Cuffless blood pressure (BP) estimation is critical for managing growing concerns about hypertension and cardiovascular diseases. Despite recent advancements in multimodal (ECG and PPG) BP estimation methods, which have achieved varying degrees of success, several challenges remain to be addressed. These include capturing the full spectrum of BPrelevant information, redundant feature spaces, and handling the multigrade classification. To address these issues, we propose a Multimodal Fusion BP Network (MuFuBP-Net), featuring a novel dual-feature pipeline architecture designed to extract hierarchical and modality-specific features from both ECG and PPG signals. Additionally, the Cascading Cross-Feature Enhancer (CCFE) module integrates multiple fusion strategies with a squeeze-and-excitation mechanism to apply channel-wise attention to spatial features, enabling dynamic re-weighting. We also employed a Sequence Context Network (SCN) module to capture global sequential features. Subsequently, a Probabilistic Feature Encoder (PFE) encodes the multilevel features from both pipelines into a compact latent space, preserving their discriminative characteristics. Our approach achieved MAE ± SDE of 2.99 ± 4.37 mmHg (SBP) and 2.63 ± 4.19 mmHg (DBP) on MIMIC-II, and 2.27 ± 4.15 mmHg (SBP) and 1.63 ± 2.96 mmHg (DBP) on MIMIC-III dataset, meeting AAMI, BHS, and IEEE grade A standards. The proposed approach demonstrated competitive results compared to existing techniques, highlighting its significance as a reliable solution for cuffless BP monitoring.

Sleep monitoring is essential for assessing sleep quality and understanding its broader implications for overall health. Although electroencephalography (EEG) remains the gold standard for sleep analysis, multichannel techniques are often cumbersome and impractical for real-world application. As a more feasible alternative, single-channel EEG offers greater practicality but still faces several persistent challenges, including reduced spatial resolution, feature instability, and limited clinical interpretability. To address these limitations, we propose KAleep-Net (Kolmogorov-Arnold based Sleep Network) for sleep stage classification. It employs a Multispectral Feature Pipeline to extract both fine-grained and coarse-grained features from single-channel EEG signals. It integrates a Temporal Sequencing Network with Flash Attention to capture rich and stable features effectively. The proposed approach achieved an accuracy of 86.5%, an F1-score of 79.6%, and a Cohen’s $\kappa $ of 79.9% on the Sleep-EDF-20 dataset, along with a 41.7% improvement in training speed. For the Sleep-EDF-78 dataset, it attained 85.0% accuracy, 77.0% F1-score, 78.0% $\kappa $ , and a 67.5% gain in training efficiency. On the SHHS dataset, the model achieved 86.4% accuracy, an F1-score of 0.79, and a $\kappa $ of 0.81, with an 8.18% improvement in training speed. For interpretability, an integrated gradient technique was adopted to enhance decision transparency and promote clinical adoption. The framework offers an efficient solution for sleep staging in resource-constrained environments with clinically trusted insights for single-channel EEG-based sleep monitoring.

Social media has significantly transformed the digital landscape by enabling an unprecedented expansion of content, further accelerated by the COVID-19 pandemic, which increased the demand for online classes, virtual meetings, and recorded conferences. While major technology companies have previously employed sentiment analysis and opinion mining to gauge user feedback, this study proposes a novel framework for emotion-based video content analysis. The proposed method extracts audio from social media videos and applies Speech-to-Text (STT) conversion. The extracted text is then processed using a pre-trained BERT model, leveraging its fine-tuned capabilities and 110 million parameters to enhance emotion recognition. To improve inference, we modify the initial embedding layers of BERT to refine emotional analysis for unseen video content, ensuring better alignment with viewers' emotional responses. Experimental results demonstrate that the pre-trained BERT model outperforms traditional deep learning and machine learning approaches, achieving 83% accuracy and an F1 score of 83. Comparatively, CNN and LSTM models achieved 74% and 73% accuracy, respectively, while SVM resulted in 72% accuracy. The proposed framework offers a more refined emotional analysis, potentially improving user engagement by making content more relatable and emotionally intuitive for viewers.