Search Results (6,151)

Progressive Fibrosing Interstitial Lung Disease (PF-ILD) is a severe phenotype of Interstitial Lung Disease (ILD) with a poor prognosis, typically requiring prolonged clinical observation and multiple CT examinations for diagnosis. Such requirements delay early detection and treatment initiation. To enable earlier identification of PF-ILD, we propose ILD-Slider, a parameter-efficient and lightweight deep learning framework that enables accurate PF-ILD identification from a limited number of CT slices. ILD-Slider introduces anatomy-based position markers (PMs) to guide the selection of representative slices (RSs). A PM extractor, trained via a multi-class classification model, achieves high PM detection accuracy despite severe class imbalance by leveraging a peak slice mining (PSM)-based strategy. Using the PM extractor, we automatically select three, five, or nine RSs per case, substantially reducing computational cost while maintaining diagnostic accuracy. The selected RSs are then processed by a slice-level 3D Adapter (Slider) for PF-ILD identification. Experiments on 613 cases from The University of Osaka Hospital (UOH) and the National Hospital Organization Osaka Toneyama Medical Center (OTMC) demonstrate the effectiveness of ILD-Slider, achieving an AUPRC of 0.790 (AUROC 0.847) using only five automatically extracted RSs. ILD-Slider further validates the feasibility of diagnosing PF-ILD from non-contiguous slices, which is particularly valuable for real-world and public datasets where contiguous volumes are often unavailable. These results highlight ILD-Slider as a practical and efficient solution for early PF-ILD identification. Full article

Objective evaluation of pilot fatigue is crucial for enhancing aviation safety. Although electroencephalography (EEG) is regarded as an effective tool for recognizing pilot fatigue, the direct application of deep learning models to raw EEG signals faces significant challenges due to issues such as massive data volume, excessively long training time, and model overfitting. Moreover, existing feature-based methods often suffer from data redundancy due to the lack of effective feature and channel selections, which compromises the model’s recognition efficiency and accuracy. To address these issues, this paper proposes a framework, named ASFT-Transformer, for fast and accurate detection of pilot fatigue. This framework first extracts time-domain and frequency-domain features from the four EEG frequency bands. Subsequently, it introduces a feature and channel selection strategy based on one-way analysis of variance and support vector machine (ANOVA-SVM) to identify the most fatigue-relevant features and pivotal EEG channels. Finally, the FT-Transformer (Feature Tokenizer + Transformer) model is employed for classification based on the selected features, transforming the fatigue recognition problem into a tabular data classification task. EEG data is collected from 32 pilots before and after actual simulator training to validate the proposed method. The results show that ASFT-Transformer achieved average accuracies of 97.24% and 87.72% based on cross-clip data partitioning and cross-subject data partitioning, which were significantly superior to several mainstream machine learning and deep learning models. Under the two types of cross-validation, the proposed feature and channel selection strategy not only improved the average accuracy by 2.45% and 8.07%, respectively, but also drastically reduced the average training time from above 1 h to under 10 min. This study offers civil aviation authorities and airline operators a tool to manage pilot fatigue objectively and effectively, thereby contributing to flight safety. Full article

Background/Objectives: Radiomics enables extraction of quantitative imaging features to support non-invasive classification of prostate cancer (PCa). Accurate detection of clinically significant PCa (csPCa; Gleason score ≥ 3 + 4) is crucial for guiding treatment decisions. However, many studies explore limited feature selection, classifier, and harmonization combinations, and lack external validation. We aimed to systematically benchmark modeling pipelines and evaluate whether combining radiomics with the lesion-to-normal ADC ratio improves classification robustness and generalizability in multicenter datasets. Methods: Radiomic features were extracted from ADC maps using IBSI-compliant pipelines. Over 100 model configurations were tested, combining eight feature selection methods, fifteen classifiers, and two harmonization strategies across two scenarios: (1) repeated cross-validation on a multicenter dataset and (2) nested cross-validation with external testing on the PROSTATEx dataset. The ADC ratio was defined as the mean lesion ADC divided by contralateral normal tissue ADC, by placing two identical ROIs in each side, enabling patient-specific normalization. Results: In Scenario 1, the best model combined radiomics, ADC ratio, LASSO, and Naïve Bayes (AUC-PR = 0.844 ± 0.040). In Scenario 2, the top-performing configuration used Recursive Feature Elimination (RFE) and Boosted GLM (a generalized linear model trained with boosting), generalizing well to the external set (AUC-PR = 0.722; F1 = 0.741). ComBat harmonization improved calibration but not external discrimination. Frequently selected features were texture-based (GLCM, GLSZM) from wavelet- and LoG-filtered ADC maps. Conclusions: Integrating radiomics with the ADC ratio improves csPCa classification and enhances generalizability, supporting its potential role as a robust, clinically interpretable imaging biomarker in multicenter MRI studies. Full article

Dietary flavonoids are emerging as multifunctional bioactive compounds with significant implications for the prevention and management of chronic diseases. Integrating the latest experimental, clinical, and epidemiological evidence, this review provides a comprehensive synthesis of flavonoid classification, chemistry, dietary sources, and bioavailability, with special attention to their structural diversity and core mechanisms. Mechanistic advances related to antioxidant, anti-inflammatory, antimicrobial, anti-obesity, neuroprotective, cardioprotective, and anticancer activities are highlighted, focusing on the modulation of critical cellular pathways such as PI3K/Akt/mTOR, NF-κB, and AMPK. Evidence from in vitro and in vivo models, supported by clinical data, demonstrates flavonoids’ capacity to regulate oxidative stress, inflammation, metabolic syndrome, adipogenesis, cell proliferation, apoptosis, autophagy, and angiogenesis. An inverse correlation between flavonoid-rich dietary patterns and the risk of obesity, cancer, cardiovascular, and neurodegenerative diseases is substantiated. However, translational challenges persist, including bioavailability and the optimization of delivery strategies. In conclusion, a varied dietary intake of flavonoids constitutes a scientifically grounded approach to non-communicable disease prevention, though further research is warranted to refine clinical applications and elucidate molecular mechanisms. Full article

The traditional Mahalanobis–Taguchi System (MTS) employs two main strategies for multi-class classification: the partial binary tree MTS (PBT-MTS) and the multi-tree MTS (MT-MTS). The PBT-MTS relies on a fixed binary tree structure, resulting in limited model flexibility, while the MT-MTS suffers from its dependence on pre-defined category partitioning. Both methods exhibit constraints in adaptability and classification efficiency within complex data environments. To overcome these limitations, this paper proposes an innovative Adaptive Tree-structured Mahalanobis–Taguchi System (ATMTS). Its core breakthrough lies in the ability to autonomously construct an optimal multi-layer classification tree structure. Unlike conventional PBT-MTS, which establishes a Mahalanobis Space (MS) containing only a single category per node, ATMTS dynamically generates the MS that incorporates multiple categories, substantially enhancing discriminative power and structural adaptability. Furthermore, compared to MT-MTS, which depends on prior label information, ATMTS operates without predefined categorical assumptions, uncovering discriminative relationships solely through data-driven learning. This enables broader applicability and stronger generalization capability. By introducing a unified multi-objective joint optimization model, our method simultaneously optimizes structure construction, feature selection, and threshold determination, effectively overcoming the drawbacks of conventional phased optimization approaches. Experimental results demonstrate that ATMTS outperforms PBT-MTS, MT-MTS, and other mainstream classification methods across multiple benchmark datasets, achieving significant improvements in the accuracy and robustness of multi-class classification tasks. Full article

Reservoir architecture significantly influences fluid flow in ultra-low permeability reservoirs, yet this critical factor is frequently neglected in development strategies. This study investigates the Huang 57 block within the Jiyuan Oilfield of China’s Ordos Basin, where we conducted detailed analysis of well logging data, production history, and sedimentological characteristics. Our research established five diagnostic criteria for identifying architectural boundaries of subaqueous distributary channels, enabling classification of two fundamental architectural patterns—isolated and amalgamated—with four distinctive stacking styles. Analysis reveals that architectural heterogeneity exerts primary control over residual oil distribution, with concentrated accumulation occurring at poorly connected channel margins, interlayer barriers, and unswept zones. We verified these findings through horizontal well data and production performance analysis. The study presents a comprehensive framework for architectural characterization in low-permeability reservoirs and proposes specific development strategies, including strategic well conversion and optimized infill drilling, to enhance injection–production connectivity and improve recovery efficiency. These practical solutions offer valuable guidance for developing similar reservoirs worldwide. Full article

Spatial density, as a key indicator of the quality of the urban residential environment, comprises both physical and perceived dimensions. Physical density refers to objective spatial characteristics (e.g., building density and population density), whereas perceived density denotes residents’ perceptual evaluations (e.g., perceived crowding, visual openness, and overall environmental quality). Clarifying the relationship between physical and perceived density is therefore critical for advancing livability-oriented urban planning and design. This study examines the relationship through an empirical analysis of 50 representative high-density communities in Guangzhou. Using morphological classification, descriptive statistics, and multiple linear regression, the analysis compares objective density indicators with residents’ perceptual evaluations and identifies key environmental factors that shape perceived density. Findings indicate that physical and perceived density are not fully aligned: compact but coherent spatial forms can enhance residents’ perceptual evaluations, whereas overcrowded and deteriorating environments intensify negative perceptions. The identified community typologies—for example, urban villages, traditional walk-up estates, and modern high-rise complexes—exhibit distinct perceptual patterns and influencing factors. These results highlight the need for density regulation to move beyond conventional physical indicators and to incorporate perceptual dimensions into planning frameworks. Overall, the study provides theoretical insights and practical guidance for tailored strategies in the renewal and management of high-density communities. Full article

Photovoltaic (PV) fault detection faces significant challenges in distinguishing subtle defects from complex backgrounds while maintaining reliability across diverse environmental conditions. Traditional approaches struggle with scalability and accuracy limitations, particularly when detecting electrical damage, physical defects, and environmental soiling in thermal imagery. This paper presents SolarFaultAttentionNet, a novel dual-attention deep learning framework that integrates channel-wise and spatial attention mechanisms within a multi-path CNN architecture for enhanced PV fault classification. The approach combines comprehensive data augmentation strategies with targeted attention modules to improve feature discrimination across six fault categories: Electrical-Damage, Physical-Damage, Snow-Covered, Dusty, Bird-Drop, and Clean. Experimental validation on a dataset of 885 images demonstrates that SolarFaultAttentionNet achieves 99.14% classification accuracy, outperforming state-of-the-art models by 5.14%. The framework exhibits perfect detection for dust accumulation (100% across all metrics) and robust electrical damage detection (99.12% F1 score) while maintaining an optimal sensitivity (98.24%) and specificity (99.91%) balance. The computational efficiency (0.0160 s inference time) and systematic performance improvements establish SolarFaultAttentionNet as a practical solution for automated PV monitoring systems, enabling reliable fault detection critical for maximizing energy production and minimizing maintenance costs in large-scale solar installations. Full article

Open-vocabulary object detection in remote sensing aims to detect novel categories not seen during training, which is crucial for practical aerial image analysis applications. While some approaches accomplish this task through large-scale data construction, such methods incur substantial annotation and computational costs. In contrast, we focus on efficient utilization of limited datasets. However, existing methods such as CastDet struggle with inefficient data utilization and class imbalance issues in pseudo-label generation for novel categories. We propose an enhanced open-vocabulary detection framework that addresses these limitations through two key innovations. First, we introduce a selective masking strategy that enables direct utilization of partially annotated images by masking base category regions in teacher model inputs. This approach eliminates the need for strict data separation and significantly improves data efficiency. Second, we develop a dynamic frequency-based class weighting that automatically adjusts category weights based on real-time pseudo-label statistics to mitigate class imbalance issues. Our approach integrates these components into a student–teacher learning framework with RemoteCLIP for novel category classification. Comprehensive experiments demonstrate significant improvements on both datasets: on VisDroneZSD, we achieve 42.7% overall mAP and 41.4% harmonic mean, substantially outperforming existing methods. On DIOR dataset, our method achieves 63.7% overall mAP with 49.5% harmonic mean. Our framework achieves more balanced performance between base and novel categories, providing a practical and data-efficient solution for open-vocabulary aerial object detection. Full article

The garment manufacturing industry, being labor-intensive, has long faced challenges in automating the sewing process due to the flexibility and deformability of fabrics. This study proposes a novel strategy for automated sewing by integrating soft fingers and machine vision technology. Firstly, leveraging the flexibility and adjustability of soft fingers, combined with the motion characteristics of the sewing machine, a sewing model was established to achieve coordinated operation between the soft fingers and the sewing machine. Experimental results indicate that the fabric feeding speed and waiting time of the soft fingers are significantly correlated with the sewing speed and stitch density of the sewing machine, but not with the fabric properties. Secondly, machine vision technology was employed to inspect the quality of the sewn fabrics, achieving a classification accuracy of 97.84%. This study not only provides theoretical and technical support for the intelligent upgrading of the garment manufacturing industry but also lays the foundation for the automation of complex sewing processes such as quilting. Future research will further optimize the system’s performance and expand its applications in more complex sewing tasks. Full article

This paper proposes TWISS (TOPSIS + Wrapper Incremental Subset Selection), a novel hybrid feature selection framework designed for electromyographic (EMG) pattern recognition in upper-limb prosthetic control. TWISS integrates the multi-criteria decision-making method TOPSIS with a forward wrapper search strategy, enabling subject-specific feature optimization based on a ranking that combines filter metrics, including Chi-squared, ANOVA, and Mutual Information. Unlike conventional static feature sets, such as the Hudgins configuration (48 features: four per channel, 12 channels) or All Features (192 features: 16 per channel, 12 channels), TWISS dynamically adapts feature subsets to each subject, addressing inter-subject variability and classification robustness challenges in EMG systems. The proposed algorithm was evaluated on the publicly available Ninapro DB7 dataset, comprising both intact and transradial amputee participants, and implemented in an open-source, fully reproducible environment. Two Google Colab tools were developed to support diverse workflows: one for end-to-end feature extraction and selection, and another for selection on precomputed feature sets. Experimental results demonstrated that TWISS achieved a median F1-macro score of 0.6614 with Logistic Regression, outperforming the All Features set (0.6536) and significantly surpassing the Hudgins set (0.5626) while reducing feature dimensionality. TWISS offers a scalable and computationally efficient solution for feature selection in biomedical signal processing and beyond, promoting the development of personalized, low-cost prosthetic control systems and other resource-constrained applications. Full article

Unmanned aerial vehicle (UAV) imagery provides an efficient approach for monitoring cotton defoliation and boll-opening rates. Deep learning, particularly convolutional neural networks (CNNs), has been widely applied in image processing and agricultural monitoring, achieving strong performance in tasks such as disease detection, weed recognition, and yield prediction. However, existing models often suffer from heavy computational costs and slow inference speed, limiting their real-time deployment in agricultural fields. To address this challenge, we propose a lightweight cotton maturity recognition model, RTCMNet (Real-time Cotton Monitoring Network). By incorporating a multi-scale convolutional attention (MSCA) module and an efficient feature fusion strategy, RTCMNet achieves high accuracy with substantially reduced computational complexity. A UAV dataset was constructed using images collected in Xinjiang, and the proposed model was benchmarked against several state-of-the-art networks. Experimental results demonstrate that RTCMNet achieves 0.96 and 0.92 accuracy on defoliation rate and boll-opening rate classification tasks, respectively. Meanwhile, it contains only 0.35 M parameters—94% fewer than DenseNet121—and only requires an inference time of 33 ms, representing a 97% reduction compared to DenseNet121. Field tests further confirm its real-time performance and robustness on UAV platforms. Overall, RTCMNet provides an efficient and low-cost solution for UAV-based cotton maturity monitoring, supporting the advancement of precision agriculture. Full article

Larix gmelinii is the fourth most important tree species in China and a typical zonal climax species in the cold temperate region, with high ecological and resource value. However, intensive logging, high-density afforestation, and insufficient scientific management have led to overly dense, homogeneous, and unstable plantations, severely limiting productivity. To clarify the mechanisms by which structural dynamics regulate productivity, we established a space-for-time sequence (T1–T3, T2-D, CK) under a consistent early-tending background. Using the “1 + 4” nearest-neighbor framework and six spatial structural parameters, we developed tree and forest spatial structure indices (TSSI and FSSI) and integrated nine structural–functional indicators for multivariate analysis. The results showed that TSSI and FSSI effectively characterized multi-level stability and supported stability classification. Along the stand-age gradient, structural stability and spatial use efficiency improved significantly, with FSSI and biomass per hectare (BPH) increasing by 91% and 18% from T1 to T3, though a “structural improvement–functional lag” occurred at T2. Moderate thinning markedly optimized stand configuration, reducing low-stability individuals from 86.45% in T1 to 42.65% in T2-D, while DBH, crown width, FSSI, and BPH (229.87 t·hm⁻²) increased to near natural-forest levels. At the tree scale, DBH, tree height, crown width, and TSSI were positive drivers, whereas a high height–diameter ratio (HDR) constrained growth. At the stand scale, canopy density, species richness, and mean DBH promoted FSSI and BPH, while mean HDR and stand density imposed major constraints. A critical management window was identified when DBH < 25 cm, HDR > 10, and TSSI < 0.25 (approximately 10–30 years post-planting). We propose a stepwise, moderate, and targeted thinning strategy with necessary underplanting to reduce density and slenderness, increase diameter and canopy structure, and enhance diversity, thereby accelerating the synergy between stability and productivity. This framework provides a practical pathway for the scientific management and high-quality development of L. gmelinii plantations. Full article

The breach of an interspecies barrier by RNA viruses has facilitated the emergence of lethal hCoVs, particularly SARS-CoV-2, resulting in significant socioeconomic setbacks and public health risks globally in recent years. Moreover, the high evolutionary plasticity of hCoVs has led to the continuous emergence of diverse variants, complicating clinical management and public health responses. Studying the evolutionary trajectory of hCoVs, which provides a molecular roadmap for understanding viruses’ adaptation, tissue tropism, spread, virulence, and immune evasion, is crucial for addressing the challenges of zoonotic spillover of viruses. Tracing the evolutionary trajectory of lethal hCoVs provides essential genomic insights required for risk stratification, variant/sub-variant classification, preparedness for outbreaks and pandemics, and the identification of critical viral elements for vaccine and therapeutic development. Therefore, this review examines the evolutionary landscape of the three known lethal hCoVs, presenting a focused narrative on SARS-CoV-2 variants under monitoring (VUMs) as of May 2025. Using advanced bioinformatics approaches and data visualization, the review highlights key spike protein substitutions, particularly within the receptor-binding domain (RBD), which drive transmissibility, immune escape, and potential resistance to therapeutics. The article highlights the importance of real-time genomic surveillance and intervention strategies in mitigating emerging variant/sub-variant risks within the ongoing COVID-19 landscape. Full article

An Adaptive Neuro-Fuzzy Inference System (ANFIS) framework for paediatric wrist injury classification (fracture versus sprain) was developed utilising infrared thermography (IRT). ANFIS combines artificial neural network (ANN) learning with interpretable fuzzy rules, mitigating the “black-box” limitation of conventional ANNs through explicit membership functions and Takagi–Sugeno rule consequents. Forty children (19 fractures, 21 sprains, confirmed by X-ray radiograph) provided thermal image sequences from which three statistically discriminative temperature distribution features namely standard deviation, inter-quartile range (IQR) and kurtosis were selected. A five-layer Sugeno ANFIS with Gaussian membership functions were trained using a hybrid least-squares/gradient descent optimisation and evaluated under three premise-parameter initialisation strategies: random seeding, K-means clustering, and fuzzy C-means (FCM) data partitioning. Five-fold cross-validation guided the selection of membership functions standard deviation (σ) and rule count, yielding an optimal nine-rule model. Comparative experiments show K-means initialisation achieved the best balance between convergence speed and generalisation versus slower but highly precise random initialisation and rapidly convergent yet unstable FCM. The proposed K-means–driven ANFIS offered data-efficient decision support, highlighting the potential of thermal feature fusion with neuro-fuzzy modelling to reduce unnecessary radiographs in emergency bone fracture triage. Full article