• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.175-181
• /
• 2022

COVID-19 is an acute respiratory syndrome that affects the host's breathing and respiratory system. The novel disease's first case was reported in 2019 and has created a state of emergency in the whole world and declared a global pandemic within months after the first case. The disease created elements of socioeconomic crisis globally. The emergency has made it imperative for professionals to take the necessary measures to make early diagnoses of the disease. The conventional diagnosis for COVID-19 is through Polymerase Chain Reaction (PCR) testing. However, in a lot of rural societies, these tests are not available or take a lot of time to provide results. Hence, we propose a COVID-19 classification system by means of machine learning and transfer learning models. The proposed approach identifies individuals with COVID-19 and distinguishes them from those who are healthy with the help of Deep Visual Embeddings (DVE). Five state-of-the-art models: VGG-19, ResNet50, Inceptionv3, MobileNetv3, and EfficientNetB7, were used in this study along with five different pooling schemes to perform deep feature extraction. In addition, the features are normalized using standard scaling, and 4-fold cross-validation is used to validate the performance over multiple versions of the validation data. The best results of 88.86% UAR, 88.27% Specificity, 89.44% Sensitivity, 88.62% Accuracy, 89.06% Precision, and 87.52% F1-score were obtained using ResNet-50 with Average Pooling and Logistic regression with class weight as the classifier.

• Journal of Elementary Mathematics Education in Korea
• /
• v.21 no.2
• /
• pp.309-341
• /
• 2017

This study aims to investigate an approach to teach percentages in elementary mathematics class by analyzing calculating strategies with percentage the students use to solve the percentage tasks and their percentages of correct answers, as well as types of errors with percentages the students make. For this research 182 sixth graders were examined. The instrument test consists of various task types in reference to the previous study; the percentages tasks are divided into algebraic-geometric, part whole-comparison-change and find part-find whole-find percentage tasks. According to the analysis of this study, percentages of correct answers of students with percentage tasks were lower than we expected, approximately 50%. Comparing the percentages of correct answers according to the task types, the part-whole tasks are higher than the comparison and change tasks, the geometric tasks are approximately equal to the algebraic tasks, and the find percentage tasks are higher than the find whole and find part tasks. As to the strategies that students employed, the percentage of using the formal strategy is not much higher than that of using the informal strategy, even after learning the formal strategy. As an insightful approach for teaching percentages, based on the study results, it is suggested to reinforce the meaning of percentage, include various types of the comparison and change tasks, emphasize the informal strategy explicitly using models prior to the formal strategy, and understand the relations among part, whole and percentage throughly in various percentage situations before calculating.

• The Mathematical Education
• /
• v.39 no.2
• /
• pp.127-144
• /
• 2000

School mathematics are composed of five major units of numbers& algebraic expressions, equations & inequalities, functions, figures, and statistics & probabilities. But if we look into the general activities of mathematics teachers in their class, they rather do not take into account students\` cognitive and affective traits or degree of difficulty which each of the unit has. For successful teaching of mathematics, teachers should take into consideration many affective items which influence the students\` scholastic achievement. Among them student\`s liking for the mathematics is commonly accepted as the most important factor for successful learning. In this study, with the five units of school mathematics, we investigated the students\` degree of likings for each unit. To fined out whether there are any differences in students\` likings for the mathematics, between regions and kind of schools, we classified the population according to the locations and kinds of schools. To do this, we divided the whole region into four parts such as Seoul, large city, medium city and town. Moreover, we partitioned the whole secondary school students into four groups of middle school students, vocational high school students, pro-science students of academic high schools, and pro-liberal arts students of academic high schools. From each partition, we sampled similar size of experimental groups which came up to total 1260 students. Analysing the answer sheets which the students responded about the questionnaire, we investigated the following questions using the ANOVA test. 1. Is there any differences in the trend of likings for each unit between the regional classifications? 2. Is there any differences in the trend of likings for each unit between the classifications of secondary schools? 3. What trends of changes are there in the degree of likings for each unit according to the rising of students\` grade?

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.6
• /
• pp.1834-1843
• /
• 2000

In this paper, we propose a modular neural network based classification method for handwritten numerals utilizing rotated and translated images of an input image. The whole numeral pattern space is divided into smaller spaces which overlap each other and form multiple clusters. On these multiple clusters, multiple multilayer perceptrons (MLP) neural networks, specialized in those clusters, are constructed. Thus, each MLP acts as an expert network on the corresponding cluster. An MLP is also used as a gating network functioning as a mediator among the multiple MLPs. In the learning phase, an input numeral image is dithered by tow geometric operations of translation and rotation so that new numeral images similar to original one are generated. In the recognition phase, we utilize not only input numeral image, but also nearly generated images through the rotation and the translation of the original image. Thus, multiple output values for those generated images were combined to make class decision by various combination methods. The experimental results confirm the validity of the proposed method.

• Journal of The Korean Association For Science Education
• /
• v.22 no.5
• /
• pp.957-969
• /
• 2002

Theoretical benefits and research findings on the use of Microcomputer-based Laboratory (MBL) are considered for using MBL in a way that will be of benefit to students and teachers, and discussed as a whole for further synthesis, including the formulation of a research agenda for future consensus-based action. Based on the findings obtained from a comprehensive review of the literature, using a systematic approach, the uses of MBL were compared and contrasted for advancing understanding of the teaching and learning processes in science and mathematics. A number of benefits were proposed by MBL developers but not investigated by educational researchers. A few research studies considered the following practical aspects raised by classroom science teachers: technical problems of MBL equipment; inaccuracy or incompleteness of presentation; efficient ways for handling class time with MBL instruction; and development of MBL curriculum materials for their own instruction. This lack of research related to the use of MBL in science classrooms resulted in educational research that was neither respected nor utilized by science teachers. Setting a research agenda based on the theoretical benefits and research findings is necessary for the effective use of MBL in science classrooms can help to maximize the prospects for successful school improvement projects while minimizing the innovation-related frustrations of individuals.

• Journal of The Korean Association For Science Education
• /
• v.13 no.1
• /
• pp.56-65
• /
• 1993

The purpose of this study is to analyze the inquiry activities of SCIIS and Korea primary school science curricular meterials and to make suggestions for the improvement of inquiry learning based on the analysis The Scientific Inquiry Evaluation Inventory (SIEI: Myung Hur, 1984) was used to evaluate the inquiry activity content of the primary school "Science, Level-6" and "SCIIS, Level-6" textbooks. The results are as follows: 1) The inquiry activities of Korean science textbooks are stressing on gathering and organizing data, but rarely require students to formulate a hypothesis, to design an experiment. 2) The SCIIS textbooks relatively tended to put more weight on interpreting/ analysing data and hypothesizing/ designing experiments. 3)The Korean science textbooks had little concern about establishing hypothesis and designing experiments, interpreting / analysing data. 4) The SCIIS textbooks require students to perform a variety of inquiry skills when compare to Korean science textbooks. 5) Competition / Cooperation Scale checks the level of competition and cooperation among student teams inherent in science curricular materials. The result from each team is incorporated into the formation of a class result. The communication is required to formulate a synthesized class response, enhances cooperation among teams. The SCIIS(84%) is the higher than Korea(50%) in cooperation scale. 6) Korean science textbooks rarely require students to discuss about experiment when compare to SCIIS textbooks. 7) Korean science textbooks provide students with both inquiry problems and experimental procedure, or including answers SCIIS textbooks provide students with both inquiry problems and experimental procedure, or problems only. 8) The Korean textbooks emphasize demonstrating or verifying of the text while the SCIlS emphasize extending the content of the text in inquiry scope scsle. The inquiry pyramid which helps analysis the inquiry activity curriculum as a whole is one of type 1- the course is centered on gathering and organizing data. The SCIIS are better than the Korean science textbook in the light of proportion of interpreting / analysing data and hypothesizing / designing experiments.

• Journal of Korean Home Economics Education Association
• /
• v.29 no.3
• /
• pp.141-160
• /
• 2017

At present, the whole world is characterized by openness, cooperation and integration as a society with information and the world, and it requires creative talents for this. The competitiveness of the nation depends on the cultivation of creative talents. It demands anthropological value by improving the competitiveness of the nation through cultivating creative talents to share and care, not to cultivate creative talents for personal desires and accomplishments. The purpose of this study is to develop a teaching - learning process to develop integrated creative talents by applying the characteristics of integrated education curriculum at the base of the 2015 revised curriculum. To do this, we first extracted the content elements of the Clothing Life area of the revised curriculum from the 1st to 2015 and the contents of the Clothing Life area of the technology and home Economics textbooks to which the 2009 revision curriculum was applied. Five topics were extracted according to content selection criteria And The Theme of 'The selection and management of clothing' was selected. Researcher developed a integrated thematic instruction Home Economics Education Clothing Life teaching - learning process (hereinafter referred to as "the process") focused on the theme of 'selection and management of clothing'. The Process was composed of 5 basic classes [basic inquiry - content 1 - content 2 - depth study - application]. The process considers integration within the curriculum and interdepartmental integration, and aims to improve the personality, creativity, and problem solving ability of consideration and sharing in the course of the integrated class. In detail, the curriculum goals of the home Economics Education curriculum and ITI goals are presented separately in the curriculum developed for each process. At the stage of the class, the element of creativity and the element of personal education were exposed and applied to the class. In Korea, new curriculum has been revised and announced from time to time, making it difficult for the teacher to carry out the class in accordance with the paradigm of change. Home curriculum is closely related to real life, so it is an appropriate subject for an integrated subject. It has the educational significance of the subject in that it allows students to integrate the creative and personal elements that are limited in other subjects. ITI process will be helpful to teachers who need to implement the 2015 revised curriculum in which the theme-centered integrated home Economics education teaching-learning process is newly introduced. It is necessary to follow - up research to verify the effectiveness of how to improve students' problem - solving ability and cultivate creativity.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.2
• /
• pp.37-44
• /
• 2020

In this paper, we proposed that a fully automatic multi-class whole heart segmentation algorithm using deep learning. The proposed method is based on U-Net architecture which consist of recurrent convolutional block, residual multi-dilated convolutional block. The evaluation was accomplished by comparing automated analysis results of the test dataset to the manual assessment. We obtained the average DSC of 96.88%, precision of 95.60%, and recall of 97.00% with CT images. We were able to observe and analyze after visualizing segmented images using three-dimensional volume rendering method. Our experiment results show that proposed method effectively performed to segment in various heart structures. We expected that our method can help doctors and radiologist to make image reading and clinical decision.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3567-3582
• /
• 2020

Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.

• Journal of Korean Elementary Science Education
• /
• v.22 no.1
• /
• pp.121-129
• /
• 2003

The enhancement of inquiry skills has been emphasized as a important objective of science education for a long time. Of these, the observation is not only a simple and basic skill, but also a very important skill, in aspect of gathering informations about the nature of all things around us, through interaction between the sense organs of body and objectives. The purpose of this study is to investigate the results of observations about the grasshopper(Oxya chinesis), made by the elementary student from the 3rd to the 6th grade, and to make use of them as the basic materials for the observative teaming and the evaluation of the observation ability. Through this study, the collected items of observation are as follows For grasshopper, a total of observation items is 95, 70 using the sight sense, 13 using the tactile sense,7 using the olfactory sense. 3 using the palate sense and 2 using the auditory sense. In this study, the findings of elementary student's observation are as follows. 1. On the whole, most of students have observed mainly by the sight and the tactile sense, when observing the grasshopper. 2. It is showed a tendency that the observation ability of student is increased with the higher grade in elementary school. 3. As the grade ascends. the observations with operating are increased, also the quantitative expression and interpretation about them are increased. 4. In the case of same grade, there is no significant difference between students' gender, though girls' ability of the observation showed somewhat higher than boys' 5. Occasionally, the interpretations on the observative facts made by student, are inaccurate. Basis on the above results, we suggested some directions for the improvement of the observative learning program in science classroom of elementary school. First, the teacher have to serve as a guide and encouragement in the observative learning class, to be accomplished the various observation, which all the sensory organ can be used by student than the sight sense. Second, to get elevated the ability of observation, it is necessary that some experimental tools(magnifying lens, stereoscope, auxiliary implements etc.) are utilized. Third, the teacher have to make often endeavors showing an example of operation, to be activated the atmosphere of operative observation.