Search Results (128)

Sleep staging is a crucial indicator for assessing sleep quality, which contributes to sleep monitoring and the diagnosis of sleep disorders. Although existing sleep staging methods achieve high classification performance, two major challenges remain: (1) the ability to effectively extract salient features from multi-channel sleep data remains limited; (2) excessive model parameters hinder efficiency improvements. To address these challenges, this work proposes a lightweight multi-channel sleep staging network (LMCSleepNet). LMCSleepNet is composed of four modules. The first module enhances frequency domain features through continuous wavelet transform. The second module extracts time–frequency features using multi-scale convolutions. The third module optimizes ResNet18 with depthwise separable convolutions to reduce parameters. The fourth module improves spatial correlation using the Convolutional Block Attention Module (CBAM). On the public datasets SleepEDF-20, SleepEDF-78, and LMCSleepNet, respectively, LMCSleepNet achieved classification accuracies of 88.2% (κ = 0.84, MF1 = 82.4%) and 84.1% (κ = 0.77, MF1 = 77.7%), while reducing model parameters to 1.49 M. Furthermore, experiments validated the influence of temporal sampling points in wavelet time–frequency maps on sleep classification performance (accuracy, Cohen’s kappa, and macro-average F1-score) and the influence of multi-scale dilated convolution module fusion methods on classification performance. LMCSleepNet is an efficient lightweight model for extracting and integrating multimodal features from multichannel Polysomnography (PSG) data, which facilitates its application in resource-constrained scenarios. Full article

Advancements in electroencephalography (EEG) technology and feature extraction methods have paved the way for wearable, non-invasive systems that enable continuous sleep monitoring outside clinical environments. This study presents the development and evaluation of an EEG-based acquisition system for sleep staging, which can be adapted for wearable applications. The system utilizes a custom experimental setup with the ADS1299EEG-FE-PDK evaluation board to acquire EEG signals from the forehead and in-ear regions under various conditions, including visual and auditory stimuli. Afterward, the acquired signals were processed to extract a wide range of features in time, frequency, and non-linear domains, selected based on their physiological relevance to sleep stages and disorders. The feature set was reduced using the Minimum Redundancy Maximum Relevance (mRMR) algorithm and Principal Component Analysis (PCA), resulting in a compact and informative subset of principal components. Experiments were conducted on the Bitbrain Open Access Sleep (BOAS) dataset to validate the selected features and assess their robustness across subjects. The feature set extracted from a single EEG frontal derivation (F4-F3) was then used to train and test a two-step deep learning model that combines Long Short-Term Memory (LSTM) and dense layers for 5-class sleep stage classification, utilizing attention and augmentation mechanisms to mitigate the natural imbalance of the feature set. The results—overall accuracies of 93.5% and 94.7% using the reduced feature sets (94% and 98% cumulative explained variance, respectively) and 97.9% using the complete feature set—demonstrate the feasibility of obtaining a reliable classification using a single EEG derivation, mainly for unobtrusive, home-based sleep monitoring systems. Full article

With the rapid development of modern industry, people’s living pressures are gradually increasing, and an increasing number of individuals are affected by sleep disorders such as insomnia, hypersomnia, and sleep apnea syndrome. Many cardiovascular and psychiatric diseases are also closely related to sleep. Therefore, the early detection, accurate diagnosis, and treatment of sleep disorders an urgent research priority. Traditional manual sleep staging methods have many problems, such as being time-consuming and cumbersome, relying on expert experience, or being subjective. To address these issues, researchers have proposed multiple algorithmic strategies for sleep staging automation based on deep learning in recent years. This paper studies MASleepNet, a sleep staging neural network model that integrates multimodal deep features. This model takes multi-channel Polysomnography (PSG) signals (including EEG (Fpz-Cz, Pz-Oz), EOG, and EMG) as input and employs a multi-scale convolutional module to extract features at different time scales in parallel. It then adaptively weights and fuses the features from each modality using a channel-wise attention mechanism. The integrated temporal features are integrated into a Bidirectional Long Short-Term Memory (BiLSTM) sequence encoder, where an attention mechanism is introduced to identify key temporal segments. The final classification result is produced by the fully connected layer. The proposed model was experimentally evaluated on the Sleep-EDF dataset (consisting of two subsets, Sleep-EDF-78 and Sleep-EDF-20), achieving classification accuracies of 82.56% and 84.53% on the two subsets, respectively. These results demonstrate that deep models that integrate multimodal signals and an attention mechanism offer the possibility to enhance the efficiency of automatic sleep staging compared to cutting-edge methods. Full article

Improving the decoding accuracy of biological signals has been a research focus for decades to advance health, automation, and robotic industries. However, challenges like inter-subject variability, data scarcity, and multifunctional variability cause low decoding accuracy, thus hindering the practical deployment of biological signal paradigms. This paper proposes a multifunctional biological signals network (Multi-BioSig-Net) that addresses the aforementioned issues by devising a novel blind few-shot learning (FSL) technique to quickly adapt to multiple target domains without needing a pre-trained model. Specifically, our proposed multimodal similarity extractor (MMSE) and self-multiple domain adaptation (SMDA) modules address data scarcity and inter-subject variability issues by exploiting and enhancing the similarity between multimodal samples and quickly adapting the target domains by adaptively adjusting the parameters’ weights and position, respectively. For multifunctional learning, we proposed inter-function discriminator (IFD) that discriminates the classes by extracting inter-class common features and then subtracts them from both classes to avoid false prediction of the proposed model due to overfitting on the common features. Furthermore, we proposed a holistic-local fusion (HLF) module that exploits contextual-detailed features to adapt the scale-varying features across multiple functions. In addition, fractal dimension estimation (FDE) was employed for the classification of left-hand motor imagery (LMI) and right-hand motor imagery (RMI), confirming that proposed method can effectively extract the discriminative features for this task. The effectiveness of our proposed algorithm was assessed quantitatively and statistically against competent state-of-the-art (SOTA) algorithms utilizing three public datasets, demonstrating that our proposed algorithm outperformed SOTA algorithms. Full article

Obstructive sleep apnea–hypopnea syndrome (OSAHS) is a prevalent sleep disorder strongly linked to increased cardiovascular and metabolic risk. While prior studies have explored snore-based analysis for OSAHS, they have largely focused on either detection or classification in isolation. Here, we present a two-stage framework that integrates precise snoring event detection with deep learning-based classification. In the first stage, we develop an Adaptive Multi-Feature Fusion Endpoint Detection algorithm (AMFF-ED), which leverages short-time energy, spectral entropy, zero-crossing rate, and spectral centroid to accurately isolate snore segments following spectral subtraction noise reduction. Through adaptive statistical thresholding, joint decision-making, and post-processing, our method achieves a segmentation accuracy of 96.4%. Building upon this, we construct a balanced dataset comprising 6830 normal and 6814 OSAHS-related snore samples, which are transformed into Mel spectrograms and input into ERBG-Net—a hybrid deep neural network combining ECA-enhanced ResNet18 with bidirectional GRUs. This architecture captures both spectral patterns and temporal dynamics of snoring sounds. The experimental results demonstrate a classification accuracy of 95.84% and an F1 score of 94.82% on the test set, highlighting the model’s robust performance and its potential as a foundation for automated, at-home OSAHS screening. Full article

The automatic classification of sleep stages and Cyclic Alternating Pattern (CAP) subtypes from electroencephalogram (EEG) recordings remains a significant challenge in computational sleep research because of the short duration of CAP events and the inherent class imbalance in clinical datasets. Background/Objectives: The research introduces a domain-specific deep learning system that employs an LSTM network optimized through a PSO-Hyperband hybrid hyperparameter tuning method. Methods: The research enhances EEG-based sleep analysis through the implementation of hybrid optimization methods within an LSTM architecture that addresses CAP sequence classification requirements without requiring architectural changes. Results: The developed model demonstrates strong performance on the CAP Sleep Database by achieving 97% accuracy for REM and 96% accuracy for stage S0 and ROC AUC scores exceeding 0.92 across challenging CAP subtypes (A1–A3). The model transparency is improved through the application of SHAP-based interpretability techniques, which highlight the role of spectral and morphological EEG features in classification outcomes. Conclusions: The proposed framework demonstrates resistance to class imbalance and better discrimination between visually similar CAP subtypes. The results demonstrate how hybrid optimization methods improve the performance, generalizability, and interpretability of deep learning models for EEG-based sleep microstructure analysis. Full article

Background/Objectives: This study shows a lightweight hybrid framework based on a feedforward neural network using a single frontopolar electroencephalography channel, which is a practical configuration for wearable systems combining memory and a sleep stage transition probability matrix. Methods: Motivated by autocorrelation analysis, revealing strong temporal dependencies across sleep stages, we incorporate prior epoch information as additional features. To capture temporal context without requiring long input sequences, we introduce a transition-aware feature derived from the softmax output of the previous epoch, weighted by a learned stage transition matrix. The model combines predictions from memory-based and no-memory networks using a confidence-driven fallback strategy. Results: The proposed model achieves up to 85.4% accuracy and 0.79 Cohen’s kappa, despite using only a single 30 s epoch per prediction. Compared to other models that use a single frontopolar channel, our method outperforms convolutional neural networks, recurrent neural networks, and decision tree approaches. Additionally, confidence-based rejection of low-certainty predictions enhances reliability, since most of the epochs with low confidence in the sleep stage classification contain transitions between sleep stages. Conclusions: These results demonstrate that the proposed method balances performance, interpretability, and computational efficiency, making it well-suited for real-time clinical and wearable sleep staging applications using battery-powered computing devices. Full article

Accurate sleep staging and sleep-disordered breathing (SDB) severity prediction are critical for the early diagnosis and management of sleep disorders. However, real-world polysomnography (PSG) data often suffer from modality heterogeneity, label scarcity, and non-independent and identically distributed (non-IID) characteristics across institutions, posing significant challenges for model generalization and clinical deployment. To address these issues, we propose a federated multi-task learning (FMTL) framework that simultaneously performs sleep staging and SDB severity classification from seven multimodal physiological signals, including EEG, ECG, respiration, etc. The proposed framework is built upon a hybrid deep neural architecture that integrates convolutional layers (CNN) for spatial representation, bidirectional GRUs for temporal modeling, and multi-head self-attention for long-range dependency learning. A shared feature extractor is combined with task-specific heads to enable joint diagnosis, while the FedAvg algorithm is employed to facilitate decentralized training across multiple institutions without sharing raw data, thereby preserving privacy and addressing non-IID challenges. We evaluate the proposed method across three public datasets (APPLES, SHHS, and HMC) treated as independent clients. For sleep staging, the model achieves accuracies of 85.3% (APPLES), 87.1% (SHHS_rest), and 79.3% (HMC), with Cohen’s Kappa scores exceeding 0.71. For SDB severity classification, it obtains macro-F1 scores of 77.6%, 76.4%, and 79.1% on APPLES, SHHS_rest, and HMC, respectively. These results demonstrate that our unified FMTL framework effectively leverages multimodal PSG signals and federated training to deliver accurate and scalable sleep disorder assessment, paving the way for the development of a privacy-preserving, generalizable, and clinically applicable digital sleep monitoring system. Full article

Automated sleep stage classification is essential for objective sleep evaluation and clinical diagnosis. While numerous algorithms have been developed, the predominant existing methods utilize single-channel electroencephalogram (EEG) signals, neglecting the complementary physiological information available from other channels. Standard polysomnography (PSG) recordings capture multiple concurrent biosignals, where sophisticated integration of these multi-channel data represents a critical factor for enhanced classification accuracy. Conventional multi-channel fusion techniques typically employ elementary concatenation approaches that insufficiently model the intricate cross-channel correlations, consequently limiting classification performance. To overcome these shortcomings, we present MCAF-Net, a novel network architecture that employs temporal convolution modules to extract channel-specific features from each input signal and introduces a dynamic gated multi-head cross-channel attention mechanism (MCAF) to effectively model the interdependencies between different physiological channels. Experimental results show that our proposed method successfully integrates information from multiple channels, achieving significant improvements in sleep stage classification compared to the vast majority of existing methods. Full article

Background/Objectives: Sarcopenia is an age-related muscle disease that reduces strength and function in older adults. Exercise is a key intervention, but existing protocols vary widely and often lack adaptation to sarcopenia severity. The present study aims to review the effectiveness of exercise protocols developed after the EWGSOP2 consensus and evaluate their adaptation to sarcopenia severity stages. Methods: This systematic review followed PRISMA guidelines. PubMed and Scopus were searched for studies published after the EWGSOP2 consensus involving participants of 65 years and over with primary sarcopenia and managed through exercise-only interventions. Risk of bias was assessed with the Cochrane Risk of Bias tool, and quality and transparency of exercise intervention were assessed with the Consensus on Exercise Reporting Template. Results: Ten studies met the inclusion criteria, with a total of 558 participants. Most interventions included resistance training, often within multicomponent programs. Statistically significant improvements were reported in muscle strength, mass, and physical performance. Additional benefits included enhancements in sleep quality, respiratory function, and specific biomarkers. However, only two studies classified sarcopenia severity, and reporting quality varied considerably. Conclusions: Exercise interventions, especially multicomponent and individualized protocols, are effective at improving outcomes related to sarcopenia in older adults. However, better alignment with diagnostic classifications and standardized reporting are needed to improve clinical translation and program replication. Full article

Background/Objectives: We present a novel approach for detecting generalized sleep pathologies through the fractal analysis of single-channel electroencephalographic (EEG) signals. We propose that the fractal scaling exponent of permutation entropy time series serves as a robust biomarker of pathological sleep patterns, capturing alterations in brain dynamics across multiple disorders. Methods: Using two public datasets (Sleep-EDF and CAP Sleep Database) comprising 200 subjects (112 healthy controls and 88 patients with various sleep pathologies), we computed the fractal scaling of the permutation entropy of these signals. Results: The results demonstrate significantly reduced scaling exponents in pathological sleep compared to healthy controls (mean = 1.24 vs. 1.06, $p<0.001$), indicating disrupted long-range temporal correlations in neural activity. The method achieved 90% classification accuracy for rapid-eye-movement (REM) sleep behavior disorder (F1-score: 0.89) and maintained 74% accuracy when aggregating all pathologies (insomnia, narcolepsy, sleep-disordered breathing, etc.). Conclusions: The advantages of this approach, including compatibility with single-channel EEG (enabling potential wearable applications), independence from sleep-stage annotations, and generalizability across recording montages and sampling rates, stablish a framework for non-specific sleep pathology detection. This is a computationally efficient method that could transform screening protocols and enable earlier intervention. The robustness of this biomarker could enable straightforward clinical applications for common sleep pathologies as well as diseases associated with neurodegenerative conditions. Full article

Health and well-being, both mental and physical, depend largely on adequate sleep. Many conditions arise from a disrupted sleep cycle, significantly deteriorating the quality of life of those affected. The analysis of the sleep cycle provide valuable information about sleep stages, which are employed in sleep medicine for the diagnosis of numerous diseases. The clinical standard for sleep data recording is polysomnography (PSG), which records electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), and other signals during sleep activity. Recently, machine learning approaches have exhibited high accuracy in applications such as the classification and prediction of biomedical signals. This study presents a hybrid neural network architecture composed of convolutional neural network (CNN) layers, bidirectional long short-term memory (BiLSTM) layers, and attention mechanism layers in order to process large volumes of EEG data in PSG files. The objective is to design a framework for automated feature extraction. To address class imbalance, an epoch-level random undersampling (E-LRUS) method is proposed, discarding full epochs from majority classes while preserving the temporal structure, unlike traditional methods that remove individual samples. This method has been tested on EEG recordings acquired from the public Sleep EDF Expanded database, achieving an overall accuracy rate of 78.67% along with an F1-score of 72.10%. The findings show that this method proves to be effective for sleep stage classification in patients. Full article

The importance of sleep has been reported for decades. Epilepsy is a heterogeneous disorder comprising multiple elements that might influence sleep and wakefulness. Notably, animal studies show disruptions of the circadian molecular system in different models of epilepsy, along with altered rest–activity and other circadian rhythms. So far, studies of molecular circadian systems in people with epilepsy are lacking, prompting further research. Seizures—the primary and most debilitating symptom of epilepsy—and interictal activity disrupt regular sleep and sleep–wake rhythms. Alterations in one’s sleep structure are seen in both drug-naïve and drug-resistant patients with epilepsy. In particular, low sleep efficiency, a reduction in total sleep time, and changes in sleep stages were found in both homogenous and mixed samples of epilepsy patients. Both ictal and interictal activity were also shown to be associated with changes in peripheral circadian phase biomarkers such as melatonin and cortisol. Moreover, epilepsy comorbidities, antiseizure medications, and a variety of syndromes can be a cause of sleep problems or even sleep disorders. Sleep disorders vary depending on various comorbidities and syndromes, and encompass all major groups of sleep disorders defined in the International Classification of Sleep Disorders. Controversial findings on the effects of various antiseizure medications were found in the literature. However, medications such as benzodiazepines, gabapentinoids, and barbiturates are particularly associated with excessive daytime sleepiness. Overall, a sleep evaluation must be included in the management of every patient with epilepsy. Full article

Sleep occupies about one-third of human life and is crucial for health, but traditional sleep staging relies on experts manually performing polysomnography (PSG), a process that is time-consuming, labor-intensive, and susceptible to subjective differences between evaluators. With the development of deep learning technologies, particularly the application of convolutional neural networks and recurrent neural networks, significant progress has been made in automatic sleep staging. However, existing methods still face challenges in feature extraction and cross-modal data fusion. This paper introduces an innovative deep learning architecture, MultiSEss, aimed at solving key issues in automatic sleep stage classification. The MultiSEss architecture utilizes a multi-scale convolution module to capture signal features from different frequency bands and incorporates a Squeeze-and-Excitation attention mechanism to enhance the learning of channel feature weights. Furthermore, the architecture discards complex attention mechanisms or encoder–decoder structures in favor of a state–space sequence coupling module, which more accurately captures and integrates correlations between multi-modal data. Experiments show that MultiSEss achieved accuracy results of 83.84% and 82.30% in five-fold cross-subject testing on the Sleep-EDF-20 and Sleep-EDF-78 datasets. MultiSEss demonstrates its potential in improving sleep stage accuracy, which is significant for enhancing the diagnosis and treatment of sleep disorders. Full article

Background/Objectives: The purpose of this research is to compare and contrast the application of machine learning and deep learning methodologies such as a dual-branch convolutional neural network (CNN) model for detecting obstructive sleep apnea (OSA) from electrocardiogram (ECG) data. Methods: This approach solves the limitations of conventional polysomnography (PSG) and presents a non-invasive method for detecting OSA in its early stages with the help of AI. Results: The research shows that both CNN and dual-branch CNN models can identify OSA from ECG signals. The CNN model achieves validation and test accuracy of about 93% and 94%, respectively, whereas the dual-branch CNN model achieves 93% validation and 94% test accuracy. Furthermore, the dual-branch CNN obtains a ROC AUC score of 0.99, meaning that it is better at distinguishing between apnea and non-apnea cases. Conclusions: The results show that CNN models, especially the dual-branch CNN, are effective in apnea classification and better than traditional methods. In addition, our proposed model has the potential to be used as a reliable, non-invasive method for accurate OSA detection that is even better than the current state-of-the-art advanced methods. Full article