Search Results (150)

To address the challenges brought by the high penetration of renewable energy in power systems, such as multi-scale dynamic interactions, high feature dimensionality, and limited model generalization, this paper proposes a transient stability assessment (TSA) method that combines temporal feature selection with deep learning-based modeling. First, a two-stage feature selection strategy is designed using the inter-class Mahalanobis distance and Spearman rank correlation. This helps extract highly discriminative and low-redundancy features from wide-area measurement system (WAMS) time-series data. Then, a parallel LSTM-Transformer architecture is constructed to capture both short-term local fluctuations and long-term global dependencies. A variational inference mechanism based on a Gaussian mixture model (GMM) is introduced to enable dynamic representations fusion and uncertainty modeling. A composite loss function combining improved focal loss and Kullback–Leibler (KL) divergence regularization is designed to enhance model robustness and training stability under complex disturbances. The proposed method is validated on a modified IEEE 39-bus system. Results show that it outperforms existing models in accuracy, robustness, interpretability, and other aspects. This provides an effective solution for TSA in power systems with high renewable energy integration. Full article

Recent advances in very high resolution PlanetScope imagery and deep-learning techniques have enabled effective mapping of small water bodies (SWBs), including ponds and ditches. SWBs typically occupy a minor proportion of remote-sensing imagery. This creates significant class imbalance that introduces bias in trained models. Most existing deep-learning approaches fail to adequately address this imbalance. Such an imbalance introduces bias in trained models. Most existing deep-learning approaches fail to adequately address the inter-class (water vs. non-water) and intra-class (SWBs vs. large water bodies) simultaneously. Consequently, they show poor detection of SWBs. To address these challenges, we propose an area-based weighted binary cross-entropy (AWBCE) loss function. AWBCE dynamically weights water bodies according to their size during model training. We evaluated our approach through large-scale SWB mapping in the middle and east of Hubei Province, China. The models were trained on 14,509 manually annotated PlanetScope image patches (512 × 512 pixels each). We implemented the AWBCE loss function in State-of-the-Art segmentation models (UNet, DeepLabV3+, HRNet, LANet, UNetFormer, and LETNet) and evaluated them using overall accuracy, F1-score, intersection over union, and Matthews correlation coefficient as accuracy metrics. The AWBCE loss function consistently improved performance, achieving better boundary accuracy and higher scores across all metrics. Quantitative and visual comparisons demonstrated AWBCE’s superiority over other imbalance-focused loss functions (weighted BCE, Dice, and Focal losses). These findings emphasize the importance of specialized approaches for comprehensive SWB mapping using high-resolution PlanetScope imagery in low-latitude regions. Full article

This study proposes an asynchronous brain–computer interface (BCI) framework based on steady-state motion visual evoked potentials (SSMVEPs), designed to enhance the accuracy and robustness of control state recognition. The method integrates filter bank common spatial patterns (FBCSPs) and filter bank canonical correlation analysis (FBCCA) to extract complementary spatial and frequency domain features from EEG signals. These multimodal features are then fused and input into a dual-classifier structure consisting of a support vector machine (SVM) and extreme gradient boosting (XGBoost). A weighted fusion strategy is applied to combine the probabilistic outputs of both classifiers, allowing the system to leverage their respective strengths. Experimental results demonstrate that the fused FB(CSP + CCA)-(SVM + XGBoost) model achieves superior performance in distinguishing intentional control (IC) and non-control (NC) states compared to models using a single feature type or classifier. Furthermore, the visualization of feature distributions using UMAP shows improved inter-class separability when combining FBCSP and FBCCA features. These findings confirm the effectiveness of both feature-level and classifier-level fusion in asynchronous BCI systems. The proposed approach offers a promising and practical solution for developing more reliable and user-adaptive BCI applications, particularly in real-world environments requiring flexible control without external cues. Full article

Eye-tracking studies in virtual reality (VR) deliver insights into behavioral function. The gold standard of evaluating gaze behavior is based on manual scoring, which is labor-intensive. Previously proposed automated eye-tracking algorithms for VR head mount display (HMD) were not validated against manual scoring, or tested in dynamic areas of interest (AOIs). Our study validates the accuracy of an automated scoring algorithm, which determines temporal fixation behavior on static and dynamic AOIs in VR, against subjective human annotation. The interclass-correlation coefficient (ICC) was calculated for the time of first fixation (TOFF) and total fixation duration (TFD), in ten participants, each presented with 36 static and dynamic AOIs. High ICC values (≥0.982; p < 0.0001) were obtained when comparing the algorithm-generated TOFF and TFD to the raters’ annotations. In sum, our algorithm is accurate in determining temporal parameters related to gaze behavior when using HMD-based VR. Thus, the significant time required for human scoring among numerous raters can be rendered obsolete with a reliable automated scoring system. The algorithm proposed here was designed to sub-serve a separate study that uses TOFF and TFD to differentiate apathy from depression in those suffering from Alzheimer’s dementia. Full article

The interference of sidelobe often causes different targets to exhibit similar features, diminishing fine-grained classification accuracy. This effect is particularly pronounced when the available data are limited. To address the aforementioned issues, a novel classification framework for sidelobe-affected SAR imagery is proposed. First, a method based on maximum median filtering is adopted to remove sidelobe by exploiting local grayscale differences between the target and sidelobe, constructing a high-quality SAR dataset. Second, a deep metric learning network is constructed for fine-grained classification. To enhance the classification performance of the network on limited samples, a feature extraction module integrating a lightweight attention mechanism is designed to extract discriminative features. Then, a hybrid loss function is proposed to strengthen intra-class correlation and inter-class separability. Experimental results based on the FUSAR-Ship dataset demonstrate that the method exhibits excellent sidelobe suppression performance. Furthermore, the proposed framework achieves an accuracy of 84.18% across five ship target classification categories, outperforming the existing methods, significantly enhancing the classification performance in the context of sidelobe interference and limited datasets. Full article

Wireless sensor networks (WSNs) use distributed nodes for tasks such as environmental monitoring and surveillance. The existing anomaly detection methods fail to fully capture correlations in multi-node, multi-modal time series data, limiting their effectiveness. Additionally, they struggle with small sample scenarios because they do not effectively map features to classes. To address these challenges, this paper presents an anomaly detection approach that integrates deep learning with metric learning. A framework incorporating a graph attention network (GAT) and a Transformer is developed to capture spatial and temporal features. A novel distance measurement module improves similarity learning by considering both intra-class and inter-class relationships. Joint metric-classification training improves model accuracy and generalization. Experiments conducted on public datasets demonstrate that the proposed approach achieves an F1 score of 0.89, outperforming the existing approaches by 7%. Full article

Background: Cardiovascular risk assessment relies heavily on coronary calcium scoring. With an emphasis on varying slice increments, this study investigates the effectiveness of true and virtual non-contrast reconstructions on photon-counting CT. Reconstruction methods’ effects on calcium severity classifications are critical to the improvement in imaging techniques. Methods: This study comprised 77 participants (mean age: 63 ± 10 years, 43% female), of whom 0 had a coronary artery calcium score (CACS) of zero. In contrast to true non-contrast (TNC) 3 × 3 mm, the reconstructions included TNC 3 × 1.5 mm, virtual non-contrast (VNC) 3 × 3 mm, and VNC 3 × 1.5 mm. Agatston units served as the basis for classifications into standard clinical diagnostic categories. Results: High concordance between acquisition types was revealed by interclass correlation values (0.97–0.99). Comparing TNC 3 × 1.5 mm reconstructions to their VNC counterparts, misclassifications were less common (Cohen Kappa = 0.94). (K = 0.83–0.85). Significant differences in the average calcium scores and rates of misclassification highlighted the impact of reconstruction methods on precise evaluations. Conclusions: VNC methods demonstrated high agreement; however, with a small rate of misclassifications as compared to the gold standard method. VNC CACS may help optimize workflows but may need differing cutoffs as compared to traditional methods. Full article

Pest infestations remain a critical threat to global agriculture, significantly compromising crop yield and quality. While accurate pest detection forms the foundation of precision pest management, current approaches face two primary challenges: (1) the scarcity of comprehensive multi-scale, multi-category pest datasets and (2) performance limitations in detection models caused by substantial target scale variations and high inter-class morphological similarity. To address these issues, we present three key contributions: First, we introduce Insect25—a novel agricultural pest detection dataset containing 25 distinct pest categories, comprising 18,349 high-resolution images. This dataset specifically addresses scale diversity through multi-resolution acquisition protocols, significantly enriching feature distribution for robust model training. Second, we propose GC-Faster RCNN, an enhanced detection framework integrating a hybrid attention mechanism that synergistically combines channel-wise correlations and spatial dependencies. This dual attention design enables more discriminative feature extraction, which is particularly effective for distinguishing morphologically similar pest species. Third, we implement an optimized training strategy featuring a cosine annealing scheduler with linear warm-up, accelerating model convergence while maintaining training stability. Experiments have shown that compared with the original Faster RCNN model, GC-Faster RCNN has improved the average accuracy mAP0.5 on the Insect25 dataset by 4.5 percentage points, and mAP0.75 by 20.4 percentage points, mAP0.5:0.95 increased by 20.8 percentage points, and the recall rate increased by 16.6 percentage points. In addition, experiments have also shown that the GC-Faster RCNN detection method can reduce interference from multiple scales and high similarity between categories, improving detection performance. Full article

(1) Background: The application of a mathematical formula to human gait at certain phases is a considerable method to avoid the issues associated with complicated procedures of gait assessment. The purpose of this study was to identify the validity and reliability of an angle (the ZAY angle) in estimating and predicting the step length in healthy subjects. (2) Methods: Thirty-three college-aged students participated in this study. For an assessment of each participant’s gait, a 4.5 m walkway was covered with a weight paper roll to mark the participant’s footprints, providing the step lengths of six consecutive steps for two trials. At the same time, a video recording was captured and analyzed by the Coach’s Eye application to determine the step angle (ß). The arc length formula was utilized to calculate the ZAY angle (θ). Spearman’s rho correlation coefficient and the interclass correlation coefficient were used to test the validity and reliability of the ZAY angle in determining individualized step lengths in healthy subjects. Simple linear regression was used to test if the calculated angle could significantly predict the step length. (3) Results: The Spearman rho correlation between the analyzed and calculated angles was significant for all three step lengths (p < 0.05). It was found that the calculated angle could significantly predict the step length (β = 0.91, p < 0.05). The ICC was very high (p < 0.05). (4) Conclusions: The ZAY angle is a valid and reliable angle that can be used to estimate individualized step lengths. Clinicians could include this angle in their gait analysis profiles to achieve individualized assessment and rehabilitation goals. Full article

Background/Objectives: Accurate localization of fractured endodontic instruments (FEIs) in periapical radiographs (PAs) remains a significant challenge. This study aimed to evaluate the performance of YOLOv8 and Mask R-CNN in detecting FEIs and root canal treatments (RCTs) and compare their diagnostic capabilities with those of experienced endodontists. Methods: A data set of 1050 annotated PAs was used. Mask R-CNN and YOLOv8 models were trained and evaluated for FEI and RCT detection. Metrics including accuracy, intersection over union (IoU), mean average precision at 0.5 IoU (mAP50), and inference time were analyzed. Observer agreement was assessed using inter-class correlation (ICC), and comparisons were made between AI predictions and human annotations. Results: YOLOv8 achieved an accuracy of 97.40%, a mAP50 of 98.9%, and an inference time of 14.6 ms, outperforming Mask R-CNN in speed and mAP50. Mask R-CNN demonstrated an accuracy of 98.21%, a mAP50 of 95%, and an inference time of 88.7 ms, excelling in detailed segmentation tasks. Comparative analysis revealed no statistically significant differences in diagnostic performance between the models and experienced endodontists. Conclusions: Both YOLOv8 and Mask R-CNN demonstrated high diagnostic accuracy and reliability, comparable to experienced endodontists. YOLOv8’s rapid detection capabilities make it particularly suitable for real-time clinical applications, while Mask R-CNN excels in precise segmentation. This study establishes a strong foundation for integrating AI into dental diagnostics, offering innovative solutions to improve clinical outcomes. Future research should address data diversity and explore multimodal imaging for enhanced diagnostic capabilities. Full article

Background and Objectives: The main objectives of our study were to assess sexual dimorphism and to compare the facial height, as well as the anteroposterior width of the upper airway, within adult Caucasians diagnosed with skeletal Class I and skeletal Class III malocclusion, based on a number of angular and linear cephalometric parameters. Materials and Methods: One hundred lateral cephalograms were selected from orthodontic adult Caucasian patients from western Romania. Several angular parameters (SNA, SNB, ANB, FMA, Y–FH, Ba–S–PNS and NL–ML angles) and linear parameters (total, upper and lower anterior facial height—TAFH, UAFH, LAFH; total posterior facial height—TPFH) were analysed for each case. The upper airway width parameters included the width of the nasopharynx, as well as the upper, middle and lower pharyngeal airway width (UPAW, MPAW and LPAW). Results: Distinct sexual dimorphism was observed regarding the vertical cephalometric parameters within both Class I and Class III groups, with males exhibiting significantly larger facial height parameters, while females demonstrated larger nasopharyngeal depth angles (Ba–S–PNS). The Y–FH angle had significantly higher values in Class I than in Class III subjects, regardless of sex. Upper airway dimensions showed sexual dimorphism specifically in Class III subjects, with females exhibiting larger UPAW values than males. The inter-class comparisons showed larger values for LPAW, especially in females. Correlation analyses revealed no statistically significant relationships between the vertical and the upper airway parameters in Class I subjects. UPAW showed a tendency to decrease in Class III subjects as TAFH and LAFH increased. Ba–S–PNS showed consistent negative correlations with the vertical dimensions in both groups. Conclusions: These findings suggest that skeletal Class I and Class III malocclusions exhibit not only different sagittal relationships, but also distinctive, sex-related vertical skeletal patterns within each group, and therefore it would be advised that male and female patients should be diagnosed and treated according to separate protocols. In our population, Class III males are more likely to require orthognathic surgery, in addition to orthodontic treatment, with a more reserved prognosis and they might have a higher risk of OSA or other respiratory disorders in comparison with Class III females. Full article

This study was designed to evaluate the influence of maturity status in the inter- and intra-session reliability of curvilinear sprinting (CS) and compare the reliability of the half-CS trials with the complete CS trials. Forty-two youth basketball players from an elite academy (13.1 ± 1.7 years; 166.7 ± 16.2 cm; 57.2 ± 17.0 kg) performed two sessions of three CS trials each on both right and left sides with seven days of separation between sessions. The predicted peak height velocity (PHV) was used to establish players’ maturity status (pre-PHV, n = 14; mid-PHV, n = 14; post-PHV = 13). Mid- and post-PHV groups showed a high relative (interclass correlation coefficient [ICC] ≥ 0.75) and absolute (coefficient of variation [CV] < 5%) reliability inter- and intra-session, and pre-PHV showed high relative and absolute reliability in the left trials and in the CS right trial, but moderate (ICC = 0.73) relative reliability in the half-CS right side. Based on these findings, it is recommended that practitioners consider players’ maturity status to ensure accurate and reliable assessments of CS performance. Full article

Complexity is one of the most important variables in how the brain performs decision making based on esthetic values. Multiple definitions of perceptual complexity have been proposed, with one of the most fruitful being the Normalized Shannon Entropy one. However, the Normalized Shannon Entropy definition has theoretical gaps that we address in this article. Focusing on visual perception, we first address whether normalization fully corrects for the effects of measurement resolution on entropy. The answer is negative, but the remaining effects are minor, and we propose alternate definitions of complexity, correcting this problem. Related to resolution, we discuss the ideal spatial range in the computation of spatial complexity. The results show that this range must be small but not too small. Furthermore, it is suggested by the analysis of this range that perceptual spatial complexity is based solely on translational isometry. Finally, we study how the complexities of distinct visual variables interact. We argue that the complexities of the variables of interest to the brain’s visual system may not interact linearly because of interclass correlation. But the interaction would be linear if the brain weighed complexities as in Kempthorne’s λ-Bayes-based compromise problem. We finish by listing several experimental tests of these theoretical ideas on complexity. Full article

In data-scarcity scenarios, few-shot object detection (FSOD) methods exhibit a notable advantage in alleviating the over-fitting problem. Currently, research on FSOD in the field of remote sensing is advancing rapidly and FSOD methods based on the fine-tuning paradigm have initially displayed their excellent performance. However, existing fine-tuning methods often encounter classification confusion issues. This is potentially because of the shortage of explicit modeling for transferable common knowledge and the biased class distribution, especially for fine-grained targets with higher inter-class similarity and intra-class variance. In view of this, we first propose a decoupled self-distillation (DSD) method to construct class prototypes in two decoupled feature spaces and measure inter-class correlations as soft labels or aggregation weights. To ensure a robust set of class prototypes during the self-distillation process, we devise a feature filtering module (FFM) to preselect high-quality class representative features. Furthermore, we introduce a progressive prototype calibration module (PPCM) with two steps, compensating the base prototypes with the prior base distribution and then calibrating the novel prototypes with adjacent calibrated base prototypes. Experiments on MAR20 and customized SHIP20 datasets have demonstrated the superior performance of our method compared to other existing advanced FSOD methods, simultaneously confirming the effectiveness of all proposed components. Full article

This study introduces a mechatronic biomedical device engineered for concurrent acquisition and analysis of four cardiac non-invasive signals: Electrocardiogram (ECG), Phonocardiogram (PCG), Impedance Cardiogram (ICG), and Photoplethysmogram (PPG). The system enables assessment of individual and simultaneous waveforms, allowing for detailed scrutiny of cardiac electrical and mechanical dynamics, encompassing heart rate variability, systolic time intervals, pre-ejection period (PEP), and aortic valve opening and closing timings (ET) through an application programmed with MATLAB App Designer, which applies derivative filters, smoothing, and FIR digital filters and evaluates the delay of each one, allowing the synchronization of all signals. These metrics are indispensable for deriving critical hemodynamic indices such as Stroke Volume (SV) and Cardiac Output (CO), paramount in the diagnostic armamentarium against cardiovascular pathologies. The device integrates an assembly of components including five electrodes, operational and instrumental amplifiers, infrared opto-couplers, accelerometers, and advanced filtering subsystems, synergistically tailored for precision and fidelity in signal processing. Rigorous validation utilizing a cohort of healthy subjects and benchmarking against established commercial instrumentation substantiates an accuracy threshold below 4.3% and an Interclass Correlation Coefficient (ICC) surpassing 0.9, attesting to the instrument’s exceptional reliability and robustness in quantification. These findings underscore the clinical potency and technical prowess of the developed device, empowering healthcare practitioners with an advanced toolset for refined diagnosis and management of cardiovascular disorders. Full article