• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.11
• /
• pp.1435-1441
• /
• 2018

Online signature verification is one of the simple and efficient methods of identity verification and has less resistance than other biometric technologies. To handle signature verification as a classification problem, it is necessary to gather forgery signatures, which is not easy in most practical applications. It is not easy to obtain a large number of genuine signatures either. In this paper, one class SVM is used to tackle the forgery signature problem and someone else's signatures are used as general handwriting data to solve the genuine signature problem. Someone else's signature does not share shape-based features with the signature to be verified, but it contains the general characteristics of a signature and useful in verification. Verification rate can be improved by using the general handwriting data, which can be confirmed through the experimental results.

• Human Ecology Research
• /
• v.60 no.2
• /
• pp.187-209
• /
• 2022

The objective of this study was to conduct a 'Theory of Home Economics Education' class using online problem-based learning(PBL) for prospective home economics(HE) teachers. The aim was to enable teachers to analyze the learning experience in the classroom, and to prepare operational strategies for online PBL on this basis. In order to achieve this, online PBL was applied to 31 students participating in the 'Theory of Home Economics Education' at the Department of HE in a university in Seoul, and the results were collected from the learning process. This also involved a reflective journal, a survey on the learning experience and the impacts was conducted. Moreover, analysis was undertaken on the learning activities, learning difficulties, and improvements. The main research results are as follows. Firstly, students accessed Webex, an online video conferencing program, and performed two PBL tasks: 'Making Home Economics Promotion Materials' and 'Presenting Teaching Strategies to Improve Learner's Immersion in Online Classes'. Secondly, learners established their own identity of HE learned about the HE class plans themselves. They also encountered realistic experience as HE teachers and learned communication and collaboration skills. Furthermore, they acquired creative problem-solving and self-directed learning ability, community consciousness, as well as the attitude of consideration and respect. Thirdly, students lacked knowledge of learning content and encountered difficulty in solving data research, analysis processes, and unstructured problems. They were affected by a lack of time and encountered problem in communicating with other team members in an online environment. As an improvement in online class operation, it was considrered necessary to reduce the learning burden by securing time and reducing the number of assignments, as well as to explain active interaction with instructors and PBL.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.233-239
• /
• 2022

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.142-151
• /
• 2023

This study is a case study on investigating students' learning behavior in the online English reading class of an on-off course. For this purpose, a survey was conducted on a total of 77 students from an English listening and reading course and phone interview with 5 students was implemented. The findings revealed that regularity of learning interval and learning sequence need to be improved through student management in order to increase the effect of online learning. In case of lecture watching, the students are good at utilizing the strengths of taped lecture, such as using pause and repeating watching. However, more research need to be done on how to develop online lecture to enhance students' understanding of the lecture. Regarding the offline review quiz that is supposed to stimulate students into their more positive watching of the lecture, it is suggested that a few of its related elements such as the online learning period and the number of quiz questions be corrected for its better effect.

• Quality Improvement in Health Care
• /
• v.30 no.1
• /
• pp.3-14
• /
• 2024

Purpose: We conducted this study with the aim of characterizing safety attitudes (SA) among medical staff in a disadvantaged area of Vietnam and examining associated factors with SA. Methods: A cross-sectional survey was conducted on 442 health staff members at four hospitals in Son La Province from June until August 2021. We used the Vietnamese shortened edition of the Safety Attitudes Questionnaire to measure the SA of study participations. We chose latent class analysis (LCA) to identifying the number of latent classes of SA among the study subjects. Multinomial logistic regression was used to examine factors associated with the identified SA classes. Results: The results of our LCA showed that there were three latent classes, namely high SA group (n=150, 33.9%), moderate SA group (n=236, 53.4%), and low SA group (n=56, 12.7%). The multinomial logistic regression analysis found that medical staff who had university education and above, who were nurses, and who served in non-clinical areas were more likely to be in the moderate SA group and in the high SA group than in the low SA group. Conclusion: Based on these results, several recommendations could be made to improve the SA of healthcare workers in disadvantaged areas. Further research with larger sample sizes and more diverse populations is needed to confirm these findings and to develop effective interventions to improve the SA of healthcare workers in disadvantaged areas.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.83-88
• /
• 2024

In this research, we propose a Semi-Supervised learning based railroad surface defect detection method. The Resnet50 model, pretrained on ImageNet, was employed for the training. Data without labels are randomly selected, and then labeled to train the ResNet50 model. The trained model is used to predict the results of the remaining unlabeled training data. The predicted values exceeding a certain threshold are selected, sorted in descending order, and added to the training data. Pseudo-labeling is performed based on the class with the highest probability during this process. An experiment was conducted to assess the overall class classification performance based on the initial number of labeled data. The results showed an accuracy of 98% at best with less than 10% labeled training data compared to the overall training data.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.61-73
• /
• 2024

Class imbalance is one of the significant challenges in deep learning tasks, particularly pronounced in areas with limited data. This study proposes a new approach that utilizes minimal labeled data for effectively classifying tomato leaf diseases. We introduced a recursive learning method using the YOLOv8 model. By utilizing the detection predictions of images on the training data as additional training data, the number of labeled data is progressively increased. Unlike conventional data augmentation and up-down sampling techniques, this method seeks to fundamentally solve the class imbalance problem by maximizing the utility of actual data. Based on the secured labeled data, tomato leaves were extracted, and diseases were classified using the EfficientNet model. This process achieved a high accuracy of 98.92%. Notably, a 12.9% improvement compared to the baseline was observed in the detection of Late blight diseases, which has the least amount of data. This research presents a methodology that addresses data imbalance issues while offering high-precision disease classification, with the expectation of application to other crops.

• Journal of the Korean association of regional geographers
• /
• v.11 no.4
• /
• pp.523-535
• /
• 2005

This study is aimed at researching the applicability of teaching-learning models in highschool geography class by designing the models on the basis of geographical experience the learners go through everyday life. The procedures and results of the application of the models are as followed. First, the systematization of the teaching concepts should be preceded to internalize the learners cognitive development, that is, to systemize cognitive structure. The concrete learning points of geographical concepts from the units about Migration and Population Changes are systemized with 'migration' as a higher concept, 'moving type' as basic concept, 'moving factors' as the lower concept. Everyday geographical experiences the students can go through are surveyed. Second, as preparation for the geography class, hand-outs about family-moving history and the change of the family number were used as basic material for real class teaching activity, showing the learners' general concepts are very effective as basic units which can be easily understood and accessed to. Third, with the experimental class, the geography class should secure the flexibility on the teaching-learning process. The result of applying the newly developed teaching-learning model to actual geography classes was that experimental group had higher achievement rate than the compared group with general teaching-learning model applied to. The result of analyzing students' response of the new teaching-learning model was that the students were interested and satisfied emphatically and they showed positive response in regard to practical use of the contents. Here, it is noticeable that the new teaching-learning model causes the students to be interested. But it's also found that there's no big difference in improving the students' inquisitive mind.

• Journal of Environmental Science International
• /
• v.13 no.3
• /
• pp.301-311
• /
• 2004

The purpose of this study was to examine teachers’ awareness of chemical waste produced in elementary school laboratory experimentation and how this awareness relates to collection and disposal of chemical waste. More specifically, the study looked at the correlation between the handling of chemical waste and factors such as years of teachers’ educational career, class size and amount of waste produced. The target population were 250 elementary school teachers in Gyeongnam area and 237 subjects were responded. Among the 237 responses, 37 cases that did not complete the questionnaire were eliminated. Therefore, 200 responses were analyzed in this study. The survey questionnaire consisted of 15 questions. The categories of the questionnaire were their skills of management and treatment of the chemical waste. The data collected were analyzed by SPSS 10.0, and the relations among variables such as class sizes and years of teaching experience were also analyzed by $x^2-test.$ The results in this study were as follows: First, there were no significant differences between the years of teaching and class sizes in the training experience of chemical waste disposal. Second, there was a significant difference between the science laboratory size and class sizes in the laboratory actual condition. In addition, in the relations between the number of times of experimentation and the years of teaching experience, there was a significant difference. Third, in terms of the discharge amount of chemical waste, there was a significant difference between the years of teaching and class sizes. Fourth, in the simple chemistry waste disposal process in the science laboratory, there also was a significant difference between the kinds of experimental equipments that used in the experimentation and the years of teaching. Based on this study, it was found that great amount of the chemical wastes produced in the science laboratory dumped into the drain and the treatment process of chemical waste was also inattentive. Even the importance of environmental education is emphasized in the elementary education, the basic problems occurred in the science laboratory is disregarded. Therefore, not only students but teachers have to pay attention to the disposal process of chemical waste in the laboratory in order to prevent environment pollution. Furthermore, the efforts of preventing environment pollution are needed such as opening the teacher training course about environment education, minimal use of chemicals, treatment of chemical waste, and so forth.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.12
• /
• pp.253-261
• /
• 2016

This study discusses the effective management of mixed-ages classes in kindergarten. For the study, 300 kindergarten teachers in charge of mixed classes for regular courses completed a self-reported questionnaire through a web survey. The data were analyzed by chi-square test and presented by frequency and percentage. Mixed-ages classes had relatively fewer children than one-age classes and they were prevalent in public kindergartens and rural areas. The results were as follows. First, mixed-ages classes were induced by the small number of young children. Second, teachers managed their classes with difficulty due to the lack of supporting staff and few chances for additional teaching training. Third, teachers needed supporting human resources for their teaching and administration assistances. About 23.0% of kindergartens received assistance such as additional training, financial assistance, and consulting supervision from related institutions. The study results suggested the challenges in regulations of age ratio in mixed-ages class, additional teaching training for teachers in mixed-ages classes and replacement of mixed-ages class to same age class as the long-term plan.