In the modern world, wearable smart devices are continuously used to monitor people’s health. This study aims to develop an automatic mental stress detection system for researchers based on Electrocardiogram (ECG) signals from smart T-shirts using machine learning classifiers. We used 20 subjects, including 10 from mental stress (after twelve hours of continuous work in the laboratory) and 10 from normal (after completing the sleep or without any work). We also applied three scoring techniques: Chalder Fatigue Scale (CFS), Specific Fatigue Scale (SFS), Depression, Anxiety, and Stress Scale (DASS), to confirm the mental stress. The total duration of ECG recording was 1800 min, including 1200 min during mental stress and 600 min during normal. We calculated two types of features, such as demographic and extracted by ECG signal. In addition, we used Decision Tree (DT), Naive Bayes (NB), Random Forest (RF), and Logistic Regression (LR) to classify the intra-subject (mental stress and normal) and inter-subject classification. The DT leave-one-out model has better performance in terms of recall (93.30%), specificity (96.70%), precision (94.40%), accuracy (93.30%), and F1 (93.50%) in the intra-subject classification. Additionally, The classification accuracy of the system in classifying inter-subjects is 94.10% when using a DT classifier. However, our findings suggest that the wearable smart T-shirt based on the DT classifier may be used in big data applications and health monitoring. Mental stress can lead to mitochondrial dysfunction, oxidative stress, blood pressure, cardiovascular disease, and various health problems. Therefore, real-time ECG signals help assess cardiovascular and related risk factors in the initial stage based on machine learning techniques.

News media always pursue informing the public at large. It is impossible to overestimate the significance of understanding the semantics of news coverage. Traditionally, a news text is assigned to a single category; however, a piece of news may contain information from more than one domain. A multi-label text classification model for news is proposed in this paper. The proposed model is an automated expert system designed to optimize CNN’s classification of multi-label news items. The performance of a CNN is highly dependent on its hyperparameters, and manually tweaking their values is a cumbersome and inefficient task. A high-level metaheuristic optimization algorithm, spotted hyena optimizer (SHO), has higher advanced exploration and exploitation capabilities. SHO generates a collection of solutions as a group of hyperparameters to be optimized, and the process is repeated until the desired optimal solution is achieved. SHO is integrated to automate the tuning of the hyperparameters of a CNN, including learning rate, momentum, number of epochs, batch size, dropout, number of nodes, and activation function. Four publicly available news datasets are used to evaluate the proposed model. The tuned hyperparameters and higher convergence rate of the proposed model result in higher performance for multi-label news classification compared to a baseline CNN and other optimizations of CNNs. The resulting accuracies are 93.6%, 90.8%, 68.7%, and 95.4% for RCV1-v2, Reuters-21578, Slashdot, and NELA-GT-2019, respectively.

Data streaming applications such as the Internet of Things (IoT) require processing or predicting from sequential data from various sensors. However, most of the data are unlabeled, making applying fully supervised learning algorithms impossible. The online manifold regularization approach allows sequential learning from partially labeled data, which is useful for sequential learning in environments with scarcely labeled data. Unfortunately, the manifold regularization technique does not work out of the box as it requires determining the radial basis function (RBF) kernel width parameter. The RBF kernel width parameter directly impacts the performance as it is used to inform the model to which class each piece of data most likely belongs. The width parameter is often determined off-line via hyperparameter search, where a vast amount of labeled data is required. Therefore, it limits its utility in applications where it is difficult to collect a great deal of labeled data, such as data stream mining. To address this issue, we proposed eliminating the RBF kernel from the manifold regularization technique altogether by combining the manifold regularization technique with a prototype learning method, which uses a finite set of prototypes to approximate the entire data set. Compared to other manifold regularization approaches, this approach instead queries the prototype-based learner to find the most similar samples for each sample instead of relying on the RBF kernel. Thus, it no longer necessitates the RBF kernel, which improves its practicality. The proposed approach can learn faster and achieve a higher classification performance than other manifold regularization techniques based on experiments on benchmark data sets. Results showed that the proposed approach can perform well even without using the RBF kernel, which improves the practicality of manifold regularization techniques for semi-supervised learning.

(1) Background: Soccer action recognition (SAR) is essential in modern sports analytics, supporting automated performance evaluation, tactical strategy analysis, and detailed player behavior modeling. Although recent advances in deep learning and computer vision have enhanced SAR capabilities, many existing methods remain limited to coarse-grained classifications, grouping actions into broad categories such as attacking, defending, or goalkeeping. These models often fall short in capturing fine-grained distinctions, contextual nuances, and long-range temporal dependencies. Transformer-based approaches offer potential improvements but are typically constrained by the need for large-scale datasets and high computational demands, limiting their practical applicability. Moreover, current SAR systems frequently encounter difficulties in handling occlusions, background clutter, and variable camera angles, which contribute to misclassifications and reduced accuracy. (2) Methods: To overcome these challenges, we propose TAT-SARNet, a structured framework designed for accurate and fine-grained SAR. The model begins by applying Sparse Dilated Attention (SDA) to emphasize relevant spatial dependencies while mitigating background noise. Refined spatial features are then processed through the Split-Stream Feature Processing Module (SSFPM), which separately extracts appearance-based (RGB) and motion-based (optical flow) features using ResNet and 3D CNNs. These features are temporally refined by the Multi-Granular Temporal Processing (MGTP) module, which integrates ResIncept Patch Consolidation (RIPC) and Progressive Scale Construction Module (PSCM) to capture both short- and long-range temporal patterns. The output is then fused via the Context-Guided Dual Transformer (CGDT), which models spatiotemporal interactions through a Bi-Transformer Connector (BTC) and Channel–Spatial Attention Block (CSAB); (3) Results: Finally, the Cascaded Temporal Classification (CTC) module maps these features to fine-grained action categories, enabling robust recognition even under challenging conditions such as occlusions and rapid movements. (4) Conclusions: This end-to-end architecture ensures high precision in complex real-world soccer scenarios.

Accurate and context-aware action recognition in soccer remains a challenging task due to the sport’s dynamic nature, overlapping actions, and complex causal relationships among events. Traditional video understanding models often rely on dense optical flow and static frame-based processing, which struggle in scenarios involving occlusion, background clutter, or subtle gameplay nuances. Furthermore, many existing systems fail to incorporate temporal reasoning or causal inference, leading to suboptimal recognition of interdependent actions like tackles, fouls, or passes. To address these limitations. This research aims to develop a cognitively inspired framework that overcomes the limitations of traditional video understanding models, particularly their reliance on dense optical flow and inability to model temporal causality and context effectively. We propose SPEAR-Net (Spiking-Perception and Episodic Abstraction for Recognition Network), a neuro-inspired action recognition system that emulates brain-like perception and reasoning. It introduces modules such as the Neuro-Perception Encoding Module (NPEM) for sparse event encoding, the Causal Relational Decoder (CRD) for DAG-based causal reasoning, the Context-Aware Environment Encoder (CAEE) for semantic context embedding, and the Micro–Macro Event Alignment (MMEA) for hierarchical temporal abstraction. Reliability is further enhanced through the Episodic Memory Replay Module (EMRM) and Self-Critic Refinement Agent (SCRA) for memory-based adaptation and confidence calibration. Empirical results on the SoccerNet-v2 benchmark demonstrate that SPEAR-Net outperforms state-of-the-art models with a Top-1 accuracy of 89.6%, robustness under occlusion (only 4.5% accuracy drop), and significantly reduced misclassification and uncertainty post-refinement, making it highly suitable for real-time, high-stakes sports analytics.