KEOD 2023 Abstracts

Full Papers Short Papers
Full Papers
Paper Nr: 20
Title:

EvdoGraph: A Knowledge Graph for the EVDOXUS Textbook Management Service for Greek Universities
Authors:

Nick Bassiliades
Abstract: Evdoxus is a web information system for the management of the total ecosystem for the free provision of textbooks to the undergraduate students at the Greek Universities. Among its users are book publishers that register textbooks, faculty members that search for appropriate textbooks for their courses, administration of university departments that register the relevant textbooks for each module of the curricula (course), and finally, students that select one book per module that they attend. All the above information (except for which students selected which books) is freely available at the Evdoxus site in the form of HTML web pages. In this paper, we present how we extracted this information and converted it into an open Knowledge Graph in RDF that can be used to generate several interesting reports and answer statistical analysis questions in SPARQL. The KG is backed by a simple ontology which is aligned with some well-known ontologies. The extraction / conversion application has been developed using SWI-Prolog’s XPath and Semantic Web libraries. The KG encompasses the Linked Open Data initiative by linking University instances with their corresponding DBpedia entries, employing the Wikipedia search engine and the DBpedia SPARQL endpoint.
Download
Paper Nr: 43
Title:

A Data Mesh Adaptable Oil and Gas Ontology Based on Open Subsurface Data Universe (OSDU)
Authors:

Neda Abolhassani, Ana Tudor and Sanjoy Paul
Abstract: Incompatible models, heterogeneous data, and siloed data present challenges for the Oil & Gas industry. Knowledge graphs provide efficient consolidation, improved quality, and universal access to data, addressing these challenges. Developed by major global Oil & Gas and cloud organizations, the Open Subsurface Data Universe (OSDU) platform provides subsurface energy data ingestion, enrichment, and consumption services, as well as metadata storage, indexing, and search services. OSDU data supply chain aligns with the main concepts of the new trending data architecture, Data Mesh, such as federated data governance, decoupling data from applications, and domain specific data products. Data integration in subsurface data industry can be achieved by building a domain knowledge graph based on standard and enriched OSDU framework schemas. A knowledge graph-based solution begins with building a domain ontology. The purpose of this article is to introduce the OSDU ontology, which is publicly available on GitHub under the Apache 2.0 license. This paper discusses OSDU ontology design, development, applications, and evaluation.
Download
Paper Nr: 55
Title:

Using Paraphrasers to Detect Duplicities in Ontologies
Authors:

Lukáš Korel, Alexander S. Behr, Norbert Kockmann and Martin Holeňa
Abstract: This paper contains a machine-learning-based approach to detect duplicities in ontologies. Ontologies are formal specifications of shared conceptualizations of application domains. Merging and enhancing ontologies may cause the introduction of duplicities into them. The approach to duplicities proposed in this work presents a solution that does not need manual corrections by domain experts. Source texts consist of short textual descriptions from considered ontologies, which have been extracted and automatically paraphrased to receive pairs of sentences with the same or a very close meaning. The sentences in the received dataset have been embedded into Euclidean vector space. The classification task was to determine whether a given pair of sentence embeddings is semantically equivalent or different. The results have been tested using test sets generated by paraphrases as well as on a small real-world ontology. We also compared solutions by the most similar existing approach, based on GloVe and WordNet, with solutions by our approach. According to all considered metrics, our approach yielded better results than the compared approach. From the results of both experiments, the most suitable for the detection of duplicities in ontologies is the combination of BERT with support vector machines. Finally, we performed an ablation study to validate whether all paraphrasers used to create the training set for the classification were essential.
Download
Paper Nr: 63
Title:

Extending the Meta Model for Enterprise Systems Dynamics from a Software Tooling Perspective
Authors:

Huda Hussain and Marne de Vries
Abstract: Literature indicates that systems dynamics (SD) has the potential of modelling the behaviour of a system to understand enterprise behaviour and the effect of enterprise policies to address multiple performance areas. Since SD concepts are ill-defined, a meta model for enterprise systems dynamics (MMESD) was developed, using the general ontology specification language (GOSL). The first version of the MMESD was applied to an existing case within the car industry, where the case was modelled with the software named Vensim. The MMESD was developed without considering meta model implementations within multiple SD software tools. This article investigates the use of SD concepts in different SD software tools, highlighting the differences in the use of symbolic formalisms. The main contribution of the paper is extracting new concepts when we compare existing software tools, identifying concepts that are not already reflected in the first version of MMESD. We use the results to further extend the first version of MMESD, and apply an extended second version of MMESD to an existing teacher education faculties case in Croatia as a demonstration. The paper concludes with suggestions for future research.
Download
Paper Nr: 83
Title:

OntoEffect: An OntoUML-Based Ontology to Explain SARS-CoV-2 Variants’ Effects
Authors:

Ruba Al Khalaf, Anna Bernasconi and Alberto G. S.
Abstract: The SARS-CoV-2 virus continuously accumulates genetic variation through mutations; mutations are the virus’ way to achieve viral adaptation. Although the huge amount of information accumulated on the virus during the COVID-19 pandemic, the knowledge that contributes to explaining and supporting the research related to SARS-CoV-2 characteristics and evolution is not currently organized, nor systematized. Here, we present OntoEffect, an ontology that captures and represents such information systematically. Specifically, we aim to represent the dimensions of the virus and its mutations, discussing their impacts on the virus itself, as well as on public health, prevention, and treatment protocols. Aiming to obtain ontological clarity in such a complex domain, OntoEffect was built using OntoUML, an ontology-driven conceptual modeling language, grounded on the Unified Foundational Ontology (UFO). In the highly specialized context of virology, we show the powerful ability of ontological models to provide clear and precise explanations of a domain and allow its shared understanding among stakeholders.
Download
Paper Nr: 88
Title:

BioSTransformers for Biomedical Ontologies Alignment
Authors:

Safaa Menad, Wissame Laddada, Saïd Abdeddaïm and Lina F. Soualmia
Abstract: This paper aims at describing the new siamese neural models that we have developed. They optimize a self supervised contrastive learning function on scientific biomedical literature articles. The results obtained on several benchmarks show that the proposed models are able to improve various biomedical tasks without examples (zero shot) and are comparable to biomedical transformers fine-tuned on supervised data specific to the problems addressed. Moreover, these new siamese models are exploited to align biomedical ontologies, demonstrating their semantic mapping capabilities. We then compare the different approaches of alignments that we have proposed. In conclusion, we propose a distinct methods and data sources that we evaluate and compare to validate our alignments.
Download
Paper Nr: 155
Title:

UpKG: A Framework to Insert New Domains in Knowledge Graphs
Authors:

Jesamin M. Zevallos-Quispe, André G. Regino, Víctor S. Chico, Víctor Hochgreb de Freitas and Julio D. Reis
Abstract: In recent years, the creation of Knowledge Graphs (KGs) has advanced significantly. They have become essential in several domains, such as e-commerce. E-commerce applications apply them in the search and recommendation of products and virtual chatbots, among other tasks. However, e-commerce must constantly cover new domains/categories to respond to new user needs. This process requires rigorous analysis to cover new domains, adding novel knowledge not stored in the KG. This study proposes, builds, and evaluates a framework we named UpKG to insert new domains in existing KGs within an e-commerce context. Our approach relies on questions and answers collected in the real-world context of the GoBots company to facilitate the new domain insertion process. Our framework was applied in GoBots company, specialized in e-commerce solutions in Latin America. The conducted case was on an existing KG, whose triples were dominated by the Automobile domain. Our work covered and inserted novel triples concerning the Appliances domain. The conducted evaluation shows that we can verify the feasibility and applicability of the UpKG framework.
Download
Paper Nr: 158
Title:

Towards an Ontology of Task Dependence in Organizations
Authors:

Mena Rizk, Mark Fox and Daniela Rosu
Abstract: In the face of an increasingly dynamic, complex, and uncertain task environment, effective coordination is crucial for organizational success. Based on a real-world case study investigating the nature of coordination challenges in a municipal infrastructure project, we identified shortcomings in the representational frameworks offered by organization studies and enterprise modelling that limit their ability to effectively model task dependence and assist in improving coordination. Starting from existing organizational research literature and domain expertise, we conducted an ontological analysis of task-related concepts, formulated representational requirements, and proposed a formalization. Our approach defines task dependence in terms of the constraints one task imposes on another, underpinned by novel constructs that define how and why a task is constrained. These constructs support the inference of dependencies between tasks, facilitating the discovery of potentially hidden, latent dependencies. We formalized our conceptualization in an ontology, detailed herein using first-order logic. Consistency-verified implementations in Prover9 and OWL are provided. We validated our approach by modelling and solving real-life scenarios provided by our domain-expert collaborators. Our approach lays the groundwork for future extensions that will tackle the modelling of different forms of dependence between agents within an organization.
Download
Paper Nr: 168
Title:

Ontology-Driven Extraction of Contextualized Information from Research Publications
Authors:

Vayianos Pertsas and Panos Constantopoulos
Abstract: We present transformer-based methods for extracting information about research processes from scholarly publications. We developed a two-stage pipeline comprising a transformer-based text classifier that predicts whether a sentence contains the entities sought in tandem with a transformer-based entity recogniser for finding the boundaries of the entities inside the sentences that contain them. This is applied to extracting two different types of entities: i) research activities, representing the acts performed by researchers, which are entities of complex lexico-syntactic structure, and ii) research methods, representing the procedures used in performing research activities, which are named entities of variable length. We also developed a system that assigns semantic context to the extracted entities by: i) linking them according to the relation employs(Activity,Method) using a transformer-based binary classifier for relation extraction; ii) associating them with information extracted from publication metadata; and iii) encoding the contextualized information at the output into an RDF Knowledge Graph. The entire workflow is ontology-driven, based on Scholarly Ontology, specifically designed for documenting scholarly work. Our methods are trained and evaluated on a dataset comprising 12,626 sentences, manually annotated for the task at hand, and shown to surpass simpler transformer-based methods and baselines.
Download
Paper Nr: 177
Title:

Characterizing Complex Network Properties of Knowledge Graphs
Authors:

Anderson Rossanez, Ricardo S. Torres and Julio D. Reis
Abstract: Knowledge Graphs have been established as one the most relevant representations to encode knowledge, with relevant applications in the public and private sectors. One common research direction concerning the analysis of created knowledge graphs relies on the assumption that their intrinsic properties and structure are similar to what is observed in complex networks. However, studies concerning identifying typical complex network structures in knowledge graphs are lacking in the literature. This paper bridges this gap by analyzing commonly and recently used knowledge graphs in the semantic web field, seeking to demonstrate their complex network properties. Evaluation involving DBpedia and Wikidata data confirms the occurrence of intrinsic complex network structures in their respective knowledge graphs.
Download
Paper Nr: 184
Title:

Knowledge Graphs Extracted from Medical Appointment Transcriptions: Results Generating Triples Relying on LLMs
Authors:

Rafael Roque de Souza, Thiago L. Pinheiro, Julio B. Oliveira and Julio D. Reis
Abstract: Knowledge Graphs (KGs) represent computer-interpretable interactions between real-world entities. This can be valuable for representing medical data semantically. We address the challenge of automatically transforming transcripted medical conversations (clinical dialogues) into RDF triples to structure clinical information. In this article, we design and develop a software tool that simplifies clinical documentation. Our solution explores advanced techniques, such as the Fine-tuned GPT-NeoX 20B model, to extract and summarize crucial information from clinical dialogues. We designed the solution’s architecture, supported by technologies such as Docker and MongoDB, to be durable and scalable. We achieve accurate medical entity detection from Portuguese-language textual data and identify semantic relationships in interactions between doctors and patients. By applying advanced Natural Language Processing techniques and Large Language Models (LLMs), our results improve the accuracy and relevance of RDF triples generated from clinical textual data.
Download
Short Papers
Paper Nr: 28
Title:

Development of an OWL Ontology Based on the Function-Oriented System Architecture to Support Data Synchronization Between SysML and Domain Models
Authors:

Yizhe Zhang, Georg Jacobs, Jia Zhao, Joerg Berroth and Gregor Hoepfner
Abstract: A promising approach to systems engineering is called Model-Based Systems Engineering (MBSE), which is increasingly accepted to support the development process of complex systems. In MBSE,engineers use Systems Modeling Language (SysML) for formalized modeling of function-oriented system architecture and solution architecture that enable the integration of various domain models to support a seamless system development process. Domain models simulate the physical behaviors of systems with design parameters so as to realize the quantitative analysis and verification of systems. These design parameters often exist in multiple heterogeneous data sources and often rely on manual importation into the SysML model. However, when systems become complex with a large data volume, manual data exchanges between multiple data sources and SysML models become time-consuming and error-prone. Therefore, this work proposes an ontology based on Web Ontology Language (OWL) for managing data in a standardized way and solving heterogeneous problems. Then, an automatic synchronization mechanism is established between the ontology and the SysML model for easy exchange of data. This work demonstrates and validates the proposed approach with a case study of a technical system (i.e., wind turbine system). The contribution of this work is the creation of a standardized OWL ontology that supports an automatic synchronization between the data from multiple domain models and the SysML models, thus reducing the manual effort of dealing with heterogeneous data sources and the risk of data inconsistency occurring in manual data transmission.
Download
Paper Nr: 71
Title:

Mechanical Fault Prediction Based on Event Knowledge Graph
Authors:

Li He, Liang Zhang and Wei Yan
Abstract: Currently, the majority of diagnoses in the field of mechanical faults are performed by experts or expert systems, which require domain experts to guide the completion while having subpar and limited portability. Consequently, we analyzed the current situation of rolling bearing fault, event knowledge graph and convolutional neural network, explored the intelligent fault diagnosis and prediction technology of rolling bearing, introduced event knowledge graph and convolutional neural network in rolling bearing fault diagnosis, provided support for fault diagnosis and prediction, enhanced the accuracy of fault diagnosis and prediction, and enabled the predictive of complex mechanical equations.
Download
Paper Nr: 76
Title:

An Ontology-Based Question-Answering, from Natural Language to SPARQL Query
Authors:

Davide Varagnolo, Dora Melo and Irene P. Rodrigues
Abstract: In this paper an Ontology-based Question-Answering system for exploring the information on CIDOC-CRM ontology representing the Portuguese Archives metadata text descriptions is presented. The proposed approach transforms the natural language input question into a SPARQL query over the target knowledge base, the Portuguese Archives CIDO-CRM Population. To interpret the userś natural language questions, a pipeline with a natural language grammar, Stanza, a Discourse Representation Structure builder and the final question interpretation on a Query ontology is used. After obtaining the best representation of the user question on the Query ontology, the query constraints classes and properties are translated to CIDOC-CRM ontology and a SPARQL query is generated. The matching of the questions DRS on the query ontology is done as a constraint satisfaction problem and the choice of the best interpretation (matching) is obtained by solving a multi-objective optimizer.
Download
Paper Nr: 79
Title:

Memory Net: Generalizable Common-Sense Reasoning over Real-World Actions and Objects
Authors:

Julian Eggert, Joerg Deigmoeller, Pavel Smirnov, Johane Takeuchi and Andreas Richter
Abstract: In this paper, we explore how artificial agents (AAs) can understand and reason about so called ”action pat-terns” within real-world settings. Essentially, we want AAs to determine which tools fit specific actions, and which actions can be executed with certain tools, objects or agents, based on real-world situations. To achieve this, we utilize a comprehensive Knowledge Graph, called ”Memory Net” filled with interconnected everyday concepts, common actions, and environmental data. Our approach involves an inference technique that harnesses semantic proximity through subgraph matching. Comparing our approach against human responses and a state-of-the-art natural language model based machine learning approach in a home scenario, our Knowledge Graph method demonstrated strong generalization capabilities, suggesting its promise in dynamic, incremental and interactive real world settings.
Download
Paper Nr: 90
Title:

Discovering Ontological Knowledge in Unstructured Recipes of a Portuguese Monk from the 16th Century
Authors:

Orlando Belo, Bruno Silva and Anabela Barros
Abstract: Ontology learning is often applied to textual data sources with the aim of identifying, extracting and representing their various data elements, as well as their semantic relationships. Ontologies are excellent instruments for the representation of knowledge about one or more domains of knowledge, which enable us to study in detail the knowledge of the domain they host. With this in mind, we devised and developed a semi-automatic ontology learning system. It was specifically oriented for discovering the knowledge contained in a set of ancient texts of culinary recipes of a monk of the 16th century. Using the system, we produced an ontology incorporating a large diversity of culinary elements and their relationships, which offer a very rich field of research of the culinary of the 16th century in Portugal – the ontology was exposed and explored using the native mechanisms of a graph database management system.
Download
Paper Nr: 91
Title:

On the Development of a Collaborative Knowledge Platform for Engineering Sciences
Authors:

Jonas Jepsen, Arthur Zamfir, Brigitte Boden, Jacopo Zamboni and Erwin Moerland
Abstract: Knowledge is undoubtedly one of the most important assets for all organizations. Losing knowledge that once was considered part of an organization always poses a problem. When knowledge is concentrated on single individuals, as is often the case in research environments, this is particularly difficult to avoid. This is also true for software developed by individuals such as Knowledge-Based Engineering (KBE) applications. In this paper we show how the Codex Framework, which is based on Semantic Web Technologies (SWT), can be used for creating, maintaining and inspecting formalized knowledge in a way which also fosters its reuse and execution. We show use cases where Codex was applied and discuss the advantages and shortcomings compared to a conventional Object-Oriented Programming (OOP) approach. From these experiences we then draw conclusions on why the adoption rate of Codex is below expectation and present a newly developed collaborative knowledge platform which is designed to overcome the identified challenges.
Download
Paper Nr: 93
Title:

Modelling Expressions of Physical Quantities
Authors:

Blair D. Hall
Abstract: To express a quantity in conventional scientific notation, a number is paired with a unit of measurement, like 10 m/s -1 . However, this notation can be ambiguous and may require people to understand the context in order to resolve interpretation difficulties. Also, the notation is intended to describe a certain type of scientific data and is ill-equipped to express other kinds of measurement results. This paper discusses an alternative formalism that is suitable for digital systems and overcomes many of the difficulties associated with conventional written notation. We present the proposal using modelling elements that are closely related to scientific concepts that underpin a wide range measurements. The alternative format for expressions is a triplet: a number and a pair of references to information stored centrally. The mathematical properties of data and, in a general sense, the property that is measured, can be captured in this extended format.
Download
Paper Nr: 104
Title:

Exploring User-Generated Content to Detect Community Problems: The Ontological Model of ALLEGRO
Authors:

Carlos Periñán-Pascual
Abstract: Social-media services contribute to creating situation awareness, thus offering a snapshot of today’s society. Citizens can use such communication channels to report problems concerning the quality of life of individuals and the well-being of the community in which they live. Therefore, we can develop applications that can analyse online user-generated data about a variety of problems from different topics (e.g. education, health, or politics, among many others) to reconstruct the state of society as interpreted by social-media users in the given community. In this context, the main objective of this paper is to describe the ontological model required for representing community problems affecting quality of life and well-being, and how this ontology supports the natural language processing and text-mining tasks of topic categorisation and keyword extraction. This ontological model can become a significant component in natural language understanding applications, particularly in those where machine-learning or neural-network models are enhanced with external knowledge to perform opinion mining.
Download
Paper Nr: 114
Title:

Towards Developing an Ontology for Safety of Navigation Sensors in Autonomous Vehicles
Authors:

Mohammed Alharbi and Hassan A. Karimi
Abstract: Understanding and handling uncertainties associated with navigation sensors in autonomous vehicles (AVs) is vital to enhancing their safety and reliability. Given the unpredictable nature of real-world driving environments, accurate interpretation and management of such uncertainties can significantly improve navigation decision-making in AVs. This paper proposes a novel semantic model (ontology) for navigation sensors and their interactions in AVs, focusing specifically on sensor uncertainties. At the heart of this new ontology is understanding the sources of sensor uncertainties within specific environments. The ultimate goal of the proposed ontology is to standardize knowledge of AV navigation systems for the purpose of alleviating safety concerns that stand in the way of widespread AV adoption. The proposed ontology was evaluated with scenarios to demonstrate its functionality.
Download
Paper Nr: 125
Title:

Design a Recommendation System in Real Estate Investment Based on Context Approach
Authors:

Tinh T. Nguyen, Sang Vu, Truc Nguyen, Vuong T. Pham and Hien D. Nguyen
Abstract: The real estate investment industry has experienced a significant increase in user participation over the years, with individuals keen on registering concurrent interests in both recent and prior projects. This growing trend necessitates the development of an approach that can recommend real estate items in a simultaneous manner. However, the presence of unrequired memberships and stop-by behaviors has introduced several challenges, resulting in numerous cold-start scenarios for new users. This study proposes a recommendation system tailored specifically for real estate, designed to offer warm-start item recommendations of cold-start users using a content-based approach and a session-based recommendation system. Herein, a system for real estate recommendation with acceptable warm-start item recommendations is proposed in the many-cold-start-users scenario. The session-based recommendation system is adapted and made use of pre-existing methods to effectively handle sequential and contextual data for the encoded attribute prediction of the next-interacted item. Then, the nearest-neighbors method is employed weighted cosine similarity to identify conforming candidates. The results demonstrate the effectiveness of efficiently integrating the information and the difficulty in performing well in item recommendations simultaneously.
Download
Paper Nr: 141
Title:

A Methodology for Knowledge Integration and Acquisition in Model-Based Systems Engineering
Authors:

Luis P. Medinacelli, Florian Noyrit and Chokri Mraidha
Abstract: In Model-Based System Engineering (MBSE) systems are represented as models using a predefined meta-language such as SysML that hides some of the complexity behind the specification of a system, and provides experts with a rich syntax to define, share and constrain these models. Even though current MBSE design tools are sophisticated and support expressive meta-languages, these tools have limited capabilities on the detection of semantic errors, the integration of expert knowledge, or the ability to formalize the knowledge from the expert’s design. Our work addresses these limitations by annotating the SysML models with domain-specific ontologies. Enabling this interaction not only makes the ontology’s semantics available to the tooling environment, but the UML model specified by the designer can be translated into Ontology Web Language format (OWL), generating a system specification in terms of the ontology. These ”annotated models” are suitable for reasoning tasks, like consistency check and instance checking. We particularly ensure the annotated model is a consistent extension of the domain-specific ontology, thus formalizing the expert’s knowledge as a sub-ontology. This extended ontology can be re-used and shared to evaluate and constrain further models, or be itself evaluated by semantic-compatible tools. In this article we present our approach for an OWL-MBSE integration, and show its feasibility via an implementation in the UAVs domain.
Download
Paper Nr: 163
Title:

Addressing Entity Change in Procedural Ontologies
Authors:

Tyler Johnson, Mohammed Alliheedi, Yetian Wang and Robert E. Mercer
Abstract: Ontologies model a domain by representing the entities, concepts, and the relations between them. The domain of interest in this position paper is the biochemistry experimental procedure. These procedures are composed of procedure steps. These steps represent actions. Actions cause change, a concept being implicitly modelled in this type of ontology. We argue that entities undergoing change need to be properly captured in the ontology. The biochemistry procedure Alkaline Agarose Gel Electrophoresis is used to demonstrate the generality of this procedural ontology.
Download
Paper Nr: 172
Title:

A Knowledge Layer in Data-Centric Architectures in the Automotive Industry
Authors:

Haonan Qiu, Adel Ayara and Christian Muehlbauer
Abstract: As the automotive industry continues its evolution towards connected and autonomous vehicles, the need to adopt a data-centric architecture for providing sophisticated driving functions increasing important. Compared to traditional application-centric architecture, data-enteric architecture allows the collection, aggregation and analysis of data from various sources. However, such architecture lack of inference capability makes it not leverage the full potential of established AI technologies such as knowledge representation and reasoning. In this work, it is our goal to investigate how we can incorporate a knowledge layer in a data centric architecture that allows reasoning and thus support decision making. A prototype is implemented and deployed in both vehicle and backend, and the feasibility is evaluated through a real-world experiment.
Download
Paper Nr: 182
Title:

Knowledge Graphs Alignment Based on Learning to Rank Methods
Authors:

Victor Yamamoto and Julio D. Reis
Abstract: Knowledge graphs (KGs) define facts expressed as triples in representing knowledge. Usually, several knowledge graphs are published in a given domain. It is relevant to create alignments both for classes that model concepts and between instances of those classes defined in different knowledge graphs. In this article, we study techniques for aligning entities expressed in KGs. Our solution explores the supervised ranking aggregation method in the alignment based on similarity values. Our experiments rely on the dataset from the Ontology Alignment Evaluation Initiative to evaluate the proposed method in experimental analyzes. Obtained results indicate the effectiveness in our alignment technique in the investigated datasets.
Download
Paper Nr: 185
Title:

An Approach to Developing Ontology-Based Tools for Event Series Analysis
Authors:

Anton Platunov, Lyudmila Lyadova, Nada Matta, Viacheslav Lanin and Elena Zamyatina
Abstract: Existing process mining methods allow to investigate processes in different domains. Besides mandatory event attributes like as identifier, activity, and timestamp, additional event attributes can be present in data sources. The analysing dynamics of changing the values of additional attributes allows to get important information on the system. The applications must be developed by programmers with programming languages to implement new methods of analysis. An approach to develop tools based on the use of algorithm designers and expression builders like those included in MS Office applications is proposed in the paper. Their use does not require programming skills. The implementation of the approach is based on a multifaceted ontology, including descriptions of the rules for developing functions, as well as a description of functions for generating and analysing event logs in accordance with these rules. The user interface for developing rules and the algorithm for their interpreting are implemented in the research prototype of the application.
Download
Paper Nr: 192
Title:

Evaluating the Perceived Quality and Functionality of DEMO Models’ Representations in the Health Domain
Authors:

David Aveiro, Vítor Freitas, Dulce Pacheco and Duarte Pinto
Abstract: Demo’s (Design and Engineering Methodology for Organizations) Way of Modelling encompasses a collection of interconnected models and diagrams designed to depict an organization’s structure and operations in a cohesive and platform-independent manner. Nevertheless, there has been a contention that the syntax and semantics of DEMO models are overly intricate and cluttered, posing challenges for laypeople in terms of interpretation. Our research team has been working on improvements to the DEMO Modelling language for Enterprise Ontology. Previous work had shown challenges in using standard DEMO notations for model communication and validation, prompting the development of new representations. This study evaluates these representations through quality and functionality testing using a health domain case and health professionals with domain knowledge. The results of the conducted tests reveal significant differences in perceived quality and functionality between the new and traditional DEMO representations. These findings indicate a strong preference for the new representations over traditional ones. This study underscores the importance of focusing on users in enhancing the effectiveness of modelling languages like DEMO, particularly in complex domains such as healthcare. The results suggest that these new representations have the potential to improve the perceived quality and functionality of DEMO models in various practical applications, including health-related information systems.
Download
Paper Nr: 193
Title:

Navigating Responsible AI Adoption
Authors:

Daniela Oliveira
Abstract: Responsible Artificial Intelligence has been a largely discussed topic among organizations that develop or are aiming to regulate Artificial Intelligence (AI) solutions. Much less attention has been given to organizations willing to adopt AI in a responsible manner. Organizations that do not develop AI need practical guidance on how to implement Responsible AI principles. This contribution outlines the challenges organizations face integrating the Responsible AI paradigm and suggests some solutions.
Download
Paper Nr: 34
Title:

A Novel Approach to Ontological View-Based Semantic Mapping in Decentralized Environments
Authors:

Fateh A. Adhnouss, Husam A. El-Asfour and Kenneth McIsaac
Abstract: Semantic integration and interoperability are vital for effective communication and data exchange in information systems. This paper explores the significance of shared referential semantics, ontological views (OVs), and intensional semantics in achieving semantic integration. It addresses the challenges arising from divergent OVs and emphasizes the role of accessibility relations in bridging gaps between different systems. The paper presents theorems establishing relationships between accessibility relations, the overlap of non-logical symbols, and the consistency and accessibility of OVs. It also examines mapping possibilities in decentralized environments by considering scenarios with shared intended models, overlapping intended models, or no intersection of intended models. The paper uses the healthcare domain as an illustrative example of applying intensional semantics and semantic interoperability. To ensure efficient semantic integration and interoperability, systems must consider the shared meaning of the vocabulary, particularly non-logical symbols, along with the underlying conceptualizations and intensional semantics.
Download
Paper Nr: 82
Title:

IoT-Enabled Agroecology: Advancing Sustainable Smart Farming Through Knowledge-Based Reasoning
Authors:

Nicolas Chollet, Naila Bouchemal and Amar Ramdane-Cherif
Abstract: The global increase in population necessitates enhanced food security, yet current agricultural practices are inadequate in feeding everyone and are detrimental to the environment. Consequently, agriculture faces the task of increasing production while minimizing resource usage and prioritizing sustainability. To assist farmers, new technological tools using AI, Robotics and IoT have been developed in a new field called Smart Farming. Unfortunately, these tools are primarily employed in unsustainable farming practices, such as mono-cropping. However, sustainable methods like Agroecology exist, which involve observing how plants interact with their environment to devise crop management strategies that work harmoniously with nature, requiring minimal resources and ensuring sustainability. In this paper, we propose an Internet of Things (IoT) platform that utilizes an ontology and a set of rules to provide farmers with recommendations for optimizing crop development while adhering to agroecology principles. This platform employs Knowledge-based reasoning to correlate crop requirements with local environmental data obtained through a wireless sensor network deployed on the farm. It can suggest crop layouts, crop calendars, detect relevant events, and manage irrigation. Our system has been tested in a simulated environment and yielded promising results, leaving ample room for future improvements and developments.
Download
Paper Nr: 120
Title:

Semiotic Knowledge Models for Personal Knowledge Repositories
Authors:

Stefano Casadei
Abstract: Knowledge graphs have been used successfully to represent and acquire general knowledge and have also been proposed for personal knowledge representations. While general knowledge data can be modelled statistically as being a noisy projection of universal (and crisp) entities, categories, and relationships, personal knowledge data requires a more refined model: each user’s peculiarities and fluctuations in associating words with meanings and meanings with words should be tracked and analysed instead of being treated as noise and averaged out. This position paper describes a semiotic knowledge model whose primitives are the signification events which occur when symbols such as words and linguistic expressions are associated with an instantaneous meaning. Semiotic structures constructed from these primitives with users’ active participation, enable them to create, update, modify, organize, re-organize and curate detailed and comprehensive representations of their own personal knowledge by means of their own personal terminologies, taxonomies, and organizational schemes.
Download
Paper Nr: 123
Title:

Towards Semi-Automatic Approach of Building an Ontology: A Case Study on Material Handling Data
Authors:

Sepideh S. Sobhgol, Mario Thron and Giuliano Persico
Abstract: InnoSale project aims to improve sales processes for complex industrial equipment and services using AI technologies. The project addresses the challenges of time-consuming back-office support and interpreting customer requests using different vocabularies. As partners involved in the project, we are developing a semiautomated approach to the creation of an ontology for the material handling domain by merging existing terminology from leading companies in the industry. This ontology will serve as the basis for a semantic search engine to improve the generation of quotations and the matching of customer requirements. Through the use of historical data and advanced machine learning techniques, the search engine streamlines the sales process, reducing manual effort and improving response times. The results showcases how the utilization of machine learning and NLP techniques can aid in constructing an ontology in a semi-automatic fashion. The study demonstrates the effectiveness of extracting terms, identifying synonyms, and uncovering various relationships, contributing to the development of an ontology. These approaches offer potential for improving the ontology construction process and enhancing semantic search capabilities, leading to more effective information retrieval. This position paper, being concise in nature, presents our initial findings and progress in this endeavor. It’s important to note that, based on new sources of information and ongoing research in the future, the results and conclusions may evolve or differ.
Download
Paper Nr: 143
Title:

Event Detection in News Articles: A Hybrid Approach Combining Topic Modeling, Clustering, and Named Entity Recognition
Authors:

Nikos Kapellas and Sarantos Kapidakis
Abstract: This research presents a comprehensive analysis of news articles with the primary objectives of exploring the underlying structure of the data and detecting events contained within news articles. The study collects articles from Greek online newspapers and focuses on analyzing a sub-set of this data, related to a predefined news topic. To achieve this, a hybrid approach that combines topic modeling, feature extraction, clustering, and named entity recognition, is employed. The obtained results prove to be satisfactory, as they demonstrate the effectiveness of the proposed methodology in news event detection and extracting relevant contextual information. This research provides valuable insights for multiple parties, including news organizations, researchers, news readers, and decision-making systems, as it contributes to the fields of event detection and clustering. Moreover, it deepens the understanding of applying solutions that do not require explicit human intervention, to real-world language challenges.
Download
Paper Nr: 171
Title:

JThermodynamicsCloud: Case Study in an Ontology-Driven NoSQL Database Cloud Based Application in Chemical Domain
Authors:

Edward Blurock
Abstract: JThermodynamicsCloud is software service for the combustion research domain to perform thermdynamic calculations and manage the data needed to make those calculations. The JThermodynamicsCloud service can be said to be a model driven application, where the ontology is a platform independent model of the data and operational structures. All the ontology concepts outlined here, from the ontology definition to the utilization of this definition in the application, have been implemented. The ontology, as used by the service, has three distinct purposes: documentation, data structure definition and operational definitions. One goal of the ontology is to place as much of the design and domain specific structures in the ontology rather than in the application code. The calculation itself is highly dependent on the varied types of molecular data found in the database The complete service is a system with three interacting components, a user interface using Angular, a (RESTful) backend written in JAVA (with the JENA API interpreting the ontology) and the Google Firestore noSQL document database and Firebase storage.
Download
Paper Nr: 178
Title:

Developing Digital Media Service Value Creation by Using Emotion Data
Authors:

Nina Helander, Mika Boedeker and Leena Mäkelä
Abstract: Digital transformation is not only changing the way value is created in service encounters, it is also offering new ways to gather and analyse data of customer behaviour and perceptions. This paper studies perceived customer value through a case study of a media company developing its digital services and service encounters. The special focus is on studying the role of emotions in value creation in a data-centric, digitally transforming media context. Through the qualitative case study, this study contributes to value creation research stream by providing rich, empirical analysis of the role of emotions in digital value creation. Both positive and negative emotions co-exist in the smart service encounters and by identifying the drivers for positive and negative affections the service providers can finetune the technological attributes related to the service.
Download