Non-stationary signals with rapidly evolving and overlapping spectral components present challenges for obtaining accurate time-frequency distribution (TFD). Conventional dynamic mode decomposition (DMD) extracts mode frequencies and damping information but struggles to represent the TFD of highly non-stationary signals. Multi-resolution DMD (MR-DMD) improves this but depends on a fixed embedding dimension, causing mode mixing and reduced resolution. This paper presents an adaptive multiresolution DMD (AMR-DMD) technique that automatically determines the embedding dimension at each decomposition level using a time-frequency resolution criterion obtained from the Heisenberg uncertainty principle for real-valued signals. The method is further extended to complex-valued signals by separating positive and negative frequency components for complete spectral characterization. Hilbert spectral analysis (HSA) is applied to the modes obtained from AMR-DMD to generate the TFD. Experimental results on real synthetic and complex signals show that the proposed AMR-DMD-based HSA technique provides improved TFDs, achieving sharper localization, lower reconstruction error, and higher quality reconstruction factor compared with empirical mode decomposition-based HSA, variational mode decomposition-based HSA, DMD-based HSA, and MR-DMD-based HSA methods.

Parkinson’s disease (PD) detection from speech signals attracts significant attention from researchers due to the effectiveness of speech impairment symptoms in PD diagnosis in its early phase. The short-time Fourier transform (STFT)-based analysis suffers from fixed resolution. The discrete wavelet transform (DWT) provides multiresolution analysis. However, an analytic wavelet transform with a flexible time-frequency covering (AWTFTFC) is a generalized form of DWT with flexible selection of redundancy, dilation factor, and Q-factor. The Fourier-Bessel series expansion (FBSE)-based flexible analytic wavelet transform (FAWT) (FBSE-FAWT) is an improved version of AWTFTFC with the replacement of the Fourier-based spectrum by the FBSE-based spectrum to have better frequency resolution. In this article, FBSE-FAWT-based time-frequency representation (TFR) is used to detect PD from speech signals. In the FBSE-FAWT-based TFR method, the FBSE-FAWT technique has been used to obtain subband signals and Hilbert spectral analysis is applied to compute TFR of speech signals. Seven different pretrained networks, namely, AlexNet, GoogleNet, SqueezeNet, DenseNet-101, InceptionNet-v3, VGG-16, and ResNet-50 are trained using the obtained TFRs to detect PD. The proposed framework with ResNet-50 demonstrates the highest performance with an accuracy of 98.05%, an F1-score of 98.27%, a specificity of 98.61%, a precision of 98.93%, and a recall of 97.62%. The robustness of the proposed framework is verified in cross-task situations where the framework has been trained on spontaneous dialogue task and tested on read text task. Further, the proposed framework achieves better performance as compared with its variant, where the FBSE-FAWT-based TFR is replaced with a spectrogram, as well as compared with other existing methods in the literature.

Depression, a prevalent mental disorder, can have severe consequences if left untreated, including self-harm and suicide. Selective Serotonin Reuptake Inhibitors (SSRI) therapy is the first course of treatment for depression disorder. Accurate prediction of SSRI therapy outcomes could significantly assist medical professionals in tailoring treatment plans to individual subjects. Electroencephalography (EEG) signals, which reflect the brain's neural activity, offer a non-invasive avenue for such predictions. However, visual analysis of EEG signals is laborious and time-consuming, given their complex, nonlinear, and nonstationary nature. EEG signals are complex, nonlinear, and nonstationary. Consequently, EEG signals need to be decomposed into several sub-bands to extract detailed and representative information. Traditional manual filter bank design for decomposition risks information loss. To address this challenge, this study proposes an automated tunable-Q wavelet transform (ATQWT) framework for automatic signal decomposition, which aims to preserve critical information during analysis. The Starfish optimization algorithm (SFOA), a bio-inspired metaheuristic approach, is employed to optimize the parameters of ATQWT, facilitating the automatic selection of optimal tuning parameters to extract meaningful sub-bands and enhance signal reconstruction during synthesis. Centered correntropy is utilized to compute features from the sub-bands, and the most discriminative features are identified using a nearest neighbor algorithm. These features are then classified using a feedforward neural network, and a 10-fold cross-validation strategy is implemented to mitigate potential bias in the results. The proposed method achieves an outstanding classification accuracy of 99.36% in predicting SSRI therapy outcomes. Results show F4, P4, C4, Fp2, F8 and Fz are the most informative channels for predicting SSRI therapy outcomes. So, the right-lateralized prefrontal and parietal lobes are more involved in depression therapy. This approach holds significant potential for assisting medical teams in clinical settings to develop more personalized and effective therapy plans for subjects with depression.

Neurological injuries or neurodegenerative diseases can lead to dysarthria, a condition that impairs speech intelligibility. Accurate detection of dysarthria and its severity from speech signals are crucial for advancing smart healthcare solutions. This study presents an automated system for dysarthria detection and severity classification, using a Fourier-Bessel series expansion-based flexible time-frequency coverage wavelet transform (FBSE-FTFCWT) and an autoencoder. Initially, FBSE-FTFCWT decomposes the speech signal into 16 sub-band signals, which are used as an input in the form of tensor for autoencoders to generate latent representation. This latent representation is subsequently used for dysarthric speech and its severity level detection. The proposed framework outperformed the current state-of-the-art in classifying dysarthric and normal speech on the UA-speech dataset, achieving 3.28% higher accuracy. Additionally, for the dysarthric severity detection task using speech signals from the same dataset, it showed 3.1% improvement in accuracy over existing methods.

Electroencephalogram (EEG)-based motor imagery (MI) (MI-EEG) decoding has established a novel experimental paradigm in brain-computer interface (BCI) applications that offer effective treatment for stroke paralyzed patients. However, existing MI-EEG-based BCI systems introduce deployment issues because of nonstationary EEG signals, suboptimal features, and limited multiclass scalability. To tackle these issues, we propose an enhanced sparse swarm decomposition method (ESSDM) based on selfish-herd optimization and sparse spectrum to solve the issue of choice of uniform decomposition and hyperparameters in swarm decomposition, and further applied to enhance MI-EEG classification. ESSDM adopts improved swarm filtering to automatically deliver optimal frequency bands in the sparse spectrum with optimized hyperparameters to extract dominant oscillatory components (OCs) that significantly enhance MI activation-related sub-bands. In addition, new fitness criteria has been designed based on the Kullback–Leibler divergence distance from the spectral kurtosis of the obtained modes to select hyperparameters that optimize decomposition effect, avoid excessive iterations, and provide fast convergence with optimal modes. Further, fused time-frequency graph (FTFG) features have been derived from computed time-frequency representation to find cross-channel mutual spectral information. The experimental results on the 2-class BCI III-4a, 2-class OpenBMI, and 4-class BCI IV-2a datasets reveal that the proposed framework based on FTFG features with capsule neural network (CapsNet), ESSDM-FTFG-CapsNet outperformed other existing methods in specific-subject, cross-subject, and cross-session scenarios.

The amplitude envelope is a crucial parameter to analyse natural systems as it provides useful amplitude modulation (AM) based information. In many cases, power spectral entropy (PSE) of a non-stationary signal is not able to discriminate AM based information. This paper proposes amplitude envelope based spectral entropy (ASE) which quantifies AM related information in the spectral domain and superiority is justified in comparison with PSE. Moreover, ASE is extended for multivariate signal analysis using joint AM based information. Efficacy of ASE is shown in various scenarios. Further, multivariate ASE is utilized for the development of a reach-and-grasp identification system using multichannel electroencephalogram (EEG) recordings. In this system, a novel correntropy based channel selection method is proposed to reduce system complexity. The number of EEG channels are reduced by almost 50% using the proposed channel selection method. The selected channels are decomposed into intrinsic mode functions (IMFs) using multivariate decomposition method. The AM based information present in these IMFs is obtained using multivariate ASE. Support vector machine classifier with radial basis function kernel is utilized to identify the type of grasp. Pearson correlation coefficient-based feature ranking is applied to select the significant features. The highest classification performance is achieved using five features with accuracy, sensitivity and specificity of$72.03~\pm ~2.39$%,$66.19~\pm ~8.96$% and$83.31~\pm ~1.67$% respectively, which is better than compared method. The proposed reach-and-grasp identification method can be used to develop real time systems to avail natural control of neuroprosthetic devices. Note to Practitioners—The multichannel recordings has wide applications in brain-computer interface and human-machine interaction. This paper suggests a novel foundation for the use of information preserved in amplitude envelope of multichannel EEG signals. We have demonstrated the idea in four steps: 1) variation of the proposed amplitude envelope based spectral entropy (ASE) for various modulation cases; 2) extension of ASE for multivariate data analysis and its possible application; 3) correntropy based significant channel selection to reduce the system complexity; and 4) potential use of amplitude envelope based neuronal information to develop an automated system for reach-and-grasp identification.

In brain–computer interface (BCI) applications, imagined speech (IMS) decoding based on electroencephalogram (EEG) has established a new neuro-paradigm that offers an intuitive communication tool for physically impaired patients. However, existing IMS–EEG-based BCI systems have introduced difficulties in feasible deployment due to nonstationary EEG signals, suboptimal feature extraction, and limited multiclass scalability. To address these challenges, we have presented a novel approach using the multivariate swarm-sparse decomposition method (MSSDM) for joint time–frequency (JTF) analysis and further developed a feasible end-to-end framework from multichannel IMS–EEG signals for IMS detection. MSSDM employs improved multivariate swarm filtering and sparse spectrum techniques to design optimal filter banks for extracting an ensemble of channel-aligned oscillatory components (CAOCs), significantly enhancing IMS activation-related sub-bands. To enhance channel-aligned information, multivariate JTF images have been constructed using JIF and instantaneous amplitude across channels from the obtained CAOCs. Further, JTF-based deep features (JTFDFs) were computed using different pretrained neural networks and mapped most discriminant features using two well-known feature correlation techniques: Canonical correlation analysis and Hellinger distance-based correlation. The proposed method has been tested on the 5-class BCI competition and 6-class Coretto IMS datasets. The experimental findings on cross-subject and cross-dataset reveal that the novel JTFDF feature-based classification model, MSSDM-SqueezeNet-JTFDF, achieved the highest classification performance against all other existing state-of-the-art methods in IMS recognition. Our introduced EEG–BCI models effectively enhance IMS–EEG patterns across multichannel data and offer great potential for the practical deployment of BCI technologies.

Classification of glaucoma stages remains challenging due to substantial inter-stage similarities, the presence of irrelevant features, and subtle lesion size, shape, and color variations in fundus images. For this purpose, few efforts have recently been made using traditional machine learning and deep learning models, specifically convolutional neural networks (CNN). While the conventional CNN models capture local contextual features within fixed receptive fields, they fail to exploit global contextual dependencies. Transformers, on the other hand, are capable of modeling global contextual information. However, they lack the ability to capture local contexts and merely focus on performing attention in the spatial domain, ignoring feature analysis in the frequency domain. To address these issues, we present a novel dual-domain global transformer network, Glaucoformer, to effectively classify glaucoma stages. Specifically, we propose a dual-domain global transformer layer (DGTL) consisting of dual-domain channel attention (DCA) and dual-domain spatial attention (DSA) with Fourier domain feature analyzer (FDFA) as the core component and integrated with a backbone. This helps in exploiting local and global contextual feature dependencies in both spatial and frequency domains, thereby learning prominent and discriminant feature representations. A shared key-query scheme is introduced to learn complementary features while reducing the parameters. In addition, the DGTL leverages the benefits of a deformable convolution to enable the model to handle complex lesion irregularities. We evaluate our method on a benchmark dataset, and the experimental results and extensive comparisons with existing CNN and vision transformer-based approaches indicate its effectiveness for glaucoma stage classification. Also, the results on an unseen dataset demonstrate the generalizability of the model.

This ongoing work introduces a novel chaotic oscillator, termed the Jagged-shape oscillator, into the filtering domain. We have formulated the dynamics of the Jagged-shape oscillator and integrated it with a noisy measurement model, capturing the complex behavior of various real-time systems. To estimate the unmeasured internal states of this chaotic system, we employ the third-degree spherical-cubature rule-based Kalman filter (CKF). The CKF has demonstrated efficiency in tracking the states of the chaotic oscillatory system. The accuracy of the state estimation is validated through different scenarios that consider low to increased noise levels.

The aircraft wing rock system is chaotic and highly oscillatory in nature. This work formulates the oscillatory chaotic dynamics of the wing rock system and integrates it with a noisy measurement model. Subsequently, we introduce a cubature rule-based particle filter (CPF) to track the roll angle and roll velocity (system internal states). The CPF uses the third-degree spherical-radial rule for integral approximation. The desired state estimation information may be used to design a state-based control scheme to regulate the motion of the wing rock. The simulation results showcase the performance of the proposed method in the presence of uncertainties.

In visual object decoding, magnetoencephalogram (MEG) and electroencephalogram (EEG) activation patterns demonstrate the utmost discriminative cognitive analysis due to their multivariate oscillatory nature. However, high noise in the recorded EEG-MEG signals and subject-specific variability make it extremely difficult to classify subject's cognitive responses to different visual stimuli. The proposed method is a multivariate extension of the swarm sparse decomposition method (MSSDM) for multivariate pattern analysis of EEG-MEG-based visual activation signals. In comparison, it is an advanced technique for decomposing nonstationary multicomponent signals into a finite number of channel-aligned oscillatory components that significantly enhance visual activation-related sub-bands. The MSSDM method adopts multivariate swarm filtering and sparse spectrum to automatically deliver optimal frequency bands in channel-specific sparse spectrums, resulting in improved filter banks. By combining the advantages of the multivariate SSDM and Riemann's correlation-assisted fusion feature (RCFF), the MSSDM-RCFF algorithm is investigated to improve the visual object recognition ability of EEG-MEG signals. We have also proposed time–frequency representation based on MSSDM to analyze discriminative cognitive patterns of different visual object classes from multichannel EEG-MEG signals. A proposed MSSDM is evaluated on multivariate synthetic signals and multivariate EEG-MEG signals using five classifiers. The proposed fusion feature and linear discriminant analysis classifier-based framework outperformed all existing state-of-the-art methods used for visual object detection and achieved the highest accuracy of 86.42% using tenfold cross-validation on EEG-MEG multichannel signals.

By considering limited resource-constraints of medical devices and advanced deep learning networks, in this paper, we explore a lightweight convolutional neural network (CNN) based AFibri event detector by finding suitable hyperparameters and activation function with best trade-off between the detection accuracy and model size (or computational time). This study presents extensive evaluation results of CNN-AFibri event detection methods that are obtained for different combination of model parameters: number of convolutional layers (CLs of 3, 4, and 5), number of filters (8, 16, 32, 64 and 128), activation functions (including the rectified linear unit (ReLU), leakyReLU (LReLU), exponential linear unit (ELU)), and kernel sizes ($3 \times 1 $,$ 4 \times 1$). In addition to different CNN-AFibri models, we validate their performances under different ECG segment duration of 5, 10 and 30 seconds. On the standard databases and unseen databases, the CNN-AFibri model with the CLs of 5, ELU function and kernel size of$ 4 \times 1$had a highest accuracy of 99.97% (specificity of 99.98% and sensitivity of 99.95%) for 5 second ECG segments as compared to the performances of 54 CNN-AFibri models reported in this paper and other existing deep learning based methods on the same validation databases. Real-time implementation of the best CNN based method with a model size of 3.14 Megabyte is demonstrated using the Raspberry Pi computing platform with Broadcom BCM2711, 1.5 GHz Cortex-A72 quad-core CPU with 8 GB RAM. Results demonstrated that the average processing times are less than 3 ms and 11 ms for processing 5 s and 30 s ECG segments, respectively with an accuracy reduction of less than 1% as compared to the same model tested on the personal computer with Intel(R) Xeon(R) W-2133 3.60 GHz Processor with 6 core and 128 GB RAM.

The accurate automated eye movement classification is gaining importance in the field of human–computer interaction (HCI). The present article aims at the classification of six types of eye movements from electromyogram (EMG) of extraocular muscles (EOM) signals using the Fourier–Bessel series expansion-based empirical wavelet transform (FBSE-EWT) with time and frequency-domain (TAFD) features. The FBSE-EWT of EMG signals results in Fourier–Bessel intrinsic mode functions (FBIMFs), which correspond to the frequency contents in the signal. A hybrid approach is used to select the prominent FBIMFs followed by the statistical and signal complexity-based feature extraction. Furthermore, metaheuristic optimization algorithms are employed to reduce the feature space dimension. The discrimination ability of the reduced feature set is verified by Kruskal–Wallis statistical test. Multiclass support vector machine (MSVM) has been employed for classification. First, the classification has been performed with TAFD features followed by the combination of TAFD and FBSE-EWT-based reduced feature set. The combination of TAFD and FBSE-EWT-based feature set has provided good classification performance. This study demonstrates the efficacy of FBSE-EWT and subsequent metaheuristic feature selection algorithms in classifying the eye movements from EMG of EOM signals. The combination of TAFD and the selected features through salp swarm optimization algorithm has provided maximum classification accuracy of 98.91% with MSVM employing Gaussian and radial basis function kernels. Thus, the proposed approach has the potential to be used in HCI applications involving biomedical signals.

The variational nonlinear chirp mode decomposition (VNCMD) requires initialization of number of modes (NMs) and instantaneous frequency (IF). This article proposes an automated method for NM selection and IF initialization, which works on the scale-space representation-based automated boundary detection in a magnitude spectrum. The proposed automated VNCMD (AVNCMD) method is applied for bearing fault detection in which the kurtosis-based dominant mode selection method is recommended. The instantaneous amplitude and IF with spectral entropy are computed from the dominant mode. Features are given to a feed-forward neural network classifier. The methodology is investigated on two datasets for inner-race, outer-race, and ball-race faults detection. The proposed method classifies inner-race, outer-race, and ball-race bearing faults with 97.52% accuracy and classifies inner-race and outer-race bearing faults with 100% accuracy. The efficacy of the proposed method is compared with the existing methods to justify the superiority.

Abstract Alzheimer's disease (AD) is the most prevalent form of dementia. Although fewer people, who suffer from AD are correctly and promptly diagnosed, due to a lack of knowledge of its cause and unavailability of treatment, AD is more manageable if the symptoms of mild cognitive impairment (MCI) are in an early stage. In recent years, computer‐aided diagnosis has been widely used for the diagnosis of AD. The main motive of this paper is to improve the classification and prediction accuracy of AD. In this paper, a novel approach is developed to classify MCI, normal control (NC), and AD using structural magnetic resonance imaging (sMRI) from the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset (50 AD, 50 NC, 50 MCI subjects). FreeSurfer is used to process these MRI data and obtain cortical features such as volume, surface area, thickness, white matter (WM), and intrinsic curvature of the brain regions. These features are modified by normalizing each cortical region's features using the absolute maximum value of that region's features from all subjects in each group of MCI, NC, and AD independently. A total of 420 features are obtained. To address the curse of dimensionality, the obtained features are reduced to 30 features using a sequential feature selection technique. Three classifiers, namely the twin support vector machine (TSVM), least squares TSVM (LSTSVM), and robust energy‐based least squares TSVM (RELS‐TSVM), are used to evaluate the classification accuracy from the obtained features. Five‐fold and 10‐fold cross‐validation are used to validate the proposed method. Experimental results show an accuracy of 100% for the studied database. The proposed approach is innovative due to its higher classification accuracy compared to methods in the existing literature.

Novel coronavirus (COVID-19) is spreading rapidly and has taken millions of lives worldwide. A medical study has shown that COVID-19 affects the lungs of patients and shows the symptoms of pneumonia. X-ray images with artificial intelligence (AI) can be useful for a fast and accurate diagnosis of COVID19. It can also solve the problem of less testing kits and fewer doctors. In this paper, we have introduced the Fourier-Bessel series expansion-based dyadic decomposition (FBD) method for image decomposition. This FBD is used to decompose an X-ray image into subband images. Obtained subband images are then fed to ResNet50 pre-trained convolution neural network (CNN) individually. Deep features from each CNN are ensembled using operations, namely; maxima (max), minima (min), average (avg), and fusion (fus). Ensemble CNN features are then fed to the softmax classifier. In the study, a total of 750 X-ray images are collected. Out of 750 X-ray images, 250 images are of pneumonia patients, 250 of COVID-19 patients, and 250 healthy subjects. The proposed model has provided an overall accuracy of 98.6% using fus ensemble ResNet-50 CNN model.

Glaucoma is a critical and irreversible neurodegenerative eye disorder caused by damaging optical nerve head due to increased intra‐ocular pressure within the eye. Detection of glaucoma is a critical job for ophthalmologists. This study presents a novel and more accurate method for automated glaucoma detection using quasi‐bivariate variational mode decomposition (QB‐VMD) from digital fundus images. In total, 505 fundus images are decomposed using QB‐VMD method which gives band limited sub‐band images (SBIs) centred around a particular frequency. These SBIs are smooth and free from mode mixing problems. The glaucoma detection accuracy depends on the most useful features as it captured appropriate information. Seventy features are extracted from QB‐VMD SBIs. Extracted features are normalised and selected using ReliefF method. Selected features are then fed to singular value decomposition to reduce their dimensionality. Finally, the reduced features are classified using least square support vector machine classifier. The obtained glaucoma detection accuracies are 85.94 and 86.13% using three‐ and ten‐fold cross validation, respectively. Obtained results are better than the existing. It may become a suitable method for ophthalmologists to examine eye disease more accurately using fundus images.

The performance of a brain–computer interface (BCI) will generally improve by increasing the volume of training data on which it is trained. However, a classifier’s generalization ability is often negatively affected when highly non-stationary data are collected across both sessions and subjects. The aim of this work is to reduce the long calibration time in BCI systems by proposing a transfer learning model which can be used for evaluating unseen single trials for a subject without the need for training session data. A method is proposed which combines a generalization of the previously proposed subject-specific “multivariate empirical-mode decomposition” preprocessing technique by taking a fixed band of 8–30[Formula: see text]Hz for all four motor imagery tasks and a novel classification model which exploits the structure of tangent space features drawn from the Riemannian geometry framework, that is shared among the training data of multiple sessions and subjects. Results demonstrate comparable performance improvement across multiple subjects without subject-specific calibration, when compared with other state-of-the-art techniques.

In this paper, we propose a new method for automated classification of focal (epileptic) and non-focal (non-epileptic) electroencephalogram (EEG) signals. We use bivariate EEG signals of both epileptic and non-epileptic classes as our dataset. Difference time series of bivariate EEG signals is first computed to eliminate the effect of noise. Then the difference time series EEG signals are decomposed into coefficients using Fourier-Bessel (FB) series expansion. FB series expansion is a new method for signal decomposition that decomposes the signal into a finite and unique set of coefficients. The decomposition process yields coefficients which are further divided into 5 segments which are considered for the extraction of features, where for each signal 17 different features are computed. These extracted features are used for binary classification of EEG signals into epileptic and non-epileptic classes. We have implemented least square support vector machine (LS-SVM) along with various kernel functions such as linear, polynomial, and radial basis function (RBF) in our work. Classification accuracies obtained using these kernels and 10-fold crossvalidation are compared. With the proposed methodology, we can classify the EEG signals into focal and non-focal class with a significant accuracy.

Glaucoma is an ocular disorder caused due to increased fluid pressure in the optic nerve. It damages the optic nerve and subsequently causes loss of vision. The available scanning methods are Heidelberg retinal tomography, scanning laser polarimetry, and optical coherence tomography. These methods are expensive and require experienced clinicians to use them. So, there is a need to diagnose glaucoma accurately with low cost. Hence, in this paper, we have presented a new methodology for an automated diagnosis of glaucoma using digital fundus images based on empirical wavelet transform (EWT). The EWT is used to decompose the image, and correntropy features are obtained from decomposed EWT components. These extracted features are ranked based on t value feature selection algorithm. Then, these features are used for the classification of normal and glaucoma images using least-squares support vector machine (LS-SVM) classifier. The LS-SVM is employed for classification with radial basis function, Morlet wavelet, and Mexican-hat wavelet kernels. The classification accuracy of the proposed method is 98.33% and 96.67% using threefold and tenfold cross validation, respectively.

The electroencephalogram (EEG) signals are commonly used for diagnosis of epilepsy. In this paper, we present a new methodology for EEG-based automated diagnosis of epilepsy. Our method involves detection of key points at multiple scales in EEG signals using a pyramid of difference of Gaussian filtered signals. Local binary patterns (LBPs) are computed at these key points and the histogram of these patterns are considered as the feature set, which is fed to the support vector machine (SVM) for the classification of EEG signals. The proposed methodology has been investigated for the four well-known classification problems namely, 1) normal and epileptic seizure, 2) epileptic seizure and seizure free, 3) normal, epileptic seizure, and seizure free, and 4) epileptic seizure and nonseizure EEG signals using publically available university of Bonn EEG database. Our experimental results in terms of classification accuracies have been compared with existing methods for the classification of the aforementioned problems. Further, performance evaluation on another EEG dataset shows that our approach is effective for classification of seizure and seizure-free EEG signals. The proposed methodology based on the LBP computed at key points is simple and easy to implement for real-time epileptic seizure detection.

In this paper, we present a new filtering method based on the empirical mode decomposition (EMD) for classification of motor imagery (MI) electroencephalogram (EEG) signals for enhancing brain-computer interface (BCI). The EMD method decomposes EEG signals into a set of intrinsic mode functions (IMFs). These IMFs can be considered narrow-band, amplitude and frequency modulated (AM-FM) signals. The mean frequency measure of these IMFs has been used to combine these IMFs in order to obtain the enhanced EEG signals which have major contributions due to μ and β rhythms. The main aim of the proposed method is to filter EEG signals before feature extraction and classification to enhance the features separability and ultimately the BCI task classification performance. The features namely, Hjorth and band power features computed from the enhanced EEG signals, have been used as a feature set for classification of left hand and right hand MIs using a linear discriminant analysis (LDA) based classification method. Significant superior performance is obtained when the method is tested on the BCI competition IV datasets, which demonstrates the effectiveness of the proposed method.

We propose a robust event-based method for estimation of the instantaneous fundamental frequency of a voiced speech signal. The amplitude and frequency modulated (AM-FM) signal model of voiced speech in the low frequency range (LFR) indicates the presence of energy only around its instantaneous fundamental frequency ( F0) and its few harmonics. The time-varying F0component of a voiced speech signal is extracted by a robust algorithm which iteratively performs eigenvalue decomposition (EVD) of the Hankel matrix, initially constructed from samples of the LFR filtered voiced speech signal. The negative cycles of the extracted time-varying F0component provide a reliable coarse estimate of intervals where glottal closure instants (GCIs) may be present. The negative cycles of the LFR filtered voiced speech signal occurring within these intervals are isolated. There is a sudden decrease in the glottal impedance at GCIs resulting in high signal strength. Therefore, GCIs are detected as local minima in the derivative of the falling edges of the isolated negative cycles of the LFR filtered voiced speech signal, followed by a selection criterion to discard false GCI candidates. The instantaneous F0is estimated as the inverse of the time interval between two consecutive GCIs. Experiments were performed on the Keele and CSTR speech databases in white and babble noise environments at various levels of degradation to assess the performance of the proposed method. The proposed method substantially reduces the gross F0estimation errors in comparison to some state of the art methods.

In this paper, we present a new method for classification of electroencephalogram (EEG) signals using empirical mode decomposition (EMD) method. The intrinsic mode functions (IMFs) generated by EMD method can be considered as a set of amplitude and frequency modulated (AM-FM) signals. The Hilbert transformation of IMFs provides an analytic signal representation of the IMFs. The two bandwidths, namely amplitude modulation bandwidth (B(AM)) and frequency modulation bandwidth (B(FM)), computed from the analytic IMFs, have been used as an input to least squares support vector machine (LS-SVM) for classifying seizure and non-seizure EEG signals. The proposed method for classification of EEG signals based on the bandwidth features (B(A M) and B (FM)) and the LS-SVM has provided better classification accuracy than the method of Liang et. al [20]. The experimental results with the recorded EEG signals from a published dataset are included to show the effectiveness of the proposed method for EEG signal classification.

This paper presents a new method for analysis of center of pressure (COP) signals using empirical mode decomposition (EMD). The EMD decomposes a COP signal into a finite set of band-limited signals termed as intrinsic mode functions (IMFs). Thereafter, a signal processing technique used in continuous chaotic modeling is used to investigate the difference between experimental conditions on the summed IMFs. This method is used to detect the degree of variability from a second-order difference plot, which is quantified using a Central Tendency Measure (CTM). Seventeen subjects were tested under eyes open (EO) and eyes closed (EC) conditions, with different vibration frequencies applied for the EC condition in order to provide additional sensory perturbation. This study has demonstrated an effective way to differentiate vibration frequencies by combining EMD and second-order difference (SOD) plots.