Search Results (12,446)

Thermal comfort in urban commercial spaces significantly impacts both business performance and public well-being. Traditional evaluation methods relying on field surveys and expert assessments are often time-consuming and labor-intensive. This study proposes a novel vision–language model (VLM)-based agent system for thermal comfort assessment in commercial spaces, simulating eight distinct heat-sensitive roles with varied demographic backgrounds through prompt engineering using ChatGPT-4o. Taking Harbin Central Street, China as a case study, we first validated model accuracy through ASHRAE scale evaluations of 30% samples (167 images) by 50 experts, and then conducted thermal comfort simulations of eight heat-sensitive roles followed by spatial and interpretability analyses. Key findings include (1) a significant correlation between VLM assessments and expert evaluations (r = 0.815, p < 0.001), confirming method feasibility; (2) notable heterogeneity in thermal comfort evaluations across eight agents, demonstrating the VLMs’ capacity to capture perceptual differences among social groups; (3) spatial analysis revealing higher thermal comfort in eastern regions compared to western and central areas despite inter-role variations, demonstrating consistency among agents; and (4) the shade and vegetation being identified as primary influencing factors that contribute to the agent’s decision making. This research validates VLM-based agents’ effectiveness in urban thermal comfort evaluation, showcasing their dual capability in replicating traditional methods while capturing social group differences. The proposed approach establishes a novel paradigm for efficient, comprehensive, and multi-perspective thermal comfort assessments in urban commercial environments. Full article

Dynamic behavior is prevalent in biological and condensed matter systems at the nano- and mesoscopic scales. Typically, we capture images as “snapshots” to demonstrate the evolution of a system, and coherent X-ray diffraction imaging (CDI), as a lensless imaging technique, provides a nanoscale resolution, allowing us to clearly observe these microscopic phenomena. This paper presents a new dynamic CDI method based on zone-plate optics aiming to overcome the limitations of existing techniques in imaging fast dynamic processes by integrating the spatio-temporal dual constraint with a probe constraint. In this method, the modulus-enforced probe constraint and the temporal correlation of the dynamic sample low-frequency information are exploited and combined with an empty static region constraint in the dynamic sample. Using this method, we achieved a temporal resolution of 20 Hz and a spatial resolution of 13.2 nm, which were verified by visualized experimental results. Further comparisons showed that the reconstructed images were consistent with the ptychography reconstruction results, confirming the accuracy and feasibility of the method. This work is expected to provide a new tool for materials science and mesoscopic life sciences, promoting a deeper understanding of complex dynamic processes. Full article

Hyperspectral (HS) and multispectral (MS) image fusion is the most favorable way to obtain a hyperspectral image that has high resolution in terms of spatial and spectral information. This fusion problem can be accomplished by formulating a mathematical model and solving it either analytically or iteratively. The mathematical solutions class has serious challenges, e.g., computation cost, manually tuning parameters, and the absence of imaging models that laboriously affect the fusion process. With the revolution of deep learning, the recent HS-MS image fusion techniques gained good outcomes by utilizing the power of the convolutional neural network (CNN) for feature extraction. Moreover, extracting intrinsic information, e.g., non-local spatial and global spectral features, is the most critical issue faced by deep learning methods. Therefore, this paper proposes an Extensive Feature-Inferring Deep Network (EFINet) with extensive-scale feature-interacting and global correlation refinement modules to improve the effectiveness of HS-MS image fusion. The proposed network retains the most vital information through the extensive-scale feature-interacting module in various feature scales. Moreover, the global semantic information is achieved by utilizing the global correlation refinement module. The proposed network is validated through rich experiments conducted on two popular datasets, the Houston and Chikusei datasets, and it attains good performance compared to the state-of-the-art HS-MS image fusion techniques. Full article

Multi-source domain adaptation (MSDA) in remote sensing (RS) scene classification has recently gained significant attention in the visual recognition community. It leverages multiple well-labeled source domains to train a model capable of achieving strong generalization on the target domain with little to no labeled data from the target domain. However, the distribution shifts among multiple source domains make it more challenging to align the distributions between the target domain and all source domains concurrently. Moreover, relying solely on global alignment risks losing fine-grained information for each class, especially in the task of RS scene classification. To alleviate these issues, we present a Multi-Source Subdomain Distribution Alignment Network (MSSDANet), which introduces novel network structures and loss functions for subdomain-oriented MSDA. By adopting a two-level feature extraction strategy, this model attains better global alignment between the target domain and multiple source domains, as well as alignment at the subdomain level. First, it includes a pre-trained convolutional neural network (CNN) as a common feature extractor to fully exploit the shared invariant features across one target and multiple source domains. Secondly, a dual-domain feature extractor is used after the common feature extractor, which maps the data from each pair of target and source domains to a specific dual-domain feature space and performs subdomain alignment. Finally, a dual-domain feature classifier is employed to make predictions by averaging the outputs from multiple classifiers. Accompanied by the above network, two novel loss functions are proposed to boost the classification performance. Discriminant Semantic Transfer (DST) loss is exploited to force the model to effectively extract semantic information among target and source domain samples, while Class Correlation (CC) loss is introduced to reduce the feature confusion from different classes within the target domain. It is noteworthy that our MSSDANet is developed in an unsupervised manner for domain adaptation, indicating that no label information from the target domain is required during training. Extensive experiments on four common RS image datasets demonstrate that the proposed method achieves state-of-the-art performance for cross-domain RS scene classification. Specifically, in the dual-source and three-source settings, MSSDANet outperforms the second-best algorithm in terms of overall accuracy (OA) by 2.2% and 1.6%, respectively. Full article

Aiming at the problems of poor image quality of traditional cameras and serious noise interference of event cameras under complex lighting conditions in coal mines, an event denoising algorithm fusing spatio-temporal information and a method of denoising event target pose estimation is proposed. The denoising algorithm constructs a spherical spatio-temporal neighborhood to enhance the spatio-temporal denseness and continuity of valid events, and combines event density and curvature to achieve event stream denoising. The attitude estimation framework adopts the noise reduction event and global optimal perspective-n-line (OPNL) methods to obtain the initial target attitude, and then establishes the event line correlation model through the robust estimation, and achieves the attitude tracking by minimizing the event line distance. The experimental results show that compared with the existing methods, the noise reduction algorithm proposed in this paper has a noise reduction rate of more than 99.26% on purely noisy data, and the event structure ratio (ESR) is improved by 47% and 5% on DVSNoise20 dataset and coal mine data, respectively. The maximum absolute trajectory error of the localization method is 2.365 cm, and the mean square error is reduced by 2.263% compared with the unfiltered event localization method. Full article

In general, graphene is known to be thermally stable. In this study, we analyzed the Raman spectra of graphene prepared on copper (Cu) and nickel (Ni) by chemical vapor deposition (CVD) as well as monolayer and multilayer graphene transferred onto SiO₂ under vacuum heating. We observed a shift in the position of the graphene G peak due to temperature changes for all substrates. For graphene on insulating substrates, the peak position returned to its original position after heating when the substrate returned to room temperature, indicating the thermal and chemical stability of graphene. In contrast, the Raman spectra of graphene on Cu and Ni, which have different carbon solubilities, showed significant shifts and broadening of the G peak as the temperature increased. We also utilized optical microscopy to observe morphological changes during heating, which complemented the Raman spectroscopy analysis. The optical microscopy images obtained in the previous study revealed morphological changes on the graphene surface that correlate with the shifts observed in the Raman spectra, especially in graphene on metal substrates. These combined findings from Raman spectroscopy and optical microscopy could provide insights for optimizing graphene growth processes. In addition, knowledge of the thermal behavior of graphene on insulating substrates could be useful for device construction. Full article

UAV aerial–ground feature matching is used for remote sensing applications, such as urban mapping, disaster management, and surveillance. However, current semi-dense detectors are sparse and inadequate for comprehensively addressing problems like scale variations from inherent viewpoint differences, occlusions, illumination changes, and repeated textures. To address these issues, we propose an efficient quadtree-attention-guided transformer (ETQ-Matcher) based on efficient LoFTR, which integrates the multi-layer transformer with channel attention (MTCA) to capture global features. Specifically, to tackle various complex urban building scenarios, we propose quadtree-attention feature fusion (QAFF), which implements alternating self- and cross-attention operations to capture the context of global images and establish correlations between image pairs. We collect 12 pairs of UAV remote sensing images using drones and handheld devices, and we further utilize representative multi-source remote sensing images along with MegaDepth datasets to demonstrate their strong generalization ability. We compare ETQ-Matcher to classic algorithms, and our experimental results demonstrate its superior performance in challenging aerial–ground urban scenes and multi-source remote sensing scenarios. Full article

Land use and land cover (LULC) classification through remote sensing imagery serves as a cornerstone for environmental monitoring, resource management, and evidence-based urban planning. While Synthetic Aperture Radar (SAR) and optical sensors individually capture distinct aspects of Earth’s surface, their complementary nature SAR excelling in structural and all-weather observation and optical sensors providing rich spectral information—offers untapped potential for improving classification robustness. However, the intrinsic differences in their imaging mechanisms (e.g., SAR’s coherent scattering versus optical’s reflectance properties) pose significant challenges in achieving effective multimodal fusion for LULC analysis. To address this gap, we propose a multimodal deep-learning framework that systematically integrates SAR and optical imagery. Our approach employs a dual-branch neural network, with two fusion paradigms being rigorously compared: the Early Fusion strategy and the Late Fusion strategy. Experiments on the SEN12MS dataset—a benchmark containing globally diverse land cover categories—demonstrate the framework’s efficacy. Our Early Fusion strategy achieved 88% accuracy (F1 score: 87%), outperforming the Late Fusion approach (84% accuracy, F1 score: 82%). The results indicate that optical data provide detailed spectral signatures useful for identifying vegetation, water bodies, and urban areas, whereas SAR data contribute valuable texture and structural details. Early Fusion’s superiority stems from synergistic low-level feature extraction, capturing cross-modal correlations lost in late-stage fusion. Compared to state-of-the-art baselines, our proposed methods show a significant improvement in classification accuracy, demonstrating that multimodal fusion mitigates single-sensor limitations (e.g., optical cloud obstruction and SAR speckle noise). This study advances remote sensing technology by providing a precise and effective method for LULC classification. Full article

Fluid mechanical conditions are crucial for cavitation formation, and significantly influence chemical reactivity. This study investigates process conditions such as pressure, degassing, cavitation and reaction volume, and the sound emission of oxidative dye degradation by cavitation. For ensuring comparability and scalability, dimensionless similarity numbers aligned to the process were introduced. A further focus of the paper is reproducibility with corresponding guidelines. Measurements of dye degradation were carried out without additional chemicals. The oxidation process was assessed by the chemiluminescence of luminol. For this purpose, configurations with three nozzle sizes at different pressure differences were investigated. The generated cavitating jet was captured by imaging techniques and correlated to degradation. The most energy-efficient configuration was obtained by the smallest nozzle diameter of 0.6 mm at a pressure difference of 40 bar. Significant degassing occurred during cavitation. It was more pronounced with smaller nozzle diameters, correlating with higher degradation. Furthermore, discontinuous treatment methods can improve efficiency. Scaling to higher flow rates through multiple reactors in parallel proved more effective, compared to increasing the nozzle diameter or the pressure difference. For the same treated volume, two parallel reactors increased degradation by a factor of 1.35. The insights provide perspectives for optimizing jet cavitation reactors for water treatment. Full article

The West Kunlun Mountains (WKL) gather lots of large-scale glaciers, which play an important role in the climate and freshwater resource for central Asia. Despite extensive studies on glaciers in this region, a comprehensive understanding of inter-annual variations in glacier area, flow velocity, and terminus remains lacking. This study used a deep learning model to derive time-series glacier boundaries and the sub-pixel cross-correlation method to calculate inter-annual surface flow velocity in this region from 71 Sentinel-2 images acquired between 2016 and 2024. We analyzed the spatial-temporal variations of glacier area, velocity, and terminus. The results indicate that, as follows: (1) The glacier area in the WKL remained relatively stable, with three glaciers expanding by more than 0.5 km² and five glaciers shrinking by over 0.5 km² from 2016 to 2024. (2) Five glaciers exhibited surging behavior during the study period. (3) Six glaciers, with velocities exceeding 50 m/y, have the potential to surge. (4) There were eight obvious advancing glaciers and nine obvious retreating glaciers during the study period. Our study demonstrates the potential of Sentinel-2 for comprehensively monitoring inter-annual changes in mountain glacier area, velocity, and terminus, as well as identifying glacier surging events in regions beyond the study area. Full article

Smart fisheries, integrating advanced technologies such as the Internet of Things (IoT), artificial intelligence (AI), and image processing, are pivotal in enhancing aquaculture efficiency, sustainability, and resource management by enabling real-time environmental monitoring, precision feeding, and disease prevention. However, underwater fish recognition faces challenges in complex aquatic environments, which hinder accurate detection and behavioral analysis. To address these issues, we propose a novel image instance segmentation framework based on a deep learning neural network, defined as the AASNet (Agricultural Aqua Segmentation Network). In order to improve the accuracy and real-time availability of fine-grained fish recognition, we introduce a Linear Correlation Attention (LCA) mechanism, which uses Pearson correlation coefficients to capture linear correlations between features. This helps resolve inconsistencies caused by lighting changes and color variations, significantly improving the extraction of semantic information for similar objects. Additionally, Dynamic Adaptive Focal Loss (DAFL) is designed to improve classification under extreme data imbalance conditions. Abundant experiments on two underwater datasets demonstrated that the proposed AASNet obtains an optimal balance between segmentation performance and efficiency. Concretely, AASNet achieves mAP scores of 31.7 and 47.4, respectively, on the UIIS and USIS dataset, significantly outperforming existing state-of-the-art methods. Moreover, AASNet achieves an inference image recognition speed of up to 28.9 ms/per, which is suitable for practical agricultural applications of smart fish farming. Full article

Background: Upper tract urothelial carcinoma (UTUC) often presents with aggressive behaviour, demanding accurate preoperative assessment to guide management. Radiomics-based approaches have shown promise in extracting quantitative features from imaging, yet few studies have explored whether perirenal fat (PRF) radiomics can augment tumour-only models. Methods: A retrospective cohort of 103 UTUC patients undergoing radical nephroureterectomy was analysed. Tumour regions of interest (ROI) and concentric PRF expansions (10–30 mm) were segmented from computed tomography (CT) scans. Radiomic features were extracted using PyRadiomics, filtered by correlation and intraclass correlation coefficients, and integrated with clinical variables (e.g., age, BMI, multifocality). Multiple machine learning models, including MLPClassifier and CatBoost, were evaluated via repeated cross-validation. Performance was assessed using the area under the ROC curve (AUC), sensitivity, specificity, F1-score, and DeLong tests. Results: The best tumour grade model (AUC = 0.961) merged tumour-derived features with a 10 mm PRF margin, exceeding PRF-only (AUC = 0.900) and tumour-only (AUC = 0.934) approaches. However, the improvement over tumour-only was not always statistically significant. For stage prediction, combining tumour and 15 mm PRF features yielded the top AUC of 0.852, surpassing the tumour-alone model (AUC = 0.802) and outperforming PRF-only (AUC ≤ 0.778). PRF features provided an additional predictive value for both grade and stage models. Conclusions: Integrating PRF radiomics with tumour-based analyses enhances predictive accuracy for UTUC grade and stage, suggesting that the tumour microenvironment contains complementary imaging cues. These findings, pending external validation, support the potential for radiomics-driven risk stratification and personalised treatment planning in UTUC. Full article

Background and Objectives: Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is a well-established technique for evaluating myocardial perfusion and function in patients with suspected or known coronary artery disease. While conventional dual-detector SPECT scanners have limitations in spatial resolution and photon detection sensitivity, recent advancements, including full-ring solid-state cadmium zinc telluride (CZT) detectors, offer enhanced image quality and improved diagnostic accuracy. This study aimed to compare the performance of Veriton-CT, a full-ring CZT SPECT system, with GE Discovery 530c, a dedicated cardiac fixed-angle gamma camera, in myocardial perfusion imaging and their correlation with coronary angiography findings. Materials and Methods: This was a prospective study that analyzed 21 patients who underwent MPI at the Department of Nuclear Medicine, Lithuanian University of Health Sciences, Kauno Klinikos. A one-day stress–rest protocol using 99mTc-Sestamibi was employed, with stress testing performed via bicycle ergometry or pharmacological induction. MPI was first conducted using GE Discovery 530c (GE Health Care, Boston, MA, USA), followed by imaging on Veriton-CT, which included low-dose CT for attenuation correction. The summed stress score (SSS), summed rest score (SRS), and summed difference score (SDS) were analyzed and compared between both imaging modalities. Coronary angiography results were retrospectively collected, and lesion-based analysis was performed to assess the correlation between imaging results and the presence of significant coronary artery stenosis (≥35% and ≥70% narrowing). Image quality and the certainty of distinguishing the inferior myocardial wall from extracardiac structures were also evaluated by two independent researchers with differing levels of experience. Results: Among the 14 patients included in the final analysis, Veriton-CT was more likely to classify MPI scans as normal (64.3%) compared to GE Discovery 530c (28.6%). Additionally, Veriton-CT provided a better assessment of the right coronary artery (RCA) basin, showing greater agreement with coronary angiography findings than GE Discovery 530c, although the difference was not statistically significant. No significant differences in lesion overlap were observed for the left anterior descending artery (LAD) or left circumflex artery (LCx) basins. Furthermore, the image quality assessment revealed slightly better delineation of extracardiac structures using Veriton-CT (Spectrum Dynamics Medical, Caesarea, Israel), particularly when evaluated by an experienced researcher. However, no significant difference was observed when assessed by a less experienced observer. Conclusions: Our findings suggest that Veriton-CT, with its full-ring CZT detector system, may offer advantages over fixed-angle gamma cameras in improving image quality and reducing attenuation artifacts in MPI. Although the difference in correlations with coronary angiography findings was not statistically significant, Veriton-CT showed a trend toward better agreement, particularly in the RCA basin. These results indicate that full-ring SPECT imaging could improve the diagnostic accuracy of non-invasive MPI, potentially reducing the need for unnecessary invasive angiography. Further studies with larger patient cohorts are required to confirm these findings and evaluate the clinical impact of full-ring SPECT technology in myocardial perfusion imaging. Full article

This study investigated Dunnian runoff in the Sauípe River basin, Bahia, Brazil, analyzing the relationship between soil moisture, terrain slope, and land use. It utilized Landsat satellite images, annual water balance data, and rainfall data from the last 10 days. The Normalized Difference Water Index (NDWI) and Normalized Difference Vegetation Index (NDVI) were calculated, along with image classification using the Random Forest machine learning algorithm. (1) Saturated zones with potential for Dunnian runoff were identified, especially on steeper slopes, with a notable negative influence of eucalyptus on soil moisture, except in areas with steeper slopes. (2) Dunnian runoff was predominantly observed from the middle course to the mouth, following the east-west direction of the watershed. (3) Higher areas exhibited Dunnian runoff with high soil moisture values, while areas with less steep slopes showed low moisture levels. (4) The results indicate a positive correlation between steeper slopes and Dunnian runoff and a negative correlation between eucalyptus plantations and soil moisture. (5) Forest fragments exhibited high NDVI and NDWI values, suggesting dense forests with high moisture, especially in areas with steep slopes. This suggests that forest fragments are in good moisture conditions, acting to delay Dunnian runoff. (6) In areas with savannization or without vegetation, significant moisture content was not observed, indicating the absence of intense rainfall in the last ten days of image acquisition. This confirms the importance of this runoff for forest remnants. Full article

As mineral resource extraction progresses to greater depths, it has become imperative for geomechanical applications to understand the thermomechanical degradation mechanisms of rocks under thermal loading. To investigate the thermomechanical characteristics of granite subjected to thermal treatments ranging from ambient to 1000 °C, we conducted uniaxial compression tests integrating P-wave velocity measurements, digital image correlation (DIC), and acoustic emission (AE) monitoring. The key findings reveal the following: (1) the specimen volume exhibits thermal expansion while the mass loss and P-wave velocity reduction demonstrate a temperature dependence; (2) the uniaxial compressive strength (UCS) and elastic modulus display progressive thermal degradation, while the peak strain shows an inverse relationship with temperature; (3) acoustic emission signals exhibit a strong correlation with failure–time curves, progressing through three distinct phases: quiescent, progressive accumulation, and accelerated failure, and fracture mechanisms transition progressively from tensile-dominated brittle failure to shear-induced ductile failure with increasing thermal loading; and (4) the damage evolution parameter exhibits exponential growth beyond 600 °C, reaching 98.85% at 1000 °C, where specimens demonstrate a complete loss of load-bearing capacity. These findings provide critical insights for designing deep geological engineering systems involving thermomechanical rock interactions. Full article