KEOD 2018 Abstracts

Full Papers Short Papers
Full Papers
Paper Nr: 11
Title:

Automated Compliance Verification in ATM using Principles from Ontology Matching
Authors:

Audun Vennesland, Joe Gorman, Scott Wilson, Bernd Neumayr and Christoph G. Schuetz
Abstract: Compliance with standard information models in diverse and complex domains such as Air Traffic Management is an important but highly challenging task. The challenges stem from the fact that the information models are often extensive, the diversity of the domain leads to diverging terminology, and the manual mapping of information elements necessary to assess compliance is very labor-intensive. This work proposes ways in which compliance verification techniques, currently based on manual techniques, can be supported and partly automated by means of a set of basic ontology matching techniques. We have evaluated these techniques in an experiment involving seven datasets consisting of various ATM ontologies that have been transformed to OWL from their original UML representations. A comparative analysis with two other state-of-the-art matching systems shows that some of our proposed matching techniques obtain good quality alignments, especially when they are combined using simple strategies. The evaluation also reveals that identifying equivalence relations is a far easier task than identifying other types of semantic relations.
Download
Paper Nr: 18
Title:

Recommender System to Improve Knowledge Sharing in Massive Open Online Courses
Authors:

Sarra Bouzayane and Inès Saad
Abstract: This paper focuses on the support process, within a Massive Open Online Course (MOOC), that is currently unsatisfactory because of the very limited size of the pedagogical team compared to the massive number of the enrolled learners who need support. Indeed, many of the MOOC learners can not appropriate the information they receive and must therefore be assisted in order to not abandon the course. Thus, to help these learners take advantage of the course they follow, we propose a tool to recommend to each of them an ordered list of “Leader learners” who are able to support him throughout his navigation in the MOOC environment. The recommendation phase is based on a multicriteria decision making approach to weekly predict the set of “Leader learners”. Moreover, since the MOOC learners’ profiles are very heterogeneous, we recommend to each of them the leaders who are most appropriate to his profile in order to ensure a good understanding between them. The recommendation we propose is validated on real data coming from a French MOOC and has proved satisfactory results.
Download
Paper Nr: 20
Title:

Semantic Representation of Neuroimaging Observations: Proof of Concept based on the VASARI Terminology
Authors:

Emna Amdouni and Bernard Gibaud
Abstract: The main objective of this work is to facilitate the identification, sharing and reasoning about cerebral tumors observations via the formalization of their semantic meanings in order to facilitate their exploitation in both the clinical practice and research. We have focused our analysis on the VASARI terminology as a proof of concept, but we are convinced that our work can be useful in other biomedical imaging contexts. In this paper, we propose (1) a methodology, a domain ontology and an annotation tool for providing unambiguous formal definitions of neuroimaging data, (2) an experimental work on the REMBRANDT dataset to demonstrate the added value of our work over existing methods, namely DICOM SR and the AIM model.
Download
Paper Nr: 21
Title:

An Ontology-based Approach to Generate the Advanced Driver Assistance Use Cases of Highway Traffic
Authors:

Wei Chen and Leïla Kloul
Abstract: Autonomous vehicles perceive the environment with different kinds of sensors (camera, radar, lidar...). They must evolve in an unpredictable environment and a wide context of dynamic execution, with strong interactions. In order to generate the safety of the autonomous vehicle, its occupants and the others road users, it is necessary to validate the decisions of the algorithms for all the situations that will be met. These situations are described and generated as different use cases of automated vehicles. In this work, we propose an approach to generate automatically use cases of autonomous vehicle for highway. This approach is based on a three layers hierarchy, which exploits static and mobile concepts we have defined in the context of three ontologies: highway, weather and vehicle. The highway ontology and the weather ontology conceptualize the environment in which evolves the autonomous vehicle, and the vehicle ontology consists of the vehicle devices and the control actions. To apply our approach, we consider a running example about the insertion of a vehicle by the right entrance lane of a highway.
Download
Paper Nr: 30
Title:

Computation Control by Prioritized ET Rules
Authors:

Kiyoshi Akama, Ekawit Nantajeewarawat and Taketo Akama
Abstract: Model-intersection problems have been invented as one of the largest classes of logical problems. By solving MI problems, we can solve proof problems and query-answering problems on first-order logic. For solving MI problems on extended clauses, we propose in this paper prioritized equivalent transformation (ET) rules. A set R of ET rules with priority ordering is employed, and at each computation step an applicable ET rule with best priority in R is selected and applied. This method can be used to decrease a search space by introducing new rules and adjusting rule priority, and is useful to solve a large class of logical problems with the guarantee of strict correctness of computation results.
Download
Paper Nr: 32
Title:

Safe Driving Mechanism: Detection, Recognition and Avoidance of Road Obstacles
Authors:

Andrea Ortalda, Abdallah Moujahid, Manolo Dulva Hina, Assia Soukane and Amar Ramdane-Cherif
Abstract: In an intelligent vehicle (autonomous or semi-autonomous), detection and recognition of road obstacle is very important for it is the failure to recognize an obstacle on time which is the primary reason for road vehicular accidents that very often leads to human fatalities. In the intelligent vehicle of the future, safe driving is a primary consideration. This is accomplished by integrating features what will assist drivers in times of needs, one of which is avoidance of obstacle. In this paper, our knowledge engineering is focused on the detection, classification and avoidance of road obstacles. Ontology and formal specifications are used to describe such mechanism. Different supervised learning algorithms are used to recognize and classify obstacles. The avoidance of obstacles is implemented using reinforcement learning. This work is a contribution to the ongoing research in safe driving, and a specific application of the use of machine learning to prevent road accidents.
Download
Paper Nr: 36
Title:

Ontology Selection for Reuse: Will It Ever Get Easier?
Authors:

Marzieh Talebpour, Martin Sykora and Tom Jackson
Abstract: Ontologists and knowledge engineers tend to examine different aspects of ontologies when assessing their suitability for reuse. However, most of the evaluation metrics and frameworks introduced in the literature are based on a limited set of internal characteristics of ontologies and dismiss how the community uses and evaluates them. This paper used a survey questionnaire to explore, clarify and also confirm the importance of the set of quality related metrics previously found in the literature and an interview study. According to the 157 responses collected from ontologists and knowledge engineers, the process of ontology selection for reuse depends on different social and community related metrics and metadata. We believe that the findings of this research can contribute to facilitating the process of selecting an ontology for reuse.
Download
Paper Nr: 38
Title:

Using DBpedia Categories to Evaluate and Explain Similarity in Linked Open Data
Authors:

Houcine Senoussi
Abstract: Similarity is defined as the degree of resemblance between two objects. In this paper we present a new method to evaluate similarity between resources in Linked Open Data. The input of our method is a pair of resources belonging to the same type (e.g. Person or Painter), described by their Dbpedia categories. We first compute the ’distance’ between each pair of categories. For that we need to explore the graph whose vertices are the categories and whose edges connect categories and sub-categories. Then we deduce a measure of the similarity/dissimilarity between the two resources. The output of our method is not limited to this measure but includes other quantitative and qualitative informations explaining similarity/dissimilarity of the two resources. In order to validate our method, we implemented it and applied it to a set of DBpedia resources that refer to painters belonging to different countries, centuries and artistic movements.
Download
Paper Nr: 52
Title:

Comparing of Term Clustering Frameworks for Modular Ontology Learning
Authors:

Ziwei Xu, Mounira Harzallah and Fabrice Guillet
Abstract: This paper aims to use term clustering to build a modular ontology according to core ontology from domain-specific text. The acquisition of semantic knowledge focuses on noun phrase appearing with the same syntactic roles in relation to a verb or its preposition combination in a sentence. The construction of this co-occurrence matrix from context helps to build feature space of noun phrases, which is then transformed to several encoding representations including feature selection and dimensionality reduction. In addition, the content has also been presented with the construction of word vectors. These representations are clustered respectively with K-Means and Affinity Propagation (AP) methods, which differentiate into the term clustering frameworks. Due to the randomness of K-Means, iteration efforts are adopted to find the optimal parameter. The frameworks are evaluated extensively where AP shows dominant effectiveness for co-occurred terms and NMF encoding technique is salient by its promising facilities in feature compression.
Download
Paper Nr: 53
Title:

Ontological Representation of Constraints for Geographical Reasoning
Authors:

Gianluca Torta, Liliana Ardissono, Marco Corona, Luigi La Riccia and Angioletta Voghera
Abstract: We describe a framework that supports multiple types of constraint-based reasoning tasks on a geographic domain, by exploiting a semantic representation of the domain itself and of its constraints. Our approach is based on an abstract graph representation of a geographical area and of its relevant properties, for performing the reasoning tasks. As a test-bed, we consider the domain of Ecological Networks (ENs), which describe the structure of existing real ecosystems and help planning their expansion, conservation and improvement by introducing constraints on land use. While some previous work has been done about supporting the verification of compliance of fully specified ENs, we aim at taking a significant step further, by addressing the automatic suggestion of suitable aggregations of land patches into elements of the EN. This automated generation of EN elements is relevant to support the human planner in the design of public policies for land use because it leverages automated tools to carry out a possibly lengthy and error-prone task.
Download
Paper Nr: 58
Title:

Redefining Hearst Patterns by using Dependency Relations
Authors:

Ahmad Issa Alaa Aldine, Mounira Harzallah, Berio Giuseppe, Nicolas Béchet and Ahmad Faour
Abstract: Hypernym relation extraction is considered the backbone of building ontologies. Hearst patterns are the most popular patterns used to extract hypernym relation. They include POS tags and lexical information, and they are applied on a shallow parsed corpora. In this paper, we propose a new formalization of Hearst patterns using dependency parser, called Dependency Hearst patterns. This formalization allows them to match better complex or ambiguous sentences. To evaluate our proposal, we have compared the performance of Dependency Hearst patterns to that of the lexico-syntactic Hearst patterns, applied on a music corpus. Dependency Hearst patterns yield a better result than lexico-syntactic patterns for extracting hypernym relations from the corpus.
Download
Short Papers
Paper Nr: 5
Title:

Harvesting Organization Linked Data from the Web
Authors:

Zhongguang Zheng, Yingju Xia, Lu Fang, Yao Meng and Jun Sun
Abstract: In this paper, we describe our approach of automatically extracting property-value pairs from the Web for organizations when only the name and address information are known. In order to explore the enormous knowledge from the Web, we first retrieve the Web pages containing organization properties by search engine, and then automatically extract the property-value pairs regardless of heterogeneous Web page structures. Our method does not require any training data or human-made template. We have constructed an organization knowledge base containing 3 million entities extracted from the Web for 4.2 million organizations which only have name and address information. The experiment shows that our approach makes it possible and effective for people to construct their own knowledge base.
Download
Paper Nr: 7
Title:

Simplifying Data Preparation for Analysis using an Ontology for Machine Data
Authors:

Dipali Tole and Nikhil Joshi
Abstract: Vehicle manufacturers gather large amounts of data through on-board sensors and other systems, for applications, such as real-time diagnostics, prognostics, design improvements, etc. However, a lot of time is spent in preparing the data for specific analyses. Moreover, this data preparation requires people having expert knowledge about various data schemas and structures used, as well as the specific domain or vehicle systems that the data pertains to. This paper proposes an approach using a formal Ontology to capture knowledge about the domain, and a reasoner to query and prepare data. Using a demonstrative example, the paper presents a comparison of the current approach to preparing data using experts with the proposed approach. The preliminary findings from the study suggest that the proposed approach is promising, and provides unique advantages specifically when faced with distributed, polymorphic data structures, that may change over time.
Download
Paper Nr: 9
Title:

Aided OWL Notation (AOWLN): Conceptual Modelling and Visualisation of Advanced SWRL Rules
Authors:

Johannes Nguyen, Jannik Geyer, Thomas Farrenkopf and Michael Guckert
Abstract: Ontologies are a common and generally accepted instrument for the documentation of knowledge in a forma-lised machine readable form. This paper focuses on ontologies encoded in Web Ontology Language (OWL). OWL is description-logic based and can be extended by using Semantic Web Rule Language (SWRL) to express Horn clause like rules that allow the ontology to go beyond the scope of the more object-centric description logic propositions. The combination of OWL and SWRL has proved to be highly useful in practical applications. However, SWRL rules soon become complex and confusing in mere textual representations. This particular issue becomes obvious when ontologies grow in size and the number of rules increases. A solution for this problem can be an appropriate graphical representation of the rules. This paper proposes a graphical visualisation concept for SWRL rules that we call Aided OWL Notation (AOWLN). Additionally, we present a prototypical Protégé plugin that automatically visualises rules.
Download
Paper Nr: 10
Title:

Reviewing Task and Planning Ontologies: An Ontology Engineering Process
Authors:

Julita Bermejo-Alonso
Abstract: Bermejo-Alonso and colleagues (Bermejo-Alonso et al., 2018) define an ontology for tasks and planning in the autonomous system domain. It focuses on an emergency scenario for Unmanned Ground Vehicles (UGVs) or Unmanned Aerial Vehicles (UAVs). In this context, it is necessary to define how the autonomous system will act, detailing how the actions should be done to achieve system goals. The planning process starts with detailing the planning domain knowledge: the initial state, the goals, the actors, the resources, etc. This domain knowledge is then fed into a planner that, if a solution exists, will produce a plan or a set of plans to be used by the robotic system. Ontologies are a useful way to provide this domain knowledge and can be used to characterise the planning domain knowledge. However, there is a number of available ontologies for planning, being unclear which one is best for autonomous systems. This paper presents a review of existing task and planning vocabularies, taxonomies and ontologies, as a necessary first step in an ontology engineering process that addressed the autonomous system planning needs. This paper describes the analised ontologies, their main features, and how the process to integrate them was carried out.
Download
Paper Nr: 12
Title:

Single Rule Evaluation (SRE): Computational Algorithmic Debugging for Complex SWRL Rules
Authors:

Jannik Geyer, Johannes Nguyen, Thomas Farrenkopf and Michael Guckert
Abstract: SWRL is an extension for OWL which allows the use of Horn clause like rules in ontologies. SWRL rules are an expressive instrument for OWL-based ontologies simplifying and augmenting deductive reasoning capabilities. With increasing size and complexity rule bases becomes more and more fragile as logical inconsistencies in the overall structure of the rule base are difficult to find. However, available debugging options require immense manual effort, if not even become an impossible task. Therefore, there is an expressed need for developers and end users to get an efficient and easy to use interactive rule evaluation instrument. In this paper we present a new method for a simplified debugging process that we call Single Rule Evaluation (SRE). This SRE method enables the user to iterate through the reasoning process of the ontology and the set of inference rules and examines each atom of a selected SWRL Rule to deliver detailed information about the inferred output. In addition to a theoretical concept, we present a prototypical implementation of SRE as a Protégé plugin that can be invoked during the modelling process to test rules for consistency.
Download
Paper Nr: 14
Title:

Controlling the Drift of Semantic Indexing Systems
Authors:

Ivan Garrido Marquez, Jorge Garcia Flores, François Lévy and Adeline Nazarenko
Abstract: Document classification is often meant to serve as semantic indexing to help readers finding documents related to a given topic. However, the quality of indexing often deteriorates with time: some categories are misused or forgotten by indexers, others become obsolete or too general to be useful. This paper proposes measures to assess the quality of an indexing system and an algorithm that guides indexers in restructuring their indexes. Focus is put on the reader’s rather than on the annotator’s point of view (Does the classification really help accessing information? vs. Is a category adequate with the content of the document?). The whole approach is illustrated on a corpus of 20 blogs which posts are associated with categories. We show that indexers have difficulties to adapt the blogs indexing systems when the number of posts increases and we show that our approach can significantly improve the quality of these indexing systems, by simulating blog restructuring.
Download
Paper Nr: 17
Title:

Modelling Weightlifting “Training-Diet-Competition” Cycle Ontology with Domain and Task Ontologies
Authors:

Piyaporn Tumnark, Miguel Abreu, Miguel Macedo, Paulo Cardoso, Jorge Cabral and Filipe Conceição
Abstract: Studies in weightlifting have been characterized by unclear results, and paucity of information. This is due to the fact that enhancing the understanding of the mechanics of successful lift requires collaborative contributions of several stakeholders such as coach, nutritionist, biomechanist, and physiologist as well as the aid of technical advances in motion analysis, data acquisition, and methods of analysis. Currently, there are still a lack of knowledge sharing between these stakeholders. The knowledge owned by these experts are not captures, classified or integrated into an information system for decision-making. In this study, we propose an ontology-driven weightlifting knowledge model as a solution for promoting a better understanding of the weightlifting domain as a whole. The study aims to build a knowledge framework for Olympic weightlifting, bringing together related knowledge subdomains such as training methodology, biomechanics, and dietary while modelling the synergy among them. In so doing, terminology, semantics, and used concepts will be unified among researchers, coaches, nutritionists, and athletes to partially obviate the recognized limitations and inconsistencies. The whole weightlifting "training-diet-competition" (TDC) cycle is semantically modelled by conceiving, designing, and integrating domain and task ontologies with the latter devising reasoning capability toward an automated and tailored weightlifting TDC cycle.
Download
Paper Nr: 23
Title:

The Treatment of Gerund Forms for Arabic Nouns with LKB System
Authors:

Samia Ben Ismail, Sirine Boukédi and Kais Haddar
Abstract: The treatment of morphological phenomena is important in Natural Language Processing (NLP), especially using a unification grammar. In Arabic grammar, the gerund is considered one of the most delicate morphological structures since it changes the grammatical category. Thus, we present in this paper, a Head-driven Phrase Structure Grammar (HPSG), treating Arabic gerund forms. The elaborated grammar is specified with Type Description Language (TDL) and validated on Linguistic Knowledge Building (LKB) system. The obtained results were encouraging, which proves the effectiveness of our system.
Download
Paper Nr: 31
Title:

Side-Change Transformation
Authors:

Kiyoshi Akama, Ekawit Nantajeewarawat and Taketo Akama
Abstract: Many logical problems, such as proof problems and query-answering problems, can be mapped into model-intersection (MI) problems, which constitute one of the largest and most fundamentally important classes of logical problems. To solve MI problems, many equivalent transformation rules have been employed. In this paper, we introduce a new transformation, called side-change transformation, and propose unfolding/side-change computation control, i.e., when neither unfolding nor definite-clause removal is applicable, an attempt is made to transform a given problem using side-change transformation so as to derive an equivalent problem to which unfolding is applicable. The correctness of side-change transformation is shown. While a resolution-based proof method increases problem size monotonically no matter what control is taken, a reduction of problem size can often be achieved by using the unfolding/side-change control.
Download
Paper Nr: 41
Title:

Quisper Ontology Learning from Personalized Dietary Web Services
Authors:

Tome Eftimov, Gordana Ispirova, Paul Finglas, Peter Korošec and Barbara Koroušić Seljak
Abstract: Unhealthy diet can lead to diseases such as diabetes, allergies, and some types of cancer, among other health-related problems. In order to help users and clinical dietitians access the relevant knowledge about food and nutrition data in e-health systems that use different data sources, ontologies about food and related domains, such as clinical medicine, individual user profile, etc., are very important in providing successful and smart e-health systems. In this paper we present an ontology-learning process using personalized dietary web services that are dealing with food-related data and knowledge rules. The result of the ontology-learning process is an OWL ontology that is developed in a semi-automatic way and can be used for the harmonization of personalized dietary web services and will enable researchers to share information in this domain. In addition, it can also use aggregated data from different sources to provide new knowledge and help people live healthier lives.
Download
Paper Nr: 44
Title:

Complex Task Ontology Conceptual Modelling: Towards the Development of the Agriculture Operations Task Ontology
Authors:

Elcio Abrahão and André Riyuiti Hirakawa
Abstract: Different from domain ontologies, task ontologies must describe the knowledge from its structural and behavioural views, considering aspects as sequence of execution, conditional deviation, external expected and unexpected events interference, pre and post conditions, task granularity, agent participation, geographic localization, resource consummation, production and change. Although the use of conceptual models is well accepted to formally describe domain ontologies, there is little research about conceptual models for complex task ontologies. This paper describes the ongoing research on the Agriculture Operations Task Ontology (AGROPTO) where OntoUML is used to develop conceptual models to describe complex task’s aspects and possible modelling solutions based on Unified Foundation Ontology (UFO). An extension of the E-OntoUML, a language for modelling task ontologies, is suggested to describe methods for modelling task objectives, external event interference, pre/post conditions and task execution state modifications in order to guide future research.
Download
Paper Nr: 46
Title:

ODYSSEY: Software Development Life Cycle Ontology
Authors:

J. I. Olszewska and I. K. Allison
Abstract: With the omnipresence of softwares in our Society from Information Technology (IT) services to autonomous agents, their systematic and efficient development is crucial for software developers. Hence, in this paper, we present an approach to assist intelligent agents (IA), whatever human beings or artificial systems, in theirs task to develop and configure softwares. The proposed method is an ontological, developer-centred approach aiding a software developer in decision making and interoperable information sharing through the use of the ODYSSEY ontology we developed for the software development life cycle (SDLC) domain. This ODYSSEY ontology has been designed following the Enterprise Ontology (EO) methodology and coded in Descriptive Logic (DL). Its implementation in OWL has been evaluated for case studies, showing promising results.
Download
Paper Nr: 47
Title:

Towards an Ontological Representation of Condition Monitoring Knowledge in the Manufacturing Domain
Authors:

Qiushi Cao, Cecilia Zanni-Merk and Christoph Reich
Abstract: In the manufacturing domain, machinery faults cause a company high costs. To avoid faulty conditions, the discipline of condition monitoring contributes significantly. The objective of condition monitoring is to determine the correctness of a machine, process or system. This is crucial for improving the productivity and availability of production systems. In most situations, when the tendency of a fault emerges, highly experienced and skilled professionals are capable of providing appropriate decisions about fault alarm launching and maintenance plans. However, production systems are becoming more complicated, and it is more likely that the professionals fail to respond to the faulty conditions timely and accurately. In this paper, we present an ontological framework, that is used for developing an intelligent system, which can provide decisions about alarm launching and maintenance plans in an intelligent and optimal manner. This framework is based on an ontological representation of condition monitoring knowledge in the manufacturing domain. The framework consists of an ontology structure which includes a core reference ontology for representing general condition monitoring concepts and relations, and several domain ontologies for formalizing manufacturing domain-specific knowledge.
Download
Paper Nr: 49
Title:

New Value Metrics using Unsupervised Machine Learning, Lexical Link Analysis and Game Theory for Discovering Innovation from Big Data and Crowd-sourcing
Authors:

Ying Zhao, Charles Zhou and Jennie K. Bellonio
Abstract: We demonstrated a machine learning and artificial intelligence method, i.e., lexical link analysis (LLA) to discover innovative ideas from big data. LLA is an unsupervised machine learning paradigm that does not require manually labeled training data. New value metrics are defined based on LLA and game theory. In this paper, we show the value metrics generated from LLA in a use case of an internet game and crowd-sourcing. We show the results from LLA are validated and correlated with the ground truth. The LLA value metrics can be used to select high-value information for a wide range of applications.
Download
Paper Nr: 50
Title:

ABC Repair System for Datalog-like Theories
Authors:

Xue Li, Alan Bundy and Alan Smaill
Abstract: This paper aims to develop a domain-independent system for repairing faulty Datalog-like theories by combining three existing techniques: abduction, belief revision and conceptual change. From the three repair technique candidates, the proposed system is named the ABC repair system. Given an observed assertion and a current theory, abduction adds axioms which represent the simplest and most likely explanation. Belief revision incorporates a new piece of information which conflicts with input theory by deleting old axioms from the input theory. Conceptual change uses the reformation algorithm for blocking unwanted proofs or unblocking wanted proofs. The former two techniques change an axiom as a whole, while reformation changes the language in which the theory is written. These three techniques are complementary: abduction adds new axioms, belief revision deletes conflicting axioms, while reformation changes the language of the theory. But they have not previously been combined into one system. We are working on aligning these three techniques in the ABC repair system, which is capable of repairing logical theories with better quality than individual techniques. Datalog is used as the underlying logic of theories in this paper, but the proposed system has the potential to be adapted to theories in other logics.
Download
Paper Nr: 51
Title:

Assessing Similarity Value between Two Ontologies
Authors:

Aly Ngoné Ngom, Guidedi Kaladzavi, Fatou Kamara-Sangaré and Moussa Lo
Abstract: The aim of this paper is to present an appraoch for assessing similarity between ontolgies. This approach is based on set theory, edges-based semantic similarity and features based similarity. We first determine the set of concepts that is shared by two ontologies and the sets of concepts that are different from them. Then we extend ontologies by using the set of concepts shared by the two ontologies. Then we redetermine set of concepts shared by the two extended ontologies. finally, we end with the assessment of the similarity between ontologies by using the average values of similarity of the sets of specific concepts to each not extended ontologies, and the set of concepts shared by extended ontologies.
Download
Paper Nr: 54
Title:

A Roadmap towards Tuneable Random Ontology Generation Via Probabilistic Generative Models
Authors:

Pietro Galliani, Oliver Kutz and Roberto Confalonieri
Abstract: As the sophistication of the tools available for manipulating ontologies increases, so does the need for novel and rich ontologies to use for purposes such as benchmarking, testing and validation. Ontology repositories are not ideally suited for this need, as the ontologies they contain are limited in number, may not generally have required properties (e.g., inconsistency), and may present unwelcome correlations between features. In order to better match this need, we hold that a highly tuneable, language-agnostic, theoretically principled tool for the automated generation of random ontologies is needed. In this position paper we describe how a probabilistic generative model (based on features obtained via the analysis of real ontologies) should be developed for use as the theoretical back-end for such an enterprise, and discuss the role of the DOL metalanguage in it.
Download
Paper Nr: 56
Title:

Ontological Analysis of the Wikipedia Category System
Authors:

Alexander Kirillovich and Olga Nevzorova
Abstract: We analyse violations of the transitivity principle of the Wikipedia category system, i.e. the situations where articles from a subcategory doesn’t logically belong to its parent category. The causes of the violation have been analysed on the base of ontological modelling methodologies such as OntoClean. We propose a new approach to eliminating the violations. This approach is based on analysis of the relation of ontological dependence between categories. As a theoretical foundation of such analysis we propose a new deflationistic interpretation of the essential account of ontological dependence. The proof of concept has been evaluated on the category C:Mathematics. We are going to apply the proposed approach to derive a new large-scale domains hierarchy from the Wikipedia category system, and use it to provide BabelNet and DBpedia with fine-grained domain annotations.
Download
Paper Nr: 59
Title:

Lean Ontology Development: An Ontology Development Paradigm based on Continuous Innovation
Authors:

Joel Cummings and Deborah Stacey
Abstract: This position paper explores the utility of adapting the principles of Lean Startup and Agile software development to the development of ontologies. A main thesis is that ontology development should be approached in a manner similar to software development. Lean Ontology Development (LOD) principles are defined and current ontology development methodologies are discussed in relation to these principles. The principles defined are Continuous Development, Minimum Viable Ontology via Prioritization, Community Evaluation, Ontology as API, Reuse, and Sustainability.
Download
Paper Nr: 61
Title:

Business Model Canvas Synthesis Process from DEMO Construction Model
Authors:

Novandra Rhezza Pratama and Junichi Iijima
Abstract: The notion of a system can be represented in two ways, as a function or as a construction. A transformation can occur between them. Function can be represented by Business Model Canvas (BMC) and construction can be represented by DEMO Construction Model (DEMO CM). To find a new BMC, we can apply these phases; transform existing BMC into DEMO CM, manipulate it into a new CM, and transform it back into new BMC to create a new business. The transformation from BMC to DEMO CM is already provided, however, it only explains about DEMO CM generation from BMC. The manipulation of DEMO CM is also already proposed. This paper proposed the final phase of the process; to synthesize BMC from DEMO CM. Decision Tree is used to generate BMC from DEMO CM, resulting in Pre-BMC. A case study of EU-Rent is used to illustrate the proposed methodology. We proposed Pre-BMC generation as an intermediate process of BMC synthesis, and refine it into a completed BMC.
Download
Paper Nr: 65
Title:

DEMO based Dynamic Information System Modeller and Executer
Authors:

Magno Andrade, David Aveiro and Duarte Pinto
Abstract: This paper presents a different approach to information systems named as Enterprise Modelling and Execution as a Service (EMEaaS). This approach, based on the DEMO methodology, has as objective to solve some of the issues found on other approaches such as software as a service or business processes as a service like the dependency from an outside third party to the organization. As a concrete implementation of this EMEaaS approach, we present a DEMO Based prototype called Dynamic Information System Modeller and Executer (DISME). DISME is a dynamic information system modeller that aims to serve at the same time as: (1) an organization modeller, (2) an information system and (3) a workflow management system that can be adapted to most organizational realities with no need for coding, just the understanding of some basics about the DEMO methodology.
Download
Paper Nr: 24
Title:

Automation of Simulation Steps using Ontological Approach
Authors:

Elena Zamyatina, Alexander Mikov and Viacheslav Lanin
Abstract: There are different Modelling and Simulation (M&S) life cycle’s steps described in the literature. One way or another some of these steps are similar: creation of conceptual model, verification and validation of simulation model, statistical data collection and processing. Authors of represented paper suggest to automate some steps and propose to use ontological approach. The automatization of steps allows to optimize the overall time of simulation experiment, to increase a reliability of simulation model and to receive more adequate results.
Download
Paper Nr: 25
Title:

Method for the Development of Recommendation Systems, Customizable to Domains, with Deep GRU Network
Authors:

Arseny Korotaev and Lyudmila Lyadova
Abstract: The GRU-based recurrent neural networks (RNN) for constructing recommendation systems are proposed. Such systems are mainly developed by large companies for specific domains. At the same time, small companies don’t have the necessary resources to develop their own unique systems. Therefore, they need universal recommendation system (or recommender platform) automatically customized for a specific domain. This system allows to develop own recommendation system from scratch for companies whose services are under development. The RNN-based approach is proposed for session-based recommendation with automatically modelling of the domain. This approach is based on the content analysis of the web sites. Several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem are considered. General scheme of the approach and architecture of the recommendation system based on proposed scheme are described in this paper.
Download
Paper Nr: 33
Title:

Toward a Domain Ontology for Computer Projects Resolution: Project Memory Challenge
Authors:

Raja Hanafi, Lassad Mejri and Henda Hajjami Ben Ghezala
Abstract: In recent years, the project management has been practiced in many special computer projects which took place in large companies. During the resolution of a project especially during the design phase, the project leaders have encountered many problems which are treated and solved in the already existing projects. The resolution of a similar new project forces project leaders to spend a lot of time accessing and reusing existing project knowledge. This is why the problem of capitalization of knowledge proves to be very important in order to solve the problem of time, of cost and of quality that a project manager can encounter during his resolution. The best solution is to propose a technique for memorizing and saving knowledge. This solution presents in a way the project memory. In literature, there are several approaches that are all about the capitalization of knowledge and the construction of project memory. All these approaches are generic models which are applied to any type of project such as the industrial and the technical project. In this paper, we present a model approach for a project memory. In practice, this challenge is addressed by proposing the domain ontology that characterizes the specification of computer project.
Download
Paper Nr: 34
Title:

A Practical Implementation of Contextual Reasoning on the Semantic Web
Authors:

Sahar Aljalbout, Gilles Falquet and Didier Buchs
Abstract: Dealing with context-sensitive information is a crucial aspect in the management of semantic web data. Despite the importance of this topic, there is so far no accepted consensus regarding the precise way of encoding and even more reasoning on contextual knowledge. In this paper, we introduce an approach to reason over contextual knowledge in RDF, while committing to the semantics of a contextual description logic. The lines of this paper are many folds. First, we present an extension of OWL 2 DL for contexts, that we call {OWL 2 DLC. It is a two-dimensional web ontology language with one dimension for contextualized object knowledge and one dimension for contexts. Second, we define an OWLC profile for contextual reasoning, similar to OWL 2 RL. And finally, we demonstrate that the model can be practically implemented using existing semantic web technologies, especially using SPIN rules.
Download
Paper Nr: 37
Title:

An Ontology for Solar Irradiation Forecast Models
Authors:

Abhilash Kantamneni and Laura E. Brown
Abstract: The growth of solar energy resources in recent years has led to increased calls for accurate forecasts of solar irradiance for the reliable and sustainable integration of solar into the national grid. A growing body of academic research has developed models for forecasting solar irradiance, identified metrics for comparing solar forecasts, and described applications and end users of solar forecasts. Ontologies are explicit and formal vocabulary of terms and their relationships that facilitate better communication, improve interoperability, and refine knowledge reuse by experts and users of the domain. This paper describes a step towards using ontologies to describe the knowledge, concepts, and relationships in the domain of solar irradiance forecasting to develop a shared understanding for diverse stakeholders that interact with the domain. A preliminary ontology on solar irradiance forecasting, SF-ONT, was created and validated on three use cases.
Download
Paper Nr: 39
Title:

Solving Poverty using Ontology
Authors:

Zarmeen Nasim and Imran Khan
Abstract: This paper presents an ontology-based approach to address poverty. Poverty has been one of the serious societal problems that the world is facing in recent times. The approach has been modeled in such a way that it can be used to solve any other wicked problem of the society as well including corruption, bad governance, traffic management, poor education and many others. The causes of the said problem were modeled at different level of granularity. The proposed model also incorporates various different ways of addressing poverty by addressing possible causes of poverty. The presented scheme of using an ontology to address the wicked problem has the inferencing capability also to infer the indirect causes of poverty.
Download
Paper Nr: 45
Title:

Conditional Game Theory as a Model for Coordinated Decision Making
Authors:

Wynn C. Stirling and Luca Tummolini
Abstract: Standard game theory is founded on the premise that choices in interactive decision situations are strategically rational—best reactions to the expected actions of others. However, when studying groups whose members are responsive to one another’s interests, a relevant notion of behavior is for them to coordinate in the pursuit of coherent group behavior. Conditional game theory provides a framework that facilitates the study of coordinated rational behavior of human social networks and the synthesis of artificial social influence networks. This framework comprises three elements: a socialization model to characterize the way individual preferences are defined in a social context; a diffusion model to define the way individual preferences propagate through the network to create an emergent social structure; and a deduction model that establishes the structure of coordinated individual choices.
Download
Paper Nr: 48
Title:

MDQM: Mediation Data Quality Model Aligned Data Quality Model for Mediation Systems
Authors:

Loubna Mimouni, Ahmed Zellou and Ali Idri
Abstract: We are in age where data is provided from multiple heterogeneous and distributed sources hence the usefulness of data integration systems (DIS). But given that the user is obliged to filter a large volume of data to achieve the most satisfactory to his request and his information need, we can say that the approach became more qualitative than quantitative. For this purpose, the main goal of this paper is to introduce the data quality aspect concerning data retrieved from Mediation systems which is the virtual approach of data integration. The paper will be finalized by establishing an attempt of a model of data quality criterions classification in relation to Mediation system (MDQM).
Download