model is evaluated for different IMFs of EMD and find the optimal IMF for sleep disorder diagnosis. For evaluating the proposed model, a benchmark dataset including 4 types of data such as Apnea, REM, PLM and healthy subjects are used in experiment. According to the experimental result, the proposed model achieves the optimal classification performance for IMF 8, i.e., 93.24% average classification accuracy.

This paper deals with the image quality assessment (IQA) task using a natural image statistics approach. A reduced reference (RRIQA) measure based on the bidimensional empirical mode decomposition is introduced. First, we decompose both, reference and distorted images, into intrinsic mode functions (IMF) and then we use the generalized Gaussian density (GGD) to model IMF coefficients of the reference image. Finally, we measure the impairment of a distorted image by fitting error between the IMF coefficients histogram of the distorted image and the estimated IMF coefficients distribution of the reference image, using the Kullback–Leibler divergence (KLD). Furthermore, to predict the quality, we propose a new support vector machine-based (SVM) classification approach as an alternative to logistic function-based regression. In order to validate the proposed measure, three benchmark datasets are involved in our experiments. Results demonstrate that the proposed metric compare favorably with alternative solutions for a wide range of degradation encountered in practical situations.

Empirical mode decomposition (EMD) is a fully unsupervised and data-driven approach to the class of nonlinear and non-stationary signals. A new approach is proposed, namely PHEEMD, to image analysis by using Peano–Hilbert space filling curves to transform 2D data (image) into 1D data, followed by ensemble EMD (EEMD) analysis, i.e., a more robust realization of EMD based on white noise excitation. Tests’ results have shown that PHEEMD exhibits a substantially reduced computational cost compared to other 2D-EMD approaches, preserving, simultaneously, the information lying at the EMD domain; hence, new perspectives for its use in low computational power devices, like portable applications, are feasible.

The existence of coherent and incoherent (random) noises in the ground penetration radar (GPR) signals using high-frequency electromagnetic waves is inevitable; therefore, the elimination of noise from GPR data before performing any additional analysis is of great importance to increase the efficiency of the interpretations. We apply the Total Variation De-noising (TVD) and Savitzky-Golay (SG) filter, on the synthetic and real GPR data. For a better perception, we compare the same trace of the data before and after the experiences. The results indicate that the TVD method is more effective than common adaptive filtering in the time domain for reducing noise such as the SG filter which acts as a low-pass filter for smoothing data based on a polynomial least-squares approximation; however, due to the visibility of staircase artifacts using the TVD method, GPR data is first transferred to the empirical mode decomposition (EMD) frame which is useful for non-linear and non-stationary signal processing, then the TVD method is applied on it; ultimately, noise reduction using TVD is compared in the time and EMD domains. The comparison of the outputs shows that the TVD algorithm in the EMD domain, based on the sequential extraction of the energy belonging to the different intrinsic time scales of the signal, provides better noise attenuation than the other algorithms. In addition, TVD-EMD preserves the event forms, signal forms and improves the continuity in sections.

Epilepsy is a neurological disorder that affects people of any age, which can be detected by Electroencephalogram (EEG) signals. This paper proposes a novel method called Volume of Phase Space Representation (VOPSR) to classify seizure and seizure-free EEG signals automatically. Primarily, the recorded EEG signal is disintegrated into several Intrinsic Mode Functions (IMFs) using the Empirical Mode Decomposition (EMD) method and the three-dimensional phase space have been reconstructed for the obtained IMFs. The volume is measured for the obtained 3D-PSR for different IMFs called VOPSR, which is used as a feature set for the classification of Epileptic seizure EEG signals. Support vector machine (SVM) is used as a classifier for the classification of epileptic and epileptic-free EEG signals. The classification performance of the proposed method is evaluated under different kernels such as Linear, Polynomial and Radial Basis Function (RBF) kernels. Finally, the proposed method outperforms noteworthy state-of-the-art classification methods in the context of epileptic EEG signals, achieving 99.13% accuracy (average) with the Linear, Polynomial, and RBF kernels. The proposed technique can be used to detect epilepsy from the EEG signals automatically without human intervention.

Field-programmable gate arrays (FPGAs) are being extensively used for a wide range of digital applications due to their flexibility and reprogrammability. This paper presents a FPGA implementation of the second-order difference plot (SODP) technique which can be used for the classification of ictal and seizure-free electroencephalogram (EEG) signals. Empirical mode decomposition (EMD) can break down an EEG signal into simple oscillatory modes called intrinsic mode functions (IMFs). The hardware design developed takes a sampled IMF of an EEG signal as input and generates its SODP while simultaneously calculating the 95 percent confidence ellipse area of the SODP. The ellipse area can be used as a parameter for detecting epileptic seizures in EEG signals. The digital circuit was designed in the Vivado integrated development environment (IDE) using Verilog hardware description language (HDL) and a Xilinx Artix-7 xc7a100tcsg324 FPGA was used to verify operation of the physical implementation. The hardware was tested on EEG data made publicly available by the University of Bonn and the results were found to be consistent with MATLAB simulations.

We present a new method for separation of the rhythms of the electroencephalogram (EEG) signal. The proposed method is based on the Hilbert-Huang transform (HHT). The HHT consists two steps namely empirical mode decomposition (EMD) and the Hilbert transform (HT). The EMD decomposes EEG signal into set of narrow-band intrinsic mode functions (IMFs), and the Hilbert transformation of these IMFs provide instantaneous frequency estimation of the IMFs. The instantaneous frequency estimation of IMFs have been used as a feature to identify the IMFs in order to separate rhythms of EEG signal. The central tendency measure (CTM) has been used to quantify the variability in second order difference (SOD) plots of rhythms of the EEG signal. The CTM parameter is very effective to discriminate epileptic seizure EEG signals from the seizure-free EEG signals. The experimental results show the effectiveness of the proposed method for epileptic seizure detection.

The electroencephalogram (EEG) signal is an electrical representation of brain's working that reflects various physiological and pathological activities such as alcoholism. Alcohol can affect whole parts of the body but, it particularly affects the brain, heart, liver, and the immune system; its effects on the brain are called brain disorders. Nowadays, automatic identification of alcoholic subjects based on EEG signals has become one of the challenging problems in biomedical research. In this study, an automatic classification method for classifying alcoholic and normal EEG signals, based on empirical mode decomposition (EMD), is proposed. The uniqueness of EMD method is to decompose non‐stationary and non‐linear signals into a set of stationary intrinsic mode functions (IMFs) that are band limited signals. These IMFs are transformed into analytic representations by applying the Hilbert transform. From these analytic IMFs, various features namely mean, kurtosis, skewness, entropy, and negentropy are extracted; these features are used as input to least squares support vector machines (LS‐SVMs) classifier with radial basis function (RBF) kernel and polynomial kernel. The accuracy results achieved for LS‐SVM classifier with polynomial and RBF kernels are found to be 96.67 and 97.92%, respectively, which are found to be better as compared with other state‐of‐the‐art methods.

The scalp electroencephalogram (EEG) signal based epileptic seizure analysis has been comprehensively studied in the past. But existing researches are generally concerned with the seizure/non-seizure detection. Few attention has been paid to the epileptic preictal state classification, which is found to be evidently more important to the injury prevention. In this paper, we study the epileptic preictal state classification for seizure prediction. The one hour preictal EEG signal is divided into non-overlapped equilong segments. Statistical features of the first intrinsic mode function (FIMF) of the empirical mode decomposition (EMD) of the EEG signal as well as the 4-level wavelet packet decomposition (WPD) of the FIMF are extracted for the EEG signal representation. A five-state classification problem is formulated, including one interictal, three preictal, and one seizure states. Experiments on the benchmark epilepsy EEG database collected by the Children's Hospital Boston and the Massachusetts Institute of Technology (CHB-MIT) using several popular classifiers are provided for the effectiveness demonstration.

In this paper, a new perceptual spread spectrum audio watermarking scheme is discussed. The watermark embedding process is performed in the Empirical Mode Decomposition (EMD) domain, and the hybrid watermark extraction process is based on the combination of EMD and ISA (Independent Subspace Analysis) techniques, followed by the generic detection system, i.e. inverse perceptual filter, predictor filter and correlation based detector. Since the EMD decomposes the audio signal into several oscillating components---the intrinsic mode functions (IMF)---the watermark information can be inserted in more than one IMF, using spread spectrum modulation, allowing hence the increase of the insertion capacity. The imperceptibility of the inserted data is ensured by the use of a psychoacoustical model. The blind extraction of the watermark signal, from the received watermarked audio, consists in the separation of the watermark from the IMFs of the received audio signal. The separation is achieved by a new proposed under-determined ISA method, here referred to as UISA. The proposed hybrid watermarking system was applied to the SQAM (Sound Quality Assessment Material) audio database (Available at http://sound.media.mit.edu/mpeg4/audio/sqam/ ) and proved to have efficient detection performances in terms of Bit Error Rate (BER) compared to a generic perceptual spread spectrum watermarking system. The perceptual quality of the watermarked audio was objectively assessed using the PEMO-Q (Tool for objective perceptual assessment of audio quality) algorithm. Also, using our technique, we can extract the different watermarks without using any information of original signal or the inserted watermark. Experimental results exhibit that the transparency and high robustness of the watermarked audio can be achieved simultaneously with a substantial increase of the amount of information transmitted. A reliability of 1.8 10Â?Â?Â?4 (against 1.5 10Â?Â?Â?2 for the generic system), for a bit rate of 400 bits/s, can be achieved when the channel is not disturbed.

The extraction of intended kinetic information from an EEG signal can have several applications related to the rehabilitation for subjects with various neurological disorders. However, the task is mainly constrained by the low signal-to-noise ratio for the EEG signals. It is well known that the cortical activity takes place at a very low frequency since it is characterized by the dropping of movement related cortical potential (MRCP) across the sampled EEG signal. The strong variations in the MRCP is indicative of the noise due to various sources. The aim of this work is to remove this noise from the EEG signals using empirical mode decomposition, which decomposes a signal into harmonics (intrinsic mode functions--IMF) of various frequencies. The IMFs pertaining to small frequencies are later used for features extraction where we extract the spatial and spectral features from the selected IMFs. The features are later used for classification using support vector machines (SVM). Our experiments show superior results to the benchmark method for the underlying dataset that has been used in this research.

The measurement of brain electrical activity recorded as EEG signals finds most application in epilepsy. EEG waveforms carry information about the underlying neural system dynamics and show different features amongst epilepsy syndromes. In this research, empirical mode decomposition (EMD) and power spectrum were employed to extract the features from EEG dataset of healthy participants, and epilepsy patients with seizure and seizure free conditions. The recorded EEG signals are represented by 500 signal segments from 5 sets of different conditions. The sum of Intrinsic Mode Function (IMF) power spectrum components gave 10 features for 50 components, and 20 features for 25 components, which were used as the classification inputs for artificial neural networks and random forest classifiers. The classifications were carried out for 3, 4, and 5 classes. From the experiments, the highest average accuracy was obtained for 3 classes using 20 features of power spectrum from the sum of 6 IMFs. For use of 6 IMFs, the accuracies had the maximum values of 92.4%, 90.4%, and 78.6% for 3, 4, and 5 classes respectively. It also improved the accuracy significantly for 5 classes.

Using filter bank property to simplify the calculations of Empirical Mode Decomposition

Primal sketch performs an important role in early vision. In this paper, we propose a novel method to obtain the primal sketch of natural images by integrating empirical mode decomposition (EMD) techniques and image gradient. 2D EMD approach can decompose the image into a finite number of intrinsic mode functions (IMF), and each one represents the original image in a different scale, with the 1st IMF representing the finest scale. To enhance the information represented by the IMF, we multiply the 1st IMF by the image gradient. This enhanced IMF highlights intensity changes in the image. By linking all the maximal points in the enhanced IMF, we obtain a primal sketch of the original image. Compared with the existed primal sketch extraction methods, our method is fully driven by the image data, and it needs neither to choose filters nor to learn the image bases. The experiment results show that our method is fast and effective.