Search Results (3,489)

Varroa destructor (Bee mite) and Deformed Wing Virus are primary causes of honeybee colony collapse. This study developed an automated AI-based vision inspection system for detecting bee mites and deformed bees using the YOLO algorithm. The system integrates an RGB camera, a beecomb rotation motor, and an image transmission module to enable automated dual-sided image acquisition of the beecomb. The image characteristics of normal bees, bee mites, and deformed bees were analyzed, and YOLO-based object detection models were developed to classify them. Six YOLO models—based on YOLOv8 and YOLOv11 architectures across three model sizes (nano, small, and large)—were evaluated on 405 test images (6441 objects). The proposed system reduced the inspection time from 240 s required for manual method to 20 s per beecomb, achieving 12-fold efficiency improvement. Comparative analysis showed model-task specialization: YOLOv8l excelled in detecting small bee mites (F1: 92.5%, mAP[0.5]: 92.1%), while YOLOv11s achieved the highest performance for morphologically diverse deformed bees (F1: 95.1%). Error analysis indicated that detection performance was influenced by morphological characteristics. Deformed bee detection errors correlated with overlap in wing-to-body ratio: DB Type II exhibited 18.6% miss rate, while DB Type III achieved perfect detection. In bee mite detection, a sensitivity–specificity trade-off was observed: YOLOv11l had the lowest false negatives (2.5%) but highest false positives, while YOLOv8l demonstrated superior discrimination. These results demonstrate the practical potential of the proposed system for field deployment in apiaries, supporting early pest diagnosis and improved colony health management. The model-task specialization framework provides guidance for architecture selection based on object characteristics. Future work will focus on multi-location validation and real-time monitoring integration. Full article

Extreme class imbalance is a persistent obstacle for machine learning-driven intrusion detection, as rare but high-impact cyberattacks occur far less frequently than benign traffic in training data. In many real-world cybersecurity datasets, this imbalance becomes extreme, with certain attack types containing a handful of samples, effectively placing the problem in a few-shot learning regime. This paper presents a controlled benchmarking study of Generative Adversarial Network (GAN) objectives for synthesizing minority-class cyberattack data. Using the UWF-ZeekData22 network traffic dataset, each MITRE ATT&CK tactic is framed as a separate binary detection task, and tactic-specific GANs are trained solely on minority samples to generate synthetic attack records. Four widely used GAN variants—Vanilla GAN, Conditional GAN (cGAN), Wasserstein GAN (WGAN), and Wasserstein GAN with Gradient Penalty (WGAN-GP)—are compared under unified training steps and fixed augmentation conditions. The utility of generated data is assessed by evaluating downstream detection performance using five traditional classifiers: Logistic Regression, Support Vector Machine, k-Nearest Neighbors, Decision Tree, and Random Forest. The results indicate that GAN augmentation generally strengthens minority-class detection across tactics and models, reducing false negatives and improving recall consistency, while not systematically harming majority-class performance. However, the effectiveness of each GAN objective varies significantly with data sparsity. Specifically, simpler adversarial objectives often outperform more complex architectures by preserving discriminative feature structure, while heavily regularized models may overly smooth minority-class distributions and reduce separability. Wasserstein-based objectives provide improved training stability, but additional regularization does not consistently translate to better detection performance. Overall, the results demonstrate that in extreme-imbalance settings, GAN effectiveness is governed more by data sparsity and structure preservation than by architectural complexity. These findings establish class-specific generative augmentation as a practical strategy for intrusion detection and provide empirical guidance for selecting appropriate GAN objectives for tabular cybersecurity data under highly imbalanced conditions. Full article

Background: Conventional analyses of physiological recovery often rely on discrete metrics that assume independence across time points, thereby ignoring intrinsic temporal continuity and masking substantial interindividual heterogeneity. This proof-of-concept study assesses the efficacy of Functional Data Analysis (FDA) as a promising framework for characterizing individual response dynamics following a functional threshold power (FTP) test. Methods: Physiological time-series data (including blood lactate, heart rate, blood pressure, and glucose levels) collected from 21 trained cyclists (10 professionals, 11 amateurs) were represented as functional objects using FDataGrid on the original sampling grid (0, 3, 5, 10, 20 min), without basis expansion or smoothing. We conducted unsupervised functional clustering (K-means; Fuzzy K-means) and supervised classification (Maximum Depth with Modified Band Depth, K-Nearest Neighbors, Nearest Centroid, functional QDA with parametric Gaussian covariance). Model performance was estimated via Repeated Stratified 5-Fold Cross-Validation with 10 repetitions (50 folds), reporting accuracy, balanced accuracy (mean ± SD), 95% CIs, permutation p-values, and sensitivity/specificity from aggregated confusion matrices. Results: Lactate (CL) and diastolic blood pressure (DBP) provided useful and statistically significant discrimination across several classifiers (e.g., KNN, Nearest Centroid, functional QDA), whereas heart rate showed modest discriminative value and glucose intermediate performance. Unsupervised analyses revealed distinct lactate recovery profiles and graded membership for hemodynamic/metabolic variables, supporting the value of FDA for resolving heterogeneity beyond group-average trends. Conclusions: FDA offers a feasible and informative approach for classifying recovery phenotypes while preserving temporal structure. Findings are promising but should be interpreted with caution due to the small sample size, sparse time points, and the need for external validation in larger, independent cohorts before translation into routine decision-making. Full article

Background: Early vascular aging (EVA) is a common complication of type 2 diabetes mellitus. Early identification is crucial in middle-aged individuals with T2DM, as vascular stiffness can occur gradually for years before cardiovascular disease. However, EVA is rarely considered in routine care. Adropin is a vasoprotective peptide that may counter-regulate endothelin-1 (ET-1). Therefore, this study aims to examine the association between circulating adropin, ET-1, oxLDL, MMP-2, VEGFA, and EVA. Methods: This observational study included 300 adults aged 25–55 years (150 T2DM; 150 age/sex-matched controls). ePWV was calculated from age and mean blood pressure. EVA was classified using a residual-based, age-specific ePWV threshold derived from controls. Associations were tested using correlation and logistic regression. ROC and decision curve analyses were performed to evaluate diagnostic performance and clinical utility. Results: EVA prevalence was 38.6% overall, occurring in 7.3% of controls and increasing across T2DM with good and poor glycemic control (56.1% and 80.95%, respectively, p < 0.001). Compared with normal vascular aging, EVA showed lower adropin and higher ET-1, oxLDL and MMP-2, with lower VEGFA (all p < 0.05). In fully adjusted models, adropin (OR 0.991 per pg/mL; p < 0.001) and ET-1 (OR 1.017 per pg/mL, p = 0.005) remained independently associated with EVA. A combined adropin + ET-1 predictor improved discrimination (AUC 0.901, 95% CI 0.868–0.934), at a predicted-probability cutoff of 0.607, 78.7% sensitivity and 87.0% specificity. Conclusions: In middle-aged T2DM, EVA was associated with lower adropin and higher ET-1 in T2DM. These findings support an association between these biomarkers and the EVA phenotype. Full article

Mold infection by Aspergillus and Penicillium spp. in Sithong sweet tamarind (Tamarindus indica L.) during commercial postharvest storage poses quality and food safety risks. However, the current visual detection method, which involves randomly cracking open the pods, is both destructive and laborious. The integration of near-infrared spectroscopy (NIRS) with artificial neural networks (ANN) enables rapid and non-destructive detection while capturing non-linear biochemical–spectral relationships, offering advantages over conventional destructive and linear analytical methods. It was tested as a mold classifier in sweet tamarind pods preserved in commercial ambient conditions (25 °C, 60% relative humidity) for five weeks. Six hundred pods were examined weekly using interactance spectroscopy (800–2500 nm) with six measurement points per pod and four spectral preprocessing methods. The ANN outperformed partial least squares discriminant analysis (PLS-DA) across all storage weeks, peaking at Week 2 with standard normal variate (SNV) preprocessing (prediction accuracy: 85.00%; sensitivity: 0.84; specificity: 0.86; F1-score: 0.85). Advanced tissue degeneration caused spectral heterogeneity, which decreased performance at Week 4 (prediction accuracy: 71.82–76.36%). Principal component loadings identified mold-induced water redistribution and carbohydrate depletion wavelengths at 938, 975–980, and 1035 nm. Week-adaptive calibration is essential for implementation because of the large difference between week-specific model accuracy (up to 85%) and overall storage model accuracy (63.53%). These findings provide a mechanistic underpinning for smaller wavelength-selective sensors and temporally adaptive mold screening systems in commercial tamarind storage. Full article

Background/Objectives: Sex estimation from craniofacial morphology is a fundamental component of biological profile construction in forensic anthropology. Population-specific reference data for Thai individuals derived from computed tomography (CT) remain limited, and direct comparisons between discriminant function analysis (DFA) and machine learning classifiers are frequently complicated by inconsistent validation protocols. This study aimed to characterize sexual dimorphism in CT-derived craniofacial measurements, compare the classification performance of DFA, support vector machine (SVM), and random forest (RF) under a unified validation protocol, and demonstrate their practical application in a forensic context. Methods: CT images from 300 Thai adults (150 males, 150 females; age range 20–90 years) were obtained from Srinagarind Hospital, Khon Kaen University. Eight linear craniofacial measurements spanning the cranial vault, facial skeleton, nasal aperture, and orbital region were obtained from each case. DFA, SVM, and RF were developed and compared under a unified leave-one-out cross-validation protocol. Classification performance was assessed using accuracy, AUC, and Matthews correlation coefficient (MCC). Results: Seven of eight measurements exhibited statistically significant sexual dimorphism, with facial breadth and nasal height demonstrating the greatest dimorphism. DFA achieved the highest classification accuracy of 85.7%, AUC of 0.924, and MCC of 0.713, incorporating five measurements into the canonical function. SVM and RF achieved comparable accuracy of 84.7% and 84.0%, respectively. All three classifiers correctly classified both forensic application cases with high confidence. Conclusions: CT-derived craniofacial measurements provide a reliable basis for sex estimation in Thai adults. The convergence of performance across all three classifiers under a unified internal validation protocol strengthens confidence in the internally validated performance estimates. The derived discriminant function equation and saved machine learning models constitute a complementary and immediately applicable toolkit for CT-based forensic sex estimation in the Thai population. Full article

Objectives: Platinum resistance remains a critical bottleneck in ovarian cancer management, yet reliable pre-treatment predictive tools are lacking. Existing markers like the platinum-free interval are retrospective, while genomic profiling is often cost-prohibitive. This study aimed to develop an accessible, machine learning-based dynamic weighted fusion (DWF) model using routine laboratory data to provide bidirectional risk stratification, particularly to reliably rule out platinum resistance before treatment initiation. Methods: In this retrospective study (2019–2023), seventy baseline clinical features were collected to differentiate platinum-resistant from platinum-sensitive ovarian cancer patients. We developed a DWF framework that dynamically integrates the top-performing classifiers from a library of 168 algorithms (combining 14 feature selection and 12 machine learning methods). Class imbalance was addressed via oversampling, and model efficacy was evaluated using area under the curve (AUC), accuracy, sensitivity, and specificity. Results: The DWF model achieved a robust AUC of 0.760 (95% CI: 0.683–0.837), outperforming all individual base classifiers. Subgroup analysis demonstrated highly consistent overall discrimination across initial treatment strategies (AUC of 0.755 for primary debulking surgery and 0.761 for neoadjuvant chemotherapy). Feature interpretation highlighted that resistance is driven by synergistic dysregulation of systemic inflammation and hypercoagulability, rather than single biomarkers. Conclusions: The proposed DWF model effectively leverages low-cost, standardized clinical data to serve as a robust bidirectional stratification tool. Its exceptional ability to rule out resistance provides clinicians with the evidence-based confidence to proceed with standard therapies, while its high-risk alerts identify candidates for early therapeutic adjustments and enhanced surveillance in ovarian cancer care. Full article

Aim: Using real-world data from an obesity clinic, we aimed primarily to define the body composition phenotype associated with increasing obesity severity and to quantify follow-up retention and clinically meaningful weight loss. As a secondary exploratory objective, we also examined how diabetes mellitus (DM) relates to these patterns beyond BMI. Methods: Among 5350 screened adults in the Obesity Clinic database, 2879 eligible individuals were included in the baseline cross-sectional analyses, including a non-obese comparison subgroup with BMI < 30 kg/m². The longitudinal cohort comprised 730 patients with obesity who returned for regular follow-up and had repeat BIA measurements at least 6 months after baseline. Patients were classified according to BMI and glycemic status. Results: Increasing BMI was associated with higher glucose, HbA1c, uric acid, triglyceride, C-reactive protein, and leukocyte levels and with lower HDL cholesterol. Body composition deterioration was driven predominantly by disproportionate increases in visceral fat score, fat mass, and total fat-to-muscle ratio rather than by parallel gains in muscle compartments. As obesity severity increased, the proportion of patients with diabetes also increased. Only 29.3% of the baseline obesity cohort achieved regular 6-month follow-up, and 79.0% of those followed lost less than 5% of baseline body weight. In age- and sex-adjusted analyses, the most pronounced DM-related body composition differences were observed in the BMI 30–39.9 kg/m² group, particularly through higher waist-to-height ratio and total fat-to-muscle ratio. Conclusions: This study shows that increasing obesity severity is accompanied by a more adverse metabolic profile and a body composition pattern characterized by greater adiposity. Within this framework, diabetes-related body composition differences were not homogeneous across BMI categories and appeared to be most evident in the BMI 30–39.9 kg/m² group. The weaker association observed in the BMI ≥ 40 kg/m² group may be related to the reduced discriminative value of waist-based measures in severe obesity, where fat accumulation may extend across multiple compartments. Given the low continuity of follow-up and the limited rates of clinically meaningful weight loss, these findings support a more refined phenotyping approach in obesity management that incorporates body composition and fat distribution in addition to BMI. Full article

This study systematically investigated the dynamic diversity, potential sources, and antifungal activities of small molecular peptides during the pile-fermentation process of post-fermented tea. By analyzing the damaging effects of small molecular peptide extracts from tea samples at different pile-fermentation stages on the spore cell membranes of Aspergillus carbonarius (A. carbonarius) and the inhibitory activity against β-1,3-glucan synthase (β-1,3-GS), it was confirmed that some small molecular peptides exhibit significant antifungal effects. The main findings are as follows: (1) The number of identified small molecular peptides showed a trend of first increasing and then decreasing with the progress of pile-fermentation, peaking at 4453 species on the 35th day of pile-fermentation, and were dominated by hexapeptides and heptapeptides with molecular weights ranging from 600 to 800 Da. (2) Based on orthogonal partial least squares discriminant analysis (OPLS-DA), the samples were divided into three characteristic stages according to the differences in small molecular peptide composition at different stages, and 156 characteristic peptides with a relative abundance higher than 0.1% were screened out. Their precursor proteins were derived from 148 proteins belonging to 16 genera, including Camellia, Aspergillus, Saccharomyces, Penicillium, and Bacillus. (3) BLAST alignment results showed that five out of the 156 characteristic peptides were degradation fragments of known antifungal peptides originating from Aspergillus and Bacillus. (4) Combining molecular docking screening and in vitro verification of synthetic peptides, a total of 27 small molecular peptides with antifungal activity were obtained, and their mechanism of action was the inhibition of β-1,3-GS activity. (5) The small molecular peptides related to antifungal activity could be classified into two categories: enzymatic hydrolysates of known antifungal peptides, and the enzymatic hydrolysates of tea-derived proteins or macromolecular peptides. Both categories were mainly distributed in the three stages of pile-fermentation, and there was a significant positive correlation among the population size of dominant microorganisms, microbial peptidase activity, and the abundance of small molecular peptides. This study reveals the dynamic generation pattern and antifungal potential of small molecular peptides during the pile-fermentation of post-fermented tea, providing a new scientific basis for evaluating the dynamic changes in microbial communities in tea and effectively controlling the contamination of harmful fungi during the pile-fermentation process. Full article

Background/Objectives: Several methods have been proposed to assess lower limb-length discrepancies; however, none have demonstrated sufficient reliability and validity for diagnosing anatomical discrepancies (DA). Objectives: This study primarily aims to evaluate the accuracy of two traditional tests—the Modified Iliac Crests Palpation and Pelvimeter with Blocks test (ICPBL) and plantar pressure analysis—by comparing them with the gold standard telemetry (TE) method for diagnosing DA. The secondary objective is to assess the intra-rater reliability of these two tests and determine their potential applicability in clinical settings. Methods: Thirty subjects between the ages of 20 and 80 were enrolled in the present prospective, cross-sectional diagnostic accuracy pilot study; thirteen with a positive TE for DA of more than 3 mm were classified into the group with the condition DA, and 17 were classified into the group without the condition DA. Pelvic tilting and plantar pressures were evaluated. Results: The TE revealed a difference of 8.09 ± 3.24 mm between the short and long limbs, while subjects without DA had only a 0.41 mm difference (p < 0.001). Similarly, the Modified ICPBL test showed a 4.38 ± 2.10 mm difference in subjects with DA, compared to 0.51 ± 0.53 mm in those without DA (p < 0.001). Additionally, plantar pressure measurements supported these findings, with a difference of 5.17 ± 3.28 kg/cm² between the short and long limbs in subjects with DA, versus 2.28 ± 1.77 kg/cm² in subjects without DA (p < 0.05). The area under the receiver operating characteristic (ROC) curve was 0.783 (95% CI: 0.456–0.877) for plantar pressures and 1.000 (95% CI: 0.742–0.942) for the Modified ICPBL test. Conclusions: The Modified ICPBL and plantar pressure tests demonstrated high diagnostic accuracy within the sample studied, suggesting they are useful tools for supporting the diagnosis of DA. In this pilot study, the Modified ICPBL showed very high discriminative ability, while plantar pressure testing demonstrated moderate sensitivity. Both methods may serve as preliminary practical alternatives to telemetry TE, potentially reducing X-ray exposure; however, these results should be interpreted with caution due to the limited sample size and the specific clinical setting of this study. Full article

Real-time facial emotion recognition remains challenging due to the high dimensionality and computational cost of dense facial representations, which limit their applicability in resource-constrained and real-time scenarios. This study proposes a compact, anatomically informed angular facial representation for efficient, interpretable emotion recognition under real-time constraints. Facial landmarks are first extracted using a standard landmark detection framework, from which a reduced facial mesh of 27 anatomically selected points is defined. Internal geometric angles computed from this mesh are analyzed using temporal variability and redundancy criteria, resulting in a minimal set of eight angular descriptors that capture the most expressive facial dynamics while preserving geometric invariance and computational efficiency. The proposed representation is evaluated using multiple supervised machine learning classifiers under two complementary validation strategies: stratified frame-level cross-validation and strict Leave-One-Subject-Out evaluation. Under mixed-subject stratified validation, the best-performing model (MLP) achieved macro-averaged F1-scores exceeding 0.95 and near-unity ROC–AUC values. However, subject-independent evaluation revealed reduced generalization performance (average accuracy ≈55%), highlighting the influence of inter-subject morphological variability embedded in absolute angular descriptors. These findings indicate that a minimal angular geometric encoding provides strong intra-subject discriminative capability while transparently characterizing its cross-subject generalization limits, offering a practical and interpretable alternative for data- and resource-constrained real-time scenarios. Full article

Early and accurate detection of skin cancer is critical for reducing mortality rates, particularly for malignant melanoma. Automated analysis of dermoscopic images has gained significant attention due to its potential to support clinical diagnosis and overcome the limitations of manual inspection. Motivated by challenges such as image noise, low contrast, lesion variability, and redundant feature representation, this study proposes an optimal deep hybrid framework for skin lesion detection and classification. The objective of this work is to design a robust and efficient system that integrates advanced preprocessing, precise segmentation, optimal feature selection, and accurate classification. Initially, contrast enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE) and noise reduction using Wiener filtering are applied to improve image quality. Lesion regions are then segmented using a Selective Kernel U-Net (SK-UNet), which adaptively captures multi-scale spatial information. Subsequently, discriminative color, texture, and shape features are extracted and optimized using the Fossa Optimization Algorithm (FOA) to eliminate redundancy. A hybrid one-dimensional Convolutional Neural Network–Gated Recurrent Unit (1D-CNN–GRU) classifier is employed for final classification, learning both spatial and sequential feature patterns. Experimental evaluation on the ISIC and DermMNIST datasets demonstrates that the proposed framework achieves classification accuracies of 97.6% and 95.6%, respectively, outperforming several existing methods. The results confirm that the proposed hybrid framework provides reliable, accurate, and scalable skin cancer diagnosis, highlighting its potential for assisting clinical decision-making and early detection. Full article

To address the challenge of accurately distinguishing UAVs and birds in a low-altitude detection field, this paper proposes a classification algorithm of UAVs and birds based on L/K dual-band micro-Doppler spectrograms and Mamba. We establish a dual-band radar detection model for unmanned aerial vehicles (UAVs) and birds, provide a method for characterizing the Doppler parameters of the echo signals, and research a UAV and bird target classification network model that integrates micro-Doppler and Mamba. Based on a dual-branch encoding framework, we use Patch block decomposition to design a classification model to serialize the two-dimensional spectrogram of the echo signal, and introduce the Mamba state-space backbone network to extract the long-term sequence features of the target’s micro-motion. The main breakthrough of the proposed classification algorithm lies in the feature fusion stage, where a late fusion strategy is adopted to integrate the dual-path high-level representation measures, fully leveraging the sensitivity of the K-band to high-frequency textures and the scale complementarity of the L-band. Then, according to the joint loss function of mutual learning and contrastive learning, we improve the model’s prediction consistency and representation discriminability. Through experimental testing, the results show that the proposed method can effectively classify UAVs and birds, and compared with other algorithms, the accuracy rate reaches 97.5%. Full article

This study frames next-day ETF market behavior as a binary regime classification problem—distinguishing between “oscillating” days, on which intraday price movements remain within a defined threshold, and “trending” days, on which movements exceed that threshold. This framing is economically motivated: active traders employing Martingale-style strategies and ETF options traders require precisely this type of regime prediction to manage risk and time positions. Using 25 years of daily data (2000–2024) for four major ETFs—IWM (Russell 2000), SPY (S&P 500), QQQ (Nasdaq-100), and DIA (Dow Jones)—the study trains and evaluates Random Forest and Neural Network classifiers enriched with macroeconomic announcement indicators and technical features (VIX, RSI, ATR) under a rolling window cross-validation framework. Oscillation is defined as daily intraday price movements within thresholds of 0.5%, 0.75%, and 1%; movements exceeding these levels constitute trending behavior. At the 0.5% threshold—the most practically relevant given typical ETF transaction costs—Neural Networks outperform a naive classifier by 13.4% for IWM, 15.4% for SPY, 4.7% for QQQ, and 3.2% for DIA. AUC values exceed 0.5 in most configurations, with stronger discrimination observed for SPY (AUC up to 0.74) and IWM (AUC up to 0.59) than for QQQ and DIA at some thresholds. Results are stronger for some ETFs and thresholds than others, and cases where AUC approaches 0.5 are explicitly acknowledged as reflecting limited discriminatory power. Full article

Autonomous Underwater Vehicles (AUVs) play a crucial role in deep-sea exploration missions. In the complex and highly dynamic marine environment, it is essential for AUVs to possess robust fault diagnosis capabilities to enhance their operational safety. In the context of AUV fault diagnosis, closed-set recognition methods tend to misclassify unknown faults as known ones, which may lead to severe operational consequences. In order to enable AUVs to adapt to new and unknown deep-sea environments and effectively detect new unknown faults, this paper proposes an open-set AUV fault recognition method based on a Convolutional Neural Network (CNN). Firstly, the CNN is employed to extract high-level discriminative features from raw sensor data. Then, a committee consisting of multiple one-class SVMs (OC-SVMs) is constructed to determine whether the input sample belongs to a known category. Finally, the identified known samples are accurately classified via the designed classifier module. This method can effectively distinguish between known faults and unknown faults. To improve the recognition accuracy of the model, an attention mechanism is introduced. By learning to automatically assign weights to different feature channels, the model can focus on more important or relevant feature channels. Experiments based on the “Haizhe” dataset demonstrate that the proposed CNN-OC-SVM model exhibits superior performance in AUV fault diagnosis tasks compared with the state-of-the-art and traditional methods. Full article