Abstract-Accuracy is one of the main elements in the disease diagnose. Thus, it is important to select most relevant attributes to generate the optimal accuracy. The objective of this study is to predict more accurately the presence of oral cancer primary stage with reduced number of attributes. Originally, 25 attributes have been identified in order to predict the oral cancer staging. In this study, the integrated diagnostic model with hybrid features selection methods is used to determine the attributes that contribute the most to the diagnosis of oral cancer, which, indirectly, reduces the number of features that are collected from a variety of patient records. Twentyfive attributes have been reduced to 14 features using hybrid feature selection. Subsequently, four classifiers: Updatable Naïve Bayes, Multilayer Perceptron, K-Nearest Neighbors and Support Vector Machine are used to predict the diagnosis of patients with oral cancer. Also, the observations indicate that the Support Vector Machine outperforms other machine learning algorithms after incorporating feature subset selection with SMOTE at preprocessing phases.
Learning style (LS) is a description of the attitudes and behaviors which determine an individual’s preferred way of learning. Since each student has different LS, it is important for the teacher to recognize the differences in LS. Thus, an appropriate technique to detect students' LS, improve the motivation and academic achievement are required. The common approach using questionnaires to identify LS is less accurate due to complete the questionnaire is a tedious task for students and tend to choose answers randomly without understanding the questions. Emotions such as anger, sadness, and happiness resulting the different questionnaire answers. Due to the approach constrains, this study has focused on automated approaches that identify student LS from student behavior in the learning process. Implementation of decision support system (DSS) as automated application systems is needed to help teachers make decisions in determining students' LS. Thus, the objective of this study is to propose the architecture of LS detection automatically using decision support system. The development of the architecture is applying the behavioral modelling, that are contained student’s behavior parameters for visual-auditory-kinesthetic (VAK) model. Evaluation of the architecture is tested with the precision DSS engine. The accuracy of the rule technique achieves significant 80% accuracy. This study aims to help teachers to identify the ability of the student through the learning style (LS) in order to create effectiveness of learning and improving student’s achievement indirectly.
Keywords— decision support system, reasoning engines, learning style detection, user behavior, visual-auditory-kinesthetic (VAK) model
The concept of visual merchandising is important to arouse internal emotions of customers to make impulse buying. This study is carried out to investigate important elements of visual merchandising that can stimulate customers' impulse buying behaviour. Based on thorough review on past literature, stimulus-organism-response (SOR) paradigm is utilized to develop conceptual framework in this study. Based on the review of past empirical findings, this study identified the elements of colour, lighting, mannequins, music and floor merchandising as important elements in attracting the customers' responses and results in impulse buying behaviour. The outcome of the study is expected to suggest a conceptual framework for future research to investigate customers' impulse buying behaviour in different retail stores from different regions. Furthermore, this study also provide an understanding for the retailers to emphasise on the specific elements of visual merchandising to increase the attention of customers to walk-in to their store and indirectly influence their purchase decision making.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.