Search Results (384)

This study presents a comparative analysis of hyperspectral image segmentation algorithms for fruit defect detection under different illumination conditions. The research evaluates the performance of four segmentation methods (Spectral Angle Mapper, Random Forest, Support Vector Machine, and Neural Network) using three distinct illumination modes (local, simultaneous and sequential). The experimental setup employed hyperspectral imaging to assess tomato fruit samples, with data acquisition performed across the 450–850 nm spectral range. Quantitative metrics, including accuracy, error rate, precision, recall, F1-score, and Intersection over Union (IoU), were used to evaluate algorithm performance. Key findings indicate that Random Forest demonstrated superior performance across most metrics, particularly under simultaneous illumination conditions. The highest accuracy was achieved by Random Forest under sequential illumination (0.9971), while the best combination of segmentation metrics was obtained under simultaneous illumination, with an F1-score of 0.8996 and an IoU of 0.8176. The Neural Network showed competitive results. The Spectral Angle Mapper proved sensitive to illumination variations but excelled in specific scenarios requiring minimal memory usage. By demonstrating that acquisition protocol optimization can substantially improve segmentation performance, our results support the development of accurate, non-contact, high-throughput inspection systems and contribute to reducing postharvest losses and improving supply chain quality control. Full article

For irregularly shaped 820CrMnTi carburizing and nitriding parts, the challenges of high reflectivity-induced overexposure, low surface contrast, and interference from minute burrs in industrial online inspection are addressed in this paper. An innovative precision detection method integrating adaptive imaging and a dual-drive heterogeneous coupling model (RGFCN) is proposed. Such parts, due to surface photovoltaic characteristic changes caused by carburizing and nitriding heat treatment and the complex on-site lighting environment, are prone to local overexposure and “false out-of-tolerance” measurements caused by outlier sensitivity in traditional inspections. First, an innovative programmatic adaptive exposure control algorithm based on grayscale histogram feedback is introduced, which dynamically adjusts imaging parameters in real time to effectively suppress high-brightness overexposure under specific working conditions. Second, a novel adaptive main-axis scanning strategy is designed to construct a dynamic follow-up coordinate system, eliminating projection errors introduced by random positioning from a geometric perspective. Additionally, Gaussian gradient energy fields are combined with the Huber M-estimation robust fitting mechanism to suppress thermal noise while automatically reducing the weight of burrs and oil stains, achieving “immunity” to non-functional defects. Meanwhile, a data-driven innovative compensation approach is introduced. Based on sample training, gradient boosting decision trees (GBDTs) are integrated to explore the nonlinear mapping relationship between multidimensional feature spaces and system residuals, achieving implicit calibration of lens distortion and environmental coupling errors. By simulating factory conditions with drastic 24 h day–night lighting fluctuations and strong oil stain interference, statistical analysis of over 1000 mass-produced parts shows that this method exhibits excellent robustness in complex environments. It reduces the false out-of-tolerance rate caused by burrs by over 90%, and the standard deviation of repeated measurements converges to the micrometer level. This effectively addresses the visual inspection challenges of irregular, highly reflective parts on dynamic production lines. Full article

Whooping cough has re-emerged as a significant global public health concern. Hence, an SEIRS model for whooping cough transmission in Japan is proposed to capture the disease dynamics because of a strong resurgence of the epidemic. The model is analyzed mathematically, establishing the non-negativity and boundedness of its solutions and investigating both the disease-free and endemic equilibria with their local and global stability. The model is fitted to actual infection data by estimating the time-varying transmission rates using a Long Short-Term Memory (LSTM) network and calibrating vaccination and treatment rates via Latin Hypercube Sampling (LHS). Sensitivity analysis identifies the key parameters for optimal control, and results indicate that simultaneously enhancing the vaccination rate most effectively mitigates the epidemic, as supported by cost-effectiveness analysis. Full article

Ballast compaction is a critical factor influencing ballast bed condition and the operational safety of heavy-haul railways. However, existing quantitative evaluation methods often suffer from overly idealized simulation models and limitations in signal processing and assessment frameworks. To address these issues, this study proposes a quantitative analysis approach for ballast compaction by integrating non-uniform medium simulation modeling, wavelet–Singular Value Decomposition (SVD) joint denoising, frequency–wavenumber (F-K) migration imaging, and wavelet packet decomposition (WPD)-based feature extraction. Forward simulations were conducted based on the constructed model, and the proposed methodology was validated using 1.5 GHz (gigahertz, 1 GHz = ${10}^9$ Hz) ground penetrating radar (GPR) data acquired from compaction experiments. The results demonstrate that wavelet–SVD joint denoising effectively suppresses deep coherent noise caused by strong reflections from sleepers, significantly enhancing the identification of deep effective signals and ensuring accurate localization and feature extraction of compaction zones. The Geometric Mean of WPD High/Low-Frequency Energy Ratio (GMHLFER) exhibits a strong positive correlation with the degree of compaction. In simulations, as the proportion of compacted material increased from $9\%$ to $21\%$, the GMHLFER rose from 21.555 to 26.581. In field tests, the value increased from 22.012 to 26.012 as compaction severity progressed from slight to severe, demonstrating stable responses across full-gradient compaction conditions and indicating high robustness and sensitivity. The proposed method provides an effective approach for quantitative characterization of ballast compaction in heavy-haul railways, and offers a promising technical pathway for intelligent inspection and condition assessment of railway ballast beds. Full article

Early fault vibration signals from rolling bearings are typically nonlinear, non-stationary, and heavily obscured by background noise, which severely impedes the accurate extraction of fault features. To overcome the limitations of traditional stochastic resonance (SR)—specifically the small-parameter restriction for high-frequency signals and the subjectivity in parameter selection—this paper proposes an adaptive SR envelope spectroscopy method based on particle swarm optimization (PSO) and local mean decomposition (LMD). First, a variable-scale transformation is introduced to compress the high-frequency fault signals into the effective frequency band required by the adiabatic approximation theory. Second, utilizing the global search capability of PSO, the potential well parameters of the bistable system are adaptively optimized by maximizing the output signal-to-noise ratio (SNR), thereby achieving optimal matching between the nonlinear system and the input signal. Finally, the enhanced signal is decomposed by LMD, and the sensitive components are selected for envelope spectrum analysis to identify fault characteristics. Experimental validation using the Case Western Reserve University bearing dataset demonstrates that the proposed method effectively amplifies weak fault signals under strong noise conditions, exhibiting superior feature extraction accuracy and noise robustness compared to traditional methods. Full article

Background/Objectives: In Puerto Rico (PR), lung cancer mortality remains high because diagnoses frequently occur at advanced stages. Although low-dose computed tomography (LDCT) lowers lung cancer–specific mortality, this screening is difficult to operationalize locally due to high false-positive rates, radiology capacity constraints, payer limitations, and geographic barriers affecting rural populations. Methods: We performed a narrative review on the literature from 2001–2026 of established and emerging detection strategies—LDCT; serum biomarkers (CEA, CYFRA-21-1, NSE, ProGRP, SCC-Ag, HE4, Hp, TAAb); breath analysis (FeNO and VOCs); and liquid biopsy (ctDNAs/CTCs/miRNAs). We assessed technical performance, feasibility, and health-system fit in PR and then synthesized these findings into an implementable biomarker-first triage workflow for are. Results: Multiplex serum panels analyzed with machine learning outperform single markers and TAAb provide high specificity with biological lead time, supporting their use as a triage gateway before LDCT. Breathomics is also feasible at the point of care. Liquid biopsy has modest sensitivity in very-early disease yet provides molecular adjudication for indeterminate nodules. A stepwise pathway—expanded risk assessment, integrated multi-panel testing in primary care, LDCT reserved for biomarker-positive individuals, and liquid biopsy when imaging is inconclusive—can enrich pre-test probability, reduce unnecessary scans, align with capitation, and protect limited radiology capacity. Conclusions: An integrated, non-invasive, biomarker-first triage model offers a pragmatic, equitable route to earlier lung cancer detection in PR and resource stewardship, while reducing disparities. Full article

Tidal-scale wave modulation is a critical yet complex process in macro-tidal estuaries. This study investigates semidiurnal wave modulations in the Changjiang River Estuary (CRE) using unique, long-term in situ observations and high-resolution ADCIRC–SWAN coupled simulations. Pronounced semidiurnal signals are identified in significant wave height (H_s), mean wave period, and wave direction. Observational results demonstrate that the modulation intensity is highest in Hangzhou Bay and the CRE mouth, decreasing gradually offshore. A key finding is that semidiurnal H_s maxima systematically coincide with peak flood currents and precede high water by approximately three hours. Long-term records confirm that this modulation persists year-round and intensifies during energetic events such as typhoons. The expression of the tidal signal depends on wave composition: wind-sea-dominated conditions exhibit stronger period modulation, whereas swell-dominated conditions favor coherent H_s modulation as kinematic tidal effects remain more apparent in the absence of strong local wind forcing. Numerical sensitivity experiments demonstrate that tidal currents are the primary driver of the observed wave modulation, while water-level effects are largely confined to shallow shoals. The results highlight that accurately reproducing the observed frequency–directional structure requires the inclusion of current-induced Doppler shifts and refraction. Beyond the classical following-current effects, the analysis suggests that the spatial deceleration of currents along the wave path acts as a kinematic trap that focuses wave action and sustains H_s intensification. This mechanism provides a physically plausible explanation for the observed phase relationship and points to the non-local nature of estuarine wave dynamics, where the wave state appears as an integrated response to cumulative current gradients along the propagation path. These findings emphasize the necessity of incorporating wave–current coupling in future coastal modeling and hazard forecasting. Full article

Soil salinity remains a major constraint to rice productivity, particularly during early developmental stages when plants are highly sensitive to osmotic and ionic stress. In this study, we evaluated 201 genetically diverse rice genotypes from the 3K Rice Diversity Panel to investigate stage-specific mechanisms of salinity tolerance and develop machine learning-based predictive models for rapid phenotypic screening. Morphological and physiological traits were measured under control and saline conditions at germination and early seedling stages to derive Stress Tolerance Indices (STIs). The average membership function value (AMFV), calculated from multi-trait STI profiles, effectively captured variation in salinity responses and enabled classification of genotypes into five tolerance categories. Genome-wide association analysis using high-density SNP markers identified 36 significant marker–trait associations, including potentially novel SNPs on chromosomes 1 and 12. Several loci co-localized with candidate genes (LTR1, LGF1, OsCPS4, OsNCX7, and OsNHX4), while functional SNPs within genes (OsDRP2C, RLCK168, and OsMed37_2) and non-synonymous variants (qSVII11.1 and qSNaK3.1) further supported their candidacy in salinity tolerance. Mining favourable SNPs of causal genes identified superior multilocus combinations consistent with STI-based phenotypic patterns, with genotype 91-382 emerging as the strongest performer, exhibiting enhanced Na⁺ exclusion, K⁺ retention, and biomass resilience across developmental stages. To address multicollinearity among STI traits, we applied cross-validated LASSO (germination) and Elastic Net (early seedling) models, achieving high predictive accuracy and revealing a developmental shift from biomass-driven tolerance at germination to ion-regulatory processes at the seedling stage. Independent validation showed strong agreement between predicted and observed AMFVs. By integrating physiological indices, GWAS-derived SNP signals, and regularized machine learning approaches, this study provides a robust framework for identifying elite donors and accelerating breeding for salt-tolerant rice. Full article

Land subsidence and coseismic deformation can interact in groundwater-stressed sedimentary basins, yet basin-scale identification of event-timed vertical offsets in InSAR products requires explicit control of referencing and processing effects. This study evaluates whether the 27 September 2021 Arkalochori earthquake (Mw 6.0; central Crete) produced detectable coseismic vertical offsets within the Messara Basin by applying a reproducible screening workflow to Copernicus European Ground Motion Service (EGMS) Level-3 Vertical time series, from two processing generations (EGMS 2015–2021 and EGMS 2018–2022). An event-centered step metric (stepEQ), defined as the difference between post-event and pre-event mean displacements over a fixed acquisition window, is evaluated across three fixed spatial masks (MESSARA, R15060, R8750) together with a dispersion-based precision proxy (σstep) and a cross-generation sensitivity diagnostic (ΔstepEQ). A supplementary 2 + 2 subset sensitivity analysis indicates that the adopted fixed 3 + 3 estimator is stable at the basin scale, with sensitivity concentrated mainly in threshold-adjacent cases. Results indicate that Arkalochori-related offsets are not expressed as a basin-wide step across Messara; instead, non-background responses form a spatially limited and coherent subset concentrated where the basin intersects the near-source footprint. In EGMS 2018–2022, the higher vertical offset class (C2; |stepEQ| > 40 mm) is exclusively subsidence-direction and is enriched toward the screening center (up to ~19% within the radii mask R8750 m) but remains sparse at the basin scale mask (MESSARA mask) (~1%). Step-dominated points co-locate with strongly subsiding mean vertical velocity regimes and are hosted almost entirely by post-Alpine basin deposits, indicating strong material and background-deformation conditioning of step detectability. Cross-generation comparison shows basin-scale stability of background behavior but localized near-source sensitivity, supporting use of ΔstepEQ as a Quality Control (QC) lens for threshold-adjacent interpretations. The workflow provides a transparent, transferable approach for prioritizing candidate coseismic-step locations in EGMS time series. Results are interpreted as screening-level evidence in the derived vertical signal using event timing, spatial coherence, and QC diagnostics. Full article

This study introduces a modified computational scheme for handling linear and nonlinear fractal time-dependent partial differential equations. The method is constructed using three different stages that provide third-order accuracy in the fractal time variable. The stability of the approach is examined using scalar fractal models and Fourier analysis, while convergence is established for coupled convection–diffusion systems. The numerical algorithm is applied to analyze the mixed convective flow of a Carreau–Yasuda non-Newtonian fluid over stationary and oscillating plates under the influence of viscous dissipation and magnetic field effects. For spatial discretization, the incompressible continuity equation is handled by a first-order difference scheme, whereas higher-order compact schemes are implemented for the momentum, thermal, and concentration equations. The numerical findings show that increasing the Weissenberg number and magnetic field inclination reduces the velocity distribution. An accuracy assessment against existing numerical techniques demonstrates that the present method yields smaller computational errors, particularly when central difference schemes are used in space. In addition, a surrogate machine learning model is developed to predict the skin friction coefficient and local Nusselt number using Reynolds, Weissenberg, Prandtl, and Eckert numbers as input features. The predictive capability of the model is validated through Parity plots, bar charts for sensitivity analysis, scatter visualization, and Taylor Diagrams, confirming strong agreement with the numerical results. Full article

Background/Objectives: Accurate detection of thyroid cancer using ultrasound remains a challenge, as malignant nodules can be microscopic and heterogeneous, easily confused with point clusters and borderline-featured tissues. Current studies in deep learning demonstrate good performance with convolutional neural networks (CNNs) and clustering; however, many approaches focus on local tissue and provide limited, non-quantitative interpretation, reducing clinical confidence. This study proposes an integrated framework combining enhanced convolutional feature encoders (DenseNet169 and VGG19) with an enhanced vision transformer (ViT-E) to integrate local feature and global relational context during learning, rather than delayed integration. Methods: The proposed framework integrates enhanced convolutional feature encoders (DenseNet169 and VGG19) with an enhanced vision transformer (ViT-E), enabling simultaneous learning of local feature representations and global relational context. This design allows feature fusion during the learning stage instead of delayed integration, aiming to improve diagnostic performance and interpretability in thyroid ultrasound image analysis. Results: The best-performing model, ViT-E–DenseNet169, achieved 98.5% accuracy, 98.9% sensitivity, 99.15% specificity, and 97.35% AUC, surpassing the robust basic hybrid model (CNN–XGBoost/ANN) and existing systems. A second contribution is improved interpretability, moving from mere illustration to validation. Gradient-weighted class activation mapping (Grad-CAM) maps demonstrated distinct and clinically understandable concentration patterns across various thyroid cancers: precise intralesional concentration for high-confidence malignancies (PTC = 0.968), edge/interface concentration for capsule risk patterns (PTC = 0.957), and broader-field activation consistent with infiltration concerns (PTC = 0.984), while benign scans showed low and diffuse activation (PTC = 0.002). Spatial audits reinforced this behavior (IoU/PAP: 0.72/91%, 0.65/78%, 0.58/62%). Conclusions: The integrated ViT-E–DenseNet169 framework provides highly accurate thyroid cancer detection while offering clinically meaningful interpretability through Grad-CAM-based spatial validation, supporting improved confidence in AI-assisted ultrasound diagnosis. Full article

Non-invasive assessment of tissue water content is clinically relevant for edema detection, fluid management, and monitoring of local inflammation. In the short-wave infrared (SWIR), water exhibits strong absorption near 1450 nm with a secondary band near 1650 nm, enabling hydration-sensitive reflectance measurements. However, many SWIR systems rely on spectrometers or high-power broadband sources, limiting translation to compact or wearable platforms. We present a compact SWIR diffuse-reflectance probe built from small-form-factor components using four discrete LEDs (1450 nm and 1650 nm) and a single photodetector to acquire spatially resolved measurements at two source–detector separations (4.5 mm and 7 mm). Probe-geometry-matched Monte Carlo simulations were used to generate lookup tables relating reduced scattering to same-wavelength spatial ratios. A diffusion-based forward model was then used to perform a calibration-anchored water-fraction consistency analysis. Eight gelatin–Intralipid phantoms spanning two scattering conditions and formulation-defined water fractions were evaluated. Spatial-ratio signatures were repeatable and monotonic with nominal water fraction, yielding a mean absolute percent error of 1.55% and a maximum absolute percent error of 3.33% under absorption-consistent conditions. These results demonstrate the feasibility of compact SWIR ratio sensing for controlled hydration changes in tissue-mimicking phantoms and provide a modeling framework for future extension to unknown or in vivo samples. Full article

Background/Objectives: Optical coherence tomography angiography (OCTA) enables noninvasive quantitative assessment of the retinal microvasculature and is widely used in diabetic retinopathy (DR). However, OCTA-derived metrics are highly dependent on post-processing techniques, particularly vessel binarization. This study aimed to compare local and global binarization methods applied after Frangi filtering for vessel enhancement in parafoveal vessel density analysis. Methods: This cross-sectional study included 69 participants: 17 healthy controls and 52 diabetic patients, classified as the following: no DR (n = 14), non-proliferative DR (NPDR, n = 18), or proliferative DR (PDR, n = 20). All subjects underwent comprehensive ophthalmological examination and OCTA imaging of the superficial capillary plexus using a Topcon OCTA system. Images were processed using a custom MATLAB protocol. Following Frangi filtering, five binarization methods were applied: three local (Phansalkar, local Otsu, adaptive mean) and two global (global mean and global Otsu). Parafoveal vessel density was quantified within the four inner quadrants of the ETDRS grid. Results: Statistically significant differences in vessel density were consistently observed between PDR group and both the control and no DR groups across all local binarization methods. Among global methods, only global Otsu thresholding detected a significant difference between PDR and control. The most robust differences were predominantly identified in the nasal and inferior quadrants. Conclusions: Local adaptive binarization methods demonstrated superior sensitivity and structural preservation for parafoveal vessel density analysis in DR. Global methods showed limited discriminative capability. These findings support the preferential use of local adaptive techniques for reliable OCTA-based vascular assessment in diabetic retinopathy. Full article

Early and reliable detection of P-wave arrivals is critical for seismic monitoring and earthquake early warning, particularly under low signal-to-noise ratio (SNR) and non-stationary noise conditions. This study presents an automatic detection method based on singular value decomposition (SVD) entropy computed in sliding time windows with local signal filtering. Within this framework, the P-wave onset is interpreted as a local structural change in the signal rather than a simple energy increase. SVD entropy captures the redistribution of energy among dominant signal components, providing high sensitivity to the initial P-wave arrival even at moderate and low noise levels ($SNR\ge 2$). The method was validated using real seismic data from four regional stations operating under different noise conditions. Analysis of detection parameters revealed strong station dependence. For stations affected by low-frequency drift, polynomial detrending was identified as a necessary preprocessing step to ensure a stable entropy response and reliable detection. The proposed approach achieves detection accuracies of up to 93–98% at $SNR\ge 2$, significantly outperforming the classical STA/LTA algorithm and demonstrating performance comparable to modern deep learning methods. Since the method does not require model training or labeled datasets, it provides an interpretable and computationally efficient solution for automatic seismic monitoring. These properties make the proposed approach particularly suitable for real-time seismic monitoring systems and distributed sensor networks operating under limited computational resources. All computational stages were performed at the Farabi Supercomputer Centre of Al-Farabi Kazakh National University. The method requires no model training or labeled data, making it an interpretable, robust, and computationally efficient solution for automatic seismic monitoring and early warning systems. Full article

Non-specific Lipid Transfer Proteins (nsLTPs) constitute a ubiquitous family of plant proteins that play a critical role in mediating plant adaptation and tolerance to abiotic stress. While their functions have been extensively characterized in model plants such as Arabidopsis thaliana and rice (Oryza sativa L.), they remain largely unexplored in Cucurbitaceae crops. We identified 31 CmnsLTP genes in the melon (Cucumis melo L.) genome, these genes were unevenly distributed across 11 chromosomes and classified into 8 subfamilies. Members of the same subfamily have similar gene structures and conserved domains, with all family members having motif 1 and motif 3. The promoter region contains cis elements that respond to light, hormones (ABA and MeJA response elements), and abiotic stress, suggesting that this gene is involved in melon growth, development, and stress response. Previous studies have identified copper resistant candidate MELO3C031073.2 through forward genetics, which belongs to the nsLTP family and was named CmnsLTPY.9 in this study. The RT qPCR results showed that the CmnsLTPY.9 exhibited specific expression in different tissues, The expression levels of CmnsLTPY.9 in leaves ranged from 0.3 to 3.2. Under copper stress, the ‘M625’ (copper-sensitive) showed a 3.2-fold increase, indicating marked upregulation. Additionally, CmnsLTPY.9 was localized to the endoplasmic reticulum, and the position remains unchanged after copper stress. This study provides the first systematic analysis of the CmnsLTP gene family in melon; these findings provide fundamental insights into their specific functions in plant development and stress response, as well as valuable genetic resources for future research on copper-tolerant molecular breeding. Full article