Search Results (921)

Ontology learning from unstructured text has become a critical task for knowledge-driven applications in Big Data and Artificial Intelligence. While significant advances have been made in the automatic extraction of concepts and relations using neural and Transformer-based models, the generation of formal Description Logic axioms required for constructing logically consistent and computationally tractable ontologies remains largely underexplored. This paper puts forward a novel pipeline for automated axiom generation through schema mapping. Our paper introduces three key innovations: a deterministic mapping framework that guarantees logical consistency (unlike stochastic Large Language Models); guaranteed formal consistency verified by OWL reasoners (unaddressed by prior statistical methods); and a transparent, scalable bridge from neural extractions to symbolic logic, eliminating manual post-processing. Technically, the pipeline builds upon the outputs of a Transformer-based fusion model for joint concept and relation extraction. We then map lexical relational phrases to formal ontological properties through a lemmatization-based schema alignment step. Entity typing and hierarchical induction are then employed to infer class structures, as well as domain and range constraints. Using RDFLib and structured data processing, we transform the extracted triples into both assertional (ABox) and terminological (TBox) axioms expressed in Description Logic. Experimental evaluation on benchmark datasets (Conll04 and NYT) demonstrates the efficacy of the approach, with expert validation showing high acceptance rates (>95%) and reasoners confirming zero inconsistencies. The pipeline thus establishes a reliable, scalable foundation for automated ontology learning, advancing the field from extraction to formally verifiable knowledge base construction. Full article

This study applies a modality-bridging framework to automatically construct Chain-of-Thought (CoT) reasoning from meteorological images, reducing the need for expert annotation. The proposed pipeline integrates semantic extraction, Pseudo-CoT generation, and logical fusion to produce structured reasoning chains. Using the WeatherQA benchmark, we build datasets under single-image, 3-image, and 20-image settings—with automated and Expert-Guided variants—and evaluate performance on Areas Affected and Conditional Concern tasks. The results show near-expert spatial reasoning and more compact, well-aligned CoTs with reduced-image inputs. Multi-image settings reveal challenges in integrating dense visual cues, while semantic classification remains difficult due to label ambiguity. Overall, modality-bridging offers a scalable, interpretable, and low-cost approach for multimodal meteorological reasoning. Full article

Large Language Models (LLMs) have demonstrated impressive capabilities in structured reasoning and symbolic tasks, with coding emerging as a particularly successful application. This progress has naturally motivated efforts to extend these models to mathematics, both in its traditional form, expressed through natural-style mathematical language, and in its formalized counterpart, expressed in a symbolic syntax suitable for automatic verification. Yet, despite apparent parallels between programming and proof construction, advances in formalized mathematics have proven significantly more challenging. This gap raises fundamental questions about the nature of reasoning in current LLM architectures, the role of supervision and feedback, and the extent to which such models maintain an internal notion of computational or deductive state. In this article, we review the current state-of-the-art in mathematical reasoning with LLMs, focusing on recent models and benchmarks. We explore three central issues at the intersection of machine learning and mathematical cognition: (i) the trade-offs between traditional and formalized mathematics as training and evaluation domains; (ii) the structural and methodological reasons why proof synthesis remains more brittle than code generation; and (iii) whether LLMs genuinely represent or merely emulate a notion of evolving logical state. Our goal is not to draw rigid distinctions but to clarify the present boundaries of these systems and outline promising directions for their extension. Full article

Automatically generated chains-of-thought (gCoTs) have become common as large language models adopt deliberative behaviors. Prior work emphasizes fidelity to internal processes, leaving explanatory properties underexplored. Our central hypothesis is that these traces, produced by highly capable reasoning models, are not arbitrary by-products of decoding but exhibit stable and practically valuable textual properties beyond answer fidelity. We apply a multidimensional text-evaluation framework that quantifies four axes—structural coherence, logical–factual consistency, linguistic clarity, and coverage/informativeness—that are standard dimensions for assessing textual quality, and use it to evaluate five reasoning models on the GSM8K arithmetic word-problem benchmark (~1.3 k–1.4 k items) with reproducible, normalized metrics. Logical verification shows near-ceiling self-consistency, measured by the Aggregate Consistency Score (ACS ≈ 0.95–1.00), and high final-answer entailment, measured by Final Answer Soundness (FAS0 ≈ 0.85–1.00); when sound, justifications are compact, with Justification Set Size (JSS ≈ 0.51–0.57) and moderate redundancy, measured by the Redundant Constraint Ratio (RCR ≈ 0.62–0.70). Results also show consistent coherence and clarity; from gCoT to answer implication is stricter than from question to gCoT support, indicating chains anchored to the prompt. We find no systematic trade-off between clarity and informativeness (within-model slopes ≈ 0). In addition to these automatic and logic-based metrics, we include an exploratory expert rating of a subset (four raters; 50 items × five models) to contextualize model differences; these human judgments are not intended to support dataset-wide generalization. Overall, gCoTs display explanatory value beyond fidelity, primarily supported by the automated and logic-based analyses, motivating hybrid evaluation (automatic + exploratory human) to map convergence/divergence zones for user-facing applications. Full article

Kidding in goats is a highly significant event with major economic implications and strong impacts on the welfare of both the offspring and the mothers. Monitoring the process is extremely demanding, as it is impossible to predict precisely when it will occur. For this reason, the automatic detection of kidding has the potential to generate substantial productivity gains while also improving animal well-being. Artificial intelligence techniques based on accelerometry data have been explored for identifying the event, but these approaches typically rely on data loggers, which cannot trigger real-time alerts or assistance. Embedding detection mechanisms directly into wearable devices enables much faster identification and supports energy-efficient operations. However, this approach also introduces considerable challenges, particularly due to the strict constraints of wearable devices in terms of weight, cost, and battery life. The present work documents the development of a real-time, automatic kidding-detection mechanism in which the detection workload is distributed between the collar and an edge device. System evaluation demonstrated the feasibility of this distributed architecture, confirming that both components can cooperate effectively to achieve reliable detection. The system achieved a Matthews Correlation Coefficient performance of 0.91, highlighting the robustness and practical viability of the proposed solution. Full article

At present, fruit picking mainly relies on manual operation. Taking the litchi (litchi chinensis Sonn.)-picking robot as an example, visual perception is often affected by illumination variations, low recognition accuracy, complex maturity judgment, and occlusion, which lead to inaccurate fruit localization. This study aims to establish an embodied perception mechanism based on “perception-reasoning-execution” to enhance the visual perception and decision-making capability of the robot in complex orchard environments. First, a Y-LitchiC instance segmentation method is proposed to achieve high-precision segmentation of litchi clusters. Second, a generative artificial intelligence model is introduced to intelligently assess fruit maturity and occlusion, providing auxiliary support for automatic picking. Based on the auxiliary judgments provided by the generative AI model, two types of dynamic harvesting decisions are formulated for subsequent operations. For unoccluded main fruit-bearing branches, a skeleton thinning algorithm is applied within the segmented region to extract the skeleton line, and the midpoint of the skeleton is used to perform the first type of localization and harvesting decision. In contrast, for main fruit-bearing branches occluded by leaves, threshold-based segmentation combined with maximum connected component extraction is employed to obtain the target region, followed by skeleton thinning, thereby completing the second type of dynamic picking decision. Experimental results show that the Y-LitchiC model improves the mean average precision (mAP) by 1.6% compared with the YOLOv11s-seg model, achieving higher accuracy in litchi cluster segmentation and recognition. The generative artificial intelligence model provides higher-level reasoning and decision-making capabilities for automatic picking. Overall, the proposed embodied perception mechanism and dynamic picking strategies effectively enhance the autonomous perception and decision-making of the picking robot in complex orchard environments, providing a reliable theoretical basis and technical support for accurate fruit localization and precision picking. Full article

About 16% of typhoons making landfall in China strike Hainan Island, where near-surface extreme winds in dense urban areas exhibit a strong spatiotemporal heterogeneity that is difficult to capture with current observations and mesoscale models. Focusing on Haikou during Super Typhoon Yagi (2024)—the strongest autumn typhoon to hit China since 1949—we developed a multiscale ERA5–WRF–PALM framework to conduct 30 m resolution large-eddy simulations. PALM results are in reasonable agreement with most of the five automatic weather stations, while performance is weaker at the most sheltered park site. Mean near-surface wind speeds increased by 20–50% relative to normal conditions, showing a coastal–urban gradient: maps of weighted cumulative exposure to strong winds (≥Beaufort force 8) show much longer and more intense events along open coasts than within built-up urban cores. Urban morphology exerted nonlinear effects: wind speeds followed a U-shaped relation with both the open-space ratio and mean building height, with suppression zones at ~0.5–0.7 openness and ~20–40 m height, while clusters of super-tall buildings induced Venturi-like acceleration of 2–3 m s⁻¹. Spatiotemporal analysis revealed banded swaths of high winds, with open areas and islands sustaining longer, broader extremes, and dense street grids experiencing shorter, localized events. Methodologically, this study provides a rare, systematically evaluated application of a multiscale ERA5–WRF–PALM framework to a real typhoon case at 30 m resolution in a tropical coastal city. These findings clarify typhoon–city interactions, quantify morphological regulation of extreme winds, and support risk assessment, urban planning, and wind-resilient design in coastal megacities. Full article

Objectives: To benchmark the performance of DeepSeek-R1 against three other advanced AI reasoning models (GPT-4o, Qwen3, Grok-3) in automatically extracting T/N staging from esophageal cancer endoscopic ultrasound (EUS) complex medical reports, and to evaluate the impact of language (Chinese/English) and prompting strategy (with/without designed prompt) on model accuracy and robustness. Methods: We retrospectively analyzed 625 EUS reports for T-staging and 579 for N-staging, which were collected from 663 patients at the Sun Yat-sen University Cancer Center between 2018 and 2020. A 2 × 2 factorial design (Language × Prompt) was employed under a zero-shot setting. The performance of the models was evaluated using accuracy, and the odds ratio (OR) was calculated to quantify the comparative performance advantage between models across different scenarios. Results: Performance was evaluated across four scenarios: (1) Chinese with-prompt, (2) Chinese without-prompt, (3) English with-prompt, and (4) English without-prompt. In both T and N-staging tasks, DeepSeek-R1 demonstrated superior overall performance compared to the competitors. For T-staging, the average accuracy was (DeepSeek-R1 vs. GPT-4o vs. Qwen3 vs. Grok-3: 91.4% vs. 84.2% vs. 89.5% vs. 81.3%). For N-staging, the respective average accuracy was 84.2% vs. 65.0% vs. 68.4% vs. 51.9%. Notably, N-staging proved more challenging than T-staging for all models, as indicated by lower accuracy. This superiority was most pronounced in the Chinese without-prompt T-staging scenario, where DeepSeek-R1 achieved significantly higher accuracy than GPT-4o (OR = 7.84, 95% CI [4.62–13.30], p < 0.001), Qwen3 (OR = 5.00, 95% CI [2.85–8.79], p < 0.001), and Grok-3 (OR = 6.47, 95% CI [4.30–9.74], p < 0.001). Conclusions: This study validates the feasibility and effectiveness of large language models (LLMs) for automated T/N staging from EUS reports. Our findings confirm that DeepSeek-R1 possesses strong intrinsic reasoning capabilities, achieving the most robust performance across diverse conditions, with the most pronounced advantage observed in the challenging English without-prompt N-staging task. By establishing a standardized, objective benchmark, DeepSeek-R1 mitigates inter-observer variability, and its deployment provides a reliable foundation for guiding precise, individualized treatment planning for esophageal cancer patients. Full article

The data collection and analytical capabilities of the Instrumentation and Control (I&C) system in nuclear power plants (NPPs) continue to advance, thereby enhancing operational state awareness and enabling more precise control. However, the data acquisition, transmission, and storage devices in nuclear power plant (NPP) I&C systems typically operate in harsh environments. This exposure can lead to device failures and susceptibility to external interference, potentially resulting in data anomalies such as missing samples, signal skipping, and measurement drift. This paper presents a Gated Recurrent Unit and Multilayer Perceptron (GRU-MLP)-based method for anomaly detection and correction in NPP I&C system data. The goal is to improve operational data quality, thereby supplying more reliable input for system analysis and automatic controllers. Firstly, the short-term prediction algorithm of operation data based on the GRU model is studied to provide a reference for operation data anomaly detection. Secondly, the MLP model is connected to the GRU model to recognize the difference between the collected value and the prediction value so as to distinguish and correct the anomalies. Finally, a series of experiments were conducted using operational data from a pressurized water reactor (PWR) to evaluate the proposed method. The experiments were designed as follows: (1) These experiments assessed the model’s prediction performance across varying time horizons. Prediction steps of 1, 3, 5, 10, and 20 were configured to verify the accuracy and robustness of the data prediction capability over short and long terms. (2) The model’s effectiveness in identifying anomalies was validated using three typical patterns: random jump, fixed-value drift, and growth drift. The growth drift category was further subdivided into linear, polynomial, and logarithmic growth to comprehensively test detection performance. (3) A comparative analysis was performed to demonstrate the superiority of the proposed GRU-MLP algorithm. It was compared against the interactive window center value method and the ARIMA algorithm. The results confirm the advantages of the proposed method for anomaly detection, and the underlying reasons are analyzed. (4) Additional experiments were carried out to discuss and verify the mobility (or transferability) of the prediction algorithm, ensuring its applicability under different operational conditions. Full article

Building pattern recognition is essential for understanding the dynamics of urban development, facilitating automatic map synthesis, and aiding in municipal planning Sefforts. Traditional research methods, which rely solely on geometric feature extraction from isolated objects, struggle to capture the complex and visually significant building patterns within urban environments, often suffering from low accuracy and robustness. This paper proposes a novel approach for recognizing I-shaped building patterns utilizing multi-scale data and knowledge graphs. The process begins by extracting inter-building relationships at and across different scales based on geometric and spatial rules derived from the Smallest Bounding Rectangle (SBR) representation, thereby establishing a comprehensive framework for recognizing I-shaped building patterns. This framework is encoded into a knowledge graph that translates specific scale-based and cross-scale recognition rules into conditions for knowledge graph reasoning. Utilizing rule-based reasoning within this framework, our method effectively identifies I-shaped building patterns that align with human visual principles. Experimental results underscore the efficacy of this approach, with significant enhancements in the recognition of I-shaped patterns being noted. Specifically, when compared to traditional methods that overlook multi-scale data and visual dynamics, our approach achieved a 24% increase in recall rate in Lanzhou and a 52.75% increase in London, while also Amaintaining high precision. Full article

Automatic radiology report generation (ARRG) has emerged as a promising application of deep learning (DL) with the potential to alleviate reporting workload and improve diagnostic consistency. However, despite rapid methodological advances, the field remains technically fragmented and not yet mature for routine clinical adoption. This scoping review maps the current ARRG research landscape by examining DL architectures, multimodal integration strategies, and evaluation practices from 2015 to April 2025. Following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, a comprehensive literature search identified 89 eligible studies, revealing a marked predominance of chest radiography datasets (87.6%), primarily driven by their public availability and the accelerated development of automated tools during the COVID-19 pandemic. Most models employed hybrid architectures (73%), particularly CNN–Transformer pairings, reflecting a shift toward systems that combine local feature extraction with global contextual reasoning. Although these approaches have achieved measurable gains in textual and semantic coherence, several challenges persist, including limited anatomical diversity, weak alignment with radiological rationale, and evaluation metrics that insufficiently reflect diagnostic adequacy or clinical impact. Overall, the findings indicate a rapidly evolving but clinically immature field, underscoring the need for validation frameworks that more closely reflect radiological practice and support future deployment in real-world settings. Full article

Financial institutions face data quality (DQ) challenges in regulatory reporting due to complex architectures where data flows through multiple systems. Data consumers struggle to assess quality because traditional DQ tools operate on data snapshots without capturing temporal event sequences and business contexts that determine whether anomalies represent genuine issues or valid behavior. Existing approaches address either semantic representation (ontologies for static knowledge) or temporal pattern detection (event processing without semantics), but not their integration. This paper presents CEDAR (Contextual Events and Domain-driven Associative Representation), integrating financial ontologies with event-driven processing for context-aware DQ assessment. Novel contributions include (1) ontology-driven rule derivation that automatically translates OWL business constraints into executable detection logic; (2) temporal ontological reasoning extending static quality assessment with event stream processing; (3) explainable assessment tracing anomalies through causal chains to violated constraints; and (4) standards-based design using W3C technologies with FIBO extensions. Following the Design Science Research Methodology, we document the first, early-stage iteration focused on design novelty and technical feasibility. We present conceptual models, a working prototype, controlled validation with synthetic equity derivative data, and comparative analysis against existing approaches. The prototype successfully detects context-dependent quality issues and enables ontological root cause exploration. Contributions: A novel integration of ontologies and event processing for financial DQ management with validated technical feasibility, demonstrating how semantic web technologies address operational challenges in event-driven architectures. Full article

Advanced Persistent Threats (APTs) exhibit covert behaviors, long attack cycles, and fragmented intelligence, creating challenges for correlation analysis and attribution. This work proposes a unified knowledge-graph-based framework for multi-level APT correlation. We construct an APT ontology and automatically extract entities and relations from threat reports using NER and relation extraction models. The resulting multi-source intelligence is normalized and integrated into a Neo4j knowledge graph containing 15,682 entities and 42,713 relations. Multi-level correlation analysis is then performed through explicit structural reasoning, semantic embedding models such as TransE and RotatE, and a temporal evolution module based on T-GCN to capture dynamic attack-path patterns. Experiments demonstrate that the proposed framework achieves an F1-score of 0.91 for relation extraction and improves APT correlation prediction accuracy by 17.3% over rule-based baselines. The system supports large-scale attack-chain reasoning and sector-oriented threat analysis, providing enhanced attribution and decision support for cybersecurity defense. Full article

This paper presents a novel approach using machine learning methods for the automated segmentation of acceleration signals measured during ball burnishing (BB) operations performed on a computer numerical controlled (CNC) milling machine. The study addresses the challenge of accurately finding actual feedrates in that finishing operation, which often deviate from programmed values due to various dynamic reasons. The method involves a two-stage process: first, an automatic signal segmentation algorithm employing Gaussian Mixture Modeling (GMM) and K-means clustering is applied to the ball burnishing (BB) process and acceleration data. Second, a Taguchi L9 experimental design is used to assess the influence of some regime parameters on the actual feedrate and the BB’s cycle duration. Results show successful segmentation of the toolpaths based on X-axis accelerations and deforming force data, with the Calinski–Harabasz Index confirming good cluster separability. Programmed feedrate and the number of toolpath points were identified as the most significant factors affecting the percentage delay between programmed and obtained feedrates. The main contribution is the development and testing of a new method for segmenting different toolpath states in ball burnishing operations, based on measured accelerations and momentary deforming force magnitudes. The present work offers valuable insights into autonomous monitoring and control in BB operations. Full article

Extreme autumn rainfall has become frequent due to climate change, making disaster prevention increasingly difficult. We combined a retrieval-augmented generation (RAG) framework with a multimodal large language model (multimodal LLM) to automatically cluster and explain weather patterns. The multimodal LLM assists in selecting an appropriate clustering method, such as hierarchical clustering, to determine the optimal number of clusters. To enhance weather map interpretation and reduce hallucinations or uncertainty, 13 specialized prompt roles are designed to guide the model’s reasoning process. The method is applied to autumn-season data from 1960 to 2019, using weather records from the Taiwan Climate Change Projection and Information Platform and the ERA5 reanalysis dataset by the European Center for Medium-Range Weather Forecasts. The results show that three dominant weather types were identified. The identified types are typhoon with companion system (TC_NE, 51%), northeasterly pattern (NE, 30%), and tropical cyclone (TC, 19%). The developed method in this study provides a new approach for interpreting extreme weather events under changing climate conditions. Full article