• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.702-723
• /
• 2020

The application of machine learning (ML) in intrusion detection has attracted much attention with the rapid growth of information security threat. As an efficient multi-label classifier, kernel extreme learning machine (KELM) has been gradually used in intrusion detection system. However, the performance of KELM heavily relies on the kernel selection. In this paper, a novel multiple kernel extreme learning machine (MKELM) model combining the ReliefF with nature-inspired methods is proposed for intrusion detection. The MKELM is designed to estimate whether the attack is carried out and the ReliefF is used as a preprocessor of MKELM to select appropriate features. In addition, the nature-inspired methods whose fitness functions are defined based on the kernel alignment are employed to build the optimal composite kernel in the MKELM. The KDD99, NSL and Kyoto datasets are used to evaluate the performance of the model. The experimental results indicate that the optimal composite kernel function can be determined by using any heuristic optimization method, including PSO, GA, GWO, BA and DE. Since the filter-based feature selection method is combined with the multiple kernel learning approach independent of the classifier, the proposed model can have a good performance while saving a lot of training time.

• Korean Journal of Human Ecology
• /
• v.19 no.5
• /
• pp.835-844
• /
• 2010

This study used meta-analysis to compare analyze data regarding the effects of music therapy on children and adolescent. The study examined 96 ESs using means and standard deviations from 77 Korean degree dissertations conducted between2000 and 2010. Results were as follows: The overall effect size (ES) of the therapy program was found to be 0.14, which, according to Cohen's ES interpretation criteria, is small. The mean ES was influenced by the subjects (children/ adolescents), ES of children(0.50) was bigger than ES of adolescents(-0.23). When results were sorted by the variables of therapy part: social, emotional and behavior development), the ES of social development was the biggest (1.11), followed by behavior development (-1.07) and emotional development (-0.01). However, other variables (total number of procedures, number of treatments per week, the average treatment time, therapist characteristics) made no statistically significant differences to the efficacy of the therapy. Finally, limitations of this study and potential future research are discussed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.597-604
• /
• 2020

This is a narrative research study conducted on the subject in order to understand the relationship between the meta-cognition, learning flow, and problem solving ability of nursing students in online class, and to find out the factors that influence problem solving ability, 88 students enrolled in 2nd and 3rd grade students who participated in online classes at G city universities. The analysis method was analyzed by means, standard deviation, t-test, one-way ANOVA, Pearson correlation, and stepwise multiple regression using SPSS version WIN 23.0. As a result of the study, the difference between learning flow and problem-solving ability according to general characteristics was significantly different depending on the perception of nurses after learning and the motivation for admission to the department of nursing, and the problem-solving ability was positively correlated with metacognition and learning flow. There was a relationship, and metacognition and learning flow were significant variables that influenced problem solving ability. The conclusion of the study is considered to be the basic data for the development of a systematic program that can increase the learning flow and meta-cognition to increase problem solving ability amid the change from nursing education to online classes, and to change the teaching method.

• Journal of Advanced Navigation Technology
• /
• v.13 no.3
• /
• pp.426-431
• /
• 2009

Recently, the application of E-learning is changing the method that is able to process the learning to learner more efficiently and conveniently. For this purpose, the application research of U-learning that is able to support the learning using mobile device such as PDA, NetBook, Tablet PC and so on is actively processing. But lots of U-learning framework is only considering the change to fit the exist learning contents the mobile device without SCORM that is able to support to make and process the learning contents by regular forms. In this paper, we proposed the learning contents interconnection of U-learning framework considering SCORM. For this purpose, we have to construct the learning by learning object and asset within SCORM. And this method can support learning information that was reconstructed it by learning contents to fit the mobile device as used the mobile device meta-data.

• Journal of Veterinary Clinics
• /
• v.40 no.4
• /
• pp.243-259
• /
• 2023

Machine learning and deep learning (ML/DL) algorithms have been successfully applied in medical practice. However, their application in veterinary medicine is relatively limited, possibly due to a lack in the quantity and quality of relevant research. Because the potential demands for ML/DL applications in veterinary clinics are significant, it is important to note the current gaps in the literature and explore the possible directions for advancement in this field. Thus, a scoping review was conducted as a situation analysis. We developed a search strategy following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. PubMed and Embase databases were used in the initial search. The identified items were screened based on predefined inclusion and exclusion criteria. Information regarding model development, quality of validation, and model performance was extracted from the included studies. The current review found 55 studies that passed the criteria. In terms of target animals, the number of studies on industrial animals was similar to that on companion animals. Quantitative scarcity of prediction studies (n = 11, including duplications) was revealed in both industrial and non-industrial animal studies compared to diagnostic studies (n = 45, including duplications). Qualitative limitations were also identified, especially regarding validation methodologies. Considering these gaps in the literature, future studies examining the prediction and validation processes, which employ a prospective and multi-center approach, are highly recommended. Veterinary practitioners should acknowledge the current limitations in this field and adopt a receptive and critical attitude towards these new technologies to avoid their abuse.

• Journal of Korean Elementary Science Education
• /
• v.20 no.1
• /
• pp.1-7
• /
• 2001

The purpose of this study is to examine the learner's variables affecting on scientific thinking and scientific process skills. To study this purpose, through the procedure study, the learner's variables were divided into cognitive variable, ego variable, and affective variable, then the questionaire survey through the reconstruction of standardization instrument was made over 120 elementary school fifth grade student in Seoul, Anyang, and Pajoo. The results of this study were as follows: 1) The learner's variables affecting on scientific thinking were cognitive variable and for female students, also affect affective variable. The subordinated catagories of statistically significant degree of explanation were achievement motivation, cognitive level, and cognitive style and another statistically significant correlation were meta-cognition, self regulated learning, self efficacy, and muliple intelligence. 2) The learner's variables affecting on science process skills were cognitive variable and affective variable. And the subordinated catagories of statistically significant degree of explanation were achievement motivation, and cognitive level. And another statistically significant correlation were meta-cognition, self regulated loaming, self efficacy, multiple intelligence, and attribution.

• Smart Structures and Systems
• /
• v.5 no.5
• /
• pp.507-515
• /
• 2009

The present work is an alternative methodology in order to balance a nonlinear highly flexible rotor by using neural networks. This procedure was developed aiming at improving the performance of classical balancing methods, which are developed in the context of linearity between acting forces and resulting displacements and are not well adapted to these situations. In this paper a fully experimental procedure using neural networks is implemented for dealing with the adaptive balancing of nonlinear rotors. The nonlinearity results from the large displacements measured due to the high flexibility of the foundation. A neural network based meta-model was developed to represent the system. The initialization of the learning procedure of the network is performed by using the influence coefficient method and the adaptive balancing strategy is prone to converge rapidly to a satisfactory solution. The methodology is tested successfully experimentally.

• English Language & Literature Teaching
• /
• v.18 no.2
• /
• pp.85-106
• /
• 2012

This paper examines the role of extensive reading in foreign language learning classrooms. The effects of extensive reading are shown both positive and negative as in Krashen (1999) and Spada (1997), particularly researches done in classroom setting. Extensive reading is hard to implement in foreign language classrooms due to the stringent school curricula despite its benefits in cognitive and affective domain of learners. This study searched 21 papers from research database on extensive reading researches in a classroom setting and synthesized 55 cognitive effects and 11 affective effects from these papers under investigation in a manner of quantifying their means and standard deviations to derive generalizations. Research synthesis in this manner has secured its own status of scientific investigation by providing secondary researchers with replicable methods that produce verifiable findings. The syntheses of researches show that extensive reading is effective in both literacy skills and other language skills such as listening and writing. It also shows positive effects across different age groups, but the effect sizes are different in that elementary and adults gained more positive effects than middle and high school students.

• Journal of Educational Research in Mathematics
• /
• v.13 no.1
• /
• pp.13-28
• /
• 2003

Practice of proof is considered in, the view of language and meta-mathematics, recognizing the role of proof that is the means of communication and development of mathematical understanding. Linguistic components in proof texts are symbol, verbal language and visual text, and contain the implicit knowledge in the meta-mathematics view. This study investigates the functions of linguistic elements according to Halliday's functional grammar and the rhetoric skills in proof texts in math textbook, teacher's note, and student's written text. We need to inquire into the aspects of language for mathematics learning process and the understanding and use of students' language.

• Advances in Computational Design
• /
• v.4 no.3
• /
• pp.197-210
• /
• 2019

Motion generation of a four-bar linkage is a type of mechanism synthesis that has a wide range of applications such as a pick-and-place operation in manufacturing. In this research, the use of meta-heuristics for motion generation of a four-bar linkage is demonstrated. Three problems of motion generation were posed as a constrained optimization probably using the weighted sum technique to handle two types of tracking errors. A simple penalty function technique was used to deal with design constraints while three meta-heuristics including differential evolution (DE), self-adaptive differential evolution (JADE) and teaching learning based optimization (TLBO) were employed to solve the problems. Comparative results and the effect of the constraint handling technique are illustrated and discussed.