Browsing by Author "Jayalal, S"

Now showing 1 - 6 of 6

item: Conference-Abstract
Agent based Protégé plugin for ontology alignment
(2016-07-12) Rajakaruna, GM; Karunananda, AS; Jayalal, S
Ontologies are extensively used to strcuture the domain knowledge. Nowadays, with the large amount of ontologies already available, there is a high demand for reusing the knowledge in existing ontologies. Since ontologies are complex structures, sharing of knowledge coming from various ontologies has become a tedious task. Ontology alignment is a popular knowledge sharing technique that is used to share information between heterogeneous information systems. There are numerous techniques for the alignment of ontologies, and the field still faces many challenges. Due to the inherent nature of multiple relationships among the ontologies, it postulates that the Multi-Agent System technology is a better technology to automate the ontology alignment with little human intervention. This paper presents multi-agent based approach for ontology alignment developed as a plug in for the popular ontological modelling environment known as Protégé. It simulates how different processes interactively operate inside the human mind to perform certain activities intelligently. Indeed, the proposed solution uses agent communication, negotiation, and coordination as the primary method of exploring the semantic relationships between the ontologies. The generated ontology could be used as a shared understanding between information systems that are running on input ontologies. The success of the proposed approach was evaluated by using two ontologies of agricultural domain. It was evident that the system could discover over 70% accurate semantic relationships, and thus, the authors claim that the proposed approach could resolve the complexity in ontology alignment for certain extend.
item: Conference-Abstract
Aligning ontologies using multi agent technology
(2016-07-12) Rajakaruna, GM; Karunananda, AS; Jayalal, S
Modern information systems extensively use ontologies to model domain knowledge. With the large amount of already available ontologies, there is a high demand for sharing and reusing the knowledge in existing ontologies. Since ontologies are complex structures, sharing of knowledge coming from various ontologies has become a tedious task. This has resulted in the birth of research area called ontology alignment. There are numerous techniques for the alignment of ontologies, and the field still faces many challenges. Due to the inherent nature of multiple relationships among the ontologies, it postulates that the Multi-Agent System technology is a better technology to automate the ontology alignment with little human intervention. This paper presents multi-agent based approach for ontology alignment, developed as a plugin for the popular ontological modelling environment known as Protege. It simulates how different processes interactively operate inside the human mind to perform certain activities intelligently. Indeed, the proposed solution uses agent communication, negotiation, and coordination as the primary method of exploring the semantic relationships between the ontologies. The system accepts ontologies maintained in any major form of ontology representation languages as its inputs, and generates ontology with new semantic relationships as its output. The generated ontology could be used as a shared understanding between information systems that are running on input ontologies. The success of the proposed approach was evaluated by using ontologies of conference organizing and agricultural domains. It was evident that the system could discover over 70% accurate relationships, and thus, the authors claim that the proposed approach could resolve the complexity in ontology alignment.
item: Conference-Full-text
Classification of cyberbullying Sinhala language comments on social media
(IEEE, 2020-07) Amali, HMAI; Jayalal, S; Jayalal, S; Weeraddana, C; Edussooriya, CUS; Abeysooriya, RP
Due to technological revolution over the years, bullying which was confined to physical boundaries has now moved online. Denigration or insult is one form of cyberbullying. According to Sri Lanka Computer Emergency Readiness Team, social media cyberbullying incidents are escalating. Insulting words are dynamic, and same word can have several meanings according to the context. Simply because a comment contains such a word, it cannot be classified as bullying. Hence, when labeling comments, simple keyword spotting techniques are inadequate. Other languages have addressed this issue using lexical databases such as WordNet which provides synonyms and homonyms of words. Since there is no proper lexical database developed for Sinhala language, detecting a word as bullying is a challenge. Therefore, we used rules to overcome this issue. Twitter comments with profane words were collected, outliers were removed, and remaining tweets were pre-processed. To determine insult in the text, five rules were used for feature extraction. Afterward, we applied Support Vector Machine (SVM), K-nearest neighbor (KNN) and Naïve Bayes algorithms. The results show that SVM with an RBF kernel performs better with an F1-score of 91%. Novelty of this research is the focus on Sinhala language cyberbully detection which has not been addressed before.
item: Conference-Abstract
OntoCD - Ontological solution for curriculum development
(2016-07-11) Karunananda, AS; Rajakaruna, GM; Jayalal, S
Design of a new curriculum and revision of an existing curriculum are considered as tedious tasks for academics. This process requires considerable amount of man hours from subject matter experts in several areas. In this paper, we present a human-assisted semi-automated solution for the design and revision of curricula for degree programmes. We postulate the curriculum design and revision as an ontology modelling process. The solution has been developed as a plug-in, named as Onto CD, for the popular ontological modelling environment, Protege. A curriculum developer can customize OntoCD by introducing benchmark domain ontology of a certain degree, and loading a skeleton curriculum for the intended degree programme. Alternatively, the domain ontology can be used to design a curriculum on the visual interface provided, and proceed to improve it. The developer can also use OntoCD to load a known curriculum and to do the modification to align with the benchmark domain ontology. The power of OntoCD exemplifies during the process of editing and improving a curriculum. In this process, OntoCD handles many tasks including the credit balancing with core and elective modules, guidance to choose elective modules to meet local needs and resolving name confusions of modules by ensuring an identity of a degree within the respective area. At this stage, OntoCD has been informally tested by designing a Computer Science degree curriculum according to benchmark domain ontology of ACM/IEEE guidelines for computing degrees. The results show that Onto CD guides the developer by reducing the burden due to clerical mistakes, oversights and negligence of some aspects in the development process.
item: Conference-Abstract
Towards multi-agent based solution for ontology alignment
(2016-07-11) Rajakaruna, GM; Karunananda, AS; Jayalal, S
Ontology alignment is an ontology mapping technique, which is used for sharing and reusing the content of disparate source of ontologies. Aligning dynamic and distributed ontologies turn out to be a research challenge for many decades. This paper discusses the complexity of the ontology alignment process and presents some major tools that have been developed to support knowledge engineers. Then, we discuss how the agent technology can be used to align dynamic ontologies in distributed environments. Our solution is inspired by how group of people communicate, negotiate, and coordinate to reach common agreements.
item: Conference-Full-text
Using agent technology for Ontology alignment
Rajakaruna, GM; Karunananda, AS; Jayalal, S
In the agricultural domain, different authorities have already developed their own ontologies and maintain them locally. However, for semantic tools to use these ontologies effectively on distributed environments, ontologies should be shared and aligned. Ontology alignment is an ontology mapping technique, which is used for sharing and reusing the content of disparate source of ontologies. Aligning dynamic and distributed ontologies turn out to be a research challenge for many decades. This paper discusses the complexity of the ontology alignment process and presents how the agent technology can be used to align dynamic ontologies in distributed environments. Our solution is inspired by how group of farmers communicate, negotiate, and coordinate to reach in common agreements. Our system is successfully used to align two dynamic ontologies describing agricultural crops.