Blood pressure (BP) is a vital sign that provides fundamental health information regarding patients. Continuous BP monitoring is important for patients with hypertension. Various studies have proposed cuff-less BP monitoring methods using pulse transit time. We propose an end-to-end deep learning architecture using only raw signals without the process of extracting features to improve the BP estimation performance using the attention mechanism. The proposed model consisted of a convolutional neural network, a bidirectional gated recurrent unit, and an attention mechanism. The model was trained by a calibration-based method, using the data of each subject. The performance of the model was compared to the model that used each combination of the three signals, and the model with the attention mechanism showed better performance than other state-of-the-art methods, including conventional linear regression method using pulse transit time (PTT). A total of 15 subjects were recruited, and electrocardiogram, ballistocardiogram, and photoplethysmogram levels were measured. The 95% confidence interval of the reference BP was [86.34, 143.74] and [51.28, 88.74] for systolic BP (SBP) and diastolic BP (DBP), respectively. The $R^2$ values were 0.52 and 0.49, and the mean-absolute-error values were 4.06 ± 4.04 and 3.33 ± 3.42 for SBP and DBP, respectively. In addition, the results complied with global standards. The results show the applicability of the proposed model as an analytical metric for BP estimation.

Considering the high death rate from cardiovascular diseases, it is important to detect an irregular heart rhythm in order to prevent potential tragedy. The purpose of this paper is to present automatic detection of arrhythmia based on electrocardiography. We suggest a one-dimensional convolutional neural network (1D CNN) with long short-term memory (LSTM). The suggested architecture is compared with two other deep learning methods: the 1D CNN and the multi-layer perceptron (MLP) model. To evaluate performance, we measured the overall accuracy, macroaveraged precision, and macro-averaged recall of our proposed method as being 92.03%, 90.98%, and 86.15%, respectively. The results demonstrate that the 1D CNN-with-LSTM model outperforms the two other models.

Automatic detection of arrhythmia using electrocardiogram (ECG) signal is an important role in the early diagnosis of cardiovascular diseases. Most of the arrhythmia detection researches have focused on the analysis of 1D time-series ECG signals, where deep neural network architecture have been applied due to its reliable and high performance. However, the hyperparameters of the deep learning model are mostly chosen empirically by the developer, which could be often suboptimal. For the optimal hyperparameter search, we propose the application of Bayesian optimization hyperband (BOHB) to the architectures of convolutional neural networks (CNN) and long short-term memory (LSTM). To evaluate the performance of the efficiently obtained DNN structures, we measured the overall accuracy and macro-averaged F1 score were measured, which were 0.7280 and 0.5931, while the overall accuracy and macro-averaged F1 score of empirically designed DNN were 0.7110 and 0.5679, respectively. The results demonstrate the optimized model outperforms the empirically designed model.

Firewall log classification is important to monitor network traffic. Most firewall log classification via machine learning has shown good result by network-related features and classifiers. However, feature with many dimensions take a lot of time to do classification. In this paper, we applied a method of feature selection using optimized bee swarm optimization with reinforcement learning. We evaluated average performance by accuracy, macro-averaged precision, macro-averaged recall, and macro-averaged F1 score in 5-stratified folds using a random forest, k-nearest neighbor, and naïve bayes classifier. As a results, it could be applied for an automatic firewall log analysis system.

Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptability. Although EEG foundation models seek broader applicability, many still rely on predefined multi-channel inputs, electrode-layout assumptions, or model-specific channel handling. To address these limitations, we introduce the Single-Channel Large EEG Model (SingLEM), a self-supervised foundation model whose hybrid convolutional-Transformer encoder maps each channel independently to a reusable representation capturing local and long-range temporal structure. These representations can be used individually or combined through channel-wise feature concatenation. We assembled 71 public EEG datasets comprising approximately 9,200 subjects and 357,000 single-channel hours. For leakage-controlled evaluation, downstream results were obtained with a model pretrained on 68 datasets after excluding the three source datasets underlying the six tasks. A model pretrained on all 71 datasets is provided for general reuse. Across six motor imagery and cognitive tasks under strict leave-one-subject-out (LOSO) evaluation, the leakage-controlled model with concatenated representations and a support vector machine (SVM) classifier achieved the best overall performance among the compared pretrained and classical feature-based methods. Additional classifier and subject-adapted analyses supported the robustness of its representations. These findings support single-channel self-supervised learning as a montage-flexible foundation for reusable EEG feature extraction and electrode-level spatial analysis. The source code and pretrained models are available at https://github.com/ttlabtuat/SingLEM.