Search Results (25,126)

This study explored the impact of social conformity when participants encountered unanimous responses from bots to both objective and subjective questions. Seventy-two participants from Heidelberg University participated in a simulated “Quiz Show”, answering general knowledge and opinion-based questions on economic policy. Using a within-subject design, participants first responded independently, then saw answers from three bots modeled after Asch’s classic conformity studies, which were displayed with usernames and profile pictures generated by artificial intelligence. The results showed significant conformity for both objective and subjective questions, regardless of whether the bot responses aligned with or opposed the initial beliefs of the participants. Gender differences emerged, with women showing higher conformity rates, as well as conformity in objective and subjective contexts appeared to be driven by distinct personality traits. Full article

The 3D reconstruction of vessel hulls is crucial for enhancing safety, efficiency, and knowledge in the maritime industry. Neural Radiance Fields (NeRFs) are an alternative to 3D reconstruction and rendering from multi-view images; particularly, tensor-based methods have proven effective in improving efficiency. However, existing tensor-based methods typically suffer from a lack of spatial coherence, resulting in gaps in the reconstruction of fine-grained geometric structures. This paper proposes a spatial multi-scale weighted NeRF (MDW-NeRF) for accurate and efficient surface reconstruction of vessel hulls. The proposed method develops a novel multi-scale feature decomposition mechanism that models 3D space by leveraging multi-resolution features, facilitating the integration of high-resolution details with low-resolution regional information. We designed separate color and density weighting, using a coarse-to-fine strategy, for density and a weighted matrix for color to decouple feature vectors from appearance attributes. To boost the efficiency of 3D reconstruction and rendering, we implement a hybrid sampling point strategy for volume rendering, selecting sample points based on volumetric density. Extensive experiments on the SVH dataset confirm MDW-NeRF’s superiority: quantitatively, it outperforms TensoRF by 1.5 dB in PSNR and 6.1% in CD, and shrinks the model size by 9%, with comparable training times; qualitatively, it resolves tensor-based methods’ inherent spatial incoherence and fine-grained gaps, enabling accurate restoration of hull cavities and realistic surface texture rendering. These results validate our method’s effectiveness in achieving excellent rendering quality, high reconstruction accuracy, and timeliness. Full article

Construction on soft, highly compressible soils increasingly requires reliable ground improvement solutions. Among these, Rigid Inclusions (RIs) have emerged as one of the most efficient soil-reinforcement techniques. This paper synthesizes evidence from over 180 studies to provide a comprehensive state-of-the-art review of RI technology encompassing its governing mechanisms, design methodologies, and field performance. While the static behavior of RI systems has now been extensively studied and is supported by international design guidelines, the response under cyclic and seismic loading, particularly in liquefiable soils, remains less documented and subject to significant uncertainty. This review critically analyzes the degradation of key load-transfer mechanisms including soil arching, membrane tension, and interface shear transfer under repeated loading conditions. It further emphasizes the distinct role of RIs in liquefiable soils, where mitigation relies primarily on reinforcement and confinement rather than on drainage-driven mechanisms typical of granular columns. The evolution of design practice is traced from analytical formulations validated under static conditions toward advanced numerical and physical modeling frameworks suitable for dynamic loading. The lack of validated seismic design guidelines is high-lighted, and critical knowledge gaps are identified, underscoring the need for advanced numerical simulations and large-scale physical testing to support the future development of performance-based seismic design (PBSD) approaches for RI-improved ground. Full article

Five prevention is an important technical means to prevent maloperations in substations, and knowledge extraction from wiring diagrams is the key to intelligent “five prevention logic verification”. To address the error accumulation caused by multimodal object matching in traditional methods, this paper proposes a hierarchical recognition-based approach for topological knowledge extraction. This method establishes a multi-level recognition framework utilizing image tiling, decomposing the wiring diagram recognition task into three hierarchical levels from top to bottom: connection modes, bay types, and switching devices. A depth-first strategy is employed to establish parent–child node relationships, forming an initial topological structure. Based on the recognition results, the proposed approach performs regularized parsing and leverages a bay topology knowledge base to achieve automated matching of inter-device topological relationships. To enhance recognition accuracy, the model incorporates a Swin Transformer block to strengthen global feature perception and adds an ultra-small target detection layer to improve small-object recognition. The experimental results demonstrate that all recognition layers achieve mAP@0.5 exceeding 90%, with an overall precision of 93.9% and a recall rate of 91.7%, outperforming traditional matching algorithms and meeting the requirements for wiring diagram topology knowledge extraction. Full article

High-quality code representations are fundamental to code intelligence. Achieving such representations with parameter-efficient fine-tuning (PEFT) remains a key challenge. While code pre-trained models (CodePTMs) offer a robust foundation for general-purpose embeddings, current PEFT approaches face two main obstacles when adapting them: (i) they fail to adequately capture the deep structural characteristics of programs, and (ii) they are limited by the model’s finite internal parameters, restricting their ability to overcome inherent knowledge bottlenecks. To address these challenges, we introduce a parameter-efficient code representation learning framework that combines retrieval augmentation with structure-aware priors. Our framework features three complementary, lightweight modules: first, a structure–semantic dual-channel retrieval mechanism that infuses high-quality external code knowledge as non-parametric memory to alleviate the knowledge bottleneck; second, a graph relative bias module that strengthens the attention mechanism’s capacity to model structural relationships within programs; and third, a span-discriminative contrastive objective that sharpens the distinctiveness and boundary clarity of span-level representations. Extensive experiments on three benchmarks spanning six programming languages show that our method consistently outperforms state-of-the-art parameter-efficient baselines. Notably, on structure-sensitive tasks using the PLBART backbone, RS-Rep surpasses full fine-tuning, delivering a 22.1% improvement in Exact Match for code generation and a 4.4% increase in BLEU scores for code refinement, all while utilizing only about 5% of the trainable parameters. Full article

Accurate measurement of semantic similarity between geographic terms is a fundamental challenge in geographic information science, directly influencing tasks such as knowledge retrieval, ontology-based reasoning, and semantic search in geographic information systems (GIS). Traditional ontology-based approaches primarily rely on a narrow set of features (e.g., semantic distance or depth), which inadequately capture the multidimensional and context-dependent nature of geographic semantics. To address this limitation, this study proposes an ontology-driven semantic similarity model that integrates a backpropagation (BP) neural network with multiple ontological features—hierarchical depth, node distance, concept density, and relational overlap. The BP network serves as a nonlinear optimization mechanism that adaptively learns the contributions of each feature through cross-validation, balancing interpretability and precision. Experimental evaluations on the Geo-Terminology Relatedness Dataset (GTRD) demonstrate that the proposed model outperforms traditional baselines, including the Thesaurus–Lexical Relatedness Measure (TLRM), Word2Vec, and SBERT (Sentence-BERT), with Spearman correlation improvements of 4.2%, 74.8% and 80.1%, respectively. Additionally, comparisons with Linear Regression and Random Forest models, as well as bootstrap analysis and error analysis, confirm the robustness and generalization of the BP-based approach. These results confirm that coupling structured ontological knowledge with data-driven learning enhances robustness and generalization in semantic similarity computation, providing a unified framework for geographic knowledge reasoning, terminology harmonization, and ontology-based information retrieval. Full article

This paper proposes a PI-Dual-STGCN fault diagnosis model based on a SHAP-LLM joint explanation framework to address issues such as the lack of transparency in the diagnostic process of deep learning models and the weak interpretability of diagnostic results. PI-Dual-STGCN enhances the interpretability of graph data by introducing physical constraints and constructs a dual-graph architecture based on physical topology graphs and signal similarity graphs. The experimental results show that the dual-graph complementary architecture enhances diagnostic accuracy to 99.22%. Second, a general-purpose SHAP-LLM explanation framework is designed: Explainable AI (XAI) technology is used to analyze the decision logic of the diagnostic model and generate visual explanations, establishing a hierarchical knowledge base that includes performance metrics, explanation reliability, and fault experience. Retrieval-Augmented Generation (RAG) technology is innovatively combined to integrate model performance and Shapley Additive Explanations (SHAP) reliability assessment through the main report prompt, while the sub-report prompt enables detailed fault analysis and repair decision generation. Finally, experiments demonstrate that this approach avoids the uncertainty of directly using large models for fault diagnosis: we delegate all fault diagnosis tasks and core explainability tasks to more mature deep learning algorithms and XAI technology and only leverage the powerful textual reasoning capabilities of large models to process pre-quantified, fact-based textual information (e.g., model performance metrics, SHAP explanation results). This method enhances diagnostic transparency through XAI-generated visual and quantitative explanations of model decision logic while reducing the risk of large model hallucinations by restricting large models to reasoning over grounded, fact-based textual content rather than direct fault diagnosis, providing verifiable intelligent decision support for industrial fault diagnosis. Full article

Interactive science galleries have transformed how the public engages with science, shifting from object-centred displays to immersive, design-led experiences. This study situates these changes within broader cultural and economic contexts, exploring how design mediates our understanding of science and reflects neoliberal and experiential values. Using archival research, qualitative interviews with museum professionals, and reflective practice, the research examines the evolution of interactive science spaces at the Science Museum in London—The Children’s Gallery, Launch Pad, and Wonderlab. The findings reveal that exhibition design increasingly prioritises entertainment, immersion, and pleasure, aligning with the rise in the experience economy and the influence of corporate models such as Disneyland. While such strategies enhance visitor engagement and accessibility, they risk simplifying complex scientific narratives and reducing learning to consumption. The study concludes that effective science communication design should balance enjoyment with critical inquiry, using both comfort and discomfort to foster curiosity, reflection, and ethical awareness. By analysing design’s role in shaping the “science experience”, this research contributes to understanding how cultural institutions can create more nuanced, thought-provoking encounters between audiences, knowledge, and space. Full article

Plastic pollution poses severe threats to ecosystems, human health, and economies as plastics fragment into macro- and microplastics that accumulate across marine and terrestrial environments. Conventional monitoring is constrained by scale, cost, and resources, particularly in under-resourced regions, whereas citizen science provides an inclusive, community-driven alternative for data collection, analysis, and remediation to support evidence-based policy. This systematic review advances the field through three novel contributions: a refined participatory typology that explicitly prioritizes co-creative models for equitable engagement in the Global South; the first comprehensive synthesis of direct citizen involvement in plastic bioremediation, including community microbial isolation, household biodegradation trials, and real-world testing of biodegradable materials; and a new conceptual framework positioning citizen science as the central nexus linking upstream prevention, technological innovation, bioremediation, and global governance. Findings highlight large-scale geotagged datasets, behavioral change, and policy influence, while persistent challenges include data standardization, digital exclusion, and Global North bias. We therefore advocate institutional mainstreaming through dedicated policy offices, decolonial integration of indigenous knowledge, and hybrid citizen–lab validation pipelines, especially in underrepresented regions such as Africa, establishing citizen science as a transformative mechanism for participatory and equitable responses to escalating plastic pollution. Full article

The increasing application of lithium-ion batteries in manufacturing and energy storage systems necessitates high-precision screening of abnormal cells during manufacturing, so as to ensure safety and performance. Existing methods struggle to break down the barrier between prior knowledge and data, suffering from limitations such as insufficient detection accuracy and poor interpretability. This becomes even more prominent when facing distributional shifts in data. In this study, we propose a knowledge-enhanced anomaly detection framework for cell screening. This framework integrates domain knowledge, such as electrochemical principles, expert heuristic rules, and manufacturing constraints, into data-driven models. By combining features extracted from charging/discharging curves with rule-based prior knowledge, the proposed framework not only improves detection accuracy but also enables a traceable reasoning process behind anomaly identification. Experiments based on real-world battery production data demonstrate that the proposed framework outperforms baseline models in both precision and recall, making it a promising preferred solution for quality control in intelligent battery manufacturing. Full article

High-resolution climate projections are essential for regional risk assessment; however, Earth System Models (ESMs) operate at scales far too coarse for local impacts. This review examines how machine learning (ML) downscaling can bridge this divide and addresses a key knowledge gap: how to achieve reliable, physically consistent downscaling under future climate change. This article synthesizes ML downscaling developments from 2010 to 2025, spanning early statistical methods to modern deep learning (e.g., convolutional neural networks (CNNs), generative adversarial networks (GANs), diffusion models, and transformers). The analysis introduces a new taxonomy of model families and frames the discussion around the “performance paradox”—the tendency for models with excellent historical skill to falter under non-stationary climate shifts. Our analysis finds that convolutional approaches efficiently capture spatial structure but tend to smooth out extremes, whereas generative models better reproduce high-intensity events at the cost of greater complexity. The study also highlights emerging solutions like physics-informed models and improved uncertainty quantification to tackle persistent issues of physical consistency and trust. Finally, the synthesis outlines a practical roadmap for operational ML downscaling, emphasizing standardized evaluation, out-of-distribution stress tests, and hybrid physics–ML approaches to bolster confidence in future projections. Full article

Detailed geochemical modelling of the potential groundwater impacts of CO₂ geo-sequestration requires site-specific knowledge of how mobile elements are hosted within rocks. We present a simple sequential extraction procedure analogous to pH conditions produced by different partial pressures of carbon dioxide (CO₂) in contact with water. The procedure consists of three sequential steps: water at pH 7; acetic acid–ammonium acetate at pH 5 and then at pH 3, with the amounts of specific elements extracted by each step considered with respect to the whole rock total element abundance. Our purpose in developing this procedure is three-fold: (1) identify readily mobilized suites of elements for groundwater baseline and monitor bore studies; (2) provide insights regarding the mode/s of occurrence of easily extracted elements within rock samples; and (3) suggest possible mechanisms for the mobilization of rock-sourced elements into groundwater under neutral to moderately acidic pH that can inform the reactive transport modelling of carbon storage sites. In our case study, the second step extracted most of the main mobile elements of interest. Full article

Metaphor is ubiquitous in daily communication and makes language expression more vivid. Identifying metaphorical words, known as metaphor detection, is crucial for capturing the real meaning of a sentence. As an important step of metaphorical understanding, the correct interpretation of metaphorical words directly affects metaphor detection. This article investigates how to use metaphor interpretation to enhance metaphor detection. Since previous approaches for metaphor interpretation are coarse-grained or constrained by ambiguous meanings of substitute words, we propose a different interpretation mechanism that explains metaphorical words by means of gloss-based interpretations. To comprehensively explore the optimal joint strategy, we go beyond previous work by designing diverse model architectures. We investigate both classification and sequence labeling paradigms, incorporating distinct component designs based on MIP and SPV theories. Furthermore, we integrate Part-of-Speech tags and external knowledge to further refine the feature representation. All methods utilize pre-trained language models to encode text and capture semantic information of the text. Since this mechanism involves both metaphor detection and metaphor interpretation but there is a lack of datasets annotated for both tasks, we have enhanced three datasets with glosses for metaphor detection: one Chinese dataset (PSUCMC) and two English datasets (TroFi and VUA). Experimental results demonstrate that the proposed joint methods are superior to or at least comparable to state-of-the-art methods on the three enhanced datasets. Results confirm that joint learning of metaphor detection and gloss-based interpretation makes metaphor detection more accurate. Full article

Diagnostic errors have been a critical concern in healthcare, leading to substantial financial burdens and serious threats to patient safety. The Improving Diagnosis in Health Care report by the National Academies of Sciences, Engineering, and Medicine (NASEM) defines diagnostic errors, focusing on accuracy, timeliness, and communication, which are influenced by clinical knowledge and the broader healthcare system. This review aims to integrate existing literature on diagnostic error from a systems-based perspective and examine the factors across various domains to present a comprehensive picture of the topic. A narrative literature review was structured upon the Systems Engineering Initiative for Patient Safety (SEIPS) model that focuses on six domains central to the diagnostic process: Diagnostic Team Members, Tasks, Technologies and Tools, Organization, Physical Environment, and External Environment. Studies on contributing factors for diagnostic error in these domains were identified and integrated. The findings reveal that the effectiveness of diagnostics is influenced by complex, interconnected factors spanning all six SEIPS domains. In particular, socio-behavioral factors, such as team communication, cognitive bias, and workload, and environmental pressures, stand out as significant but difficult-to-capture contributors in traditional and commonly used data resources like electronic health records (EHRs), which limits the scope of many studies on diagnostic errors. Factors associated with diagnostic errors are often interconnected across healthcare system stakeholders and organizations. Future research should address both technical and behavioral elements within the diagnostic ecosystem to reduce errors and enhance patient outcomes. Full article

This study investigates regional heterogeneity and spatial interdependence in digital skills mismatch across Indonesia by constructing a Digital Skills Supply–Demand Ratio (DSSDR) from the Indonesia Digital Society Index (IMDI). In line with SDG 10 (Reduced Inequalities) and SDG 4 (Quality Education), the study aims to provide policy-relevant evidence to support a more inclusive and balanced digital transformation. Using district-level data and spatial econometric models (OLS, SAR, and the SDM), the analysis evaluates both local determinants and cross-regional spillover effects. Model comparison identifies the Spatial Durbin Model as the best specification, revealing strong spatial dependence in digital skills imbalance. The results show that most local socioeconomic and digital readiness indicators do not have significant direct effects on DSSDR, while school internet coverage exhibits a consistently negative association, indicating that digital demand expands faster than local supply. In contrast, spatial spillovers are decisive: a higher share of ICT study programs in neighboring regions improves local DSSDR through knowledge and human-capital diffusion, whereas higher GRDP per capita in adjacent regions exacerbates local mismatch, consistent with a talent-attraction mechanism. These findings demonstrate that digital skills mismatch is a spatially interconnected phenomenon driven more by interregional dynamics than by local conditions alone, implying that policy responses should move beyond isolated district-level interventions toward coordinated regional strategies integrating education systems, labor markets, and digital ecosystem development. The study contributes a spatially explicit, supply–demand-based framework for diagnosing regional digital inequality and supporting more equitable and sustainable digital development in Indonesia. Full article