Explore the vast range of titles available.

Understanding the relationship between land use/land cover (LULC) and land surface temperature (LST) has long been an area of interest in urban and environmental study fields. To examine this, existing studies have utilized both white-box and black-box approaches, including regression, decision tree, and artificial intelligence models. To overcome the limitations of previous models, this study adopted the explainable artificial intelligence (XAI) approach in examining the relationships between LULC and LST. By integrating the XGBoost and SHAP model, we developed the LST prediction model in Seoul and estimated the LST reduction effects after specific LULC changes. Results showed that the prediction accuracy of LST was maximized when landscape, topographic, and LULC features within a 150 m buffer radius were adopted as independent variables. Specifically, the existence of surrounding built-up and vegetation areas were found to be the most influencing factors in explaining LST. In this study, after the LULC changes from expressway to green areas, approximately 1.5 °C of decreasing LST was predicted. The findings of our study can be utilized for assessing and monitoring the thermal environmental impact of urban planning and projects. Also, this study can contribute to determining the priorities of different policy measures for improving the thermal environment.

Recently, studies on driver inattention state recognition as an advanced mobility application technology are being actively conducted to prevent traffic accidents caused by driver drowsiness and distraction. The driver inattention state recognition system is a technology that recognizes drowsiness and distraction by using driver behavior, biosignals, and vehicle data characteristics. Existing driver drowsiness detection systems are wearable accessories that have partial occlusion of facial features and light scattering due to changes in internal and external lighting, which results in momentary image resolution degradation, making it difficult to recognize the driver’s condition. In this paper, we propose a transformer based spatial temporal fusion network (STFTransNet) that fuses multi-modality information for improved driver inattention state recognition in images where the driver’s face is partially occluded by wearing accessories and the instantaneous resolution is degraded due to light scattering from changes in lighting in a driving environment. The proposed STFTransNet consists of (i) a mediapipe face mesh-based facial landmark extraction process for facial feature extraction, (ii) an RCN-based two-stream cross-attention process for learning spatial features of driver face and body action images, (iii) a TCN-based temporal feature extraction process for learning temporal features of extracted features, and (iv) an ensemble of spatial and temporal features and a classification process to recognize the final driver state. As a result of the experiment, the proposed STFTransNet achieved an accuracy of 4.56% better than the existing VBFLLFA model in the NTHU-DDD public DB, 3.48% better than the existing InceptionV3 + HRNN model in the StateFarm public DB, and 3.78% better than the existing VBFLLFA model in the YawDD public DB. The proposed STFTransNet is designed as a two-stream network that can input the driver’s face and action images and solves the degradation in driver inattention state recognition performance due to partial facial feature occlusion and light blur through spatial feature and temporal feature fusion.

•χ-separation, a magnetic susceptibility source separation method, is applied to explore iron and myelin profiles across layers of cortex and white matter.•The depth-wise profiles of χpos and χneg were consistent with the profiles of iron and myelin from literatures.•The depth-wise profiles of χpos and χneg were different from those of QSM or R2*, carrying different information. The in-vivo profiling of iron and myelin across cortical depths and underlying white matter has important implications for advancing knowledge about their roles in brain development and degeneration. Here, we utilize χ-separation, a recently-proposed advanced susceptibility mapping that creates positive (χpos) and negative (χneg) susceptibility maps, to generate the depth-wise profiles of χpos and χneg as surrogate biomarkers for iron and myelin, respectively. Two regional sulcal fundi of precentral and middle frontal areas are profiled and compared with findings from previous studies. The results show that the χpos profiles peak at superificial white matter (SWM), which is an area beneath cortical gray matter known to have the highest accumulation of iron within the cortex and white matter. On the other hand, the χneg profiles increase in SWM toward deeper white matter. These characteristics in the two profiles are in agreement with histological findings of iron and myelin. Furthermore, the χneg profiles report regional differences that agree with well-known distributions of myelin concentration. When the two profiles are compared with those of QSM and R2*, different shapes and peak locations are observed. This preliminary study offers an insight into one of the possible applications of χ-separation for exploring microstructural information of the human brain, as well as clinical applications in monitoring changes of iron and myelin in related diseases.

Unplanned and rapid urban growth requires the reckless expansion of infrastructure including water, sewage, energy, and transportation facilities, and thus causes environmental problems such as deterioration of old towns, reduction of open spaces, and air pollution. To alleviate and prevent such problems induced by urban growth, the accurate prediction and management of urban expansion is crucial. In this context, this study aims at modeling and predicting urban expansion in Seoul metropolitan area (SMA), Korea, using GIS and XAI techniques. To this end, we examined the effects of land-cover, socio-economic, and environmental features in 2007 and 2019, within the optimal radius from a certain raster cell. Then, this study combined the extreme gradient boosting (XGBoost) model and Shapley additive explanations (SHAP) in analyzing urban expansion. The findings of this study suggest urban growth is dominantly affected by land-cover characteristics, followed by topographic attributes. In addition, the existence of water body and high ECVAM grades tend to significantly reduce the possibility of urban expansion. The findings of this study are expected to provide several policy implications in urban and environmental planning fields, particularly for effective and sustainable management of lands.

Over the past few decades, most cities worldwide have experienced a rapid expansion with unprecedented population growth and industrialization. Currently, half of the world’s population is living in urban areas, which only account for less than 1% of the Earth. A rapid and unplanned urban expansion, however, has also resulted in serious challenges to sustainable development of the cities, such as traffic congestion and loss of natural environment and open spaces. This study aims at modeling and predicting the expansion of urban areas in South Korea by utilizing an explainable artificial intelligence (XAI) model. To this end, the study utilized the land-cover maps in 2007 and 2019, as well as several socioeconomic, physical, and environmental attributes. The findings of this study suggest that the urban expansion tends to be promoted when a certain area is close to economically developed area with gentle topography. In addition, the existence of mountainous area and legislative regulations on land use were found to significantly reduce the possibility of urban expansion. Compared to previous studies, this study is novel in that it captures the relative importance of various influencing factors in predicting the urban expansion by integrating the XGBoost model and SHAP values.

Face anti-spoofing (FAS) has become a crucial component in securing face recognition systems against presentation attacks, such as printed photos, replay videos, and 3D masks. While recent advances have improved generalization to unseen spoofing attempts, many existing methods remain black-box models that provide binary decisions without interpretable reasoning. In this paper, we investigate explainable face anti-spoofing from a supervision-centric perspective, using a vision-language model (VLM) to analyze how natural language explanations influence model behavior. To enable this study under controlled conditions, we construct an explanation-augmented benchmark by enriching four standard FAS datasets—MSU-MFSD, CASIA-FASD, Replay-Attack, and OULU-NPU—with both vanilla and reasoning-structured captions generated via the GPT-4o API. We further adopt a dual-objective training strategy that combines spoof classification loss with explanation generation loss, allowing us to examine the effect of explanation-based supervision while keeping the backbone architecture fixed. Through extensive cross-dataset evaluations, we show that reasoning-style captions can enhance detection performance and domain generalization in many settings, while also introducing inductive biases that may degrade performance when emphasized cues are misaligned with unseen attack types. These findings suggest that explanations in FAS should be viewed not only as interpretable outputs, but also as controllable training signals that shape generalization behavior. To support reproducibility, we publicly release the explanation annotations and associated metadata—excluding all face images—via a Hugging Face repository at https://huggingface.co/datasets/DescriptiveFAS/MCIO_public.

•A novel pipeline is proposed to improve the generalization of pre-trained deep learning-based dipole inversion networks for input local field maps of varying resolutions.•The proposed pipeline enables accurate QSM reconstruction from various resolutions (e.g., 1 mm isotropic, 1 × 1 × 3 mm³) using a QSMnet trained solely on single-resolution data (1.5 mm isotropic), outperforming alternative pipelines in quantitative metrics with respect to reference QSM maps.•The proposed method achieves superior performance over three existing deep learning-based approaches for reconstructing QSM from thick-slice (1 × 1 × 3 mm³) input data.•The pipeline’s practical applicability is demonstrated with 0.6 mm isotropic QSM reconstruction using QSMnet+ trained at 1.0 mm isotropic resolution. Deep learning-based dipole inversion networks for quantitative susceptibility mapping (QSM) display low performance when test data resolution is different from network-trained data resolution. While several approaches were proposed to enhance the dipole inversion networks’ resolution generalizability, they modify network architecture or parameter, limiting direct application to existing pre-trained dipole inversion networks. This study presents a novel pipeline that enables pre-trained dipole inversion networks to reconstruct QSM from input local field maps of various resolutions. The developed pipeline consisted of four steps. (ⅰ) The local field map was re-sampled at multiple different spatial locations, generating multiple local field maps at network-trained resolution. (ⅱ) The re-sampled local field maps were inferred through the network, generating QSM maps. (ⅲ) These QSM maps were combined, and then (ⅳ) compensated for systematic errors, introduced by the previous re-sampling and combining process, by “dipole compensation”. The performance of the proposed pipeline was compared with two alternative pipelines using the same network: interpolating the input data to the trained resolution prior to inference (interpolation pipeline), and naïvely inferencing (naïve-input pipeline). Through qualitative and quantitative evaluations, we demonstrate that the proposed pipeline displays superior performance compared to the alternative pipelines. Specifically, when a local field map of 1 mm3 resolution was tested using QSMnet pre-trained at 1.5 mm3 resolution, the proposed pipeline outperformed the two alternative pipelines (NRMSE: 43.1/49.3/56.0, SSIM: 0.933/0.910/0.920, PSNR: 47.1/46.0/44.8, HFEN: 39.9/40.8/48.0 for proposed/interpolation/naïve-input pipeline). This study provides a promising solution for enhancing the generalizability of pre-trained dipole inversion networks to different input data resolutions, widening their applications in clinical settings. [Display omitted]

Phenolic acids, found in cereals, legumes, vegetables, and fruits, have various biological functions. We aimed to compare the antihypertensive potential of different phenolic acids by evaluating their ACE inhibitory activity and cytoprotective capacity in EA.hy 926 endothelial cells. In addition, we explored the mechanism underlying the antihypertensive activity of sinapic acid. Of all the phenolic acids studied, sinapic acid, caffeic acid, coumaric acid, and ferulic acid significantly inhibited ACE activity. Moreover, gallic acid, sinapic acid, and ferulic acid significantly enhanced intracellular NO production. Based on the results of GSH depletion, ROS production, and MDA level analyses, sinapic acid was selected to study the mechanism underlying the antihypertensive effect. Sinapic acid decreases endothelial dysfunction by enhancing the expression of antioxidant-related proteins. Sinapic acid increased phosphorylation of eNOS and Akt in a dose-dependent manner. These findings indicate the potential of sinapic acid as a treatment for hypertension.

This study aimed to examine the associations between cognitive function, physical activity, and vitamin D with dysmobility syndrome (DMS), and to assess the mediation effects of physical activity and vitamin D. This cross-sectional study included 181 community-dwelling older women. Cognitive function was assessed using the Korean version of the Mini-Mental State Examination. Physical activity was measured using the International Physical Activity Questionnaire and categorized as active or inactive. Serum vitamin D was analyzed and classified as either '≥20 ng/mL' or '<20 ng/mL'. DMS was defined as meeting at least three of six clinical criteria, including low muscle mass, high body fat, osteoporosis, slow gait speed, low hand-grip strength and history of fall. Mediation analysis revealed mediation effects for both physical activity (Indirect effect = -0.0091) and vitamin D (Indirect effect = -0.0066) on the relationship between cognitive function and DMS through independent paths. Additionally, the sequential path of physical activity → vitamin D showed partial mediation (Indirect effect = -0.0013). This study suggested that regular physical activity and adequate vitamin D levels can contribute to the prevention and management of cognitive impairment-related DMS in older Korean women.

Targeting neovascularization in glioblastoma (GBM) is hampered by poor understanding of the underlying mechanisms and unclear linkages to tumour molecular landscapes. Here we report that different molecular subtypes of human glioma stem cells (GSC) trigger distinct endothelial responses involving either angiogenic or circumferential vascular growth (vasectasia). The latter process is selectively triggered by mesenchymal (but not proneural) GSCs and is mediated by a subset of extracellular vesicles (EVs) able to transfer EGFR/EGFRvIII transcript to endothelial cells. Inhibition of the expression and phosphorylation of EGFR in endothelial cells, either pharmacologically (Dacomitinib) or genetically (gene editing), abolishes their EV responses in vitro and disrupts vasectasia in vivo. Therapeutic inhibition of EGFR markedly extends anticancer effects of VEGF blockade in mice, coupled with abrogation of vasectasia and prolonged survival. Thus, vasectasia driven by intercellular transfer of oncogenic EGFR may represent a new therapeutic target in a subset of GBMs. Vasectasia is a newly described, non-angiogenic form of blood vessel formation induced by mesenchymal glioblastoma cells, and driven by endothelial cell responses to extracellular vesicles containing oncogenic EGFR.