Search Results (44)

The causal analysis of historical aviation accidents documented in investigation reports is important for the design, manufacture, operation, and maintenance of aircraft. However, given that most accident data are unstructured or semi-structured, identifying and extracting causal information remain labor intensive and inefficient. This gap is further deepened by tasks, such as system identification from component information, that require extensive domain-specific knowledge. In addition, there is a consequential demand for causation pattern analysis across multiple accidents and the extraction of critical causation chains. To bridge those gaps, this study proposes an aviation accident causation and relation analysis framework that integrates prompt engineering with a retrieval-augmented generation approach. A total of 343 real-world accident reports from the NTSB were analyzed to extract causation factors and their interrelations. An innovative causation classification schema was also developed to cluster the extracted causations. The clustering accuracy for the four main causation categories—Human, Aircraft, Environment, and Organization—reached 0.958, 0.865, 0.979, and 0.903, respectively. Based on the clustering results, a causation knowledge graph for aviation accidents was constructed, and by designing a set of safety evaluation indicators, “pilot—decision error” and “landing gear system malfunction” are identified as high-risk causations. For each high-risk causation, critical combinations of causation chains are identified and “Aircraft operator—policy or procedural deficiency/pilot—procedural violation/Runway contamination → pilot—decision error → pilot procedural violation/32 landing gear/57 wings” was identified as the critical causation combinations for “pilot—decision error”. Finally, safety recommendations for organizations and personnel were proposed based on the analysis results, which offer practical guidance for aviation risk prevention and mitigation. The proposed approach demonstrates the potential of combining AI techniques with domain knowledge to achieve scalable, data-driven causation analysis and strengthen proactive safety decision-making in aviation. Full article

Recent text to image systems can synthesize Islamic heritage elements with high visual fidelity, but their outputs rarely translate into fabricable geometry or integrate into interiors without substantial redrawing. We present an end-to-end workflow that links historically grounded precedent retrieval, controllable tileable generation, semantic segmentation and vectorization, and geometry-aware mapping into Computer-Aided Design (CAD) environments. Contributions include the following: (i) a license-audited dataset schema and a retrieval classifier for common Islamic motif families and architectural elements; (ii) precedent retrieval via a ResNet 50 and Vision Transformer (ViT) embedding pipeline; (iii) a Low-Rank Adaptation (LoRA) tuned diffusion model that generates tileable motifs with motif/region controls; (iv) a raster-to-vector pipeline that enforces curve closure and minimum feature widths for CNC/laser fabrication; and (v) a rubric and domain metrics (symmetry coherence, seam/tileability error, spline closure and junction valence, UV distortion, feature width compliance) that quantify “depth of integration” beyond surface texture. Quantitative metrics and blinded expert ratings compare the workflow against strong parametric baselines, while scripts translate images to fabrication-ready vectors/solids across walls, ceilings, partitions, floors, and furniture. Cultural safeguards cover calligraphy handling, regional balance audits, and provenance/credit. The workflow advances heritage-aware generative design by carrying imagery across the last mile into buildable detail and by providing practical checklists for adoption in interior architecture and conservation. Full article

Electronic health records (EHRs) are typically stored in relational databases, making them difficult to query for nontechnical users, especially under privacy constraints. We evaluate two practical clinical NLP workflows, natural language to SQL (NL2SQL) for EHR querying and retrieval-augmented generation for clinical question answering (RAG-QA), with a focus on privacy-preserving deployment. We benchmark nine large language models, spanning open-weight options (DeepSeek V3/V3.1, Llama-3.3-70B, Qwen2.5-32B, Mixtral-8 × 22B, BioMistral-7B, and GPT-OSS-20B) and proprietary APIs (GPT-4o and GPT-5). The models were chosen to represent a diverse cross-section spanning sparse MoE, dense general-purpose, domain-adapted, and proprietary LLMs. On MIMICSQL (27,000 generations; nine models × three runs), the best NL2SQL execution accuracy (EX) is 66.1% (GPT-4o), followed by 64.6% (GPT-5). Among open-weight models, DeepSeek V3.1 reaches 59.8% EX, while DeepSeek V3 reaches 58.8%, with Llama-3.3-70B at 54.5% and BioMistral-7B achieving only 11.8%, underscoring a persistent gap relative to general-domain benchmarks. We introduce SQL-EC, a deterministic SQL error-classification framework with adjudication, revealing string mismatches as the dominant failure (86.3%), followed by query-join misinterpretations (49.7%), while incorrect aggregation-function usage accounts for only 6.7%. This highlights lexical/ontology grounding as the key bottleneck for NL2SQL in the biomedical domain. For RAG-QA, evaluated on 100 synthetic patient records across 20 questions (54,000 reference–generation pairs; three runs), BLEU and ROUGE-L fluctuate more strongly across models, whereas BERTScore remains high on most, with DeepSeek V3.1 and GPT-4o among the top performers; pairwise t-tests confirm that significant differences were observed among the LLMs. Cost–performance analysis based on measured token usage shows per-query costs ranging from USD 0.000285 (GPT-OSS-20B) to USD 0.005918 (GPT-4o); DeepSeek V3.1 offers the best open-weight cost–accuracy trade-off, and GPT-5 provides a balanced API alternative. Overall, the privacy-conscious RAG-QA attains strong semantic fidelity, whereas the clinical NL2SQL remains brittle under lexical variation. SQL-EC pinpoints actionable failure modes, motivating ontology-aware normalization and schema-linked prompting for robust clinical querying. Full article

This paper proposes a knowledge graph (KG) construction method for a part machining process in response to the low degree of structuring of historical process data association relationships within the enterprise in the field of part machining, which makes it difficult to reuse effectively. The part types are mainly shafts, gears, boxes and other common parts. First, the schema layer of the process knowledge graph was constructed using a top-down approach. Second, deep learning techniques were employed for entity extraction, while knowledge fusion and ontology relationship establishment methods were combined to build the data layer of the process knowledge graph (PKG) from the bottom up. Third, the mapping between the schema layer and data layer was implemented in the Neo4j graph database. Based on the constructed process KG, process route recommendation and rapid retrieval of process information were thus accomplished. Finally, a shaft part was used as the target part to verify the effectiveness of the proposed method. In over 300 trials, the similarity-based recommendation model achieved a hit rate of 91.7% (the target part’s route appeared in the recommended list in 91.7% of cases). These results indicate that the proposed machining PKG construction is feasible and can assist in process planning, potentially improving the efficiency of retrieving and reusing machining knowledge. Full article

As BIM projects grow in volume and complexity, automated Information Compliance Checking (ICC) is becoming essential to meet demanding regulatory and contractual requirements. This study presents novel controlled vocabularies and processes for the management of information requirements, along with a structured evaluation of the Information Delivery Specification (IDS) and its associated tools. The controlled vocabularies are important as they provide support to standardization, information retrieval, data-driven workflows, and AI integration. Information requirements are classified by input type and project interaction context (phase, origin, project role, and communication), as well as by applicability (data management function, model granularity, BIM usage, and checkability). The ontology comprises seven categories: identity, geometry, design/performance, fabrication/construction, operation/maintenance, cost, and regulatory category, each linked to verification principles such as uniqueness and consistency. This enables systematic implementation of validation checks aligned with company and project needs. We introduce three ICC workflows in relation to the BIM authoring tools (inside, outside, and hybrid) and suggest key criteria for the functional and non-functional evaluation of IDS tools. Empirical results from a real project using five IDS tools reveal implementation issues with the classification facet, regular expressions, and issue reporting. The proposed ontology and framework lay the foundation for a scalable, transparent ICC within openBIM. The results also provide ICC process guidance for practitioners, a SWOT analysis that can inform enhancements to the existing IDS schema, identify possible inputs for certification of IDS tools, and generate innovative ideas for research and development. Full article

Retrieval-Augmented Generation (RAG) systems have emerged as a critical approach for enhancing large language models with external knowledge, yet the field lacks systematic theoretical analysis for understanding their fundamental characteristics and optimization principles. A novel information-theoretic approach for analyzing and optimizing RAG systems is introduced in this paper by modeling them as cascading information channel systems where each component (query encoding, retrieval, context integration, and generation) functions as a distinct information-theoretic channel with measurable capacity. Following established practices in information theory research, theoretical insights are evaluated through systematic experimentation on controlled synthetic datasets that enable precise manipulation of schema entropy and isolation of information flow dynamics. Through this controlled experimental approach, the following key theoretical insights are supported: (1) RAG performance is bounded by the minimum capacity across constituent channels, (2) the retrieval channel represents the primary information bottleneck, (3) errors propagate through channel-dependent mechanisms with specific interaction patterns, and (4) retrieval capacity is fundamentally limited by the minimum of embedding dimension and schema entropy. Both quantitative metrics for evaluating RAG systems and practical design principles for optimization are provided by the proposed approach. Retrieval improvements yield 58–85% performance gains and generation improvements yield 58–110% gains, substantially higher than context integration improvements (∼9%) and query encoding modifications, as shown by experimental results on controlled synthetic environments, supporting the theoretical approach. A systematic theoretical analysis for understanding RAG system dynamics is provided by this work, with real-world validation and practical implementation refinements representing natural next phases for this research. Full article

Logistics transports of various resources such as production materials, foods, and products support the operation of smart cities. The ability to trace the states of logistics transports requires an efficient storage and retrieval of the states of logistics transports and locations of logistics objects. However, the restriction of sharing states and locations of logistics objects across organizations makes it hard to deploy a centralized database for supporting traceability in a cross-organization logistics system. This paper proposes a semantic data model on Blockchain to represent a logistics process based on the Semantic Link Network model, where each semantic link represents a logistics transport of a logistics object between two organizations. A state representation model is designed to represent the states of a logistics transport with semantic links. It enables the locations of logistics objects to be derived from the link states. A mapping from the semantic links into the blockchain transactions is designed to enable the schema of semantic links and the states of semantic links to be published in blockchain transactions. To improve the efficiency of tracing a path of semantic links on a blockchain platform, an algorithm is designed to build shortcuts along the path of semantic links to enable a query on the path of a logistics object to reach the target in logarithmic steps on the blockchain platform. A reward–penalty policy is designed to allow participants to confirm the states of links on the blockchain. Analysis and simulation demonstrate the flexibility, effectiveness, and efficiency of the Semantic Link Network on immutable blockchain for implementing logistics traceability. Full article

The increasing complexity of Internet of Drones (IoD) platforms demands more accessible ways for users to interact with unmanned aerial vehicle (UAV) data systems. Traditional methods requiring technical API knowledge create barriers for non-specialist users in dynamic operational environments. To address this challenge, we propose a retrieval-augmented generation (RAG) architecture that enables natural language querying over UAV telemetry, mission, and detection data. Our approach builds a semantic retrieval index from structured application programming interface (API) documentation and uses lightweight large language models to map user queries into executable API calls validated against platform schemas. This design minimizes fine-tuning needs, adapts to evolving APIs, and ensures schema conformity for operational safety. Evaluations conducted on a curated IoD dataset show 91.3% endpoint accuracy, 87.6% parameter match rate, and 95.2% schema conformity, confirming the system’s robustness and scalability. The results demonstrate that combining retrieval-augmented semantic grounding with structured validation bridges the gap between human intent and complex UAV data access, improving usability while maintaining a practical level of operational reliability. Full article

Large-language models (LLMs) show promise for automating evidence synthesis, yet head-to-head evaluations remain scarce. We benchmarked five state-of-the-art LLMs—openai/o1-mini, x-ai/grok-2-1212, meta-llama/Llama-3.3-70B-Instruct, google/Gemini-Flash-1.5-8B, and deepseek/DeepSeek-R1-70B-Distill—on extracting protocol details from transcranial direct-current stimulation (tDCS) trials enrolling older adults. A multi-LLM ensemble pipeline ingested ClinicalTrials.gov records, applied a structured JSON schema, and generated comparable outputs from unstructured text. The pipeline retrieved 83 aging-related tDCS trials—roughly double the yield of a conventional keyword search. Across models, agreement was almost perfect for the binary field brain stimulation used (Fleiss κ ≈ 0.92) and substantial for the categorical primary target (κ ≈ 0.71). Numeric parameters such as stimulation intensity and session duration showed excellent consistency when explicitly reported (ICC 0.95–0.96); secondary targets and free-text duration phrases remained challenging (κ ≈ 0.61; ICC ≈ 0.35). An ensemble consensus (majority vote or averaging) resolved most disagreements and delivered near-perfect reliability on core stimulation attributes (κ = 0.94). These results demonstrate that multi-LLM ensembles can markedly expand trial coverage and reach expert-level accuracy on well-defined fields while still requiring human oversight for nuanced or sparsely reported details. The benchmark and open-source workflow set a solid baseline for future advances in prompt engineering, model specialization, and ensemble strategies aimed at fully automated evidence synthesis in neurostimulation research involving aging populations. Overall, the five-model multi-LLM ensemble doubled the number of eligible aging-related tDCS trials retrieved versus keyword searching and achieved near-perfect agreement on core stimulation parameters (κ ≈ 0.94), demonstrating expert-level extraction accuracy. Full article

This paper introduces a novel framework enabling natural language question answering on Piping and Instrumentation Diagrams (P&IDs), addressing a critical gap between engineering design documentation and intuitive information retrieval. Our approach transforms static P&IDs into queryable knowledge bases through a three-stage pipeline. First, we recognize entities in a P&ID image and organize their relationships to form a base entity graph. Second, this entity graph is converted into a Labeled Property Graph (LPG), enriched with semantic attributes for nodes and edges. Third, a Large Language Model (LLM)-based information retrieval system translates a user query into a graph query language (Cypher) and retrieves the answer by executing it on LPG. For our experiments, we augmented a publicly available P&ID image dataset with our novel PIDQA dataset, which comprises 64,000 question–answer pairs spanning four categories: (I) simple counting, (II) spatial counting, (III) spatial connections, and (IV) value-based questions. Our experiments (using gpt-3.5-turbo) demonstrate that grounding the LLM with dynamic few-shot sampling robustly elevates accuracy by 10.6–43.5% over schema contextualization alone, even under high lexical diversity conditions (e.g., paraphrasing, ambiguity). By reducing barriers in retrieving P&ID data, this work advances human–AI collaboration for industrial workflows in design validation and safety audits. Full article

Educational AI systems often do not employ proper sophistication techniques to enhance learner interactions, organize their contextual knowledge or even deliver personalized feedback. To address this gap, this paper seeks to reform the way ChatGPT supports learners by employing fuzzy memory retention and thematic clustering. To achieve this, three modules have been developed: (a) the Fuzzy Memory Module which models human memory retention using time decay fuzzy weights to assign relevance to user interactions, (b) the Schema Manager which then organizes these prioritized interactions into thematic clusters for structured contextual representation, and (c) the Response Generator which uses the output of the other two modules to provide feedback to ChatGPT by synthesizing personalized responses. The synergy of these three modules is a novel approach to intelligent and AI tutoring that enhances the output of ChatGPT to learners for a more personalized learning experience. The system was evaluated by 120 undergraduate students in the course of Java programming, and the results are very promising, showing memory retrieval accuracy, schema relevance and personalized response quality. The results also show the system outperforms traditional methods in delivering adaptive and contextually enriched educational feedback. Full article

To support data-driven decision-making in a Manufacturing Execution System (MES) environment, a system that can quickly and accurately analyze a wide range of production, quality, asset, and material information must be deployed. However, existing MES data management approaches rely on predefined queries or report templates that lack flexibility and limit real-time decision support. In this paper, we proposes a domain-specific Retrieval-Augmented Generation (RAG) architecture that extends LangChain’s capabilities with Manufacturing Execution System (MES)-specific components and the Ollama-based Local Large Language Model (LLM). The proposed architecture addresses unique MES requirements including real-time sensor data processing, complex manufacturing workflows, and domain-specific knowledge integration. It implements a three-layer structure: an application layer using FastAPI for high-performance asynchronous processing, an LLM layer for natural language understanding, and a data storage layer combining MariaDB, Redis, and Weaviate for efficient data management. The system effectively handles MES-specific challenges such as schema relationships, temporal data processing, and security concerns without exposing sensitive factory data. This is an industry-specific, customized approach focusing on problem-solving in manufacturing sites, going beyond simple text-based RAG. The proposed architecture considers the specificity of data sources, real-time and high-availability requirements, the reflection of domain knowledge and workflows, compliance with security and quality control regulations, and direct interoperability with MES systems. The architecture can be further enhanced through integration with various manufacturing systems, an advanced LLM, and distributed processing frameworks while maintaining its core focus on MES domain specialization. Full article

In the complex process of assembling biomass heating systems, traditional paper documents and construction process card management methods have weak information correlation and take a long time for information retrieval, which seriously restricts the assembly efficiency and quality. Moreover, the assembly process involves numerous components and complex processes, making it difficult for traditional management methods to cope with. To address this issue, a knowledge graph-based assembly information integration method is proposed to integrate scattered assembly information into a graph database, providing pathways for accessing assembly information and assisting on-site management. The biomass heating system assembly knowledge graph (BAKG) adopts the top-down method construction. After the construction of the upper schema layer, the 3DXML file was parsed, the XML.dom parser in Python3.7.16 was used to extract the equipment structure information, and the RoBERTa-BiLSTM-CRF model was applied to the named entity recognition of the assembly document, which improved the accuracy of entity recognition. The experimental results show that the F1 score of the RoBERTa-BiLSTM-CRF model in entity recognition during the assembly process reaches 92.19%, which is 3.1% higher than that of the traditional BERT-BiLSTM-CRF model. Moreover, the knowledge graph structure generated by the equipment structure data based on 3DXML file is similar to the equipment structure tree, but is more clear and intuitive. Finally, taking the second-phase construction process records of a company as an example, BAKG was constructed and assembly information was stored in the Neo4j graph database in the form of graphs, which verified the effectiveness of the method. Full article

Geographic Knowledge Base Question Answering (GeoKBQA) has garnered increasing attention for its ability to process complex geographic queries. This study focuses on schema retrieval, a critical step in GeoKBQA that involves extracting relevant schema items (classes, relations, and properties) to generate accurate operational queries. Current GeoKBQA studies primarily rely on rule-based approaches for schema retrieval. These predefine words or descriptions for each schema item. This rule-based method has three critical limitations: (1) poor generalization to undefined schema items, (2) failure to consider the semantic meaning of user queries, and (3) an inability to adapt to languages not used in the predefined step. In this study, we present a schema retrieval model by using few-shot prompting on GPT-4 Turbo to address these issues. Using the SKRE dataset, we searched for the best prompt in terms of enabling the model to handle Korean geographic questions across various generalization levels. Notably, this method outperformed fine-tuning in zero-shot scenarios, underscoring its adaptability to unseen data. To our knowledge, this is the first attempt to develop a schema retrieval model for GeoKBQA that purely utilizes a language model and is capable of processing Korean geographic questions. Full article

Beliefs are information-processing structures formed along an individual’s developmental pathway. Beliefs can legitimize involvement in inappropriate or violent behaviors, particularly when they crystallize into cognitive schemas. While beliefs aid individuals in interpreting the surrounding world, overly rigid and inflexible beliefs can constrain the individual’s ability to process available information. This Systematic Review, carried out according to the PRISMA norms and guidelines, aims to understand the most prevalent beliefs regarding relationships among young adults and to examine their associations with violent or deviant behaviors. Articles included in this review were retrieved from the EBSCO, PubMed, and Web of Science databases in July 2022, resulting in a total of 594 studies, which were subsequently screened by two independent reviewers. A total of 51 studies were then selected for full reading, but 36 were excluded based on pre-defined eligibility criteria, leaving a final sample of 18 studies published between 2014 and 2022. The main objectives, country of origin, instruments used, sample composition and age, main results and conclusions were extracted from each study. Findings point toward the presence of related and legitimate beliefs about violence in intimate relationships, domestic violence, sexual violence, acceptance of the rape myth, or consent to engage in sexual activities. Full article