Maizura Mohamad Noor

Ontological-based for supporting multi criteria decision-making

Large amount of unstructured information is much benefited for organizations if it could be analyzed and used especially to support decision-making process. It is impractical and time consuming for decision makers to manually process the ill-defined information since the standard tools available designed for structured data analysis. It motivates to devising an intelligent and automated tool to process this kind of information and make them recognizable for Decision Support Systems (DSS). This has addressed the need to have uniform knowledge representation in order to structure data into machine readable format for decision-making process. A framework of ontological-based for supporting multi criteria decision-making is proposed in this paper. Currently, the framework is under implementation as a research prototype. A case study is drawn from the Malaysian construction tender evaluation to demonstrate the applicability of our approach.

A Hybrid Selection Method Based on HCELFS and SVM for the Diagnosis of Oral Cancer Staging

A diagnostic model based on Support Vector Machines (SVM) with a proposed hybrid feature selection method is developed to diagnose the stage of oral cancer in patients. The hybrid feature selection method, named Hybrid Correlation Evaluator and Linear Forward Selection (HCELFS), combines the advantages of filters and wrappers to select the optimal feature subset from the original feature set. In HCELFS, Correlation Attribute Evaluator acts as filters to remove redundant features and Linear Forward Selection with SVM acts as the wrappers to select the ideal feature subset from the remaining features. This study conducted experiments in WEKA with ten fold cross validation. The experimental results with oral cancer data sets demonstrate that our proposed model has a better performance than well-known feature selection algorithms.

Intelligent interpretation and analysis of child sexual abuse forensic evidence: A preliminary study

In sexual abuse case, the victims body is the most important source of physical evidence. Meanwhile, medical personnel play a role as part of the police investigation in forensic examination. Forensic evidence in sexual assault will be collected because of intimate nature of this evidence and different special expertises are needed to conduct a detail examination. Therefore, in child sexual abuse cases, uncertainties regarding of various context in decision making can lead to failure of successful investigation. Various types of evidence data need to be analyzed and interpreted to come out a reliable and precise report. Thus, this paper present a preliminary study of this topic in order to gain a solution of decision making in child sexual abuse forensic field through intelligent decision support system.

Data preparation for pre-processing on oral cancer dataset

In this paper, data pre-processing tasks involving data interpretation, data integration, noisy data, missing data, and data inconsistency are presented. The dataset prepared includes all the fields that are required for the research, pertaining to oral cancer diagnosis with demographics, social habit, clinical symptoms, and histological variables. After data normalization and transformation, the finding of the study prepared oral cancer dataset with 27 attributes as a part of study contribution. There are only one continuous and one numerical variable, which are case_id and age. The remaining variables are discrete or categorical variables.

Supporting decision making in situational crime prevention using fuzzy association rule

Crime happens everywhere including in our house and is always related with human life. It will make a country lose valuable assets and properties. Most crimes will take place only if there is an opportunity to do crime. To curb this problem, the IT field tries to develop a smart technology that can work in predicting of crime in the future. This new tool uses decision support system (DSS) and fuzzy association rule mining (FARM), in which it can extract the factors of situational (opportunity) crime precisely based on previous data obtained.

Ontological-Based Information Extraction of Construction Tender Documents

Extracting potentially relevant information either from unstructured, semi structured or structured information on construction tender documents is paramount with respect to improve decision-making processes in tender evaluation. However, various forms of information on tender documents make the information extraction process non trivial. Manually identification, aggregation and synthesize of information by decision makers is inefficient and time consuming. Thus, semantic analysis of content and document structure using domain knowledge representation is proposed to overcome the problem. The ontological-based information extraction processes contain three important components; document structure ontology, document preprocessing and information acquisition. The findings are significantly good in precision and recall which the performance measures have reached accuracy of precision about 82.35 % (concepts), 96.10 % (attributes), 100% (values) and 100 % of recall for both parameters of concepts and attributes, while 91.08 % for values.

A new framework to extract WordNet lexicographer files for semi-formal notation: A preliminary study

Despite its original use, which was very different, WordNet is used and used today as ontology. WordNet has a complex concepts concerning specific knowledge on semantic domain. The main objective is to analyze and recognize the most suitable and easier method for extracting WordNet lexicographer files which is very useful in developing the propose framework. In this paper, we describe the methodologies of this research. They are information binding, WordNet forensic, case analysis and method analysis. Some benefits are expected from this study are the development of framework for extracting WordNet lexicographer files for semi-formal notation, the development of middleware for extracting WordNet lexicographer files, the creation of own database for storing extracted lexicographer files from WordNet. The proposed framework will make WordNet efficiently exploitable in several applications.

A theoretical discussion of factors affecting the acceptance of m-commerce among SMTEs by integrating TTF with TAM

Tourism is an information-based industry and innovative mobile applications are believed to provide new business opportunities for the industry. Most tourism firms throughout the globe consist of small and medium-sized enterprises (SMEs) and as such, SMEs utilisation of information systems (IS) is crucial in terms of added efficiency, effectiveness and innovation. However, the acceptance of m-commerce in SMEs remains very low, while the factors impacting the application of IS are still ambiguous. The objective of the current study was to integrate TTF with TAM to investigate the determinants of user acceptance of m-commerce among SMTEs. The study provides advanced knowledge of customers acceptance of m-commerce in SMTEs, which will help the m-commerce providers in such enterprises to understand the factors that influence the acceptance of m-commerce in SMTEs. This in turn would play an important role in increasing the acceptance level of m-commerce among SMTEs.

Integrating e-Learning with Radio Frequency Identification (RFID) for Learning Disabilities: A Preliminary Study

Integrating learning styles in adaptive educational systems are a growing trend in technology enhanced learning. Children have different learning styles, abilities, preferences that focus on different types of information and process new information in different ways. Providing adaptively based on learning styles can promote interest for learners and make learning easier for them. The purpose of our research is to adopt an e-Learning approach Radio Frequency Identification (RFID) technology in order to model the Visual, Auditory and Kinesthetic (VAK) learning style focused on Learning Disabilities (LD) children. Today’s technology offers great chances to assist students with disabilities to live freely and learn more easily. Developing the learning environments assisted by technology is a new way in making their learning processes successful.

Evolutionary Framework of a Decision Support System for Forensic DNA Analysis

Research trend in DSS has moved from the issue of DSS development into DSS evolution. Initial works has been done in 1980s but further research has not been done continuously. The evolution issue of DSS has gained interests again; hence the focus in this research is mainly about evolution decision support systems (DSS) especially from the state-of-art of the proposed frameworks. Chosen area of interest to be demonstrated in solving problems for the evolution of DSS frameworks in this paper is in domain forensic science, or more specifically, forensic DNA analysis. DSS frameworks for forensic science are explored first. From the literatures, it shows that there are significant lacks of available research works for evolution of a DSS in many areas of interests, and not only in forensic science. Types of frameworks for a DSS in general are studied and summaries are presented. The proposed evolutionary framework for a DSS in forensic DNA analysis is initiated.