Search Results (1,217)

Hyperspectral image (HSI) clustering aims to partition pixels into distinct clusters by leveraging spectral and spatial features, thereby providing crucial support for the interpretation and information extraction of hyperspectral data. However, due to high spectral variability, complex spatial distribution, and noise interference, HSI clustering still faces considerable challenges. Graph-based clustering represents a prominent learning framework and achieves competitive performance on HSI analysis. However, most existing methods ignore spatial information and suffer from high computational cost, rendering them incapable of effectively dealing with large-scale HSIs. To address the aforementioned challenges, this paper proposes an anchor-level spectral–spatial graph clustering (ASSGC) model for HSIs. The proposed ASSGC employs a band-wise median strategy within each superpixel to generate representative anchors to suppress noise and outlier effects. A novel distance metric is designed to integrate spectral features and spatial positions to effectively identify neighbors and construct a spectral–spatial joint affinity matrix at the anchor-level, thereby reducing computational burden and memory consumption. Subsequently, spectral clustering is applied to obtain anchor labels, which are propagated to the corresponding superpixels to achieve full-image clustering. Experiments on four HSI datasets yield ACC of 64.13% on Indian Pines, 71.33% on Pavia University, 87.86% on Salinas, and 99.23% on Salinas A, demonstrating that the proposed ASSGC outperforms several existing state-of-the-art methods while maintaining low time complexity. Full article

Lithological mapping with multispectral remote sensing remains challenging when diagnostic spectral information is limited and reliable labeled samples are scarce. This problem is particularly relevant when convolutional neural networks (CNNs) are applied to lithological classification, because limited spectral dimensionality and scarce training samples may hinder the learning of discriminative spatial–spectral features. In this study, we developed a limited-sample lithological mapping framework for the Shibaocheng area of Subei County, Gansu Province, China, using band-integrated ASTER and Sentinel-2A multispectral imagery. ASTER shortwave infrared (SWIR) bands were co-registered and resampled to Sentinel-2A imagery, and then integrated with Sentinel-2A visible and near-infrared (VNIR) and red-edge bands to construct a complementary multispectral dataset. A compact spectrally enhanced multi-scale CNN was designed, incorporating a residual spectral feature enhancement module for inter-band representation learning and a parallel multi-scale hybrid convolution module for capturing spatial–spectral features. Eight lithological units were classified under limited-label conditions using 8158 training samples and 3497 spatially independent validation samples. Experimental results show that the band-integrated ASTER–Sentinel-2A dataset improved classification performance compared with single-sensor inputs. Using the proposed model, the band-integrated dataset achieved an overall accuracy (OA) of 94.12%, average accuracy (AA) of 94.04%, and Kappa coefficient of 0.932, compared with OA values of 93.14% and 92.40% obtained using ASTER and Sentinel-2A alone, respectively. The positive effect of band-level integration was also observed for spectral angle mapper (SAM), support vector machine (SVM), and 3D-CNN, whose OA values increased to 54.33%, 86.12%, and 92.29%, respectively. The proposed CNN achieved the highest OA among the evaluated methods, outperforming SAM, SVM, and the conventional 3D-CNN. In addition, t-SNE visualization indicated that incorporating spatial texture features produced more compact and better-separated lithological clusters than using spectral features alone. Ablation experiments further demonstrated that the proposed spectral feature enhancement and multi-scale hybrid convolution modules each contributed to improving lithological classification performance. These results demonstrate that integrating freely available multispectral data with a lightweight spectral–spatial CNN provides a practical and cost-effective solution for lithological mapping in bedrock-exposed arid to semi-arid regions, especially where hyperspectral imagery and dense field samples are unavailable. Full article

Resource-constrained electromagnetic interference (EMI) management requires a frequency-domain feedback path, while FFT-based full-spectrum processing introduces redundant computation, storage, and data movement for decision tasks. This paper proposes a limit-aware sparse frequency-domain decision engine for internal EMI risk feedback. The engine redefines EMI analysis from spectrum reconstruction to selective exceedance verification and uses randomized spectral reordering, flat-window bucket aggregation, and folded sampling to compress the length-N spectral search into bucket-level observations. Then, by comparing bucket-level amplitude envelopes with local limit envelopes, the method excludes risk-negative buckets, and only uncertain buckets are further refined through phase localization and sequential verification. Degradation experiments involving continuous background uplift, main-harmonic sidebands, and parasitic resonance clusters clarify the applicability boundary of the proposed method, and measured GaN power-converter spectra acquired through an in situ EMI sensing chain remain inside the empirical usable region. RTL evaluation at 100 MHz shows that the proposed design achieves an average decision latency of 6.031 ms. Compared with two FFT baseline implementations, it reduces BRAM usage by 95.17% and 97.59%, dynamic power by 54.0% and 83.0%, and per-decision dynamic energy by 46.3× and 33.3×, respectively. The results show that the proposed decision engine reduces hardware overhead for frequency-domain EMI risk feedback in resource-constrained systems. Full article

In this work, the structural, optical, vibrational, and stability properties of a series of Al_xAs_x nanostructures are systematically investigated using density functional theory (DFT) and time-dependent density functional theory (TD-DFT). Starting from the fundamental cubic-like Al₄As₄ building block, progressively larger nanostructures were constructed through directional elongation and structural rearrangements, allowing for the exploration of one-dimensional chains, two-dimensional planar structures, and several exotic geometries. The calculated UV–visible absorption spectra reveal that structural dimensionality and topology strongly influence the electronic transitions of the nanostructures, with elongated and distorted configurations exhibiting broader absorption features and richer spectral distribution. Vibrational analysis shows that increasing structural complexity and reducing symmetry lead to a higher density of IR-active modes and more complex infrared spectra. The stability of the nanostructures is evaluated through binding energy calculations, which indicate a clear size-dependent stabilization trend, with the Al₂₄As₂₄-L1 configuration exhibiting the highest stability among the examined systems. In addition, the calculated HOMO-LUMO gaps reveal the semiconducting character of the clusters and demonstrate their sensitivity to geometric topology. The present results establish clear structure–property relationships between dimensional growth and the optical response of AlAs nanoparticles and provide theoretical reference data for future experimental investigations of III-V semiconductor nanostructures. Full article

UAV-assisted communication is widely regarded as a key component of next-generation Space-Air-Ground Integrated Networks (SAGINs), where integrated sensing and communication (ISAC) further drives the demand for accurate and reliable channel modeling. Terahertz (THz) communications are particularly attractive for UAV platforms, offering ultra-high data rates and physically secure transmission. However, the physical heterogeneity between reflection and scattering mechanisms in THz UAV channels poses significant modeling challenges, as conventional unified approaches tend to introduce energy distribution distortion and non-stationary prediction errors. To address this, we propose a 3D non-stationary geometry-based stochastic model (GBSM) based on an ellipse-sphere hierarchical geometric framework, where reflection paths are confined to ground-plane ellipses and scattering paths are distributed over spatial spheres. The model accounts for atmospheric molecular absorption, multipath fading, and non-stationarity induced by random 3D UAV trajectories. A cluster birth-death mechanism is introduced to capture the time-varying evolution of scattering clusters. Key statistical properties, including the temporal auto-correlation function (T-ACF), spatial cross-correlation function (S-CCF), and Doppler power spectral density (DPSD), are derived and analyzed. Simulation results agree well with theoretical derivations, validating the proposed model and providing practical guidance for THz UAV-ISAC system design. Full article

The Rio Santiago basin is one of the most environmentally stressed river systems in Mexico, with persistent organic, nutrient, microbial, surfactant, and metal contamination. This study develops a near-term quantum machine learning workflow for environmental monitoring and water-pollution profiling using multivariate records from 13 stations between 2009 and 2022. QML is evaluated here because quantum feature maps can define nonlinear, interaction-rich kernels that remain executable on present quantum hardware, providing an alternative representation to compare with classical PCA, RBF, UMAP, and HDBSCAN baselines rather than a presumed computational advantage. After quality screening, log transformation, standardization, and domain-guided feature selection, pollution profiles are evaluated across PCA, RBF spectral clustering, UMAP/KMeans, UMAP/HDBSCAN, a simulated ZZ-style quantum feature-map kernel, and Qiskit Runtime hardware evaluations of the same kernel concept. The initial cleaned-data results show that classical PCA clustering identifies broad lower-load, high organic/surfactant, and rain-season solids/microbial profiles. UMAP/HDBSCAN provides the strongest cleaned full-sample nonlinear baseline, with a silhouette score of 0.568 after excluding 177 noise samples. The simulated quantum-kernel representation separates station-linked gradients, while matched n = 650 stability diagnostics show near-identical quantum-kernel clustering across random initializations (mean ARI = 0.994 for cleaned data) but retain the RBF kernel as the strongest nonlinear comparator. Two 24-sample Qiskit hardware runs and two matched 8-record hardware checks provide proof-of-execution evidence. The analysis is framed as a controlled representation study, not as a claim of quantum advantage. Full article

To address yield uncertainties from contrasting hydrothermal events in black soil regions, this study developed a universal estimation framework integrating multi-dimensional features. The universal yield estimation framework leveraged data from contrasting flood (2024) and drought (2025) scenarios in Youyi Farm in the Northeast Black Soil Region. And we fused multi-dimensional environmental features, including remote sensing, soil, and micro-topography factors, to identify “Regime Shifts” in yield-driving mechanisms across contrasting years. We evaluated four ML algorithms (RF, XGBoost, MLP, and TabNet) using Recursive Feature Elimination with Cross-Validation (RFECV) for variable optimization. Results showed the following: (1) The Universal RF model achieved superior robustness (R² = 0.80), overcoming inter-annual fluctuations. (2) Mechanistic analysis identified a “Regime Shift” in yield drivers, transitioning from micro-topography-governed “drainage limitation” during flooding to soil-texture-dominant (SAND) “linear limitation” during drought. (3) Dynamic growth-stage differential features successfully corrected asymmetric spectral responses, resolving slope inversion and overestimation driven by “non-productive greenness” during flooding. (4) Spatio-temporal yield mapping revealed a transition from topography-constrained linear distributions (2024) to soil-moisture-driven “patchy mosaic” structures (2025). Moran’s I increased from 0.21 to 0.45, reflecting intensified yield clustering and intensified spatial clustering under drought. This study provides a robust tool for food security monitoring and site-specific management in climate-vulnerable intensive agricultural zones. Full article

Standard scalar indicators of systemic dependence, such as the mean pairwise correlation, the absorption ratio, and the dispersion of the eigenvalue spectrum, summarise the magnitude of co-movement but are by construction blind to its spatial arrangement. We propose treating the time-varying cross-asset correlation matrix as a greyscale image and quantifying its spatial organisation with the multiscale gliding-box lacunarity. Using a controlled block-factor generative model in which the average correlation is held fixed while the sectoral block strength is varied, we show that lacunarity recovers the planted block structure almost perfectly (partial Spearman $\rho =0.92$ at fixed mean correlation), a recovery that persists under fat-tailed innovations, time-varying loadings, and overlapping communities, whereas the mean correlation and the absorption ratio remain flat. Applied to twenty years of daily data for sixty-two sector-spanning United States equities, lacunarity tracks a model-free index of block heterogeneity after controlling for correlation magnitude (partial Spearman $\rho =0.46$, ninety-five percent bootstrap interval $[0.33,0.58]$) and improves the out-of-sample prediction of block structure beyond the magnitude baselines. We are explicit about two boundaries. A simple permutation-invariant dispersion statistic, the standard deviation of the off-diagonal correlations, tracks block heterogeneity even more strongly than lacunarity, so lacunarity is not the most efficient estimator of that quantity; its distinct role, confirmed by a scrambling test, is that it responds to the spatial arrangement of dependence, which dispersion measures are invariant to, and it remains informative under a canonical clustering or spectral ordering. The measure is descriptive rather than predictive of future drawdowns. The results position correlation-image lacunarity as an interpretable, computationally light, and arrangement-sensitive complement to the existing magnitude and dispersion descriptors of systemic dependence. Full article

Purpose: To analyze choroidal thickness (CT) and choroidal volume (CV) using ultra-wide-field (UWF) spectral-domain optical coherence tomography (SD-OCT) in patients with central serous chorioretinopathy (CSC) and to assess their associations with disease duration and best-corrected visual acuity (BCVA). Methods: This prospective case–controlled study included 50 eyes of 41 CSC patients and 56 eyes of 32 healthy controls matched for age and sex. CT was measured at 24 points using the REVO 130 UWF SD-OCT device with a wide-field adapter, covering a 21 × 21 mm retinal area across central, mid-peripheral (4 mm), and peripheral (8 mm) zones. CV was estimated using a quadratic nonlinear model. ROC curve analysis and univariate logistic regression were applied to evaluate discriminative capacity and odds ratios (OR) for CT and CV. Results: CT was significantly higher in CSC eyes at all 24 measurement points (all p < 0.0001). Mean subfoveal CT was 472.6 µm vs. 344.8 µm in controls (+37%), with greater relative increases at mid-peripheral (+46%) and peripheral (+44%) zones. Mean CV was 61.47 (±11.37) mm³ vs. 42.29 (±10.02) (+45%; p < 0.0001). CV showed a higher OR for CSC occurrence than central CT (OR = 2.88; 95% CI: 1.53–5.42 vs. OR = 1.04; 95% CI: 1.02–1.07). Significant discriminative CT points (AUC > 0.60) clustered at the 2/8, 4/10, and 6/12 clock meridians. Both CT and CV correlated positively with disease duration (Spearman rho 0.35–0.41; p ≤ 0.0004) but not with BCVA. Conclusions: UWF SD-OCT confirms diffuse pachychoroid thickening in CSC extending to the periphery. CV is a sensitive biomarker in association with CSC status. Peripheral CT and CV correlate with disease duration, supporting the link between higher volumetric choroidal values and longer disease course. Integration of these parameters may improve CSC diagnosis and prognostic evaluation. Full article

Decades of cultivation and the often exclusive use of mineral fertilisers as a substitute for organic inputs have reduced the soil organic carbon (SOC) content of agricultural soils, meaning they now represent a potential sink for carbon sequestration to mitigate climate change and improve soil function. As well as being a legacy of management, SOC will also be dependent on local scale climate, topography, and soil properties; accounting for this local context is important when benchmarking fields and quantifying the potential for additional carbon sequestration. We developed a landscape-scale methodology, using a handheld infrared device, for baselining SOC stocks in the top 30 cm across a 45,000 ha farm cluster in the UK. The cluster is exploring opportunities for landscape-scale environmental improvement with a focus on natural flood protection and water pollution reduction through conversion of arable land to permanent grassland. We used the baseline data to estimate additional benefits of arable reversion for soil carbon sequestration. Because all the farms in the cluster share the same pedoclimatic conditions, variance in SOC at the field scale could be confidently attributed to differences in soil type and land use. Average SOC stocks in arable and permanent pasture fields were 103.9 and 140.3 Mg C ha⁻¹, respectively. Variance in %SOC was modelled using soil series, sample depth, land use, and clay content, and fields were benchmarked based on deviation from the expected value. The fields with the largest SOC stocks were identified and used as references to predict future potential sequestration. The conversion of arable land to permanent pasture resulted in a predicted average uplift in SOC of 55.0 Mg C ha⁻¹. Our landscape-scale methodology provides robust evidence on current and future carbon stocks for public subsidy schemes and natural capital markets that account for local constraints and opportunities. Full article

Hyperspectral remote sensing enables precise identification of alteration mineral through spectral–image integration and high-resolution capabilities. However, vegetation interference significantly hinders the extraction of alteration information in vegetated areas, thereby posing challenges to the reliable identification of alteration minerals. This study employs GF-5B satellite AHSI imagery acquired in the Huzhou region of Zhejiang Province, China, to address this challenge via a novel Zonal Adaptive Vegetation Suppression Technique (ZAVST). By constructing segmented statistical models that links reflectance characteristics across multiple spectral bands to NDVI values, ZAVST demonstrates an enhanced capability to mitigate vegetation obscuration effects on subsurface lithological features while substantially improving the identification of subtle spectral signatures characteristic of mineralization. Results reveal distinct spatial patterns: Fe-bearing alteration minerals (hematite, pyrite) align along NE-trending faults and volcanic basin margins; Al-OH alterations (montmorillonite, kaolinite) cluster near intrusive contacts; Mg-OH alterations (chlorite, epidote) occur at interfaces between carbonate sequences and concealed intrusions. Composite alteration anomalies exhibiting stacked mineral signatures (up to four distinct types) were identified across the region, demonstrating a strong spatial correlation with known mineralization centers. By integrating alteration zonation, structural lineaments, stratigraphy, geochemical anomalies, and orebody records, this study delineated four priority targets: Lijiaxiang Town, eastern Meixi Town, Miaoxi Town, and the central Moganshan Volcanic Basin. Full article

Surface-enhanced Raman scattering (SERS) offers a powerful route for biomolecular detection because it combines molecular specificity with high sensitivity, rapid optical readout, and multiplexing capability. In real biological samples, however, analytical performance is rarely determined by signal enhancement alone. Biofluids such as serum, plasma, saliva, urine, and interstitial fluid contain complex biomolecular mixtures that interfere with target capture, spectral response, and data interpretation. A practical SERS biosensor must therefore localize targets, stabilize spectral responses, tolerate matrix-induced variation, and convert complex spectra into reliable analytical information. This review discusses recent progress in SERS biosensing from an integrated system perspective, with particular focus on artificial intelligence/machine learning (AI/ML)-assisted interpretation. Direct label-free SERS provides chemically transparent readouts but is limited by stochastic adsorption, hotspot heterogeneity, and spectral variation in complex samples. Bio-recognition interfaces improve target localization, while signal-transduction strategies based on nanotags, immunoassays, clustered regularly interspaced short palindromic repeats (CRISPR) systems, nanozymes, and lateral-flow formats decouple molecular recognition from spectral generation. Digital SERS further improves measurement robustness by converting fluctuating intensities into countable, event-based outputs. AI/ML-assisted analysis can support full-spectrum classification, calibration transfer, explainability, and patient-level decision-making. We frame AI/ML-assisted SERS biosensing as an integrated architecture connecting substrate design, interface engineering, signal transduction, digital measurement, and clinical validation. Future progress will depend as much on validation-ready workflows as on plasmonic enhancement itself, especially for systems intended to operate across different samples, instruments, and clinical settings. Full article

While classical clustering methods, particularly k-means, produce powerful and practical solutions based on metric distances between data points, they can be limited in complex, nonlinear, and structurally disordered datasets. This study proposes a hybrid topological–metric clustering framework, referred to as Hybrid-NHTSI, that integrates persistent homology-based structural information into the clustering update process. The method is based on the Topological Cluster Separation Index (TCSI), a persistent homology (PH)-based metric for topological separation. In addition to TCSI, the proposed framework uses the Normalized Topological Cluster Separation Index (NTCSI), the Hybrid Topological Clustering Index (HTCI), and the Normalized Hybrid Topological Separation Index (NHTSI) to evaluate clustering performance from both geometric and topological perspectives. In the proposed approach, while the topological separation between clusters is increased, intra-cluster geometric scattering is controlled by a regularization term. This formulation enables the extraction of clusters that are consistent not only topologically but also geometrically. The performance of the method was evaluated on synthetic circles-and-moons benchmark datasets under different noise and overlap levels, and on the UCI Human Activity Recognition real sensor dataset. The experimental results showed that DBSCAN achieved the strongest overall performance on the density-favorable synthetic benchmark, which is consistent with the nonconvex and density-separable structure of the data. However, Hybrid-NHTSI produced higher NTCSI, HTCI, and NHTSI values than classical metric/geometric baselines such as k-means, Spectral Clustering, and Agglomerative Clustering. Pairwise statistical comparisons based on NHTSI confirmed that these improvements were significant against several competing methods. In the real-data experiment, although Spectral Clustering achieved the highest ARI value, Hybrid-NHTSI obtained the highest NTCSI, HTCI, and NHTSI values and significantly outperformed all competing methods in terms of NHTSI. The findings demonstrate that considering both metric and topological information together, rather than relying solely on metric or topological information, provides a more structurally informed evaluation and optimization mechanism for complex clustering problems. Accordingly, the proposed method should not be interpreted as a universally superior clustering algorithm across all metrics, but rather as a topology-aware hybrid refinement framework that enriches metric-based clustering with persistent homology. Full article

Signals generated during tool wear are nonlinear, non-stationary, and easily affected by machining noise, which makes reliable tool condition monitoring difficult in intelligent manufacturing. To address this issue, this study proposes a tool wear degree classification framework, FCTrans-CA, that fuses time-domain and frequency-domain information through a lightweight cross-attention (CA) bridge. Fast Fourier transform (FFT) is first used to obtain frequency-domain representations. The raw time-domain signals are processed by a multi-scale one-dimensional convolutional neural network (MS-CNN) to extract temporal wear features, while the FFT-derived representations provide complementary spectral cues. These two feature streams are fused by an asymmetric CA module in which frequency-domain features guide the selection of wear-sensitive temporal features. K-means clustering is used to divide the measured flank wear (VB) trajectory of each tool into initial-, normal-, and severe-wear stages, thereby reducing subjectivity in label generation. Experiments on the PHM2010 milling dataset show that FCTrans-CA achieves 99.43% classification accuracy on 40,648 test samples. The results indicate that cross-domain feature interaction improves the separability of wear states and provides a reproducible data-driven route for tool wear monitoring. Full article

L-carnitine plays a central role in mitochondrial fatty acid transport and cellular energy regulation; effects on the biochemical phenotype of brain cancer cells remain insufficiently characterized. Here, we applied confocal Raman spectroscopy and imaging to investigate the biochemical alterations induced by L-carnitine supplementation—administered as its tartrate salt—in human astrocytoma cells. Raman spectral analysis revealed distinct changes in lipid-, protein-, nucleic acid-, and cytochrome-associated vibrational features following 24 h of treatment, suggesting alterations in mitochondrial activity and cellular energy-related processes. Principal component analysis identified PC1 (93.87%) as representing the intrinsic biochemical composition of the cells, whereas PC2 (1.19%) and PC3 (0.59%) captured subtle yet consistent variations in lipid organization, protein conformation, and redox-sensitive vibrational features associated with L-carnitine exposure. Pearson correlation analysis of Raman cluster spectra indicated biochemical differences across cellular compartments, with the most pronounced changes observed in lipid droplets, supporting modifications in lipid-associated cellular processes. These findings demonstrate that Raman imaging provides a sensitive, label-free platform for resolving L-carnitine-induced biochemical heterogeneity at the single-cell level. Overall, this study highlights vibrational spectroscopy as a powerful tool for characterizing cellular responses to metabolic modulators and provides insight into the biochemical impact of exogenous L-carnitine in brain cancer cells. Full article