Search Results (19)

Neonatal seizures are a critical early indicator of neurological injury, yet effective automated detection is challenged by significant inter-subject variability in electroencephalogram (EEG) signals. To address this generalization gap, this study introduces the Domain-Adversarial Spatiotemporal Network (DA-STNet) for robust cross-subject seizure detection. Utilizing Short-Time Fourier Transform (STFT) spectrograms, the architecture employs a hierarchical backbone comprising a Channel-Independent CNN (CI-CNN) for local texture extraction, a Spatial Bidirectional Long Short-Term Memory (Bi-LSTM) for modeling topological dependencies, and Attention Pooling to dynamically prioritize pathological channels while suppressing noise. Crucially, a Gradient Reversal Layer (GRL) is integrated to enforce domain-adversarial training, decoupling pathological features from subject-specific identity to ensure domain invariance. Under rigorous 5-fold cross-validation, the model achieves State-of-the-Art performance with an average Area Under the Curve (AUC) of 0.9998 and an F1-score of 0.9952. Data scaling experiments further reveal that optimal generalization is attainable using only 80% of source data, highlighting the model’s superior data efficiency. These findings demonstrate the proposed method’s capability to reduce reliance on extensive clinical annotations while maintaining high diagnostic precision in complex clinical scenarios. Full article

Accurate classification of brain activity from electroencephalogram signals is essential for diagnosing neurological disorders such as epilepsy. In this paper, we propose an explainable deep learning method for epileptic seizure detection. The proposed approach converts electroencephalogram signals into audio waveforms, which are then transformed into time–frequency representations using two distinct continuous wavelet transforms, i.e., the Morlet and the Mexican Hat. These wavelet-based spectrograms effectively capture both temporal and spectral characteristics of the electroencephalogram signal data and serve as inputs to a set of convolutional neural network models with the aim to detect seizure activity. To improve model transparency, the proposed method integrates three class activation mapping techniques aimed to visualize the salient regions in the wavelet images that influence each prediction. Experimental evaluation on a real-world dataset emphasizes the efficacy of wavelet-based preprocessing in electroencephalogram signal analysis in prompt epileptic seizure detection, showing an accuracy equal to 0.922. Full article

Despite the popularity of electroencephalograms (EEGs) as tools for assessing brain health, they can sometimes be abstract and prone to noise, making them difficult to interpret. The following work aims to implement a Quaternion Convolutional Neural Network (QCNN) to detect abnormal EEGs obtained from a database that includes both people with excellent mental health and individuals with different types of mental illnesses. Unlike other approaches in which the QCNN is used exclusively for image processing, in the present work, a unique architecture with mainly quaternionic layers is proposed, specifically designed for the classification of time-varying signals. Using the database “The TUH EEG Abnormal Corpus”, the signals are preprocessed using the Wavelet Transform, a mathematical tool capable of performing simultaneous time and frequency analysis, configured with a level 4 decomposition value. Subsequently, the results are subjected to a partial spectrogram-type treatment to integrate the energy parameter into the analysis. They are then conditioned in each of the elements of the quaternion and processed by the QCNN, leveraging quaternion algebra to maintain the relationships between its elements, both in the input and in the convolutional product. In this way, it is possible to obtain significant percentages in the precision, recall, and accuracy metrics with values higher than 77%. Its performance, which uses 4 times less computational memory, allows the QCNN to be considered an alternative for classifying EEG signals. Finally, a comparison of the proposed model was made with other architectures commonly used in the literature, as well as with developments in other research and with a hybrid model whose performance places it at the highest classification standard, not to mention the ability of the QCNN to preserve multi-channel dependencies in EEG signals in a more natural way, achieving parameter efficiencies by leveraging quaternion algebra, reducing the computational cost compared to real-valued CNNs. Full article

Diagnosing dementia and recognizing substantial cognitive decline are challenging tasks. Thus, the objective of this study was to classify electroencephalograms (EEGs) recorded during a working memory task in 15 patients with mild cognitive impairment (MCogImp), 5 patients with vascular dementia (VasD), and 15 healthy controls (NC). Before creating spectrogram pictures from the EEG dataset, the data were subjected to preprocessing, which included preprocessing using conventional filters and the discrete wavelet transformation. The convolutional neural network (CNN) MobileNetV2 was employed in our investigation to identify features and assess the severity of dementia. The features were extracted from five layers of the MobileNetV2 CNN architecture—convolutional layers (‘Conv-1’), batch normalization (‘Conv-1-bn’), clipped ReLU (‘out-relu’), 2D Global Average Pooling (‘global-average-pooling2d1’), and fully connected (‘Logits’) layers. This was carried out to find the efficient features layer for dementia severity from EEGs. Feature extraction from MobileNetV2’s five layers was carried out using a decision tree (DT) and k-nearest neighbor (KNN) machine learning (ML) classifier, in conjunction with a MobileNetV2 deep learning (DL) network. The study’s findings show that the DT classifier performed best using features derived from MobileNetV2 with the 2D Global Average Pooling (global-average-pooling2d-1) layer, achieving an accuracy score of 95.9%. Second place went to the characteristics of the fully connected (Logits) layer, which achieved a score of 95.3%. The findings of this study endorse the utilization of deep processing algorithms, offering a viable approach for improving early dementia identification with high precision, hence facilitating the differentiation among NC individuals, VasD patients, and MCogImp patients. Full article

Electroencephalogram (EEG) analysis is essential for diagnosing neurological disorders but typically requires expert interpretation and significant time. Purpose: This study aims to automate the classification of normal and abnormal EEG recordings to support clinical diagnosis and reduce manual workload. Automating the initial screening of EEGs can help clinicians quickly identify potential neurological abnormalities, enabling timely intervention and guiding further diagnostic and treatment strategies. Methodology: We utilized the Temple University Hospital EEG dataset to develop a DenseNet-based deep learning model. To enable a fair comparison of different EEG representations, we used three input types: signal images, spectrograms, and scalograms. To reduce dimensionality and simplify computation, we focused on two channels: T5 and O1. For interpretability, we applied Local Interpretable Model-agnostic Explanations (LIME) and Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize the EEG regions influencing the model’s predictions. Key Findings: Among the input types, spectrogram-based representations achieved the highest classification accuracy, indicating that time-frequency features are especially effective for this task. The model demonstrated strong performance overall, and the integration of LIME and Grad-CAM provided transparent explanations of its decisions, enhancing interpretability. This approach offers a practical and interpretable solution for automated EEG screening, contributing to more efficient clinical workflows and better understanding of complex neurological conditions. Full article

Background/Objectives: Epilepsy is a common neurological disorder with pathological mechanisms closely associated with the spatiotemporal dynamic characteristics of electroencephalogram (EEG) signals. Although significant progress has been made in epileptic seizure detection methods using time–frequency analysis, current research still faces challenges in terms of an insufficient utilization of phase information. Methods: In this study, we propose an effective epileptic seizure detection framework based on continuous wavelet transform (CWT) and a hybrid network consisting of convolutional neural network (CNN) and vision transformer (ViT). First, the raw EEG signals are processed by the CWT. Then, the phase spectrogram and power spectrogram of the EEG are generated, and they are sent into the designed CNN and ViT branches of the network to extract more discriminative EEG features. Finally, the features output from the two branches are fused and fed into the classification network to obtain the detection results. Results: Experimental results on the CHB-MIT public dataset and our SH-SDU clinical dataset show that the proposed framework achieves sensitivities of 98.09% and 89.02%, specificities of 98.21% and 95.46%, and average accuracies of 98.45% and 94.66%, respectively. Furthermore, we compared the spectral characteristics of CWT with other time–frequency transforms within the hybrid architecture, demonstrating the advantages of the CWT-based CNN-ViT architecture. Conclusions: These results highlight the outstanding epileptic seizure detection performance of the proposed framework and its significant clinical feasibility. Full article

The electroencephalogram (EEG) is a cornerstone tool for the diagnosis, management, and prognosis of selected patient populations. EEGs offer significant advantages such as high temporal resolution, real-time cortical function assessment, and bedside usability. The quantitative EEG (qEEG) added the possibility of long recordings being processed in a compressive manner, making EEG revision more efficient for experienced users, and more friendly for new ones. Recent advancements in commercially available software, such as Persyst, have significantly expanded and facilitated the use of qEEGs, marking the beginning of a new era in its application. As a result, there has been a notable increase in the practical, real-world utilization of qEEGs in recent years. This paper aims to provide an overview of the current applications of qEEGs in daily neurological emergencies and ICU practice, and some elementary principles of qEEGs using Persyst software in clinical settings. This article illustrates basic qEEG patterns encountered in critical care and adopts the new terminology proposed for spectrogram reporting. Full article

Epileptic seizure detection has undergone progressive advancements since its conception in the 1970s. From proof-of-concept experiments in the latter part of that decade, it has now become a vibrant area of clinical and laboratory research. In an effort to bring this technology closer to practical application in human patients, this study introduces a customized approach to selecting electroencephalogram (EEG) features and electrode positions for seizure prediction. The focus is on identifying precursors that occur within 10 min of the onset of abnormal electrical activity during a seizure. However, there are security concerns related to safeguarding patient EEG recordings against unauthorized access and network-based attacks. Therefore, there is an urgent need for an efficient prediction and classification method for encrypted EEG data. This paper presents an effective system for analyzing and recognizing encrypted EEG information using Arnold transform algorithms, chaotic mapping, and convolutional neural networks (CNNs). In this system, the EEG time series from each channel is converted into a 2D spectrogram image, which is then encrypted using chaotic algorithms. The encrypted data is subsequently processed by CNNs coupled with transfer learning (TL) frameworks. To optimize the fusion parameters of the ensemble learning classifiers, a hybridized spoofing optimization method is developed by combining the characteristics of corvid and gregarious-seeking agents. The evaluation of the model’s effectiveness yielded the following results: 98.9 ± 0.3% accuracy, 98.2 ± 0.7% sensitivity, 98.6 ± 0.6% specificity, 98.6 ± 0.6% precision, and an F1 measure of 98.9 ± 0.6%. When compared with other state-of-the-art techniques applied to the same dataset, this novel strategy demonstrated one of the most effective seizure detection systems, as evidenced by these results. Full article

Migraine is a neurological disorder that is associated with severe headaches and seriously affects the lives of patients. Diagnosing Migraine Disease (MD) can be laborious and time-consuming for specialists. For this reason, systems that can assist specialists in the early diagnosis of MD are important. Although migraine is one of the most common neurological diseases, there are very few studies on the diagnosis of MD, especially electroencephalogram (EEG)-and deep learning (DL)-based studies. For this reason, in this study, a new system has been proposed for the early diagnosis of EEG- and DL-based MD. In the proposed study, EEG signals obtained from the resting state (R), visual stimulus (V), and auditory stimulus (A) from 18 migraine patients and 21 healthy control (HC) groups were used. By applying continuous wavelet transform (CWT) and short-time Fourier transform (STFT) methods to these EEG signals, scalogram-spectrogram images were obtained in the time-frequency (T-F) plane. Then, these images were applied as inputs in three different convolutional neural networks (CNN) architectures (AlexNet, ResNet50, SqueezeNet) that proposed deep convolutional neural network (DCNN) models and classification was performed. The results of the classification process were evaluated, taking into account accuracy (acc.), sensitivity (sens.), specificity (spec.), and performance criteria, and the performances of the preferred methods and models in this study were compared. In this way, the situation, method, and model that showed the most successful performance for the early diagnosis of MD were determined. Although the classification results are close to each other, the resting state, CWT method, and AlexNet classifier showed the most successful performance (Acc: 99.74%, Sens: 99.9%, Spec: 99.52%). We think that the results obtained in this study are promising for the early diagnosis of MD and can be of help to experts. Full article

The accurate identification of the human emotional status is crucial for an efficient human–robot interaction (HRI). As such, we have witnessed extensive research efforts made in developing robust and accurate brain–computer interfacing models based on diverse biosignals. In particular, previous research has shown that an Electroencephalogram (EEG) can provide deep insight into the state of emotion. Recently, various handcrafted and deep neural network (DNN) models were proposed by researchers for extracting emotion-relevant features, which offer limited robustness to noise that leads to reduced precision and increased computational complexity. The DNN models developed to date were shown to be efficient in extracting robust features relevant to emotion classification; however, their massive feature dimensionality problem leads to a high computational load. In this paper, we propose a bag-of-hybrid-deep-features (BoHDF) extraction model for classifying EEG signals into their respective emotion class. The invariance and robustness of the BoHDF is further enhanced by transforming EEG signals into 2D spectrograms before the feature extraction stage. Such a time-frequency representation fits well with the time-varying behavior of EEG patterns. Here, we propose to combine the deep features from the GoogLeNet fully connected layer (one of the simplest DNN models) together with the OMTLBP_SMC texture-based features, which we recently developed, followed by a K-nearest neighbor (KNN) clustering algorithm. The proposed model, when evaluated on the DEAP and SEED databases, achieves a 93.83 and 96.95% recognition accuracy, respectively. The experimental results using the proposed BoHDF-based algorithm show an improved performance in comparison to previously reported works with similar setups. Full article

Emotion charting using multimodal signals has gained great demand for stroke-affected patients, for psychiatrists while examining patients, and for neuromarketing applications. Multimodal signals for emotion charting include electrocardiogram (ECG) signals, electroencephalogram (EEG) signals, and galvanic skin response (GSR) signals. EEG, ECG, and GSR are also known as physiological signals, which can be used for identification of human emotions. Due to the unbiased nature of physiological signals, this field has become a great motivation in recent research as physiological signals are generated autonomously from human central nervous system. Researchers have developed multiple methods for the classification of these signals for emotion detection. However, due to the non-linear nature of these signals and the inclusion of noise, while recording, accurate classification of physiological signals is a challenge for emotion charting. Valence and arousal are two important states for emotion detection; therefore, this paper presents a novel ensemble learning method based on deep learning for the classification of four different emotional states including high valence and high arousal (HVHA), low valence and low arousal (LVLA), high valence and low arousal (HVLA) and low valence high arousal (LVHA). In the proposed method, multimodal signals (EEG, ECG, and GSR) are preprocessed using bandpass filtering and independent components analysis (ICA) for noise removal in EEG signals followed by discrete wavelet transform for time domain to frequency domain conversion. Discrete wavelet transform results in spectrograms of the physiological signal and then features are extracted using stacked autoencoders from those spectrograms. A feature vector is obtained from the bottleneck layer of the autoencoder and is fed to three classifiers SVM (support vector machine), RF (random forest), and LSTM (long short-term memory) followed by majority voting as ensemble classification. The proposed system is trained and tested on the AMIGOS dataset with k-fold cross-validation. The proposed system obtained the highest accuracy of 94.5% and shows improved results of the proposed method compared with other state-of-the-art methods. Full article

The classification of sleep stages is an important process. However, this process is time-consuming, subjective, and error-prone. Many automated classification methods use electroencephalogram (EEG) signals for classification. These methods do not classify well enough and perform poorly in the N1 due to unbalanced data. In this paper, we propose a sleep stage classification method using EEG spectrogram. We have designed a deep learning model called EEGSNet based on multi-layer convolutional neural networks (CNNs) to extract time and frequency features from the EEG spectrogram, and two-layer bi-directional long short-term memory networks (Bi-LSTMs) to learn the transition rules between features from adjacent epochs and to perform the classification of sleep stages. In addition, to improve the generalization ability of the model, we have used Gaussian error linear units (GELUs) as the activation function of CNN. The proposed method was evaluated by four public databases, the Sleep-EDFX-8, Sleep-EDFX-20, Sleep-EDFX-78, and SHHS. The accuracy of the method is 94.17%, 86.82%, 83.02% and 85.12%, respectively, for the four datasets, the MF1 is 87.78%, 81.57%, 77.26% and 78.54%, respectively, and the Kappa is 0.91, 0.82, 0.77 and 0.79, respectively. In addition, our proposed method achieved better classification results on N1, with an F1-score of 70.16%, 52.41%, 50.03% and 47.26% for the four datasets. Full article

A promising approach to overcome the various shortcomings of password systems is the use of biometric authentication, in particular the use of electroencephalogram (EEG) data. In this paper, we propose a subject-independent learning method for EEG-based biometrics using Hilbert spectrograms of the data. The proposed neural network architecture treats the spectrogram as a collection of one-dimensional series and applies one-dimensional dilated convolutions over them, and a multi-similarity loss was used as the loss function for subject-independent learning. The architecture was tested on the publicly available PhysioNet EEG Motor Movement/Imagery Dataset (PEEGMIMDB) with a 14.63% Equal Error Rate (EER) achieved. The proposed approach’s main advantages are subject independence and suitability for interpretation via created spectrograms and the integrated gradients method. Full article

Non-stationary signals are often analyzed using raw waveform data or spectrograms of those data; however, the possibility of alternative time–frequency representations being more informative than the original data or spectrograms is yet to be investigated. This paper tested whether alternative time–frequency representations could be more informative for machine learning classification of seismological data. The mentioned hypothesis was evaluated by training three well-established convolutional neural networks using nine time–frequency representations. The results were compared to the base model, which was trained on the raw waveform data. The signals that were used in the experiment are three-component seismogram instances from the Local Earthquakes and Noise DataBase (LEN-DB). The results demonstrate that Pseudo Wigner–Ville and Wigner–Ville time–frequency representations yield significantly better results than the base model, while spectrogram and Margenau–Hill perform significantly worse (p < 0.01). Interestingly, the spectrogram, which is often used in signal analysis, had inferior performance when compared to the base model. The findings presented in this research could have notable impacts in the fields of geophysics and seismology as the phenomena that were previously hidden in the seismic noise are now more easily identified. Furthermore, the results indicate that applying Pseudo Wigner–Ville or Wigner–Ville time–frequency representations could result in a large increase in earthquakes in the catalogs and lessen the need to add new stations with an overall reduction in the costs. Finally, the proposed approach of extracting valuable information through time–frequency representations could be applied in other domains as well, such as electroencephalogram and electrocardiogram signal analysis, speech recognition, gravitational waves investigation, and so on. Full article

Parkinson’s disease (PD) is globally the most common neurodegenerative movement disorder. It is characterized by a loss of dopaminergic neurons in the substantia nigra of the brain. However, current methods to diagnose PD on the basis of clinical features of Parkinsonism may lead to misdiagnoses. Hence, noninvasive methods such as electroencephalographic (EEG) recordings of PD patients can be an alternative biomarker. In this study, a deep-learning model is proposed for automated PD diagnosis. EEG recordings of 16 healthy controls and 15 PD patients were used for analysis. Using Gabor transform, EEG recordings were converted into spectrograms, which were used to train the proposed two-dimensional convolutional neural network (2D-CNN) model. As a result, the proposed model achieved high classification accuracy of 99.46% (±0.73) for 3-class classification (healthy controls, and PD patients with and without medication) using tenfold cross-validation. This indicates the potential of proposed model to simultaneously automatically detect PD patients and their medication status. The proposed model is ready to be validated with a larger database before implementation as a computer-aided diagnostic (CAD) tool for clinical-decision support. Full article