Taneth Ruangrajitpakorn

OAM: An Ontology Application Management Framework for Simplifying Ontology-Based Semantic Web Application Development

Although the Semantic Web data standards are established, ontology-based applications built on the standards are relatively limited. This is partly due to high learning curve and efforts demanded in building ontology-based Semantic Web applications. In this paper, we describe an ontology application management (OAM) framework that aims to simplify creation and adoption of ontology-based application that is based on the Semantic Web technology. OAM introduces an intermediate layer between user application and programming and development environment in order to support ontology-based data publishing and access, abstraction and interoperability. The framework focuses on providing reusable and configurable data and application templates, which allow the users to create the applications without programming skill required. Three forms of templates are introduced: database to ontology mapping configuration, recommendation rule and application templates. We describe two case studies that adopted the framework: activity recognition in smart home domain and thalassemia clinical support system, and how the framework was used in simplifying development in both projects. In addition, we provide some performance evaluation results to show that, by limiting expressiveness of the rule language, a specialized form of recommendation processor can be developed for more efficient performance. Some advantages and limitations of the application framework in ontology-based applications are also discussed.

A Syntactic Resource for Thai: CG Treebank

This paper presents Thai syntactic resource: Thai CG treebank, a categorial approach of language resources. Since there are very few Thai syntactic resources, we designed to create treebank based on CG formalism. Thai corpus was parsed with existing CG syntactic dictionary and LALR parser. The correct parsed trees were collected as preliminary CG treebank. It consists of 50,346 trees from 27,239 utterances. Trees can be split into three grammatical types. There are 12,876 sentential trees, 13,728 noun phrasal trees, and 18,342 verb phrasal trees. There are 17,847 utterances that obtain one tree, and an average tree per an utterance is 1.85.

Ontology Design Approaches for Development of an Excise Duty Recommender System

Excise duty is a type of tax charged on certain products and services. Determining an excise product class can be a difficult task since the regulation written in legal language can be difficult for the users to interpret. Excise duty recommender system aims to simplify the users’ effort in product classification task and reduce errors in tax payment. This paper describes an initiative to develop excise product ontology to provide explicit and formal definitions of excise products and their classifications. It focuses on ontology design approaches for some excise products to support excise duty recommender system development. Two excise products were used as case studies: beverage and petroleum products. Steps in defining product mapping rules and developing the recommender system are described. A Semantic Web-based system architecture was adopted to enable future support for data sharing and reuse based on the Linked Data technology.

Biomarker Selection and Classification of ''-Omics'' Data Using a Two-Step Bayes Classification Framework

Identification of suitable biomarkers for accurate prediction of phenotypic outcomes is a goal for personalized medicine. However, current machine learning approaches are either too complex or perform poorly. Here, a novel two-step machine-learning framework is presented to address this need. First, a Naïve Bayes estimator is used to rank features from which the top-ranked will most likely contain the most informative features for prediction of the underlying biological classes. The top-ranked features are then used in a Hidden Naïve Bayes classifier to construct a classification prediction model from these filtered attributes. In order to obtain the minimum set of the most informative biomarkers, the bottom-ranked features are successively removed from the Naïve Bayes-filtered feature list one at a time, and the classification accuracy of the Hidden Naïve Bayes classifier is checked for each pruned feature set. The performance of the proposed two-step Bayes classification framework was tested on different types of -omics datasets including gene expression microarray, single nucleotide polymorphism microarray (SNParray), and surface-enhanced laser desorption/ionization time-of-flight (SELDI-TOF) proteomic data. The proposed two-step Bayes classification framework was equal to and, in some cases, outperformed other classification methods in terms of prediction accuracy, minimum number of classification markers, and computational time.

A development of knowledge representation for thalassemia prevention and control program

The spreading of thalassemia, the most common genetic disease in tropical areas, is increasing due to a migration thus the prevention and control program (PCP) of Thalassemia has been established. To better promote the yet unsuccessful PCP for thalassemia, ontology called PCPThalOnto is developed. The proposed ontology represents domain knowledge while a list of executable production rule is generated to represent operational knowledge. The PCPThalOnto consists of 1) class component to represent concepts of strategies, methodologies, techniques and activities of the PCP and 2) relation component to link between those classes or class and its instance. In the production rules, conditions for individual case determination are employed to execute a proper action. The well-constructed knowledge representation of PCP for thalassemia is developed as an electronic knowledge base for future applications to efficiently disseminate the underlying knowledge to people bridging the gap that deter the success of PCP.

Framework of waste recycling suggestion in Sufficiency Economy farming

In the Sufficiency Economy farming, recycling wastes for feeding its own farm is the core concept of self-reliance and sustainability. However, a wide choice of available wastes can cause confusion to farmers in waste distribution since wastes have their advantage and limitation in usage. This work presents a framework to assist in selection of appropriate wastes for farm objects. It is designed to dynamically support the difference in farm setting and available wastes in farm. The main features using in suggestion are nutrients and price of the waste. Nutrition is a representative of biological compatibility in diet variedly needed from farm product types while price represents an economical aspect in agricultural business. Users are allowed to freely weight features to reflect their preference. With a list of available wastes in a farm and knowledge of organic agriculture, a rational suggestion is automatically made to provide an optimisation in waste usage.

Development of the Belief Culture Ontology and Its Application: Case Study of the GreaterMekong Subregion

In this paper, the development of an ontology that represents the knowledge of belief culture in the Greater Mekong subregion(GMS) is presented. The ontology was carefully designed to specify the concepts relevant to intangible and tangible cultural heritage and the relations among them. The knowledge domain in this work focuses on the cultural context and implicit attributes of the GMS as an initial case study. To further illustrate the potential of the developed ontology, a semantic search application was implemented and then evaluated by experts. On the evaluation processes, several complicated queries were designed in order to fully utilize the relations among ontological classes, and the results were returned accurately. The evaluation proved that the ontology was welldefined in aspects of its hierarchical structure and relations from intermediate concept layers.

OXPIRT: Ontology-based eXpert system for Production of a generic Immediate Release Tablet

Abstract: We introduce an ontology based expert system for suggesting production of an immediately released tablet in generic version called OXPIRT. It was designed to assist pharmacists by providing a list of ingredients in formulation, a manufacturing process, a step-by-step instruction of laboratorial scale production for testing, and a validation in terms of pharmaceutical equivalence to the original drug. For practical usage and efficacy, the domain knowledge of an original drug and a generic drug production from a regulated guidebook and expired patents is represented in ontology format while the operational knowledge for calculating a formulation and suggesting a manufacturing process is given in the production rules. Experiments were conducted on four drugs to approve its capability, and we found that the system worked very well on recommending a generic table production in an actual situation.

A Comparative Study on Applying Hierarchical Phrase-Based and Phrase-Based on Thai-Chinese Translation

To set an appropriate goal of SMT research for Thai-based translation, the comparative study of potential and suitability between phrase-based translation (PBT) and hierarchical phrase-based translation (HPBT) becomes an initial question. Thai-Chinese language-pair is chosen as experimental subject since they share most of common syntactic pattern and Chinese resource is numerous. Based on standard setting, we gain a result that 3-gram HPBT gains significantly better BLEU point over 3-gram PBT while 3-gram HPBT is approximately equal to 5-gram PBT. Moreover, from the results, a Chinese-to-Thai translation obtains better accuracies than a Thai-to-Chinese translation from every approach.

A Semi-Supervised Approach on Using Syntactic Prior Knowledge for Construction Thai Treebank

This paper presents an efficient approach to use small syntactic category for constructing large tree with the assist of linguistic knowledge for parsing Thai language. VB-EM algorithm is exploited to adjust parameters of any trees for selecting the best tree. Our best result is 70.62% accuracy of bracketing recovery.