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.

As the infrastructure for semantic integration modeling of course knowledge points, learning tasks and evaluation indicators, the Curriculum Knowledge Graph (CKG) has become a key fulcrum for educational digitalization. Under the theoretical framework of networked learning and knowledge organization, this paper defines the conceptual boundary and mechanism of CKG, and summarizes the engineering processes such as ontology modeling, information extraction, entity alignment, knowledge warehousing and reasoning. Further integrating application evidence such as instructional design optimization, personalized path generation, and enhanced generation of learning situation diagnosis and retrieval (RAG), a quality assessment system and versified governance approach centered on structural consistency, coverage completeness, usability benefits, and trusted traceability are proposed. And discuss the synergy of large language models in term discovery, relational assumptions, and weakly supervised annotations, as well as the auditability gains and consistency risk they bring.

ABSTRACTAs a core industrial equipment, the stable operation of centrifugal compressors is crucial to production. Current research on its fault diagnosis mostly focuses on structured monitoring data, with insufficient mining of unstructured operation and maintenance experience data. To address this, this paper constructs an intelligent diagnosis model integrating ontology knowledge reasoning, knowledge graph modeling, and Bayesian Network (BN), realizing cross‐modal fault accurate localization and root cause analysis through the deep integration of “knowledge + probability.” Firstly, an ontology knowledge model is established based on fault information mined from unstructured data (such as fault reports and maintenance records), enabling standardized expression and semantic association of fault knowledge. The model is then imported into the Neo4j database, and specific fault information files are exported through Python queries to serve as the basic data for BN reasoning. Next, a probabilistic reasoning model between fault components and symptoms is built based on BN. Combining expert experience and historical data, the node conditional probabilities are determined to describe the uncertainty of fault propagation. Finally, a fusion method of ontology and BN is designed: ontology reasoning is used to optimize the BN structure, and intelligent diagnostic reasoning is realized through dynamic updating of posterior probabilities. Experiments using fault reports of centrifugal compressors from a certain enterprise show that the proposed fusion model can improve the interpretability and dynamic reasoning ability of fault diagnosis. Case verification demonstrates that the fault recognition accuracy of this method reaches 85%, indicating good performance. Therefore, this research provides a feasible solution for utilizing unstructured operation and maintenance data, enhancing the practicality of intelligent diagnosis for complex industrial equipment, which can shorten fault downtime, reduce maintenance costs, and thus has practical application value.

Ontological reasoning for automated tunnel defect diagnosis and root cause identification

A multi-model approach to construction site safety: Fault trees, Bayesian networks, and ontology reasoning

Catalysis research is complex and interdisciplinary, involving diverse physical effects and challenging data practices. Research data often captures only selected aspects, such as specific reactants and products, limiting its utility for machine learning and the implementation of FAIR (Findable, Accessible, Interoperable, Reusable) workflows. To improve this, semantic structuring through ontologies is essential. This work extends the established ontologies by refining logical relations and integrating semantic tools such as the Web Ontology Language or the Shape Constraint Language. It incorporates application programming interfaces from chemical databases, such as the Kyoto Encyclopedia of Genes and Genomes and the National Institute of Health’s PubChem database, and builds upon established ontologies. A key innovation lies in automatically decomposing chemical substances through database entries and chemical identifier representations to identify functional groups, enabling more generalized reaction classification. Using new semantic functionality, functional groups are flexibly addressed, improving the classification of reactions such as saponification and ester cleavage with simultaneous oxidation. A graphical interface (GUI) supports user interaction with the knowledge graph, enabling ontological reasoning and querying. This approach demonstrates improved specificity of the newly established ontology over its predecessors and offers a more user-friendly interface for engaging with structured chemical knowledge. Future work will focus on expanding ontology coverage to support a wider range of reactions in catalysis research.

This paper deals with the metaphysical interpretations of Laozi (老子), focusing on the works of Eom Gunpyeong(嚴君平)’s Laozi Zigu (老子指歸) and Wang P'il(王弼)'s Laozi Zhu(老子注). Generally, Wang P'il's Laozi Zhu is characterized by its metaphysical interpretative approach. Here, the author questions whether Wang P'il's metaphysical interpretation was truly an original insight unique to him. The conclusion is that there was already a typical metaphysical interpretation before Wang P'il, namely Eom Gunpyeong's Laozi Zigu from the late Western Han period. To substantiate this point, the author conducted the following analyses: First, by analyzing the Yuan Wu Lun(元無論) in Laozi Zigu, it was revealed that in Laozi Zigu, the concept of 'Wu(無)' (nothingness) merges both cosmological and ontological aspects. Second, it was demonstrated that in Laozi Zigu, the term 'Wu' is often equated with the 'Dao(道)'. Third, by analyzing Wang P'il's Gui Wu Lun(貴無論), it was shown that its main ideas such as 'Yi Wu Wei Ben(以無爲本)'(taking nothingness as fundamental) and 'Yi Wu Wei Dao(以無爲道)' (taking nothingness as the Dao) can be traced back to the origins within Laozi Zigu. Through these discussions, it was confirmed that Wang P'il's theory of 'Gui Wu(貴無)'(respect for nothingness) and his scholarly thought were directly influenced by the ontological reasoning of Laozi Zigu, and that the concept of 'Wu' (nothingness) serves as a philosophical core, establishing a continuity between these ideas.

In this paper the authors propose Well-Architected Semantic GEOframework (WasGeo), a unified framework for addressing semantic heterogeneity and intrinsic complexity in geospatial data. Its architecture integrates relational databases and semantic technologies to support Structured Query Language for data handling, SPARQL Protocol and Resource Description Framework Query Language for semantic querying, and Web Ontology Language for ontology reasoning. The performance of the proposed framework was tested using predefined queries processed on LinkedGeoData datasets. Benchmark comparisons were made to evaluate WasGeo against Ontop and GeoSPARQL. The proposed framework achieved a reasoning accuracy of 95%, processed up to 1 million Resource Description Framework triples, and demonstrated execution times ranging from 0.3 to 7.7 seconds. Comparative benchmarks show that WasGeo provides greater reasoning depth than GeoSPARQL and Ontop, while maintaining better balance between scalability and analytical power. These results position WasGeo as a robust and practical framework for advanced semantic geospatial querying, although future enhancements are needed for scalability.

Abstract Infrastructure as Code (IaC) uses versionable software code to define, deploy, and configure physical computational resources, software execution platforms, and applications. As a result, IaC enables the scalable management of complex computing environments while preventing environment drift. IaC frameworks typically offer specific languages such as the industrial Terraform, Ansible, Chef, or TOSCA—standing for Topology and Orchestration Specification for Cloud Applications—the OASIS (Organization for the Advancement of Structured Information Standards) open standard approach to IaC. Developing high-quality IaC for deploying and managing applications demands expertise and knowledge in specific IaC languages, infrastructure resources, resource providers, quality issues in IaC scripts, and so on. While several model-driven engineering (MDE) approaches have been proposed to simplify IaC development, they cannot capture and use expert knowledge to assist with modeling tasks and MDE processes by providing interactive recommendations. This paper presents a knowledge-based framework for guiding the model-driven development of IaC. We use TOSCA as the target IaC language as it is an open standard. We enable IaC and resource experts to share their IaC and resource-related knowledge with application operational experts to help simplify the development of application deployment models. We use an ontology to record the relevant deployment knowledge and ontology reasoning to implement modeling guidance capabilities such as TOSCA model auto-completion, code smell and error detection, and model element matchmaking. We show the flexibility of our methodology by applying it to three industrial applications, covering cloud, edge, and HPC (High-Performance Computing) domains. Moreover, we also assess the use acceptance of our approach and framework by conducting controlled experiments with expert and non-expert IaC users. The results indicate that our method can simplify IaC development by providing appropriate recommendations.

The article describes the development of a dish search engine for digital restaurant menus in Kyiv, focusing on Ukrainian-speaking users. The system integrates modern Natural Language Processing (NLP) methods such as lemmatization, text classification, and data filtering, alongside Retrieval-Augmented Generation (RAG), specialized ingredient dictionaries, a database, and an ontological knowledge base designed in Protégé. Using rules from the Semantic Web Rule Language (SWRL) and logical inference through the Pellet reasoning engine, the system performs semantic analysis of user queries, automatically identifying relationships between dish components, and improving search relevance.The search algorithm utilizes a multi-layered approach that combines machine learning, logical reasoning, and rule-based filtering. User queries, often containing informal or varied phrasing, are first processed by a large language model (LLM) to identify and standardize key terms. The LLM is enhanced with predefined dictionaries (e.g., for cheese types like “mascarpone”, “brie,” or “cheddar”) and connected to an ontological knowledge base, which enriches the query with semantic relationships. RAG extends this functionality by automatically expanding search terms to include synonyms or related concepts, such as linking “pasta” to “macaroni” or “spaghetti.”The study incorporates principles of computational social science to analyze semi-structured data from digital restaurant menus, such as the popularity of dishes and their ingredients, as well as the impact of restaurant location on pricing. The data highlights trends in customer preferences and provides actionable insights for optimizing restaurant menus.The developed system successfully integrates NLP techniques, logical reasoning, and structured data storage, achieving high accuracy and relevance in search results. By incorporating an LLM, RAG, and ontological reasoning, the system demonstrates the potential for significantly enhancing customer-oriented services in the restaurant industry through advanced data analysis and semantic search tools.

The current disruptive era demands many changes in various areas of life. Likewise, the technological transformation has significant unavoidable consequences. This is where it is necessary to consider a strong foundation for students from the elementary level. This article examines the application and reflection of philosophy on the content of elementary school mathematics in Indonesia. The background of this study is the need for an era where there is a need for constructive mathematics learning from an early age towards learning the Industrial Revolution 4.0. The purpose of this study is to identify (1) the nature of symptoms or objects of application and reflection of philosophy in elementary mathematics (ontological reasons), (2) how to obtain or manage symptoms or objects (epistemological reasons), (3) the benefits of symptoms or objects (axiological reasons), and two-way understanding of phenomena and objects (hermeneutics). Data is obtained based on relevant sources such as journal articles, books, and previous research results supported by qualitative analysis. The results of this study indicate the need to reveal the application and reflection of philosophy in low-grade mathematics content through the ontology of mathematics, epistemology, axiology, and hermeneutics.

Abstract In the wake of the recent resurgence of the Datalog language of databases, together with its extensions for ontological reasoning settings, this work aims to bridge the gap between the theoretical studies of DatalogMTL (Datalog extended with metric temporal logic) and the development of production-ready reasoning systems. In particular, we lay out the functional and architectural desiderata of a modern reasoner and propose our system, Temporal Vadalog. Leveraging the vast amount of experience from the database community, we go beyond the typical chase-based implementations of reasoners, and propose a set of novel techniques and a system that adopts a modern data pipeline architecture. We discuss crucial architectural choices, such as how to guarantee termination when infinitely many time intervals are possibly generated, how to merge intervals, and how to sustain a limited memory footprint. We discuss advanced features of the system, such as the support for time series, and present an extensive experimental evaluation. This paper is a substantially extended version of “The Temporal Vadalog System” as presented at RuleML+RR ’22.

As the Industrial Internet of Things (IIoT) increasingly integrates with traditional networks, advanced persistent threats (APTs) pose significant risks to critical infrastructure. Traditional Intrusion Detection Systems (IDSs) and Anomaly Detection Systems (ADSs) are often inadequate in countering sophisticated multi-step APT attacks. This highlights the necessity of studying attacker strategies and developing predictive models to mitigate potential threats. To address these challenges, we propose DeepOP, a hybrid framework for attack sequence prediction that combines deep learning and ontological reasoning. DeepOP leverages the MITRE ATT&CK framework to standardize attacker behavior and predict future attacks with fine-grained precision. Our framework’s core is a novel causal window self-attention mechanism embedded within a transformer-based architecture. This mechanism effectively captures local causal relationships and global dependencies within attack sequences, enabling accurate multi-step attack predictions. In addition, we construct a comprehensive dataset by extracting causally connected attack events from cyber threat intelligence (CTI) reports using ontological reasoning, mapping them to the ATT&CK framework. This approach addresses the challenge of insufficient data for fine-grained attack prediction and enhances the model’s ability to generalize across diverse scenarios. Experimental results demonstrate that the proposed model effectively predicts attacker behavior, achieving competitive performance in multi-step attack prediction tasks. Furthermore, DeepOP bridges the gap between theoretical modeling and practical security applications, providing a robust solution for countering complex APT threats.

Smart wearable devices detection and recording of people’s everyday activities is critical for health monitoring, helping persons with disabilities, and providing care for the elderly. Most of the research that is being conducted uses a machine learning-based methodology; however, these approaches frequently have issues with high computing resource consumption, burdensome training data gathering, and restricted scalability across many contexts. This research suggests a behaviour detection technology based on multi-source sensing and logical reasoning to address these problems. In order to realize the natural fusion of signal processing and logical reasoning in behavior recognition research, this work designs a lightweight behavior recognition solution using the pertinent theories of ontology reasoning in classical artificial intelligence. Machine learning technology is also employed for behavior recognition using the same data set. Once the best model has been chosen, the cross-person recognition results after testing and modification of parameters are 90.8% and 92.1%, respectively. This technology was used to create a behaviour recognition system, and several tests were run to assess how well it worked. The findings demonstrate that the suggested strategy achieves over 90% recognition accuracy for 11 different daily activities, including jogging, walking, and stair climbing. Additionally, the suggested strategy dramatically minimises the quantity of user-provided training data needed in comparison to machine learning-based behaviour identification techniques.

The paper investigates the relationship between Trusted Artificial Intelligence and Explainable AI 2.0 (XAI 2.0). It demonstrates that XAI 2.0 is the structural core of Trusted AI and a prerequisite for Responsible AI. A critical review of the evolution from XAI 1.0 to XAI 2.0 confirms the need for multilayer, contextadaptive explanations. A neurosymbolic hierarchical architecture is proposed, integrating deep networks with fuzzy layers, ontological reasoning, and an LLMbased verbalisation module. A comparative study of leading frameworks and guidelines reveals convergence of explainability practices throughout the MLSecOps pipeline. A sevenlevel explainability scale (L0–L6) and an integral Trust Index are introduced to formalise progress toward selfexplanatory intelligence (L6). The solution already achieves levels L4–L5 and provides an engineering foundation for selfauditing, trustworthy AI systems.

Semantic Segmentation of Assembly Images Combining Deep Learning and Ontological Reasoning

Abstract Under the rapid development of the digital era, the personalized needs of college students for sports instruction are becoming more and more prominent. This requires college physical education teachers to change their roles and develop teaching innovations. Combining the characteristics and laws of college physical education courses in colleges and universities and based on the flipped classroom teaching model, this study designs an exercise prescription recommendation method based on ontological reasoning and similarity fusion calculation. The method, on the path of the construction of personalized exercise prescription intelligent recommendation system under artificial intelligence, uses ontological rule reasoning to determine the constraint space of exercise prescription parameters, as well as similarity fusion calculation of the parameters of high-quality cases of exercise prescription, to obtain the parameters of personalized exercise prescription within the constraint space which has its better effect and higher fitness. Finally, this paper analyzes the above-designed methods through experiments, and the experimental results show that the recommendation method using similarity fusion computation obtains relatively high ratings on most users compared to the traditional cooperation-based recommendation method, with an average value of 4.04, while the ResNet-EP and collaborative filtering recommendation methods have an average value of 3.75 and 3.10, respectively. This proves that the ontology-based reasoning of the exercise prescription recommendation model has high accuracy and effectiveness in recommending exercise effects, and has better performance compared to other algorithms, while it may be more suitable for exercise recommendation tasks in practical applications, and can provide users with a better exercise experience. In addition, the experimental data also showed that the pull-up performance and 1000 meters performance of the students in the experimental group who used the exercise prescription model under the flipped classroom teaching mode were significantly different from those of the students in the control group, with P<0.05, which proved that the method of recommending exercise prescription under the flipped classroom teaching mode was effective in promoting the improvement of students’ endurance quality and the quality of their upper limb strength, and verified the usability and validity of the method.

A lightweight Method for Detecting Bearing Surface Defects Based on Deep Learning and Ontological Reasoning

Fine-Tuning Large Language Models for Financial Markets via Ontological Reasoning

ABSTRACT Not only is freedom a shared concern of Sartre and Schelling, which would not be anything particularly unique, but for both philosophers, freedom must be articulated out of an ontological ground, or within the confines of an ontological system. A contradiction nevertheless appears to arise regarding the “orientation” of Sartre and Schelling’s respective “ontologies of freedom”: the freedom of Sartre, reflecting a contemporary stoic-inspired doctrine, is directed toward the future, while for Schelling, with affinities to the temporal logic of psychoanalysis, freedom is oriented toward the past. This article presents both Sartre and Schelling’s ontological reasoning out of which either a progressively oriented freedom (the freedom to negate the present in the name of future “possibles”) or a retrogressively oriented freedom (the freedom to determine the ground of the present out of an indefinite, a-temporal becoming), before attempting to resolve this contradiction in the temporality of freedom by examining the position and role of the negative (of negation, contradiction, or nothingness), as either secondary or primary, within the ontology of each respective philosopher.