Search Results (946)

This study presents a comparative analysis of electrocardiogram (ECG) and accelerometer (ACC) data in the context of unsupervised human activity recognition and subject identification. Recordings were obtained from 30 participants performing activities of daily living such as walking, sitting, lying, cleaning the floor, and climbing stairs. Distance-based signal comparison methods and clustering techniques were employed to evaluate the feasibility of each modality, both individually and in combination, to discriminate between individuals and activities. Results indicate that ACC signals provide superior performance in activity recognition (NMI = 0.728, accuracy = 0.817), while ECG signals show higher discriminative power for subject identification (NMI = 0.641, accuracy = 0.500). In contrast, combining ACC and ECG signals yielded lower scores in both tasks, suggesting that multimodal fusion introduced additional variability. These findings highlight the importance of selecting the most appropriate modality depending on the recognition objective and emphasize the challenges associated with multimodal approaches in unsupervised scenarios. Full article

Arrhythmias are a common and potentially life-threatening category of cardiac disorders, making accurate and early detection crucial for improving clinical outcomes. Electrocardiograms are widely used to monitor heart rhythms, yet their manual interpretation remains prone to inconsistencies due to the complexity of the signals. This research investigates the effectiveness of machine learning and deep learning techniques for automated arrhythmia classification using ECG signals from the MIT-BIH dataset. We compared Gradient Boosting Machine (GBM) and Multilayer Perceptron (MLP) as traditional machine learning models with a hybrid deep learning model combining one-dimensional convolutional neural networks (1D-CNNs) and long short-term memory (LSTM) networks. Furthermore, the Grey Wolf Optimizer (GWO) was utilized to automatically optimize the hyperparameters of the 1D-CNN-LSTM model, enhancing its performance. Experimental results show that the proposed 1D-CNN-LSTM model achieved the highest accuracy of 97%, outperforming both classical machine learning and other deep learning baselines. The classification report and confusion matrix confirm the model’s robustness in identifying various arrhythmia types. These findings emphasize the possible benefits of integrating metaheuristic optimization with hybrid deep learning. Full article

The deployment of conditionally automated vehicles raises safety concerns, as drivers often engage in non-driving-related tasks (NDRTs), delaying takeover responses. This study investigates driver state monitoring (DSM) using multimodal physiological and ocular signals from the TD2D (Takeover during Distracted L2 Automated Driving) dataset, which includes synchronized electrocardiogram (ECG), photoplethysmography (PPG), electrodermal activity (EDA), and eye-tracking data from 50 participants across ten task conditions. Tasks were reassigned into three workload-based categories informed by NASA-TLX ratings. A unified preprocessing and feature extraction pipeline was applied, and 25 informative features were selected. Random Forest outperformed Support Vector Machine and Multilayer Perceptron models, achieving 0.96 accuracy in within-subject evaluation and 0.69 in cross-subject evaluation with subject-disjoint splits. Sensitivity analysis showed that temporal overlap had a stronger effect than window length, with moderately long windows (5–8 s) and partial overlap providing the most robust generalization. SHAP (Shapley Additive Explanations) analysis confirmed ocular features as the dominant discriminators, while EDA contributed complementary robustness. Additional validation across age strata confirmed stable performance beyond the training cohort. Overall, the results highlight the effectiveness of physiological and ocular measures for distraction detection in automated driving and the need for strategies to further improve cross-driver robustness. Full article

This work reports the fabrication of innovative flexible conductive polymer composites (FCPCs), composed of poly (2,3-dihydrothieno-1,4-dioxin)-poly (styrenesulfonate) (PEDOT:PSS), polypyrrole (PPy) and copper phthalocyanine (CuPc). These FCPCs were deposited by the drop-casting technique on flexible substrates such as polyethylene terephthalate (PET), Xuan paper and ethylene–vinyl acetate (EVA) foam sheets. Wearable photoactive electrocardiogram (ECG) electrodes and flexible strain sensors were fabricated. Morphological characterization by SEM revealed a stark contrast between the smooth, continuous PEDOT:PSS films and the rough, globular PPy films. EDS confirmed the successful and homogeneous incorporation of the CuPc, evidenced by the strong spatial correlation of the nitrogen and copper signals. The highest mechanical resistance was present in the FCPCs on PET with a limit of proportionality between 4074–6240 KPa. Optical parameters were obtained by Ultraviolet–Visible Spectroscopy and their Reflectance is below 15% and could be used as photoelectrodes. Three Signal Quality Indexes (SQIs) were used to evaluate the ECG signal obtained with the electrodes. The results of all the SQIs demonstrated that the obtained signals have a comparable quality to that of a signal obtained from commercial electrodes. To evaluate the flexible strain sensors, the change in output voltage caused by mechanical deformation was measured. Full article

Cardiovascular diseases are the leading cause of death worldwide, with arrhythmia being a prevalent and potentially fatal condition. The multi-lead electrocardiogram (ECG) is the primary tool for detecting arrhythmias. However, existing detection methods have shortcomings: they cannot dynamically integrate inter-lead correlations with multi-scale temporal changes in cardiac electrical activity. They also lack mechanisms to simultaneously focus on key leads and time segments, and thus fail to address multi-lead redundancy or capture comprehensive spatial-temporal relationships. To solve these problems, we propose a Multi-Scale Lead-Temporal Co-Attention Framework (MS-LTCAF). Our framework incorporates two key components: a Lead-Temporal Co-Attention Residual (LTCAR) module that dynamically weights the importance of leads and time segments, and a multi-scale branch structure that integrates features of cardiac electrical activity across different time periods. Together, these components enable the framework to automatically extract and integrate features within a single lead, between different leads, and across multiple time scales from ECG signals. Experimental results demonstrate that MS-LTCAF outperforms existing methods. On the PTB-XL dataset, it achieves an AUC of 0.927, approximately 1% higher than the current optimal baseline model (DNN_zhu’s 0.918). On the LUDB dataset, it ranks first in terms of AUC (0.942), accuracy (0.920), and F1-score (0.745). Furthermore, the framework can focus on key leads and time segments through the co-attention mechanism, while the multi-scale branches help capture both the details of local waveforms (such as QRS complexes) and the overall rhythm patterns (such as RR intervals). Full article

Continuous blood pressure (BP) monitoring is essential for the early detection and prevention of cardiovascular diseases like hypertension. Recently, interest in continuous BP estimation systems and algorithms has grown. Various physiological signals reflect BP variations from different perspectives, and combining multiple signals can enhance the accuracy of BP measurements. However, research integrating electrocardiogram (ECG), photoplethysmography (PPG), and impedance cardiography (ICG) signals for BP monitoring remains limited, with related technologies still in early development. A major challenge is the increased system complexity associated with acquiring multiple signals simultaneously, along with the difficulty of efficiently extracting and integrating key features for accurate BP estimation. To address this, we developed a BP monitoring system that can synchronously acquire and process ECG, PPG, and ICG signals. Optimizing the circuit design allowed ECG and ICG modules to share electrodes, reducing components and improving compactness. Using this system, we collected 400 min of signals from 40 healthy subjects, yielding 4390 records. Experiments were conducted to evaluate the system’s performance in BP estimation. The results demonstrated that combining pulse wave analysis features with the XGBoost model yielded the most accurate BP predictions. Specifically, the mean absolute error for systolic blood pressure was 3.76 ± 3.98 mmHg, and for diastolic blood pressure, it was 2.71 ± 2.57 mmHg, both of which achieved grade A performance under the BHS standard. These results are comparable to or better than existing studies based on multi-signal methods. These findings suggest that the proposed system offers an efficient and practical solution for BP monitoring. Full article

Cybersickness poses a significant challenge to the widespread adoption of virtual reality (VR), as it impairs user experience and operational performance. This study proposes a physiological modeling approach to objectively assess cybersickness severity during VR experience. An interactive VR experiment was conducted, inducing varying levels of cybersickness through VR navigation tasks under different field-of-view and graphic quality settings. Physiological signals (i.e., electrodermal activity (EDA) and electrocardiogram (ECG)) were continuously recorded and extracted to build multiple machine learning regression models for cybersickness prediction. The results showed that EDA-based models consistently outperformed ECG-based models across all algorithms, with the Ensemble Learning model achieving the highest predictive accuracy (R² = 0.98). In contrast, ECG-based models yielded limited predictive capability (R² = 0.53). Combining ECG with EDA features showed little improvement in model accuracy, suggesting a limited complementary role of ECG features. SHAP-based feature importance analysis revealed that EDA features (e.g., mean, maximum, and variance of skin conductance) were the most effective features in cybersickness prediction, which captured both tonic arousal and phasic autonomic responses during the cybersickness process. ECG features such as SDNN and HRMAD contributed modestly, offering physiological interpretability despite being less effective in cybersickness prediction. The findings demonstrate the feasibility of using low-burden physiological signals for accurate and interpretable prediction of cybersickness severity. The proposed approach supports the development of lightweight, real-time monitoring systems for VR applications, offering practical advantages in terms of simplicity, adaptability, and deployment potential. Full article

Background: Electrocardiogram (ECG) signals are crucial for cardiovascular diagnosis, but their analysis face challenges from noise contamination, compression difficulties due to their non-stationary nature, and the inherent complexity of its morphological components, particularly for low-amplitude P- and T-waves obscured by noise. Methodology: This study proposes a novel, multi-stage framework for ECG signal denoising, compressing, and component decomposition. The proposed framework leverages the sparsity of ECG signal to denoise and compress these signals using autoencoder-driven dictionary (AE-DD) with matching pursuit. In this work, a data-driven dictionary was developed using a regularized autoencoder. Appropriate trained weights along with matching pursuit were used to compress the denoised ECG segments. This study explored different weight regularization techniques: L1- and L2-regularization. Results: The proposed framework achieves remarkable performance in simultaneous ECG denoising, compression, and morphological decomposition. The L1-DAE model delivers superior noise suppression (SNR improvement up to 18.6 dB at $-3$ dB input SNR) and near-lossless reconstruction ($\mathrm{MSE}<{10}^{-5}$). The L1-AE dictionary enables high-fidelity compression (CR = 28:1 ratio, $\mathrm{MSE}\approx 0.58\times {10}^{-5}$, PRD = 2.1%), outperforming non-regularized models and traditional dictionaries (DCT/wavelets), while its trained weights naturally decompose into interpretable sub-dictionaries for P-wave, QRS complex, and T-wave enabling precise, label-free analysis of ECG components. Moreover, the learned sub-dictionaries naturally decompose into interpretable P-wave, QRS complex, and T-wave components with high accuracy, yielding strong correlation with the original ECG ($r=0.98$, $r=0.99$, and $r=0.95$, respectively) and very low MSE ($1.93\times {10}^{-5}$, $9.26\times {10}^{-4}$, and $3.38\times {10}^{-4}$, respectively). Conclusions: This study introduces a novel autoencoder-driven framework that simultaneously performs ECG denoising, compression, and morphological decomposition. By leveraging L1-regularized autoencoders with matching pursuit, the method effectively enhances signal quality while enabling direct decomposition of ECG signals into clinically relevant components without additional processing. This unified approach offers significant potential for improving automated ECG analysis and facilitating efficient long-term cardiac monitoring. Full article

Introduction: Advanced identification and intervention for Congenital Heart Defects (CHDs) in pediatric populations are crucial, as approximately 1% of neonates worldwide present with these conditions. Traditional methods of diagnosing CHDs often rely on stethoscope auscultation, which heavily depends on the clinician’s expertise and may lead to the oversight of subtle acoustic indicators. Objectives: This study introduces an innovative deep-learning framework designed for the early diagnosis of congenital heart disease. It utilizes time-series data obtained from cardiac auditory signals captured through stethoscopes. Methods: The audio signals were processed into time–frequency representations using Mel-Frequency Cepstral Coefficients (MFCCs). The architecture of the model combines Convolutional Neural Networks (CNNs) for effective feature extraction with Long Short-Term Memory (LSTM) networks to accurately model temporal dependencies. Impressively, the model achieved an accuracy of 98.91% in the early detection of CHDs. Results: While traditional diagnostic tools like Electrocardiograms (ECG) and Phonocardiograms (PCG) remain indispensable for confirming diagnoses, many AI studies have primarily targeted ECG and PCG datasets. This approach emphasizes the potential of cardiac acoustics for the early diagnosis of CHDs, which could lead to improved clinical outcomes for infants. Notably, the dataset used in this research is publicly available, enabling wider application and model training within the research community. Full article

Electrocardiogram reports are an important component of cardiovascular diagnostics, routinely generated in hospitals and clinical settings to monitor cardiac activity and guide medical decision-making. ECG reports often consist of structured waveform data accompanied by free-text interpretations written by clinicians. Although the waveform data can be analyzed using signal processing techniques, the unstructured text component contains rich, contextual insights into diagnoses, conditions, and patient-specific observations that are not easily captured by conventional methods. Extracting meaningful patterns from clinical narratives poses significant challenges. In this work, we present an unsupervised framework for exploring and analyzing ECG diagnostic reports using transformer-based language modeling and clustering techniques. We use the domain-specific language model BioBERT to encode text-based ECG reports into dense vector representations that capture the semantics of medical language. These embeddings are subsequently standardized and subjected to a series of clustering algorithms, including KMeans, hierarchical clustering, DBSCAN, and K-Medoids, to uncover latent groupings within the data. Full article

Predicting paroxysmal atrial fibrillation (PAF) is challenging due to its transient nature. Existing methods often rely solely on electrocardiogram (ECG) waveforms or Electronic Health Record (EHR)-based clinical risk factors. We hypothesized that explicitly balancing the contributions of these heterogeneous data sources could improve prediction accuracy. We developed a Transformer-based deep learning model that integrates 12-lead ECG signals and 47 structured EHR variables from 189 patients with cryptogenic stroke, including 49 with PAF. By systematically varying the relative contributions of ECG and EHR data, we identified an optimal ratio for prediction. Best performance (accuracy: 0.70, sensitivity: 0.72, specificity: 0.87, Area Under Curve - Receiver Operating Characteristics (AUROC): 0.65, Area Under the Precision-Recall Curve (AUPRC): 0.43) was achieved using a 5-fold cross-validation when EHR data contributed one-third and ECG data two-thirds of the model’s input. This multimodal approach outperformed unimodal models, improving accuracy by 35% over EHR-only and 5% over ECG-only methods. Our results support the value of combining ECG and structured EHR information to improve accuracy and sensitivity in this pilot cohort, motivating validation in larger studies. Full article

Cardiovascular diseases are known as major contributors to death globally. Accurate identification and classification of cardiac arrhythmias from electrocardiogram (ECG) signals is essential for early diagnosis and treatment of cardiovascular diseases. This research introduces an innovative deep learning architecture that integrates Convolutional Neural Networks with a channel attention mechanism, enhancing the model’s capacity to concentrate on essential aspects of the ECG signals. Unlike most prior studies that depend on single-lead data or complex hybrid models, this work presents a novel yet simple deep learning architecture to classify five arrhythmia classes that effectively utilizes both 2-lead and 12-lead ECG signals, providing more accurate representations of clinical scenarios. The model’s performance was evaluated on the MIT-BIH and INCART arrhythmia datasets, achieving accuracies of 99.18% and 99.48%, respectively, along with F1 scores of 99.18% and 99.48%. These high-performance metrics demonstrate the model’s ability to differentiate between normal and arrhythmic signals, as well as accurately identify various arrhythmia types. The proposed architecture ensures high accuracy without excessive complexity, making it well-suited for real-time and clinical applications. This approach could improve the efficiency of healthcare systems and contribute to better patient outcomes. Full article

Objective: In this paper, we propose a novel approach to heart rate (HR) detection based on the evaluation of oscillatory patterns of continuous wavelet transform as a method of time-frequency analysis. HR detection based on electrocardiogram (ECG) or photoplethysmogram (PPG) signals can be performed using the same technique. Methods: The developed approach was tested on ECG (lead V1) and PPG (standard recording on the ring finger of the left hand and differential signal) for 10 min in 40 generally healthy volunteers (aged 26.8 ± 3.22 years). A comparison was made with the traditional HR detection method based on R-peak shape analysis. Results: Based on a number of statistical evaluations, the comparison yielded an acceptable degree of agreement between the results of the proposed method and the traditional method (the discrepancy between the results did not exceed 3.41%). The distortion of the signal shape and its noise do not affect the quality of HR detection by the proposed method; so, additional filtering or changes in the implemented algorithm are not required, as demonstrated by processing both the differential PPG signal and the PPG signals recorded during the patient’s walking. Conclusions: The proposed method allows obtaining HR information with a higher equidistant sampling frequency and expansion of the information on the frequency composition of HRV. Full article

Wearable systems are increasingly adopted for health monitoring and wellness promotion. Among the most relevant biosignals, the electrocardiogram (ECG) plays a key role; however, in wearable settings (e.g., during physical activity), it is often corrupted by electromyogram (EMG) interference. This study presents a novel adaptive algorithm, template masking (TM), which integrates the stationary wavelet transform (SWT) with template matching for denoising the ECG from EMG. The method identifies the optimal wavelet and decomposition level to maximise detail sparsity. To mitigate EMG interference, after alignment in the SWT domain with a template, the detail coefficients are multiplied by a binary mask and smoothed. TM was compared with soft and hard thresholding on (1) simulations combining clinical ECGs (MIT-BIH database) and synthetic EMGs with different signal-to-noise ratios (SNRs), and (2) experimental signals including ECGs acquired with dry electrodes corrupted by EMGs (SimEMG database, also varying SNRs), as a potential wearable scenario. In both cases, TM yielded significantly lower reconstruction errors at SNRs below 5 dB ($p<0.01$) and significantly outperformed thresholding in the sensitivity of R-peaks estimation ($p<0.001$). These results demonstrate the potential of TM, highlighting the value of adaptive denoising algorithms. Full article

In recent years, electrocardiogram (ECG) biometrics has received extensive attention and achieved a series of exciting results. In order to achieve optimal ECG biometric recognition, it is crucial to effectively process the original ECG signals. However, most existing methods only focus on extracting features from one-dimensional time series, limiting the discriminability of individual identification to some extent. To overcome this limitation, we propose a novel framework that integrates dual-level features, i.e., 1D (time series) and 2D (relative position matrix) representations, through collaborative embedding, dimensional attention weight learning, and projection matrix learning. Specifically, we leverage collective matrix factorization to learn the shared latent representations by embedding dual-level features to fully mine these two kinds of features and preserve as much information as possible. To further enhance the discrimination of learned representations, we preserve the diverse information for different dimensions of the latent representations by means of dimensional attention weight learning. In addition, the learned projection matrix simultaneously facilitates the integration of dual-level features and enables the transformation of out-of-sample queries into the discriminative latent representation space. Furthermore, we propose an effective and efficient optimization algorithm to minimize the overall objective loss. To evaluate the effectiveness of our learned latent representations, we conducted experiments on two benchmark datasets, and our experimental results show that our method can outperform state-of-the-art methods. Full article