• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1773-1793
• /
• 2023

Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.

• Journal of Elementary Mathematics Education in Korea
• /
• v.11 no.1
• /
• pp.43-59
• /
• 2007

The goal of this thesis was to examine the effects of applying meta-problems to elementary school mathematics class In their achievements, beliefs and attitudes. To achieve this goal the following research questions were asked. a. What effects does the class applied with meta-problem have on students' mathematical achievements? b. What effects does the class applied with meta-problem have on students' mathematical beliefs and attitudes? To answer questions, an experimental study was designed and conducted. The subjects were 6th-grade students at S Elementary School located in Dobong-Gu, Seoul where the researcher teaches. Among them, the class that the researcher teach was chosen as the experimental group. During the experimental study, a teaching-learning with meta-problems was applied to the experimental group and a teaching-learning with general problems was applied to the comparative group. To examine changes in the mathematical achievements of the experimental group and the comparative group, a post-test of mathematical achievements was conducted and the results were t-tested. As well, to find answers to the second research question, a pre-test and a post-test of mathematical beliefs and attitudes were conducted on the experimental group and the results were t-tested. The results of this study were as follows First, the experimental group which was taught applying meta-problems got higher mathematical achievement than the comparative group. Second, the class with meta-problems did not bring significant changes in students' mathematical beliefs and attitudes. Synthesizing the study results above, a teaching-learning with meta-problems is a teaching-learning method that can accommodate problem solving naturally in school mathematics and give a positive effect on students' mathematical achievements.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.49-64
• /
• 1999

본 연구는 백화점 고객이 신용 카드 신청 요구 시에 작성되는 가입 정보 및 사용되고 있는 고객의 거래 정보는 카드 사용 패턴으로 신용도를 예측하는 여러 방법론을 제시하고 성능을 비교하였다. 가입 정보를 분석하기 위해 역전파 신경망(Back-Propagation Neural Network, BPNN), 사례기반추론(Case-Based reasoning)을, 거래 정보를 분석하기 위해 역전파 신경망과 더불어 시간지연 신경망(Time-Delayed Neural Network, TDNN)을 각각 사용하여 그 결과를 비교하였다. 또한 전체시스템의 적중률을 높이기 위햐여, ID3와 신경망을 이용한 Meta-Leaning 방법을 제시하였으며, Meta-Learning 방법과 다른 방법들을 비교, 분석을 하였다. 본 연구에서는 모형 수립과 검증을 위하여 T백화점의 실제 신용 카드 가입 고객 데이터를 이용하여 실험하였다. 데이터의 성격에 따라 각 모델의 예측력에는 차이가 나타났으나, 신경망 모형의 예측력이 우수하였으며, 시간적 특성을 고려하는 시간지연 신경회로망 모형의 예측력은 더욱 우수하게 나타났다. 또한 Meta-Learning 모형을 사용하면 예측력이 더 높아진다는 것을 확인할 수 있었다.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• The Mathematical Education
• /
• v.58 no.4
• /
• pp.519-530
• /
• 2019

According to previous studies, meta-affect based on the interaction between cognitive and affective elements in mathematics learning activities maintains a close mechanical relationship with the learner's mathematical ability in a similar way to meta-cognition. In this study, in order to grasp these characteristics phenomenologically, small group problem-solving cases of 5th grade elementary mathematically gifted children were analyzed from a meta-affective perspective. As a result, the two types of problem-solving cases of mathematically gifted children were relatively frequent in the types of meta-affect in which cognitive element related to the cognitive characteristics of mathematically gifted children appeared first. Meta-affects were actively acted as the meta-function of evaluation and attitude types. In the case of successful problem-solving, it was largely biased by the meta-function of evaluation type. In the case of unsuccessful problem-solving, it was largely biased by the meta-function of the monitoring type. It could be seen that the cognitive and affective characteristics of mathematically gifted children appear in problem solving activities through meta-affective activities. In particular, it was found that the affective competence of the problem solver acted on problem-solving activities by meta-affect in the form of emotion or attitude. The meta-affecive characteristics of mathematically gifted children and their working principles will provide implications in terms of emotions and attitudes related to mathematics learning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1755-1777
• /
• 2022

The development of wireless communication technology has led to the underutilization of radio spectra. To address this limitation, an intelligent cognitive radio network was developed. Specific emitter identification (SEI) is a key technology in this network. However, in realistic non-cooperative scenarios, the system may detect signal classes beyond those in the training database, and only a few labeled signal samples are available for network training, both of which deteriorate identification performance. To overcome these challenges, a meta-learning-based open-set identification system is proposed for SEI. First, the received signals were pre-processed using bi-spectral analysis and a Radon transform to obtain signal representation vectors, which were then fed into an open-set SEI network. This network consisted of a deep feature extractor and an intrinsic feature memorizer that can detect signals of unknown classes and classify signals of different known classes. The training loss functions and the procedures of the open-set SEI network were then designed for parameter optimization. Considering the few-shot problems of open-set SEI, meta-training loss functions and meta-training procedures that require only a few labeled signal samples were further developed for open-set SEI network training. The experimental results demonstrate that this approach outperforms other state-of-the-art SEI methods in open-set scenarios. In addition, excellent open-set SEI performance was achieved using at least 50 training signal samples, and effective operation in low signal-to-noise ratio (SNR) environments was demonstrated.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.3
• /
• pp.99-108
• /
• 2003

This paper indicates limitations of the existing VOD(Video on Demand)-based on-line education systems and presents the design and implementation of Education on Demand (EOD) system as an alternative. EOD system is based on meta information expressed in XML and component technology. Overall system consists of authoring tool. contents server, learning policy system and contents viewer. which are utilized throughout the learning contents life-cycle. EOD system enables automated contents management using meta information exchange methodology that is conformant to the SCORM meta data presentation scheme. In addition, integrated management of interaction and feedback information along with the learning policy system provides customized learning guide for each individual learner. With the development of EOD system, this paper discusses about advanced on-line education system which surpasses existing content-providing-only systems.

• Journal of Korean Elementary Science Education
• /
• v.35 no.1
• /
• pp.39-53
• /
• 2016

This study aimed to understand students' learning in elementary science classes in terms of participatory perspective. Participatory perspective is based on the participationist views on learning. Based on the participatory perspective, this study used two concepts of participationism: 'the changes of learning on commognition' of Sfard (2007) and 'the identity' of Wenger (1998/2007). Based on these concepts, four episodes of an elementary science class were analyzed. The results showed that students carried out their learning from objective-level learning to meta-level learning. And students defined who they are by identifying and negotiating scientific meaning during the learning. These results showed students become members of science community through their participations in science class.

• Journal of Internet of Things and Convergence
• /
• v.8 no.6
• /
• pp.1-13
• /
• 2022

The Paper Using the meta-analysis research method, first through literature retrieval to obtain 23 relevant empirical studies in China, and then using Review Manager for quantitative analysis, it is found that VR technology has a positive impact on students' overall learning effect and VR technology has a significant positive impact on all dimensions of learning effect (theoretical performance, operational performance, learning motivation, learning interest, learning attitude). There is no significant difference between the dimensions. Significant differences were found for moderating variables such as Discipline types, Teaching Length, and Teaching Method. No significant differences were found for the Academic segments and VR technology types.

• The Journal of Information Systems
• /
• v.28 no.4
• /
• pp.293-311
• /
• 2019

Purpose This paper is to make a meta-analysis of the relationship between the social media use and learning performance as well as its potential moderating variables to clarify the differences in research conclusions in existing literatures, and refine the situational and method factors that affect the relationship between them. Methodology Meta-analysis used in this study can combine the quantitative data from different empirical studies, focus on the same research problem, and finally reach a research conclusion. Findings The results show that social media use and learning performance have a moderating positive correlation. The moderating effect test of usage scenarios shows that social media types, usage groups, application platforms and discipline fields have moderating effects on the relationship between social media use and learning performance. The moderating effect test of the research method found that measurement models, data attributes and learning performance indicators also had moderating effects on the relationship between social media use and learning performance.