Search Results (146)

As complex socio-ecological systems, cultural landscapes face increasing challenges under climate change. Taking the Eight Scenic Spots of Mount Song in Henan Province, China as a case study, this research examines meteorological–cultural genes as integrated expressions of meteorological conditions, cultural meanings, and human perception. Historical texts, meteorological observations, and tourist surveys were analyzed within the framework of landsenses ecology. Historical materials were coded using NVivo, while meteorological and perceptual indicators were standardized and weighted through the entropy-weight method. A dynamic coupling coordination model was then applied to evaluate interactions between meteorological conditions and multisensory landscape perception. The study identified astronomical-calendar, microclimate-adaptation, poetic–symbolic, and ritual–spatial genes. The results reveal strong climate–perception interactions but comparatively weaker coordination, indicating that environmental sensitivity does not necessarily translate into effective climate adaptability. Based on these findings, a meteorological–sensory dynamic coupling framework and a threshold-responsive management pathway are proposed to support gene identification, climate-risk diagnosis, and differentiated adaptive intervention. The study provides a methodological and practical basis for maintaining cultural expression, multisensory experience, and landscape resilience under climate change. Full article

Background/Objectives: Artificial intelligence (AI) is entering interventional pulmonology (IP) faster than its potential risks have been systematically catalogued. We explored whether general-purpose large language models (LLMs), now widely consulted informally by patients and clinicians, could provide a rapid and structured means of enumerating and ranking candidate AI-related risks in IP, potentially contributing to risk awareness and hypothesis generation. Methods: Five LLMs (ChatGPT, Claude, Gemini, Grok, DeepSeek) were each queried once, in independent, memory-free sessions, with one standardised prompt requesting ten ranked AI-related risks with impact and likelihood scores (1–5); an informal repeat administration was performed, but output stability was not formally assessed. The resulting 50 risk statements were inductively coded, by an AI coder with independent human validation by two reviewers, into 15 constructs nested in 8 higher-order domains. Results: Mean self-assigned impact was 3.92 (SD 0.78) and mean likelihood 3.54 (SD 0.68). The eight domains comprised AI technical/perceptual accuracy (diagnostic, detection and navigational error); automation bias and over-reliance; generalisability, algorithmic bias and health equity; model and system reliability over time; erosion of procedural competence; explainability, transparency and accountability; cybersecurity, privacy and data integrity; and cognitive and workflow burden. Five domains were raised by all five models and the remaining three by four of five. Two domains-AI technical/perceptual accuracy and automation bias-together accounted for every model’s two highest-ranked risks, and no risk statement outside these two domains was ranked first or second by any model. Deskilling (erosion of procedural competence), although listed by all five models, was never ranked above third by any model, whereas practising IP specialists in our prior international survey rated it the single highest research priority. Conclusions: These exploratory and hypothesis-generating findings suggest that general-purpose LLMs may have potential as a rapid, low-burden means of enumerating and ranking candidate AI-related risks and broadening awareness of issues that may warrant further investigation in IP. The lower ranking of deskilling by the LLMs than by domain experts indicates that LLM-generated rankings may under-prioritise risks that clinicians consider most important. Although their outputs are not validated measures of clinical risk and do not replace expert appraisal, we believe they may provide a starting point for subsequent human-led risk assessment and prioritization in an area of research that remains largely unexplored yet is highly relevant to patient safety. Full article

Understanding how visual structure shapes attentional allocation is central to models of perceptual processing. Less is known about how formal properties like harmony and complexity shape exploration independent of salience or semantic content. This study examined how controlled structural variations relate to attention, facial engagement, and subjective judgment using eye-tracking and webcam-based facial coding. Participants ($N=40$) viewed stimuli derived from a common geometric base, manipulated into three conditions: high harmony (symmetrical, low complexity), high complexity (asymmetrical, disorganized), and structured complexity (high complexity with underlying order). Eye movements and facial expressions were recorded during free viewing. Metrics included time to first fixation, fixation duration, number of fixations, scanpath entropy, spatial dispersion, and facial-coding indices (neutral, happy, and surprise expression, and the ambient/focal coefficient K). None of the eye-tracking or facial-coding metrics differed significantly across conditions; given that the study was powered to detect only medium-to-large effects, this indicates no detectable difference under the present webcam-based, brief-exposure design rather than evidence that visual structure has no effect on attention. Subjective complexity ratings differed robustly across conditions, surviving correction for multiple comparisons: unexpectedly, the high-complexity condition was rated as less complex than the harmony and structured-complexity conditions, indicating the intended manipulation did not translate into perceived complexity as designed. A nominally significant difference in pleasantness ratings did not survive this correction. Using repeated-measures correlation to account for the non-independence of within-participant observations, scanpath entropy showed a nominal negative association with pleasantness that did not survive correction for multiple comparisons, and the coefficient K showed a weaker and partly inconsistent pattern of association with independent oculomotor indices than initial uncorrected analyses suggested. These findings indicate that, in the present study, formal visual structure shaped subjective complexity judgments more robustly than it shaped overt attentional or facial-affective engagement, a pattern consistent with—though not conclusive proof of—a broader dissociation between evaluative and attentional responses reported in face perception and developmental aesthetics research. Beyond this substantive finding, we report in detail how accounting for repeated-measures non-independence and applying an explicit multiplicity strategy changed our statistical conclusions, offering a worked methodological example for similarly structured webcam-based eye-tracking and facial-coding studies. Full article

Coaching leadership is experienced through both subjective perceptions and observable actions, but these sources do not represent equivalent constructs. This descriptive multi-case study examined coach–athlete perceptual alignment and match-observed behaviors in four elite youth soccer coach–team cases. Four male youth soccer coaches and 64 male athletes (14–18 years) from a single Romanian elite soccer academy participated in the study. Athletes completed the Multidimensional Scale of Leadership in Sport (MSLS) before and after an official match; each coach completed one post-match self-rating referring to that match. Each coach was compared only with his corresponding team’s post-match mean. Dimension-specific discrepancy scores and a mean absolute discrepancy (MAD) index were calculated. Pre–post comparisons used Wilcoxon signed-rank tests with Holm correction. One match per coach was coded descriptively using the Coach Analysis and Intervention System (CAIS). The MAD index was lowest for the U17 case (1.93) and highest for the U18 case (4.35). After Holm correction, post-match scores were lower for Inspiration, Individualization, and Support. Instruction was highly rated in the MSLS and was the most frequent CAIS category in all four matches (25.2–41.6%), representing a parallel descriptive pattern rather than formal agreement. The findings are specific to four coach–team cases and provide complementary, preliminary perspectives on perceived and match-observed leadership. The single-match, single-observer design and absence of observational reliability assessment preclude characterization of habitual coaching behavior. Full article

As urban development in China shifts toward improving existing areas, the focus of evaluation is moving from availability to quality, yet assessments of the neighborhood built environment and living circles still stop at facility provision. This study decomposes the conversion from spatial supply to need fulfillment into three links—availability, reach-and-visibility, and need fulfillment. Encounterability (E) captures how far a spatial element enters everyday experience through physical reach or visual exposure; perceptual affordance (P) captures how well an encountered element supports six perceptual needs: social interaction, recreation and leisure, aesthetic experience, emotional experience, broad learning, and humanistic enrichment. Taking Xi’an’s historic old city as a typical case, public needs were translated through grounded coding into auditable elements, which trained assessors evaluated at the city, district, and neighborhood levels, with a four-quadrant diagnosis locating the gaps. The results show that, within this context of comparatively rich provision, the principal experiential gaps arise at the encounter and support links: encounterability is similar across levels while perceptual affordance diverges, and the share of synergy categories differs significantly across levels (p = 0.007), forming resource–encounter, node–route, and frequency–support mismatches; the principal mismatch patterns are robust to equal weighting and to moderate shifts in the quadrant thresholds. Basic needs fail on quality and advanced needs fail on encounter and interpretation, pointing to three renewal actions: retrofitting, opening, and interpretation. This study extends evaluation objects from facilities to a fuller spectrum of spatial elements, extends encounter to reach and visibility together, and extends output from ranking to gap localization, offering a low-cost diagnostic tool for the human-centered assessment of the built environment, applicable to living-circle evaluation, urban physical examination, and livability improvement in historic neighborhoods. Full article

Geometric deviations in unsupported overhang features pose one of the most persistent quality challenges in Laser Powder Bed Fusion (LPBF), where even small deviations from the intended geometry can undermine part functionality and reliability. This study presents a geometrically informed conditional Generative Adversarial Network (cGAN), implemented through the Pix2Pix framework, to predict layer-wise geometric deviations in LPBF-printed parts with overhang geometries, using paired two-dimensional Computer-Aided Design (2D CAD) slices and corresponding X-ray Computed Tomography (XCT)-derived ground truth slices. The study investigates how geometric information can be encoded within the conditional input of the Pix2Pix framework to more effectively guide deviation prediction. A total of 18 models were trained and evaluated across multiple overhang geometry groups and batch size configurations, assessed through a combination of perceptual, structural, and boundary-focused metrics, namely Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Learned Perceptual Image Patch Similarity (LPIPS), Fréchet Inception Distance (FID), and Edge Intersection over Union (Edge IoU). The results demonstrated that color-coded inputs consistently improved prediction fidelity, perceptual similarity, and edge alignment relative to their non-color-coded counterparts. Furthermore, a model trained on a balanced multi-geometry dataset showed improved prediction performance on withheld 30° and 60° overhang configurations within the benchmark geometry family. The proposed framework offers a data-driven, design-stage tool for anticipating geometry-dependent deviations in LPBF overhang structures, supporting design for additive manufacturing. Full article

With extremely low odor thresholds and potent flavor activity, sulfur-containing aroma compounds (SACs) constitute the molecular cornerstone of characteristic flavors in meat, coffee, and fermented foods. Research has advanced from early component identification to the elucidation of structure–activity relationships, olfactory receptor recognition mechanisms, and food-flavor improvement. This review first summarizes the detection and quantification methods for SACs, their distribution in foods, key odor contributions, and major formation pathways. It then highlights progress in understanding molecular structural parameters, olfactory receptor recognition, and computational simulations that decode flavor perception mechanisms. From a translational perspective, we further discuss flavor retention in real food matrices, off-flavor regulation, cross-modal perceptual enhancement, and functional applications. Current challenges include food matrix complexity, high compound reactivity, and nonlinear olfactory combinatorial coding. Future directions involve constructing a multiscale predictive framework integrating neuroscience, developing explainable artificial intelligence to decode olfactory coding, and advancing closed-loop green biomanufacturing for the precise design and sustainable production of SACs. Full article

Image compression has evolved from human-centric perceptual coding toward support for diverse machine vision applications, requiring modern codecs to serve both human viewing and downstream tasks in closed-set settings (where target tasks are incorporated during training) and open-set settings (where previously unseen tasks arise at test time). While recent learned compression methods jointly optimize perceptual quality and closed-set task performance, they often fail to generalize to unseen open-set tasks due to fixed training assumptions and objectives. Our prior work, LoRA-comp (Low-Rank Adaptation Compression), effectively addresses open-set challenges via instance-specific test-time fine-tuning (TTFT) without requiring task-specific pre-training. Nevertheless, its fixed LoRA architecture, which assigns a uniform rank across all layers, often leads to suboptimal instance-level performance. Moreover, allocating the same number of training epochs to every instance introduces unnecessary encoding-time overhead. To address these challenges, we propose Instance-Specific Early Stopping with Dynamic Rank Adaptation (ISER), which extends LoRA-comp. Building upon the LoRA-comp–based instance-specific adaptation framework, ISER introduces (i) instance-specific early stopping (ISES) combined with a multi-scale training strategy (MSTS) to reduce TTFT overhead and (ii) instance-specific dynamic rank adaptation (ISRA) to tailor the LoRA architecture per instance. Experiments demonstrate that ISER consistently outperforms competing methods. Compared to LoRA-comp, ISER achieves up to a 7% BD-Rate improvement and up to a 44% reduction in encoding time. Moreover, ISER achieves up to a 98% relative improvement in BD-Rate gain and up to a 19.2% reduction in decoding time over TransTIC. Full article

Deep joint source-channel coding (DeepJSCC) has emerged as a promising paradigm for semantic-aware wireless image transmission, achieving strong performance under challenging channel conditions. However, MSE-trained DeepJSCC systems typically achieve high peak signal-to-noise ratio (PSNR) values but suppress high-frequency details, resulting in perceptually blurry reconstructions that fail to capture fine textures and edge information. Existing perceptual enhancement approaches for JSCC systems face significant practical limitations: full transceiver redesign methods require replacing both the transmitter and the receiver with large models (19–31 million parameters), incurring substantial deployment costs; diffusion-based refinement approaches require over 1700 million additional parameters and introduce inference latency exceeding 13 s, rendering them unsuitable for latency-constrained wireless applications; and generic image restoration networks lack channel state awareness and cannot adapt to varying signal-to-noise ratio (SNR) conditions. This paper proposes a lightweight receiver-only perceptual enhancer designed for use with frozen DeepJSCC backbones. The proposed module adopts residual learning with feature-wise linear modulation (FiLM)-based SNR-adaptive modulation to dynamically adjust the enhancement strength under varying channel conditions. A radially weighted FFT magnitude loss is further introduced to guide high-frequency recovery. The enhancer adds only 0.29 million trainable parameters (<1% of the backbone) and requires neither transmitter modification nor backbone retraining. Extensive experiments on the Kodak24 and DIV2K datasets demonstrate a 34.4–37.5% LPIPS reduction over the frozen DeepJSCC baseline under AWGN channels. Supplementary robustness evaluations further show a 30–33% LPIPS reduction under Rayleigh fading, and stable generalization to unseen SNR levels. The receiver-side decoder-plus-enhancer pipeline requires 43 ms at 768 × 512 resolution, corresponding to approximately 23 frames per second. Full article

Unlike natural image deblurring, which primarily emphasizes perceptual quality and pixel-level fidelity, Quick Response (QR) code deblurring must retain decoding-critical structures to guarantee successful decoding. QR codes contain regular binary module grids and functional patterns with sharp boundaries, providing a strong structural prior for restoration. However, most existing learning-based QR restoration methods capture QR-specific structural information via implicit feature learning. To address this limitation, we propose an Edge-Guided Attention Block (EGAB), which explicitly extracts multi-directional edge priors and injects them into the query–key correlations of Transformer attention. Based on EGAB, we develop an Edge-Guided Restormer (EG-Restormer) for restoring severely blurred QR codes. For mildly blurred inputs, we introduce a Lightweight and Efficient Network (LENet) that performs fast restoration with low computational overhead. We further integrate EG-Restormer and LENet into an Adaptive Dual-network (ADNet), which selects the appropriate restoration branch according to the input blur level. Extensive experiments demonstrate the effectiveness of the proposed framework. EG-Restormer boosts the decoding rate by 8.67 percentage points under GoPro-only training and achieves the highest decoding rate among the evaluated methods after QRData fine-tuning. Moreover, ADNet reduces average inference latency by 19% while maintaining comparable decoding performance. These results suggest that explicit edge prior modeling enhances the recovery of structures critical for decoding, while adaptive routing provides an effective balance between decoding accuracy and computational efficiency. Full article

City image links perceptions of urban form and environmental quality to place identity and sociocultural sustainability. However, city-scale research rarely integrates visible streetscape characteristics with visitor narratives. Using Wuhan, China, as a case study, this study integrates panoramic streetscape imagery with online visitor reviews. Semantic segmentation was employed to quantify nine streetscape visual indicators, such as building interfaces, visible greenery and water, color characteristics, and visual disturbances. High-frequency term extraction and thematic coding identified four dimensions of visitor perception: cultural, aesthetic, leisure, and scientific–educational perceptions. Statistical and spatial analyses were subsequently conducted to examine the relationships between the visual indicators and these perceptual dimensions. Leisure and aesthetic perceptions emerged as the most prominent dimensions. Color harmony, water visibility, and visible greenery were positively associated with cultural, aesthetic, and leisure perceptions. Dense building interfaces and visual disturbances were negatively associated with aesthetic and leisure perceptions but positively associated with scientific–educational perception. Hotspots of cultural, aesthetic, and leisure narrative intensity were concentrated in core Wuchang and the East Lake area, whereas scientific–educational perception showed weaker overall spatial clustering, with localized hotspots in central urban areas. These findings suggest that integrating street-view imagery with visitor narratives can help identify spatially differentiated relationships between visible urban environments and city image. The proposed framework may facilitate the identification of sustainability-relevant visual resources and provide diagnostic evidence that may inform urban design and public-space management. Full article

Underground spaces are becoming increasingly important in high-density urban environments, yet their restricted sensory conditions, limited natural references, and distinctive spatial characteristics make human responses difficult to evaluate. Virtual reality (VR) provides a controlled platform for investigating perception, cognition, and emotion in underground environments. This review synthesizes a focused body of evidence at the intersection of VR-based simulation, underground environments, and human-response assessment. A corpus of 28 studies was analysed using qualitative coding and evidence mapping. Environmental variables were organised into six categories, and reported outcomes were interpreted through a perception cognition emotion (PCE) framework. The reviewed studies show that visual conditions and biophilic interventions are frequently associated with perceptual, cognitive, and emotional outcomes, while wayfinding-related factors are most commonly represented in cognitive outcomes involving orientation, route choice, and decision-making under uncertainty or stress. The evidence also reveals a strong methodological emphasis on visually oriented and single-factor experimental designs, while multi-factor interactions and non-visual environmental influences remain comparatively underexplored. By providing a structured synthesis of current evidence, this review highlights methodological characteristics, identifies research gaps, and offers directions for future VR-based underground-environment research and human-centred design. Full article

Robust watermarking has emerged as a pivotal field in digital security, particularly for protecting intellectual property. This study introduces a robust watermarking framework specifically engineered to withstand JPEG compression attacks. To evaluate our scheme, several performance metrics should be considered, including robustness against intentional JPEG compression, embedding capacity, and the perceptual quality of watermarked images. For practical applications, we choose the quick response code to serve as the watermark, and we extend our evaluation to high-resolution pictures, both captured by the authors and obtained on the Internet with no copyright issues. These images possess resolutions that are dozens-of-times higher than conventional test images, facilitating a vastly increased capacity. This expanded capacity makes the integration of visual secret sharing practical, adding an additional layer of cryptographic protection to the watermarking scheme. Simulation results present the effectiveness of our implementation, demonstrating that our approach achieves a superior balance between data integrity and visual fidelity, even when subjected to rigorous attack conditions. Full article

Autonomous vehicle (AV) technologies have advanced rapidly in recent years, driving an increasing demand for large-scale, high-quality annotated data. However, collecting and annotating real-world pedestrian video datasets is time-consuming, costly, and often insufficient to cover rare and safety-critical scenarios. Recent world foundation models have demonstrated impressive capabilities in generating realistic videos, yet their suitability for safety-critical autonomous driving applications remains largely unexplored. In this work, we investigate whether current world foundation models can generate driving scenarios that are sufficiently realistic and behaviourally consistent for autonomous driving research. We conduct a case study centred on pedestrian–vehicle interactions captured from ego-vehicle dashcam viewpoints, where subtle behavioural and geometric errors can have significant safety implications. To support this investigation, we develop SynPeDAS, an open research framework comprising a collection of synthetic pedestrian-interaction videos, a reusable generation pipeline for transforming real-world driving footage into synthetic scenarios, an automated evaluation suite, and downstream demonstration code. Through quantitative evaluation and structured human assessment, we identify several recurring failure modes, including dynamic misalignment, depth drift, and object persistence inconsistencies. More importantly, we find that commonly used evaluation metrics frequently exhibit ceiling effects and weak alignment with human judgement, limiting their ability to detect safety-critical behavioural errors. These findings indicate that, despite high perceptual realism at the frame level, current generative world models and existing evaluation methodologies remain insufficient for capturing physically grounded motion and task-critical semantics. Consequently, significant challenges remain before world model-generated videos can be considered reliable for safety-critical autonomous driving applications. SynPeDAS provides an open platform for systematically studying these challenges and developing improved generation and evaluation methods. Full article

Joint statistical learning enables interacting individuals to form shared representations, but prior research has primarily focused on homogeneous dyads with equivalent expertise. Real-world interactions often involve knowledge asymmetries, yet it remains unclear how novices implicitly acquire statistical regularities from expert partners via sensorimotor signals. This study investigated whether novices can implicitly extract sequence regularities to enhance joint statistical learning and compared two candidate mechanisms, action feedback versus action visibility. Using a modified serial reaction time task across three experiments, we found that novices paired with trained experts exhibited significantly steeper declines in reaction time compared to those paired with pseudo-experts. Moreover, expert-paired novices demonstrated a pronounced quadratic trajectory, indicating sequence-specific learning. Experiment 2 revealed that the absence of immediate action feedback eliminated this sequence-specific interference effect in novices, highlighting the critical role of shared perceptual outcomes in the implicit transmission of task regularities. Conversely, Experiment 3 showed that the absence of visual access to the expert’s physical movements attenuated neither the novices’ general sequence acquisition nor their sequence-specific interference effect. These findings extend the Theory of Event Coding framework to asymmetric social contexts by demonstrating that effect-based coding, rather than direct kinematic observation, drives implicit behavioral facilitation in joint action. Full article