Search Results (2,664)

Intensive salmon farming is associated with high mortality rates, highlighting the need for new welfare indicators that can detect adverse conditions earlier and less invasively than many current approaches. Existing animal-based indicators used in the industry typically depend on subjective scoring and provide information mostly after welfare problems have already developed, thereby raising questions about their efficacy. Examples include emaciation, wounds, or scale loss, etc. Preliminary data and ongoing investigation suggest that melanin-based skin pigmentation may change dynamically with stress and condition in salmonid fishes. In this study, we present a semi-automated methodology for assessing changes in the grayscale intensity of melanin-based skin spots within the operculum region of adult Atlantic salmon (Salmo salar) kept in seawater. The pipeline combines computer vision models to detect the operculum, segment individual spots, and extract grayscale-based features for spot-level analysis over time. The method was applied to out-of-water images collected before and after exposure to a confinement episode. The results showed an overall shift in grayscale intensity from black to pigmentation fading after the challenge, although responses varied among individuals. These findings indicate that the proposed methodology can detect temporal changes in opercular melanin-based spots under applied experimental conditions. We therefore present this work as proof of principle for using computer vision to quantify changes in melanin-based skin spots as a potentially useful, non-invasive indicator of stress and welfare in Atlantic Salmon. Full article

Computational fluid dynamics (CFD)-based simulation of coronary blood flow provides valuable hemodynamic markers, such as pressure gradients, for diagnosing coronary artery disease (CAD). However, CFD is computationally expensive, time-consuming, and difficult to integrate into large-scale clinical workflows. These limitations restrict the availability of labeled hemodynamic data for training AI models and hinder the broad adoption of non-invasive, physiology-based CAD assessment. To address these challenges, we develop an end-to-end pipeline that automates coronary geometry extraction from coronary computed tomography angiography (CCTA), streamlines simulation data generation, and enables efficient learning of coronary blood pressure distributions. The pipeline reduces the manual burden associated with traditional CFD workflows while producing consistent training data. Furthermore, we introduce a diffusion-based regression model. Specifically, the inverted conditional diffusion (ICD) model is designed to predict coronary blood pressure directly from CCTA-derived features, thereby bypassing the need for computationally intensive CFD during inference. The proposed model is trained and validated on two CCTA datasets using the Adam optimizer with a weight decay of $1\times {10}^{-3}$, a learning rate of $1\times {10}^{-5}$, a batch size of 100, and Huber loss. It is then evaluated on a test set of ten simulated coronary hemodynamic cases. Experimental results demonstrate state-of-the-art performance. Compared with Long Short-Term Memory (LSTM), the proposed model improves the $R^2$ score by 19.78%, reduces the root mean squared error (RMSE) by 19.44%, and lowers the normalized root mean squared error (NRMSE) by 18%. Compared with a multilayer perceptron (MLP), it improves the $R^2$ score by 8.38%, reduces RMSE by 4.3%, and reduces NRMSE by 5.4%. This work represents a first step toward a scalable and accessible framework for rapid, non-invasive, CFD-based blood pressure prediction, with the potential to support CAD diagnosis. Full article

Precise temporal segmentation of acoustic cough signals is critical for digital health, yet existing literature predominantly focuses on simple event detection rather than exact boundary delineation. To bridge this gap, we introduce a comprehensive benchmarking framework specifically designed to systematically evaluate continuous boundary detection performance using modern deep learning architectures. Built upon this evaluation paradigm, we propose a novel Dual-Branch Bi-Mamba architecture that effectively integrates the local morphological feature extraction capabilities of a 2D U-Net with the long-range sequential modeling power of 1D Bidirectional State-Space Models (SSMs). Evaluated on the clinical DKPNet41 dataset, the proposed compact 0.54-million-parameter model achieved an F1-Score of 87.66% while reducing offset boundary error by over 50%. Operating 56× faster than real time on a standard CPU, this study establishes a reliable evaluation framework for precise boundary segmentation and provides a computationally efficient architectural solution for high-resolution automated acoustic signal processing. Full article

The rising incidence of skin cancer necessitates scalable and accurate diagnostic tools. While dermoscopy-based systems have achieved expert-level performance, clinical smartphone images pose challenges due to variability in lighting, resolution, and artifacts. Recent advances in multimodal deep learning have shown promise, yet most approaches rely on simple feature concatenation or single-model classifiers, limiting their ability to capture complex cross-modal interactions. This study aims to bridge the diagnostic gap in resource-limited settings by developing a robust multimodal framework that synergizes clinical smartphone images with structured patient metadata for automated skin cancer classification. We propose a novel hybrid architecture integrating a Swin Transformer V2 (SwinV2-Tiny) for hierarchical visual feature extraction and a Denoising Autoencoder (DAE) with PCA for robust metadata embedding. These heterogeneous modalities are fused via a Gated Attention Mechanism that dynamically weighs feature importance across streams. Classification is performed by a Heterogeneous Meta-Stack Ensemble comprising CatBoost, LightGBM, XGBoost, and Logistic Regression, designed to maximize calibration and generalization across imbalanced classes. Evaluated on the PAD-UFES-20 dataset (2298 clinical smartphone images, six diagnostic classes), the proposed framework achieves state-of-the-art performance with a macro-averaged F1-score of 0.977, accuracy of 0.978, and an AUC of 0.990. It significantly outperforms unimodal baselines and existing multimodal methods, demonstrating superior sensitivity (0.974) and precision (0.981), particularly for underrepresented malignant classes like Melanoma (F1: 0.995) and Squamous Cell Carcinoma (F1: 0.960). The integration of clinical metadata with advanced visual embeddings via gated attention significantly enhances diagnostic reliability. Comprehensive ablation studies confirm the contribution of each architectural component. This framework offers a viable pathway for deploying high-precision, AI-driven dermatological screening tools on standard smartphone devices. Full article

Objectives: This study aimed to evaluate and compare the performance of three tooth wear indices—BEWE, simplified TWI (sTWI), and TWES 2.0—based on the visual assessment of digital intraoral scans. A secondary exploratory objective was to examine unadjusted sex-stratified score distributions. Methods: This retrospective study included 246 anonymized intraoral scans obtained using Medit i700 and iTero Element 2 systems. All scans were independently evaluated by two calibrated examiners using the BEWE, simplified TWI (sTWI), and TWES 2.0 indices. Scoring was performed through visual assessment of the digital models, without applying automated measurements or software-assisted analysis tools. Unadjusted sex-stratified patterns were explored using mixed-effects linear models, with a significance threshold set at p < 0.05. Estimated marginal means were calculated, and graphical approaches, including heatmaps, were used to present score distributions and inter-examiner variability. Results: The indices exhibited different scoring characteristics. BEWE produced the most consistent sextant-based patterns, with low variability between examiners. TWES 2.0 showed generally stable scoring, although with slightly greater dispersion, particularly in posterior sextants. In contrast, sTWI demonstrated the highest variability and more pronounced surface-specific differences, especially on occlusal and palatal surfaces. Sex-stratified analyses indicated minor and inconsistent variations. Although isolated statistically significant findings were observed (BEWE Sextant 6; TWES 2.0 Sextant 5), they did not form a consistent or interpretable pattern. Conclusions: Assessment based on digital intraoral scans highlighted differences in scoring behavior depending on the index used. BEWE demonstrated the most stable scoring patterns, TWES 2.0 showed moderate consistency, while sTWI was associated with the greatest variability. Differences observed in sex-stratified analyses were minor and lacked consistency. Clinical significance: BEWE enables consistent scoring when applied to digital scans and may be appropriate for monitoring purposes. TWES 2.0 provides a structured approach to screening. The higher variability observed with sTWI indicates that caution is warranted when it is used exclusively on digital models. Overall, the choice of index has a substantial impact on the assessment of tooth wear in digital workflows. Full article

Speech alterations are early markers of neurodegenerative diseases. Transformer-based speech models such as Whisper have advanced automated speech assessment, but most systems rely on cloud-based computation, raising privacy concerns. On-device processing could offer a scalable and privacy-preserving alternative. This research’s objective was to evaluate whether a fully on-device speech analysis pipeline can achieve competitive accuracy in detecting Alzheimer’s disease and to quantify the contributions of acoustic, linguistic, and embedding features. Therefore, we developed an iOS application running all components, including acoustic analysis, two transformer-based speech-to-text modules (WhisperBase and quantized CrisperWhisper), linguistic feature extraction, and embedding generation, directly on the device. Using the ADReSS Challenge 2020 dataset (N = 156), we trained classical machine-learning classifiers across 20 configurations and evaluated them via a stratified 10-fold cross-validation. Area under the receiver operating curve (AUC), accuracy, precision, recall, and F1 scores were used as performance metrics. An ablation study examined the relevance of each feature group. The best-performing setup (Random Forest with CrisperWhisper transcription and Apple embeddings) achieved an accuracy of 85.4% and an AUC of 0.85. Performance was 5–7% below benchmark models relying on manual transcripts or server-based processing. Embedding features provided the strongest individual contribution, but the highest accuracy required combining acoustic, linguistic, and embedding information. A fully on-device pipeline for Alzheimer’s disease detection from speech is feasible and achieves competitive accuracy while maintaining strict data privacy. These findings highlight the potential of on-device transformer architectures for scalable, privacy-preserving digital screening. Future work should validate the approach in larger and more diverse cohorts. Full article

Computational chemistry has played a central role in early-stage drug discovery by accelerating target selection, hit identification, and lead optimization. This review summarizes recent developments in molecular docking, pharmacophore modeling, molecular dynamics (MD), and virtual screening (VS), with a focus on their application in practical drug discovery workflows. Advances in docking protocols, including consensus scoring, physics-based rescoring, and ensemble approaches, addressed the challenges of receptor flexibility. Both ligand-based and structure-based pharmacophore models facilitated scaffold hopping and guided library prioritization. MD simulations were used to assess binding pose stability, identify cryptic binding pockets, and characterize solvent interactions. These simulations also supported free-energy calculations using endpoint and alchemical methods. Large-scale VS campaigns employed curated compound libraries, often composed of make-on-demand molecules, and relied on high-performance computing or cloud infrastructure to screen up to 10⁹ compounds. Hits were validated using orthogonal biophysical assays and filtered by absorption, distribution, metabolism, excretion, and toxicity (ADMET) predictions. Integrated pipelines combining pharmacophore modeling, docking, MD, and free-energy calculations improved enrichment rates and reduced the number of compounds requiring synthesis. Several case studies demonstrated the identification of nanomolar-affinity leads from ultra-large screening campaigns. The review also addressed ongoing challenges, such as inconsistent scoring of binding affinity, protonation, and tautomeric errors, dataset bias, and reproducibility issues. Strategies to mitigate these limitations included standardized library preparation, adherence to FAIR (Findable, Accessible, Interoperable, and Reusable) data principles, and the use of prospective benchmarking protocols. The review discussed emerging trends, including the use of quantum chemistry for electronic structure refinement, ensemble docking guided by cryo-electron microscopy (cryo-EM) data, and the integration of computational tools with automated synthesis and high-throughput screening in closed-loop discovery systems. These approaches have the potential to accelerate the design–make–test cycle, increase hit novelty, and improve decision-making in early drug development programs. Full article

Efficient phenotyping is essential for accelerating genetic improvement in turfgrass breeding, where manual measurements are labor-intensive. This study evaluated hyperspectral imaging (HSI) as a high-throughput tool for assessing Zoysia spp. breeding populations consisting of 464 genotypes. HSI data (400–1000 nm) were processed through a user-in-the-loop hybrid segmentation pipeline integrating UMAP dimensionality reduction, DBSCAN clustering, Random Forest classification, and pseudo-RGB refinement. To independently assess vegetation classification performance, 10,000 manually annotated reference points from 50 pseudo-RGB images were compared with the automated module, yielding an overall accuracy of 0.9697, a precision of 0.8830, a recall of 0.9240, a specificity of 0.9779, an F1-score of 0.9030, and Cohen’s kappa of 0.8851. A Combined Ranking Score (CRS) integrating five vegetation indices and vegetation pixel count was significantly associated with aerial shoot count (r = −0.445, p < 0.001) and runner count (r = −0.207, p < 0.001). The highest-ranked genotype showed a 9370.3-pixel increase in vegetation area between 6 and 16 weeks after transplanting, compared with 1417.7 pixels for the lowest-ranked genotype. Classification performance declined under high-coverage conditions, indicating increased mixed-pixel ambiguity in dense canopies. These results suggest that HSI-based CRS can support rapid, objective, and non-destructive relative ranking of density-related vegetative growth in turfgrass breeding. Because the study was conducted at a single location and season and correlations with manual traits were moderate, the framework is best interpreted as a screening and ranking tool rather than a direct predictive model. Full article

Accurate and reproducible delineation of stream bankfull geometry remains a persistent challenge in environmental planning. To address this gap, we developed the Cross-Sections and Dimensions Tool, a semi-automated, slope-based method for extracting stream cross-sections and estimating bankfull width, elevation and depth using high-resolution elevation data. The tool applies a configurable slope threshold to identify bank edges, generates perpendicular cross-sections from a stream centreline, and stores all outputs in a structured geodatabase to ensure transparency and reproducibility. Validation against manually delineated bankfull polygons across 191 km of stream length in Greater Melbourne, Australia, demonstrated strong spatial agreement, with an average F1 score (a measure of prediction-observation overlap) of 74% and a mean absolute error of 0.64 m in bankfull elevation. The tool was most reliable in larger streams (Strahler order 5 and above) with low to moderate vegetation canopy cover (<80%). We also investigated the practical visibility limits of small or indistinct channels typically encountered by human mappers and verified that the tool did not produce unrealistic channel delineations. This approach advances geomorphic feature extraction by grounding bankfull delineation in deterministic geometry rather than hydrological recurrence or data-driven modelling. In practice, it enables scalable, transparent, and repeatable analysis of stream morphology for ecological assessment, infrastructure planning, and waterway management. Full article

Automated warehouses must coordinate fleets of mobile robots online while meeting order deadlines. In online Multi-Agent Pickup and Delivery with Deadlines (MAPD-D), committing to a feasible task immediately may restrict flexibility and increase downstream tardiness through congestion and reservation interactions. We propose Deliberate Assignment Deferral (DAD-$\theta$), a one-parameter gate on top of deadline-aware Token Passing baselines (D-TP and D-TPTS). At each token turn, the token holder evaluates the baseline-defined assignable tasks using the baseline score (lower is better); it commits only if the best score is at most $\theta$, and otherwise follows the baseline fallback. A safety override forces assignment once any assignable task reaches non-positive pickup slack. We also introduce a scale-normalized score that makes $\theta$ dimensionless for transfer across maps and deadline scales. In 100-seed paired simulations across four arrival/deadline regimes on a benchmark map, scenario-calibrated DAD-$\theta$ reduces cumulative tardiness by 9–58% and increases on-time completion by 1.3–10.0 percentage points relative to always-assign. We discuss how $\theta$ can be calibrated offline in a digital twin and monitored online via deferral and safety-trigger rates for service-level control. Full article

Automated long-essay scoring (ALES) is gradually considered as a means to enhance efficiency and consistency in large-scale assessment; however, concerns remain regarding its suitability, particularly as it relates to the reliability, validity, and fairness of ALES-assigned grades relative to human-grades in high-stakes professional contexts. This study examines these concerns using over 15,000 long essay examination scripts from a professional accounting certification examination. The study examines whether the ALES confidence index (CI) meaningfully predicts grading accuracy or points to systemic grading failures. Findings reveal fair overall agreement between human and ALES grades, with high within ±1 grade agreement, and rare yet task-concentrated ALES grading failures, while CI shows statistically significant but practically weak predictive value and limited discrimination. The results support the use of ALES as an assistive, human oversight tool rather than an independent grader, highlighting the importance of task-based validation, stronger calibration analysis, and continuous human supervision in high-stakes professional assessment contexts. The study advances innovative assessment practices, but calls for cautious deployment of ALES and recommends integration of a hybrid human-in-the-loop approach, multi-disciplinary validation, and capacity building to strengthen ethical and responsible AI usage in accounting education and professional practice, aligning with SDGs 4 and 9. Full article

Background/Objectives: Osteonecrosis of the femoral head (ONFH) is difficult to diagnose, particularly in the early stages, because radiological findings may be subtle. Delayed or inaccurate staging may increase the risk of femoral head collapse and functional loss. Although magnetic resonance imaging is highly sensitive for early-stage lesion detection, interpretation may vary depending on observer experience. Therefore, reliable and explainable automated decision support approaches are needed. Methods: In this study, a deep learning-based approach was proposed to classify ONFH into early and late stages according to the Ficat–Arlet staging system. Stage I–II cases were defined as early-stage, whereas Stage III–IV cases were defined as late-stage. Axial and coronal MR images were evaluated separately to investigate plane-dependent classification performance. The images were converted into a three-channel format, resized to a common spatial resolution, normalized, and augmented during training. Feature extraction was performed using transfer learning with modern convolutional neural network architectures. ConvNeXt Tiny was used as the main classification backbone. Weighted loss was applied to reduce the effect of class imbalance, and the decision threshold was optimized on validation data to reduce missed clinically critical late-stage cases. Results: A dataset collected from the Orthopedics and Traumatology Department of Firat University Hospital was used in the experimental evaluation. The dataset was divided into training and test sets using an 80:20 split, and 10-fold cross-validation was additionally performed to assess model stability. In the hold-out test, the axial plane model achieved 94.51% accuracy, 96.80% sensitivity, 93.49% specificity, 0.9162 F1-score, and 0.981 AUC. In the coronal plane model, 92.84% accuracy, 96.13% sensitivity, 90.96% specificity, 0.9072 F1-score, and 0.988 AUC were obtained. The 10-fold cross-validation results provided a more conservative estimate of generalization performance. Conclusions: The findings indicate that deep learning-based plane-wise analysis of MR images can distinguish early- and late-stage ONFH with high performance. Grad-CAM-based visual explanations showed that the model focused mainly on clinically relevant subchondral and weight-bearing regions of the femoral head. The proposed approach may serve as an explainable decision support tool for reducing observer-dependent variability in clinical staging. Future studies should validate the method using external, multicenter datasets and paired patient-level axial–coronal images. Full article

Valve stiction remains a persistent nonlinear phenomenon in industrial control loops, often inducing limit-cycle oscillations that degrade control performance, compromise stability, and reduce process efficiency. Reliable detection of stiction is therefore essential for condition-based maintenance and improved operational performance. This study proposes a Hybrid Wavelet–Convolutional Neural Network (HW-CNN) framework for the detection of valve stiction in closed-loop systems. The approach employs the continuous wavelet transform (CWT) to generate time–frequency scalograms that preserve localized energy distributions associated with stick–slip behavior, including transient release events and sustained oscillatory patterns. These representations are subsequently processed using a fine-tuned deep residual neural network to enable automated feature extraction and classification. Unlike conventional signal-based or generic time–frequency learning approaches, the proposed framework is designed to retain control system-specific dynamics within the feature representation, thereby improving the separability of stiction-induced signatures under varying operating conditions. The methodology is evaluated using both simulated control loop data and real industrial datasets obtained from the International Stiction Database (ISDB), ensuring evaluation under controlled and practical conditions. To enhance reliability, performance metrics are reported as averages over repeated experimental runs. The results demonstrate that the proposed HW-CNN framework achieves an accuracy of 96.1% and an F1-score of 96.0% on simulated datasets, and 90.4% accuracy with an F1-score of 90.0% on industrial data. Additional analysis indicates that the model maintains consistent detection capability despite increased variability in real-world conditions. Furthermore, interpretability is supported through Grad-CAM analysis, which shows that the network focuses on physically meaningful regions within the scalograms corresponding to known stiction dynamics. The findings confirm that the integration of wavelet-based feature encoding with deep residual learning provides a robust and interpretable framework for valve stiction detection. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder primarily caused by the degeneration of dopamine-producing neurons in the substantia nigra, leading to characteristic motor symptoms such as tremors, rigidity, and bradykinesia, as well as non-motor manifestations including depression, sleep disturbances, and speech impairments. Among these symptoms, speech abnormalities affect approximately 90% of individuals with PD, making acoustic analysis a promising non-invasive cue for early detection. However, subtle speech variations are often imperceptible to the human ear, and speech-only analysis may overlook complementary visual manifestations, such as hypomimia—reduced facial expressivity commonly observed in PD patients. To address these limitations, we propose Parkinson’s Detection via Attentional Fusion Network (PDAF-Net), a novel multimodal deep learning framework for early PD detection that jointly models acoustic and facial dynamic features in a binary classification setting. The proposed architecture consists of a Dual-Stream Feature Encoder (DSFE), with an audio branch based on a one-dimensional convolutional neural network (1D-CNN) and bidirectional long short-term memory (BiLSTM), and a visual branch built upon a two-dimensional convolutional neural network (2D-CNN) and a Transformer encoder. Multimodal integration is achieved through a Cross-Attention-guided Attentional Feature Fusion (CA-AFF) module, which explicitly models bidirectional cross-modal interactions and performs adaptive feature recalibration via an iterative attentional fusion mechanism. We conducted experiments on a self-collected Chinese multimodal dataset comprising 100 PD patients and 100 healthy controls. Although the data are balanced at the subject level, sliding-window segmentation introduces sample-level imbalance; to address this issue, a class-balanced focal loss is employed. Model performance was evaluated using subject-wise five-fold cross-validation. The results demonstrate that PDAF-Net consistently outperforms unimodal baselines across multiple evaluation metrics, achieving an accuracy of 89.3%, an F1-score of 0.884, and an AUC of 0.916. These findings highlight the effectiveness of explicit cross-modal interaction modeling and adaptive feature fusion for improving automated early PD screening in real-world clinical settings. Full article

Glamping tourism has expanded rapidly as travelers increasingly seek nature-based experiences combined with comfort and privacy, particularly in the post-COVID-19 period. Online reviews provide a valuable source of insight into how guests perceive such experiential accommodation, yet large-scale, data-driven analyses of glamping sentiment remain limited. This study applies machine-learning techniques to classify customer sentiment expressed in online reviews of glamping sites in South Korea. A total of 3233 reviews were collected from ten leading glamping locations on Naver Map, cleaned, and translated from Korean to English. Sentiment labels (negative, neutral, and positive) were generated using VADER (Valence Aware Dictionary and sEntiment Reasoner), a lexicon-based sentiment scoring tool validated for short informal texts and the labeled corpus was subsequently used to train and evaluate six supervised classifiers. Six supervised classifiers—Naïve Bayes, k-Nearest Neighbors, Random Forest, Logistic Regression, Gradient Boosting, and Support Vector Machine (SVM)—were trained and evaluated through stratified ten-fold cross-validation using accuracy, AUC, F1-score, and Matthews Correlation Coefficient (MCC). Results indicate that SVM achieved the strongest overall discriminatory performance, particularly in identifying minority sentiment classes under substantial class imbalance. These findings suggest that automated sentiment classification holds practical potential for supporting evidence-based service monitoring and reputation management in glamping tourism, although further validation in operational settings is needed before deployment can be recommended. Full article