Search Results (5,960)

Objectives: The present study examined the sensory preferences adopted by students over three years of training in a specialized training program for security forces (STPSF). It determines their impact on karate performance metrics. Methods: Thirty-one students aged 20 to 26 (SD = 0.81) completed the modified Visual, Aural, Read/Write, and Kinesthetic questionnaire (VARK), a tool designed to help identify students’ preferred learning styles. This research suggests a theoretical model in which the balanced and optimal engagement of visual, auditory, and kinesthetic modalities rather than a strict mathematical equation might provide an optimal foundation for improving proficiency in martial arts. Balanced engagement of these sensory modalities can foster a deeper understanding of karate techniques, improve performance, minimize dependence on a single sensory channel, and bolster real-time adaptability. The students were tested at two points: once at the beginning of their enrolment and again after completing their three-year training program. Results: After a relatively intensive intervention over three years, the findings suggest a positive shift in the ratio of the primary modalities, moving toward an optimal balance. Considering the ideal sensory balance of 50:50:50%, the visual modality increased from 45.8 to 50.4, approaching the optimal value. The auditory modality, initially above the ideal level at 53.8, adjusted closer to balance, reaching 51.9. In contrast, the kinesthetic modality slightly decreased from 50 to 47.5, indicating a minor deviation from the ideal state. It was further confirmed that a higher technical level, such as the third kyu, exhibits an equal distribution, approaching the optimal use of the three modalities: visual 51.5 auditory 47.6 and kinesthetic 50.7. Moreover, the progress toward an optimal synergy and a more efficient evaluation of situational possibilities within the decision-making process was more frequently noted in females than in male students. Conclusions: Acknowledging students’ sensory processing preferences can assist the teacher, trainer, coach, and student in advancing interaction, optimizing learning strategies, improving performance, promoting analytical skills, and fostering self-assurance and determination. Full article

There are two problems with traditional knowledge distillation methods in industrial anomaly detection: first, traditional methods mostly use feature alignment between the same layers. The second is that similar or even identical structures are usually used to build teacher-student models, thus limiting the ability to represent anomalies in multiple ways. To address these issues, this work proposes a Hierarchical Knowledge Transfer (HKT) framework for detecting industrial surface anomalies. First, HKT utilizes the deep knowledge of the highest feature layer in the teacher’s network to guide student learning at every level, thus enabling cross-layer interactions. Multiple projectors are built inside the model to facilitate the teacher in transferring knowledge to each layer of the student. Second, the teacher-student structural symmetry is decoupled by embedding Convolutional Block Attention Modules (CBAM) in the student network. Finally, based on HKT, a more powerful anomaly detection model, HKT+, is developed. By adding two additional convolutional layers to the teacher and student networks of HKT, HKT+ achieves enhanced detection capabilities at the cost of a relatively small increase in model parameters. Experiments on the MVTec AD and BeanTech AD(BTAD) datasets show that HKT+ achieves state-of-the-art performance with average area under the receiver operating characteristic curve (AUROC) scores of 98.69% and 94.58%, respectively, which outperforms most current state-of-the-art methods. Full article

Background/Objectives: The timely and accurate detection of atrial fibrillation (AF) is critical from a clinical perspective. Detecting short or transient AF events is challenging in 24–72 h Holter ECG recordings, especially when symptoms are infrequent. This study aims to explore the potential of deep transfer learning with ImageNet deep neural networks (DNNs) to improve the interpretation of short-term ECHOView images for the presence of AF. Methods: Thirty-second ECHOView images, composed of stacked heartbeat amplitudes, were rescaled to fit the input of 18 pretrained ImageNet DNNs with the top layers modified for binary classification (AF, non-AF). Transfer learning provided both retrained DNNs by training only the top layers (513–2048 trainable parameters) and fine-tuned DNNs by slowly training retrained DNNs (0.38–23.48 M parameters). Results: Transfer learning used 13,536 training and 6624 validation samples from the two leads in the IRIDIA-AF Holter ECG database, evenly split between AF and non-AF cases. The top-ranked DNNs evaluated on 11,400 test samples from independent records are the retrained EfficientNetV2B1 (96.3% accuracy with minimal inter-patient (1%) and inter-lead (0.3%) drops), and fine-tuned EfficientNetV2B1 and DenseNet-121, -169, -201 (97.2–97.6% accuracy with inter-patient (1.4–1.6%) and inter-lead (0.5–1.2%) drops). These models can process shorter ECG episodes with a tolerable accuracy drop of up to 0.6% for 20 s and 4–15% for 10 s. Case studies present the GradCAM heatmaps of retrained EfficientNetV2B1 overlaid on raw ECG and ECHOView images to illustrate model interpretability. Conclusions: In an extended deep transfer learning study, we validate that ImageNet DNNs applied to short-term ECHOView images through retraining and fine-tuning can significantly enhance automated AF diagnoses. GradCAM heatmaps provide meaningful model interpretability, highlighting ECG regions of interest aligned with cardiologist focus. Full article

Background: Domain transfer plays a vital role in medical image analysis. It mitigates the challenges posed by variations in imaging equipment, protocols, and patient demographics, ultimately improving model performance across different domains or edge-intelligence devices; Methods: This paper introduces a new unsupervised domain adaptation approach, named Consistency-regularized Joint Distribution Alignment (C-JDA). Specifically, our method leverages Convolutional Neural Networks (CNNs) to align the joint distributions of source and target domains in the feature space, which involves the pseudo-labels of the target data for computing the relative chi-square divergence to measure the distribution relationship or asymmetry. Compared with traditional alignment methods with complex architectures or adversarial training, our model can be solved with a close-form equation, which is convenient for transferring among various scenarios. Additionally, we further propose symmetric consistency regularization to improve the robustness of the pseudo-label generation with diverse data augmentation strategies, where the augmented data are symmetric to their original data and should share the same predictions. Therefore, both components between distribution alignment and pseudo-label generation can be mutually improved for better performance. Results: Extensive experiments on multiple public medical image benchmarks demonstrate that C-JDA consistently outperforms both traditional domain adaptation methods and deep learning-based approaches. For the colon disease classification task, C-JDA achieved an accuracy of 87.41%, outperforming existing methods by 3.31%, with an F1 score of 87.26% and an improvement of 2.99%. For the Diabetic Retinopathy (DR) classification task, our method attained an accuracy and F1 score of 96.93%, surpassing state-of-the-art methods by 2.4%. Additionally, ablation studies validated the effectiveness of both the joint distribution alignment and symmetric consistency regularization components. Conclusions: Our C-JDA can significantly outperform existing domain adaptation methods by achieving state-of-the-art performance via improved joint distribution alignment with symmetric consistency regularization. Full article

Despite the widespread use of information measures in analyzing probabilistic systems, effective visualization tools for understanding complex dependencies in sequential data are scarce. In this work, we introduce the information matrix (InfoMat), a novel and intuitive matrix representation of information transfer in sequential systems. InfoMat provides a structured visual perspective on mutual information decompositions, enabling the discovery of new relationships between sequential information measures and enhancing interpretability in time series data analytics. We demonstrate how InfoMat captures key sequential information measures, such as directed information and transfer entropy. To facilitate its application in real-world datasets, we propose both an efficient Gaussian mutual information estimator and a neural InfoMat estimator based on masked autoregressive flows to model more complex dependencies. These estimators make InfoMat a valuable tool for uncovering hidden patterns in data analytics applications, encompassing neuroscience, finance, communication systems, and machine learning. We further illustrate the utility of InfoMat in visualizing information flow in real-world sequential physiological data analysis and in visualizing information flow in communication channels under various coding schemes. By mapping visual patterns in InfoMat to various modes of dependence structures, we provide a data-driven framework for analyzing causal relationships and temporal interactions. InfoMat thus serves as both a theoretical and empirical tool for data-driven decision making, bridging the gap between information theory and applied data analytics. Full article

Communication barriers pose significant challenges for the Deaf and Hard-of-Hearing (DHH) community, limiting their access to essential services, social interactions, and professional opportunities. To bridge this gap, assistive technologies leveraging artificial intelligence (AI) and deep learning have gained prominence. This study presents a real-time American Sign Language (ASL) interpretation system that integrates deep learning with keypoint tracking to enhance accessibility and foster inclusivity. By combining the YOLOv11 model for gesture recognition with MediaPipe for precise hand tracking, the system achieves high accuracy in identifying ASL alphabet letters in real time. The proposed approach addresses challenges such as gesture ambiguity, environmental variations, and computational efficiency. Additionally, this system enables users to spell out names and locations, further improving its practical applications. Experimental results demonstrate that the model attains a mean Average Precision (mAP@0.5) of 98.2%, with an inference speed optimized for real-world deployment. This research underscores the critical role of AI-driven assistive technologies in empowering the DHH community by enabling seamless communication and interaction. Full article

Determining the electrochemical, thermal, and mass transfer dynamics embedded in an alkaline electrolysis (AEL) system provides important information about the application of ancillary services provided by hydrogen energy for the elimination of carbon emissions. Therefore, there is an urgent need to develop methodologies for evaluating key parameters, such as overvoltage coefficients, stack transfer capacity, diaphragm thickness, and permeability, to accurately capture the system’s fluctuating characteristics. However, limited by the lack of superior sensor technology, some significant variables cannot be measured directly. In this context, comprehensively accurate parameters of an estimation strategy offer a novel alternative to characterize the system’s corresponding intrinsic nature. This paper was motivated by this arduous challenge and aims to address the large branching factors with irregular properties. Specifically, the associated mathematical models reflecting the transient operating parameters in terms of electrochemical, heat transfer, and mass transfer are first established. Subsequently, k-means clustering analysis is conducted to deduce the similarity of distribution of the measured variables, which can function as proxies of the separator to distinguish the working status. Furthermore, online reinforcement learning (RL), renowned for its ability to operate without extensive predefined datasets, is employed to conduct dynamic parameter estimation, thereby approximating the robust nonlinear and stochastic behaviors within AEL components. Finally, the experimental results verify that the proposed model achieves significant improvements in estimation errors compared to existing parameter estimation methods (such as EKF and UKF). The enhancements are 76.7%, 54.96%, 51.84%, and 31% in terms of RMSE, NRMSE, PCC, and MPE, respectively. Full article

This paper aims to mitigate multipath interference (MPI) in intensity modulation with direct detection (IM-DD) systems using machine learning techniques, specifically for four-level pulse amplitude modulation (PAM4) systems. We propose a machine learning-assisted MPI mitigation scheme, called KNN-aided SVM+RF-M. In this scheme, KNN-aided SVM serves as a soft decision algorithm that adapts the decision threshold to signal amplitude fluctuations, improving the decision accuracy for MPI-affected PAM4 signals. By replacing the original hard decision in the RF-M algorithm with KNN-aided SVM, we mitigate the error transfer problem inherent in RF-M. MPI mitigation is then achieved through MPI estimation and noise value cancellation methods applied to signals after soft decision processing. Our proposed scheme is validated in a 28 GBaud PAM4-DD transmission system, and the simulation results show that our proposed scheme can improve SIR tolerance by 2 dB and receiver sensitivity by about 1 dB at the 7% HD-FEC threshold compared to the original RF-M scheme. Full article

This study investigates the English adjective amplifier system of eleven Mandarin Chinese L2 speakers of English residing in Australia compared to a sample of ten native Australian English (AusE) speakers from the AusTalk corpus. Employing a variationist framework, we find that the L2 speakers employ a markedly overall higher rate (50.2%) of use of adjective amplifiers than AusE speakers (34.8%). This has been shown to be a common phenomenon among L2 speakers, who have a smaller range of adjectives at their disposal, and thus “over-use” amplifiers. However, we also argue that the propensity for amplifier–adjective bigrams in Mandarin Chinese transfers to their L2 English. The results show that Chinese L2 speakers use very more than really, whereas really is more frequent than very in AusE, suggesting that the L2 speakers may be lagging behind in this previously-reported change in AusE. The results also show that higher rates of English proficiency and length of residence in Australia result in more Australian-like amplifier behavior among the Chinese L2 group. The present paper can provide meaningful insights for future language teaching and learning in classroom and naturalistic settings, revealing potential for the instruction of more authentic language among L2 English learners. Full article

Background/Objectives: Social determinants of health (SDOHs) are especially impactful with respect to emergency reliance among patients with cancer. Methods: To better predict the extent to which SDOHs affect emergency admissions in homeless patients with metastatic disease, we employed machine learning models, Lasso, ridge, random forest (RF), and elastic net (EN) regression. We also examined prostate cancer (PC), breast cancer (BC), lung (LC) cancer, and cancers of the lip, oral cavity, and pharynx (CLOP) for association between key SDOH variables—homelessness and living alone—and clinical outcomes. For this, we utilized generalized linear models to assess the association while controlling for patient and clinical characteristics. We used the United States National Inpatient Sample database for this study. Results: There were 2635 (weighted) metastatic cancer patients with homelessness. Transfer from another facility or not, elective admission or not, deficiency anemia, alcohol dependence, weekend admission or not, and blood loss anemia were the important predictors of emergency admission. C-statistics were associated with Lasso (train AUC-0.85; test AUC—0.86), ridge (85, 88), RF (0.96, 0.85), and EN (0.83, 0.80), respectively. In the adjusted analysis, PC homelessness was significantly associated with anxiety and depression (5.15, 95% CI: 3.17–8.35) and a longer LOS (1.96; 95% CI: 1.03–3.74). Findings were comparable in the BC, LC, and CLOP cohorts. Cancer patients with poor SDOHs presented with the worst clinical outcomes. Conclusions: Cancer patients with poor SDOH presented with worst clinical outcomes. The findings of this study highlight a vacuum in the cancer literature, and the recommendations stress the value of social support in achieving a better prognosis and Quality of life. Full article

Deep learning-based image classification techniques have been widely utilized in low-voltage AC series-type fault arc detection. However, the transformation of signals into images frequently leads to significant loss of current signal characteristics, thereby compromising arc recognition accuracy. Additionally, uncharacterized signal content may be lost due to multiple factors, including sensor bandwidth limitations, sensor-event distance, and the topological configuration of the circuit where the fault originated. To address this challenge, a novel framework for identifying series-type low-voltage AC fault arcs is presented, which integrates the Markov transfer field (MTF) with multi-feature fusion and an improved residual neural network (ResNet18). This approach employs fast Fourier transform (FFT) to compute magnitude and phase data and then converts the original current signals, magnitude spectrograms, and phase spectrograms into MTF images. An adaptive weighted averaging strategy is subsequently applied to fuse these MTF images, generating composite discriminative features that preserve both amplitude and phase information from the original signals. The proposed system incorporates a convolutional block-based attention mechanism (CBAM) into the ResNet18 architecture to enhance feature representation while reducing training complexity. Extensive experimental evaluations on a diverse dataset demonstrate that the developed method achieves an impressive recognition accuracy of 99.88% for series fault arcs. This result validates the effectiveness of the proposed framework in maintaining critical signal characteristics and improving detection precision compared to existing approaches. Full article

Adjunct clauses have traditionally been assumed to be syntactic configurations from which extraction is universally impossible. However, numerous studies have challenged this assumption and extraction from finite adjunct clauses has been shown to be acceptable to varying degrees in the Mainland Scandinavian languages, as well as in English. The relative acceptability of extraction appears to depend on a number of factors, including the type of adjunct clause and the type of extraction dependency. Research on L2 learning has shown that learners often transfer properties of their L1 grammar into their L2 during the process of learning a second language. Our previous studies on L1 English and L1 Danish found a surprising contrast in which L1 English users found relativization out of adverbial clauses to be better than L1 Danish users did. Based on these findings, we conducted an L2 acceptability judgment experiment on extraction from three types of finite adjunct clauses in Danish (corresponding to English if-, when- and because-clauses) in order to test whether language-specific parameters related to extractability are transferred from L1 to L2. Our results show that the judgments from L2 Danish speakers are intermediate between and significantly different from L1 English and L1 Danish, which does not suggest a parameter resetting. Full article

Symbolic regression (SR) has emerged as a powerful tool for the characterization of Wireless Power Transfer (WPT) systems, estimating the distance between coils and finding the relationship between frequency and phase so as to find the best frequency to increase the power factor. This study explores the application of SR on both simulated and experimental data, demonstrating its effectiveness with low prediction errors. SR employs a genetic algorithm to identify the analytical formula that best represents the input–output relationship, combining the strengths of traditional machine learning and analytical modeling. The results, with prediction errors of less than 1%, indicate that SR not only enhances predictive accuracy but also provides insights into the underlying physical principles governing WPT systems. This dual advantage positions SR as a valuable method for optimizing WPT applications, paving the way for further research and development in this field. Full article

To address the challenge of low diagnostic accuracy in rolling bearing fault diagnosis under varying operating conditions, this paper proposes a novel method integrating the synchronized wavelet transform (SWT) with an enhanced Vision Transformer architecture, referred to as ResCAA-ViT. The SWT is first applied to process raw vibration signals, generating high-resolution time–frequency maps as input for the network model. By compressing and reordering wavelet transform coefficients in the frequency domain, the SWT enhances time–frequency resolution, enabling the clear capture of instantaneous changes and local features in the signals. Transfer learning further leverages pre-trained ResNet50 parameters to initialize the convolutional and residual layers of the ResCAA-ViT model, facilitating efficient feature extraction. The extracted features are processed by a dual-branch architecture: the left branch employs a residual network module with a CAA attention mechanism, improving sensitivity to critical fault characteristics through strip convolution and adaptive channel weighting. The right branch utilizes a Vision Transformer to capture global features via the self-attention mechanism. The outputs of both branches are fused through addition, and the diagnostic results are obtained using a Softmax classifier. This hybrid architecture combines the strengths of convolutional neural networks and Transformers while leveraging the CAA attention mechanism to enhance feature representation, resulting in robust fault diagnosis. To further enhance generalization, the model combines cross-entropy and mean squared error loss functions. The experimental results show that the proposed method achieves average accuracy rates of 99.96% and 96.51% under constant and varying load conditions, respectively, on the Case Western Reserve University bearing fault dataset, outperforming other methods. Additionally, it achieves an average diagnostic accuracy of 99.25% on a real-world dataset of generator non-drive end bearings in wind turbines, surpassing competing approaches. These findings highlight the effectiveness of the SWT and ResCAA-ViT-based approach in addressing complex variations in operating conditions, demonstrating its significant practical applicability. Full article

Highlighting the importance of artificial intelligence and machine learning approaches in engineering and fluid mechanics problems, especially in heat transfer applications is main goal of the presented article. With the advancement in Artificial Intelligence (AI) and Machine Learning (ML) techniques, the computational efficiency and accuracy of numerical results are enhanced. The theme of the study is to use machine learning techniques to examine the thermal analysis of MHD boundary layer flow of Eyring-Powell Hybrid Nanofluid (EPHNFs) passing a horizontal cylinder embedded in a porous medium with heat source/sink and viscous dissipation effects. The considered base fluid is water ($H_{2}O$) and hybrid nanoparticles titanium oxide (${TiO}_2$) and Copper oxide ($CuO$). The governing flow equations are nonlinear PDEs. Non-similar system of PDEs are obtained with efficient conversion variables. The dimensionless PDEs are truncated using a local non-similarity approach up to third level and numerical solution is evaluated using MATLAB built-in-function bvp4c. Artificial Neural Networks (ANNs) simulation approach is used to trained the networks to predict the solution behavior. Thermal boundary layer improves with the enhancement in the value of $Rd$. The accuracy and reliability of ANNs predicted solution is addressed with computation of correlation index and residual analysis. The RMSE is evaluated [0.04892, 0.0007597, 0.0007596, 0.01546, 0.008871, 0.01686] for various scenarios. It is observed that when concentration of hybrid nanoparticles increases then thermal characteristics of the Eyring-Powell Hybrid Nanofluid (EPHNFs) passing a horizontal cylinder. Full article