Search Results (1,854)

Automata and artificial intelligence (AI) have long occupied a central place in cultural and artistic imagination, and the recent proliferation of AI-generated artworks has intensified debates about authorship, creativity, and human agency. Empirical studies show that audiences often perceive AI-generated works as less authentic or emotionally resonant than human creations, with authorship attribution strongly shaping esthetic judgments. Yet little attention has been paid to how AI systems themselves evaluate creative authorship. This study investigates how large language models (LLMs) evaluate literary quality under different framings of authorship—Human, AI, or Human+AI collaboration. Using a questionnaire-based experimental design, we prompted four instruction-tuned LLMs (ChatGPT 4, Gemini 2, Gemma 3, and LLaMA 3) to read and assess three short stories in Italian, originally generated by ChatGPT 4 in the narrative style of Roald Dahl. For each story × authorship condition × model combination, we collected 100 questionnaire completions, yielding 3600 responses in total. Across esthetic, literary, and inclusiveness dimensions, the stated authorship systematically conditioned model judgments: identical stories were consistently rated more favorably when framed as human-authored or human–AI co-authored than when labeled as AI-authored, revealing a robust negative bias toward AI authorship. Model-specific analyses further indicate distinctive evaluative profiles and inclusiveness thresholds across proprietary and open-source systems. Our findings extend research on attribution bias into the computational realm, showing that LLM-based evaluations reproduce human-like assumptions about creative agency and literary value. We publicly release all materials to facilitate transparency and future comparative work on AI-mediated literary evaluation. Full article

Unstructured POI name texts are widely used in fine-grained urban analysis, yet missing labels and semantic ambiguity often limit their value for spatial inference. This study proposes a large language model-based semantic–spatial inference framework (LLM-SSIF), a lightweight semantic–spatial pipeline that translates POI texts into interpretable, fine-grained spatial evidence through an end-to-end workflow that couples scalable label expansion with scale-controlled spatial diagnostics at a 500 m resolution. A key advantage of LLM-SSIF is its deployability: LoRA-based parameter-efficient fine-tuning of an open LLM enables lightweight adaptation under limited compute while scaling fine-label coverage. Trained on a nationwide cuisine-labeled dataset (~220,000 records), the model achieves strong multi-class short-text recognition (macro-F1 = 0.843) and, in the Guangzhou–Shenzhen demonstration, expands usable fine-category labels by ~14–15× to support grid-level inference under long-tail sparsity. The spatial module then isolates cuisine-specific over/under-representation beyond overall restaurant intensity, revealing contrasting cultural configurations between Guangzhou and Shenzhen. Overall, LLM-SSIF provides a reproducible and transferable way to translate unstructured POI texts into spatial–statistical evidence for comparative urban analysis. Full article

Background/Objectives: Accurate identification of dental malocclusions from routine clinical photographs can be time-consuming and subject to interobserver variability. A YOLOv11-based deep learning approach is presented and evaluated for automatic malocclusion detection on routine intraoral photographs, testing the hypothesis that training on a structured annotation protocol enables reliable detection of multiple clinically relevant malocclusions. Methods: An anonymized dataset of 5854 intraoral photographs (frontal occlusion; right/left buccal; maxillary/mandibular occlusal) was labeled according to standardized instructions derived from the Index of Orthodontic Treatment Need (IOTN) A total of 17 clinically relevant classes were annotated with bounding boxes. Due to an insufficient number of examples, two malocclusions (transposition and non-occlusion) were excluded from our quantitative analysis. A YOLOv11 model was trained with augmented data and evaluated on a held-out test set using mean average precision at IoU 0.5 (mAP50), macro precision (macro-P), and macro recall (macro-R). Results: Across 15 analyzed classes, the model achieved 87.8% mAP50, 76.9% macro-P, and 86.1% macro-R. The highest per-class AP₅₀ was observed for Deep bite (98.8%), Diastema (97.9%), Angle Class II canine (97.5%), Anterior open bite (92.8%), Midline shift (91.8%), Angle Class II molar (91.1%), Spacing (91%), and Crowding (90.1%). Moderate performance included Anterior crossbite (88.3%), Angle Class III molar (87.4%), Head bite (82.7%), and Posterior open bite (80.2%). Lower values were seen for Angle Class III canine (76%), Posterior crossbite (75.6%), and Big overjet (75.3%). Precision–recall trends indicate earlier precision drop-off for posterior/transverse classes and comparatively more missed detections in Posterior crossbite, whereas Big overjet exhibited more false positives at the chosen threshold. Conclusion: A YOLOv11-based deep learning system can accurately detect several clinically salient malocclusions on routine intraoral photographs, supporting efficient screening and standardized documentation. Performance gaps align with limited examples and visualization constraints in posterior regions. Larger, multi-center datasets, protocol standardization, quantitative metrics, and multimodal inputs may further improve robustness. Full article

Background and Objectives: This study evaluates the safety, tolerability, and efficacy of preservative-free Dorzolamide 2%-Timolol 0.5% (PF-DT), with a focus on improving the ocular microenvironment in a real-world transition setting. Materials and Methods: A prospective, multicenter, open-label study involving thirty patients with dry eye disease previously treated with BAK-DT was conducted. Participants were transitioned to PF-DT, and evaluated at weeks 4, 12, and 24. The primary endpoint was the Ocular Surface Disease Index (OSDI) score. Secondary outcomes included Break-Up Time (BUT), Schirmer test results, corneal staining, conjunctival hyperemia, intraocular pressure (IOP), and patient satisfaction. Results: Twenty-five patients completed the study. The OSDI improved from 21.5 to 12.5 (p < 0.001), with 60.0% of patients showing improvement and 52.0% achieving complete symptom resolution. Among eyes with corneal staining, 78.4% demonstrated a reduction of at least one grade, and 50.0% of those with conjunctival redness showed similar improvement. By week 24, 78.0% exhibited no corneal staining, and 50.0% had no conjunctival redness. BUT increased from 5.0 to 7.0 (p < 0.01), while IOP decreased by 1 mmHg (p < 0.01). Satisfaction regarding comfort (≥80%) and handling (≥50%) was high, with 88.0% preferring PF-DT. Conclusions: Transitioning to PF-DT improved ocular surface health while maintaining IOP control, supporting the benefits of preservative-free formulations in restoring microenvironment homeostasis and enhancing tolerability and patient satisfaction. Full article

Mobile edge-AI plant monitoring systems enable automated disease control in greenhouses and open fields, reducing dependence on manual inspection and the variability of visual diagnostics. This paper proposes a lightweight two-stage edge-AI system for strawberries, in which a YOLOv10n detector on board a mobile agricultural robot locates leaves affected by seven common diseases (including Leaf Spot) with real-time capability on an embedded platform. Patches are then automatically extracted for leaves classified as Leaf Spot and transmitted to the second module—a compact MobileViT-S-based classifier with ordinal output that assesses the severity of Leaf Spot on three levels (S1—mild, S2—moderate, S3—severe) on a specialised set of 373 manually labelled leaf patches. In a comparative experiment with lightweight architectures ResNet-18, EfficientNet-B0, MobileNetV3-Small and Swin-Tiny, the proposed Ordinal MobileViT-S demonstrated the highest accuracy in assessing the severity of Leaf Spot (accuracy ≈ 0.97 with 4.9 million parameters), surpassing both the baseline models and the standard MobileViT-S with a cross-entropy loss function. On the original image set, the YOLOv10n detector achieves an mAP@0.5 of 0.960, an F1 score of 0.93 and a recall of 0.917, ensuring reliable detection of affected leaves for subsequent Leaf Spot severity assessment. The results show that the “YOLOv10n + Ordinal MobileViT-S” cascade provides practical severity-aware Leaf Spot diagnosis on a mobile agricultural robot and can serve as the basis for real-time strawberry crop health monitoring systems. Full article

Midline shift (MLS) is one of the conditions that strongly affects mortality and prognosis in critical neurological emergencies such as traumatic brain injury (TBI). Especially, MLS over 5 mm requires urgent diagnosis and treatment. Despite widespread tomography imaging capabilities, the lack of radiologists capable of interpreting the images causes delays in the diagnosis process. Therefore, there is a need for AI-supported diagnostic systems specifically tailored to the field for MLS detection. However, the lack of open, disorder-specific datasets in the literature has limited research in the field and hindered the ability to make comparisons against a reliable reference point. Therefore, the current state of deep learning (DL) methods in the field is not sufficiently addressed. Within the scope of this study, a DL architecture is proposed for MLS detection as a classification task, with millimeter-scale MLS measurements used for evaluation and stratified analysis. This process also comprehensively addresses the status of MLS detection in contemporary DL architecture. Furthermore, to address the lack of open datasets in the literature, two publicly available datasets originally collected with a primary focus on TBI have been annotated for MLS detection. The proposed model was tested on two different open datasets and achieved mean sensitivity values of 0.9467–0.9600 for the Radiological Society of North America (RSNA) dataset and 0.8623–0.8984 for the CQ500 dataset in detecting MLS presence above 5 mm across two different scenarios. It achieved a mean Area Under the Curve-Receiver Operating Characteristic (AUC-ROC) value of 0.9219–0.9816 for the RSNA dataset and 0.9443–0.9690 for the CQ500 dataset. The aim of the study is to detect not only emergency cases but also small MLSs independent of quantity for patient follow-up, so the overall performance of the proposed model (MLS present/absent) was calculated without an MLS quantity threshold. Mean F1 Score values of 0.7403 for the RSNA dataset and 0.7271 for the CQ500 dataset were obtained, along with mean AUC-ROC values of 0.8941 for the RSNA dataset and 0.9301 for the CQ500 dataset. The study presents a clinically applicable, optimized, fast, reliable, up-to-date, and successful DL solution for the rapid diagnosis of MLS, intervention in emergencies, and monitoring of small MLS. It also contributes to the literature by enabling a high level of reproducibility in the scientific community with labeled open data. Full article

Mobile augmented reality games (MARGs) generate rich digital traces of how students engage with complex, place-based learning tasks. This study analyses gameplay logs from the Art Nouveau Path, a location-based MARG within the EduCITY Digital Teaching and Learning Ecosystem (DTLE), to develop a learning analytics workflow that uses detailed gameplay logs to inform sustainability-focused educational design. During the post-game segment of a repeated cross-sectional intervention, 439 students in 118 collaborative groups completed 36 quiz tasks at 8 Art Nouveau heritage Points of Interest (POI). Group-level logs (4248 group-item responses) capturing correctness, AR-specific scores, session duration and pacing were transformed into interpretable indicators, combined with error mapping and cluster analysis, and triangulated with post-game open-ended reflections. Results show high overall feasibility (mean accuracy 85.33%) and a small subset of six conceptually demanding items with lower accuracy (mean 68.36%, range 58.47% to 72.88%) concentrated in specific path segments and media types. Cluster analysis yields three collaborative gameplay profiles, labeled ‘fast but fragile’, ‘slow but moderate’ and ‘thorough and successful’, which differ systematically in accuracy, pacing and engagement with AR-mediated tasks. The study proposes a replicable event-based workflow that links mobile AR gameplay logs to design decisions for heritage-based education for sustainability. Full article

Synthetic aperture radar (SAR), with its unique imaging principle and technical characteristics, has significant advantages in surface observation and thus has been widely applied in tasks such as object detection and target classification. However, limited by the lack of labeled SAR image datasets, the accuracy and generalization ability of the existing models in practical applications still need to be improved. In order to solve this problem, this paper proposes a spaceborne SAR image simulation technology and innovatively introduces the concept of bounce number map (BNM), establishing a high-resolution, parameterized simulated data support system for target recognition and classification tasks. In addition, an electromagnetic scattering characteristic-enhanced dual-branch network with simulated image guidance for SAR ship classification (SeDSG) was designed in this paper. It adopts a multi-source data utilization strategy, taking SAR images as the main branch input to capture the global features of real scenes, and using simulated data as the auxiliary branch input to excavate the electromagnetic scattering characteristics and detailed structural features. Through feature fusion, the advantages of the two branches are integrated to improve the adaptability and stability of the model to complex scenes. Experimental results show that the classification accuracy of the proposed network is improved on the OpenSARShip and FUSAR-Ship datasets. Meanwhile, the transfer learning classification results based on the SRSDD dataset verify the enhanced generalization and adaptive capabilities of the network, providing a new approach for data classification tasks with an insufficient number of samples. Full article

To address the limitations of conventional social force models in simulating high-density pedestrian crowds, this study proposes an enhanced model that incorporates visual perception constraints, group-type labeling, and collective avoidance mechanisms. Pedestrian trajectories were extracted from a bidirectional commercial street scenario using OpenCV, with YOLOv8 and DeepSORT employed for multiple object tracking. Analysis of pedestrian grouping patterns revealed that 52% of pedestrians walked in pairs, with distinct avoidance behaviors observed. The improved model integrates three key mechanisms: a restricted 120° forward visual field, group-type classification based on social relationships, and an exponentially formulated inter-group repulsive force. Simulation results in MATLAB R2023b demonstrate that the proposed model outperforms conventional approaches in multiple aspects: speed distribution (error < 8%); spatial density overlap (>85%); trajectory similarity (reduction of 32% in Dynamic Time Warping distance); and avoidance behavior accuracy (82% simulated vs. 85% measured). This model serves as a quantitative simulation tool and decision-making basis for the planning of pedestrian spaces, crowd organization management, and the optimization of emergency evacuation schemes in high-density pedestrian areas such as commercial streets and subway stations. Consequently, it contributes to enhancing pedestrian mobility efficiency and public safety, thereby supporting the development of a sustainable urban slow transportation system. Full article

Background: Tumor necrosis factor-α (TNFα) inhibitors have significantly improved outcomes in children with non-systemic juvenile idiopathic arthritis (JIA), achieving long-term clinical remission for many patients. However, the optimal strategy for TNF-α inhibitor withdrawal remains unknown, whether through abrupt discontinuation, gradual dose reduction, or interval extension. Objective: We aim to identify patient-, disease-, and treatment-related predictors of successful TNF-α inhibitor withdrawal in children with non-systemic JIA. Methods: In this prospective, randomized, open-label, single-center study, 76 children with non-systemic JIA in stable remission for ≥24 months on etanercept or adalimumab were enrolled. At the time of TNF-α inhibitor discontinuation, all patients underwent a comprehensive evaluation, including a clinical examination, laboratory tests (serum calprotectin [S100 proteins] and high-sensitivity C-reactive protein [hsCRP]), and advanced joint imaging (musculoskeletal ultrasound and magnetic resonance imaging [MRI]) to assess subclinical disease activity. Patients were randomized (1:1:1, sealed-envelope allocation) to one of three predefined tapering strategies: (I) abrupt discontinuation; (II) extension of dosing intervals (etanercept 0.8 mg/kg every 2 weeks; adalimumab 24 mg/m² every 4 weeks); or (III) gradual dose reduction (etanercept 0.4 mg/kg weekly; adalimumab 12 mg/m² every 2 weeks). Follow-up visits were scheduled at 3, 6, 9, 12, and 18 months to monitor for disease relapse. Results: Higher baseline Childhood Health Assessment Questionnaire (CHAQ) scores (≥2), elevated serum calprotectin [S100 proteins] and hsCRP levels at withdrawal, imaging evidence of subclinical synovitis, and a history of uveitis were all significantly associated with increased risk of flare. No significant associations were found for other clinical or demographic characteristics. Conclusions: Early significant clinical response, absence of subclinical disease activity, and concomitant low-dose methotrexate therapy were key predictors of sustained drug-free remission. These findings may inform personalized strategies for biologic tapering in pediatric JIA. Full article

Digital twin technology is widely promoted as a transformative step for precision livestock farming, yet no fully realized, engineering-grade digital twins are deployed in commercial dairy or poultry systems today. This work establishes the current state of knowledge on dairy and poultry digital twins by synthesizing evidence through systematic database searches, thematic evidence mapping and critical analysis of validation gaps, carbon accounting and adoption barriers. Existing platforms are better described as near-digital-twin systems with partial sensing and modelling, digital-twin-inspired prototypes, simulation frameworks or decision-support tools that are often labelled as twins despite lacking continuous synchronization and closed-loop control. This distinction matters because the empirical foundation supporting many claims remains limited. Three critical gaps emerge: life-cycle carbon impacts of digital infrastructures are rarely quantified even as sustainability benefits are frequently asserted; field-validated improvements in feed efficiency, particularly in poultry feed conversion ratios, are scarce and inconsistent; and systematic reporting of failure rates, downtime and technology abandonment is almost absent, leaving uncertainties about long-term reliability. Adoption barriers persist across technical, economic and social dimensions, including rural connectivity limitations, sensor durability challenges, capital and operating costs, and farmer concerns regarding data rights, transparency and trust. Progress for cows and chickens will require rigorous validation in commercial environments, integration of mechanistic and statistical modelling, open and modular architectures and governance structures that support biological, economic and environmental accountability whilst ensuring that system intelligence is worth its material and energy cost. Full article

Remote sensing image semantic segmentation (RSISS) aims to assign a correct class label to each pixel in remote sensing images and has wide applications. With the development of artificial intelligence, RSISS based on deep learning has made significant progress. However, existing methods remain more focused on predefined semantic classes and require costly retraining when confronted with new classes. To address this limitation, we propose the hierarchical guidance open-vocabulary semantic segmentation framework for remote sensing images (named HG-RSOVSSeg), enabling flexible segmentation of arbitrary semantic classes without model retraining. Our framework leverages pretrained text-embedding models to provide class common knowledge and aligns multimodal features through a dual-stream architecture. Specifically, we propose a multimodal feature aggregation module for pixel-level alignment and a hierarchical visual feature decoder guided by text feature alignment, which progressively refines visual features using language priors, preserving semantic coherence during high-resolution decoding. Extensive experiments were conducted on six representative public datasets, and the results showed that our method has the highest mean mIoU value, establishing state-of-the-art performance in the field of open-vocabulary semantic segmentation of remote sensing images. Full article

Foreign object intrusion severely threatens railway safety. Existing methods struggle with open-set categories, high annotation costs, and poor label-efficient generalization. To address these issues, we propose UG-Net, an unsupervised-guided label-efficient detection framework. The core idea is a two-stage strategy: first, a masked autoencoder (MAE) learns “normality” priors from unlabeled data and generates a spatial attention mask via a deep feature difference strategy; then, this mask is fused as a fourth channel into a lightweight YOLOv8n detector. This approach effectively alleviates reliance on manual annotations. On a self-constructed railway dataset, UG-Net achieved 94.56% mAP@0.5 using only 200 labeled samples, significantly outperforming the YOLOv8n baseline (86.91%). The framework provides a label-efficient solution for industrial anomaly detection. Full article

Agroecology is a long-term solution for changing agri-food systems as climate change and food security problems become worse. In North Africa, especially Algeria, this change needs a profound understanding of how people feel and act toward food that is grown in an environmentally friendly way. This study looks at what Algerian consumers know, how much they are ready to pay (WTP), and how their social and demographic factors affect their attitudes toward agroecological products and practices. A principal component analysis (PCA) and multiple linear regression have been used on 552 responses from a nationally representative sample collected as part of the NATAE Horizon Europe project to find the psychological and structural factors that affect sustainable consumption. The results show that age, education, job level, and living in a city have a big effect on how aware and open-minded consumers are. People over 45 who have more education and a better job are more likely to care about the environment and be willing to spend more on eco-friendly products, notably, olive oil, fruits, and vegetables. People still do not know much about it, though, and WTP differs by product category. This case study shows how important it is to have targeted education and labelling regulations to fill in knowledge gaps and get people more involved in agroecological changes in Algeria. Full article

Background: The traditional formula Liqi Yangyin (LQYY) has shown clinical and preclinical efficacy for depression with constipation, yet its molecular mechanisms remain incompletely defined. This study aimed to elucidate its mechanisms using an integrative approach. Methods: Constituents of LQYY were profiled by UPLC-MS/MS and integrated with network pharmacology and molecular docking to identify brain-accessible components and putative targets. A chronic unpredictable mild stress (CUMS) model was used for experimental validation. Outcomes included behavioral tests (sucrose preference test, open field test, and forced swimming test), gastrointestinal indices, including fecal water content, time of first black stool, and intestinal propulsion rate, histopathology of the prefrontal cortex (PFC) and colon, TUNEL staining, NeuN immunofluorescence, Western blotting, and qRT-PCR. Results: LQYY attenuated CUMS-induced weight loss and depressive-like behaviors and improved intestinal transit metrics. It reduced neuronal apoptosis in the PFC and ameliorated colonic injury. Mechanistically, docking and enrichment analyses highlighted hub targets (STAT3, AKT1, ESR1, IL-6, TNF, TP53) and the JAK/STAT pathway. In vivo, LQYY decreased IL-6, TNF-α, ESR1, TP53, and STAT3, and increased AKT1 in the PFC and colon; it also reduced the TUNEL-positive rate and restored NeuN labeling, upregulated Bcl-2, and downregulated p-JAK2/JAK2 and p-STAT3/STAT3 ratios, and the expression of Bax and cleaved-caspase-3 in the PFC, consistent with the suppression of pro-inflammatory and apoptotic signaling. Conclusions: LQYY exerts antidepressant and pro-motility effects in CUMS mice by modulating JAK2/STAT3-centered networks and inhibiting neuronal apoptosis, thus supporting a multi-component, multi-target strategy for treating depression with constipation, and providing a defined molecular hypothesis for future investigation. Full article