• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.189-201
• /
• 2022

In this study, we propose factor augmentation to improve forecasting power of cryptocurrency return. We consider financial and economic variables as well as psychological aspect for possible factors. To be more specific, financial and economic factors are obtained by applying principal factor analysis. Psychological factor is summarized by news sentiment analysis. We also visualize such factors through impulse response analysis. In the modeling perspective, we consider ARIMAX as the classical model, and random forest and deep learning to accommodate nonlinear features. As a result, we show that factor augmentation reduces prediction error and the GRU performed the best amongst all models considered.

• Genomics & Informatics
• /
• v.20 no.2
• /
• pp.23.1-23.9
• /
• 2022

A survival prediction model has recently been developed to evaluate the prognosis of resected nonmetastatic pancreatic ductal adenocarcinoma based on a Cox model using two nationwide databases: Surveillance, Epidemiology and End Results (SEER) and Korea Tumor Registry System-Biliary Pancreas (KOTUS-BP). In this study, we applied two machine learning methods-random survival forests (RSF) and support vector machines (SVM)-for survival analysis and compared their prediction performance using the SEER and KOTUS-BP datasets. Three schemes were used for model development and evaluation. First, we utilized data from SEER for model development and used data from KOTUS-BP for external evaluation. Second, these two datasets were swapped by taking data from KOTUS-BP for model development and data from SEER for external evaluation. Finally, we mixed these two datasets half and half and utilized the mixed datasets for model development and validation. We used 9,624 patients from SEER and 3,281 patients from KOTUS-BP to construct a prediction model with seven covariates: age, sex, histologic differentiation, adjuvant treatment, resection margin status, and the American Joint Committee on Cancer 8th edition T-stage and N-stage. Comparing the three schemes, the performance of the Cox model, RSF, and SVM was better when using the mixed datasets than when using the unmixed datasets. When using the mixed datasets, the C-index, 1-year, 2-year, and 3-year time-dependent areas under the curve for the Cox model were 0.644, 0.698, 0.680, and 0.687, respectively. The Cox model performed slightly better than RSF and SVM.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.291-297
• /
• 2022

Modern challenges in the educational environment force scientists and practitioners to search for an adequate answer. In particular, the war in Ukraine demonstrated the importance of developing information competence as one of the main means of distinguishing true information from a whole stream of fake news. This is especially relevant in connection with the introduction of distance learning when students must find and process a large amount of information on their own. Therefore, the purpose of the article is to analyze the training of higher education students through the prism of acquiring the necessary level of informational competence in war conditions. For this, general scientific and special research methods, as well as the experimental method, were used. In the results, the peculiarities of the interpretation of information competence in the distance form of education among modern researchers are determined, the psychological components of resistance to fakes are analyzed. Based on the conducted empirical measurements, it was established that thorough work on student education gives positive skills when working independently with Internet materials, strengthens the ability to distinguish false information and propaganda from the real state of affairs. The conclusions summarize the results of the empirical research and suggest ways to improve the situation with the formation of information competence.

• Journal of The Korean Association of Information Education
• /
• v.26 no.4
• /
• pp.285-293
• /
• 2022

The COVID-19 outbreak, which took longer than expected, caused considerable damage to students' basic academic ability in mathematics. In this paper, a multiplication table practice application that can help students improve their basic multiplication arithmetic skills has been developed based on a cloud-service. The performance of the application was improved by integrating the Flutter framework, Google Cloud, and Google Sheets. As a result of applying this application to 72 6th graders in elementary schools located in K Metropolitan City, for one week. students' spending time required for solving multiplication table problems was reduced by more than 28% compared to the initial period, while students' learning data was able to be accurately collected without errors. It is hoped that the development case conducted through the Flutter framework in this study can lead to the development of other educational learning applications.

• Education of Primary School Mathematics
• /
• v.25 no.3
• /
• pp.213-232
• /
• 2022

With the importance of number line in learning fractions, this study investigated how 4th grade students understand fractions and its operations in number line. The questionnaire consisted 22 items which were related to representing fractions, comparing the size of fractions, and operating addition and subtraction of fractions. Both structured number line and sub-structured number line were presented in the items. As results of the study, the overall success rates were not high and even some items showed higher incorrect answer rates than the success rates. Also, the students showed a difficulty in solving non-structured number line tasks. It was also noticeable that students showed several types of incorrect answers, which means that students had incomplete understanding of both fractions and number line. This paper is expected to shed light on elementary students' understanding of fractions and number line and to provide implications of how to deal with number line in teaching and learning fractions in the elementary school.

• Imaging Science in Dentistry
• /
• v.52 no.4
• /
• pp.383-391
• /
• 2022

Purpose: Periodontitis, the most prevalent chronic inflammatory condition affecting teeth-supporting tissues, is diagnosed and classified through clinical and radiographic examinations. The staging of periodontitis using panoramic radiographs provides information for designing computer-assisted diagnostic systems. Performing image segmentation in periodontitis is required for image processing in diagnostic applications. This study evaluated image segmentation for periodontitis staging based on deep learning approaches. Materials and Methods: Multi-Label U-Net and Mask R-CNN models were compared for image segmentation to detect periodontitis using 100 digital panoramic radiographs. Normal conditions and 4 stages of periodontitis were annotated on these panoramic radiographs. A total of 1100 original and augmented images were then randomly divided into a training (75%) dataset to produce segmentation models and a testing (25%) dataset to determine the evaluation metrics of the segmentation models. Results: The performance of the segmentation models against the radiographic diagnosis of periodontitis conducted by a dentist was described by evaluation metrics(i.e., dice coefficient and intersection-over-union [IoU] score). MultiLabel U-Net achieved a dice coefficient of 0.96 and an IoU score of 0.97. Meanwhile, Mask R-CNN attained a dice coefficient of 0.87 and an IoU score of 0.74. U-Net showed the characteristic of semantic segmentation, and Mask R-CNN performed instance segmentation with accuracy, precision, recall, and F1-score values of 95%, 85.6%, 88.2%, and 86.6%, respectively. Conclusion: Multi-Label U-Net produced superior image segmentation to that of Mask R-CNN. The authors recommend integrating it with other techniques to develop hybrid models for automatic periodontitis detection.

• Communications of Mathematical Education
• /
• v.36 no.1
• /
• pp.59-72
• /
• 2022

The purpose of this study is to understand the characteristics of the mathematical modeling tasks and lesson designs developed by pre-service teachers based on the inherent awareness of mathematical modeling, considering the importance of creating a task to perform mathematical modeling activity and designing a lesson. As a result, the mathematical modeling tasks developed by pre-service teachers mainly presents an appropriate amount of information using real life contexts for the purpose of learning using concepts, and it showed a tendency to develop to the level of cognitive demand that required procedures with connections to understanding, meaning, or concepts. And most of the developed modeling task-based lessons showed a tendency to design warm-up activity, model-eliciting activity, and model-exploration activity. This result is due to the lack of experience of pre-service teachers in creating mathematical modeling tasks. Therefore, it is necessary to continuously provide opportunities for pre-service teachers to learn concepts or create mathematical modeling tasks intended for exploration according to various mathematical contents, thereby actively cultivating their ability to create modeling tasks in the course of training pre-service teachers. Furthermore, it is necessary to strengthen the expertise in mathematical modeling teaching and learning by providing opportunities to actually perform the mathematical modeling-based classes designed by pre-service teachers and to experience the process of reflecting on the lessons.

• Education of Primary School Mathematics
• /
• v.26 no.4
• /
• pp.349-368
• /
• 2023

The purpose of this study is to explore ways for students to connect conceptual and procedural knowledge in mathematical modeling lessons. Accordingly, we selected the greatest common divisor among the learning contents in which elementary school students have difficulties connecting conceptual and procedural knowledge. A mathematical modeling lesson was designed and implemented to solve problems related to the greatest common divisor while connecting conceptual and procedural knowledge. As a result of the analysis, it was found that the mathematical modeling lesson had positive effects on students solving problems by connecting conceptual and procedural knowledge. In addition, through actual class application, a teaching and learning plan was derived to meaningfully connect conceptual and procedural knowledge in mathematical modeling lessons.

• Journal of Gifted/Talented Education
• /
• v.22 no.3
• /
• pp.619-637
• /
• 2012

The purpose of this study is to develop a new program for elementary math-gifted students by using 'Girih Tililng' and apply it to the elementary students to improve their math-ability. Girih Tililng is well known for 'the secrets of mathematics hidden in Mosque decoration' with lots of recent attention from the world. The process of this study is as follows; (1) Reference research has been done for various tiling theories and the theories have been utilized for making this study applicable. (2) The characteristic features of Mosque tiles and their basic structures have been analyzed. After logical examination of the patterns, their mathematic attributes have been found out. (3) After development of Girih tiling program, the program has been applied to math-gifted students and the program has been modified and complemented. This program which has been developed for math-gifted students is called 'Exploring the Secrets of Girih Hidden in Mosque Patterns'. The program was based on the Renzulli's three-part in-depth learning. The first part of the in-depth learning activity, as a research stage, is designed to examine Islamic patterns in various ways and get the gifted students to understand and have them motivated to learn the concept of the tiling, understanding the characteristics of Islamic patterns, investigating Islamic design, and experiencing the Girih tiles. The second part of the in-depth learning activity, as a discovery stage, is focused on investigating the mathematical features of the Girih tile, comparing Girih tiled patterns with non-Girih tiled ones, investigating the mathematical characteristics of the five Girih tiles, and filling out the blank of Islamic patterns. The third part of the in-depth learning activity, as an inquiry or a creative stage, is planned to show the students' mathematical creativity by thinking over different types of Girih tiling, making the students' own tile patterns, presenting artifacts and reflecting over production process. This program was applied to 6 students who were enrolled in an unified(math and science) gifted class of D elementary school in Daejeon. After analyzing the results produced by its application, the program was modified and complemented repeatedly. It is expected that this program and its materials used in this study will guide a direction of how to develop methodical materials for math-gifted education in elementary schools. This program is originally developed for gifted education in elementary schools, but for further study, it is hoped that this study and the program will be also utilized in the field of math-gifted or unified gifted education in secondary schools in connection with 'Penrose Tiling' or material of 'quasi-crystal'.

• Journal of Elementary Mathematics Education in Korea
• /
• v.16 no.3
• /
• pp.359-388
• /
• 2012

The study aims to extract the framework of sub-factors of spatial sense, to develop test instruments based on the framework to investigate the actual spatial sense ability of fourth to sixth graders in elementary school and to analyze the results. According to the framework of sub-factors of spatial sense of the study, spatial sense has two factors of spatial visualization and spatial orientation. Spatial visualization is divided into mental rotation, mental transformation and figure-ground perception while spatial orientation is categorized into direction sense, distance sense, and location sense. Based on the framework, the test instrument for spatial sense ability was developed and the test was conducted to 430 fourth to sixth students in five elementary schools in capital areas. The following conclusions were drawn from the results obtained in the study. Firstly, the higher school year gets, the more spatial sense grows. However, spatial visualization is developed much more than spatial orientation and their order is reversed with higher graders. Secondly, the most insufficient abilities among fourth to sixth elementary school students' spatial sense were mental transformation of spatial visualization and location sense of spatial orientation. Thirdly, the reasons of differences in sub-factors of spatial sense and graders seem to be from effects of students' learning experiences of spatial sense of mathematics curriculum and the complexities of test items.