• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.437-446
• /
• 2022

Text classification task from Natural Language Processing (NLP) combined with state-of-the-art (SOTA) Machine Learning (ML) and Deep Learning (DL) algorithms as the core engine is widely used to detect and classify voice phishing call transcripts. While numerous studies on the classification of voice phishing call transcripts are being conducted and demonstrated good performances, with the increase of non-face-to-face financial transactions, there is still the need for improvement using the latest NLP technologies. This paper conducts a benchmarking of Korean voice phishing detection performances of the pre-trained Korean language model KoBERT, against multiple other SOTA algorithms based on the classification of related transcripts from the labeled Korean voice phishing dataset called KorCCVi. The results of the experiments reveal that the classification accuracy on a test set of the KoBERT model outperforms the performances of all other models with an accuracy score of 99.60%.

• Communications for Statistical Applications and Methods
• /
• v.28 no.4
• /
• pp.329-338
• /
• 2021

Deep learning methods have been developed, used in various fields, and they have shown outstanding performances in many cases. Many studies predicted a daily stock return, a classic example of time-series data, using deep learning methods. We also tried to apply deep learning methods to Korea's stock market data. We used Korea's stock market index (KOSPI) and several individual stocks to forecast daily returns and directions. We compared several deep learning models with other machine learning methods, including random forest and XGBoost. In regression, long short term memory (LSTM) and gated recurrent unit (GRU) models are better than other prediction models. For the classification applications, there is no clear winner. However, even the best deep learning models cannot predict significantly better than the simple base model. We believe that it is challenging to predict daily stock return data even if we use the latest deep learning methods.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.10a
• /
• pp.339-344
• /
• 1993

A study for a lathe to machine workpieces with noncircular corss-sections is presented. The noncircular cutting is accomplished by controlling the radial tool position synchronized with the revolution angle of spindle. A learning control algorithm is suggested for the toll positioning, of which the control performances are analyzed and simulated on a numerical computer that the effectiveness of the control is convinced. The learning control is tested on a NC-lathe which shows successful results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.11
• /
• pp.4220-4227
• /
• 2010

Recently there have been many arguments about the admission officers system, but the majority of researches about admission officer has not focused student performance. We compared learning performances of students selected by admission officers and students selected by standardized test. We checked the marks of students at college entrance point and the average grade for their freshman year. Analyzing the data, we got two major findings. At the point of entrance, the students selected by admission officers had less performances. But the analysis of average grade for 1 year, there were no statistical differences between two groups of students.

• International Commerce and Information Review
• /
• v.11 no.1
• /
• pp.239-264
• /
• 2009

As the competitive market environment and industry circumstances become more and more competitive on a daily basis, it is not easy to find an opportunity to initiate small business, or increase performances of Small and Medium Business. The research findings are as follows. First, entrepreneurship(innovation, progressive, social responsibility) has significant effects on the market orientation. Second, company competence(individual resource, technology resource) has significant effects on the market orientation. Third, market orientation has significant effects on the non-financial performance(Internal process performance, learning & growth performance, customer performance). Finally, non-financial performance(Internal process performance, learning & growth performance, customer performance) has significant effects on the financial performance.

• The Journal of Asian Finance, Economics and Business
• /
• v.6 no.1
• /
• pp.205-215
• /
• 2019

Researchers have confirmed the relationship between ambidexterity learning and innovation performance, but according to the resource-based theory, the relationship between ambidexterity learning and innovation performance is also affected by the internal resources of the organization. Internal resources are an important factor affecting the transformation of learning outcomes into performance. In addition, few scholars have pointed out whether different types of learning have different effects on different types of innovation performance. This study collects data from 170 High-tech enterprises in Shandong, china, and discusses the effects of exploitative learning and explorative learning on management innovation performance and technological innovation performance. This study further examines the moderating role of slack resource on the relationship between ambidexterity learning and innovation performance. Results show that ambidexterity learning has positive effect on innovation performance. Compared with exploitative learning, explorative learning has a greater impact on management innovation performance; compared with explorative learning, exploitative learning has a greater impact on technological innovation performances. Slack resource has positive moderating role between the relationship of exploitative learning, explorative learning and technology innovation performance. But Slack resource has no moderating role between the relationship of exploitative learning, explorative learning and management innovation performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.193-196
• /
• 2008

Z. Cao had proposed NFRM(new fuzzy reasoning method) which infers in detail using relation matrix. In spite of the small inference rules, it shows good performance than mamdani's fuzzy inference method. In this paper, we propose 2. Cao's fuzzy inference method using learning ability witch is used a gradient descent method in order to improve the performances. Because it is difficult to determine the relation matrix elements by trial and error method which is needed many hours and effort. Simulation results are applied linear and nonlinear system show that the proposed inference method has good performances.

• Asian Journal of Business Environment
• /
• v.9 no.3
• /
• pp.27-38
• /
• 2019

Purpose - The aim of this study is to explore the effectiveness in educational differences between students of the government's financial-funded groups and the non-financial-funded groups at a university in Korea. Research design, data, and methodology - The study was conducted using a survey tool of National Assessment for Student Engagement in Learning. In total, 334 participants were surveyed, of which 290 students were participants in economic support program and 44 were nonattendance program students. The general characteristics of all of the participants were investigated by frequency analysis. The analysis of participants' collective characteristics used independent t and f-test, and one-way ANOVA with IBM SPSS Statistics package program 22.0. Results - The number of participating students is higher than that of non-participating students in relation to in-activities of university immersion, but the number of participating students is lower than that of non-participating students in relation to in-quality of student support. However, there was no statistical significance. The confidence coefficient of the university-immersion and student support questionnaire is 0.860 and 0.913, respectively. Conclusions - There is no significant difference in the activities of university immersion and student support between students who participate in the economic support program and those who do not.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.21-29
• /
• 2020

Accurate estimation of human pose relies on backbone method in which its role is to extract feature map. Up to dated, the method of backbone feature extraction is conducted by the plain convolutional neural networks named by CNN and the residual neural networks named by Resnet, both of which have various architectures and performances. The CNN family network such as VGG which is well-known as a multiple stacked hidden layers architecture of deep learning methods, is base and simple while Resnet which is a bottleneck layers architecture yields fewer parameters and outperform. They have achieved inspired results as a backbone network in human pose estimation. However, they were used then followed by different pose estimation networks named by pose parsing module. Therefore, in this paper, we present a comparison between the plain CNN family network (VGG) and bottleneck network (Resnet) as a backbone method in the same pose parsing module. We investigate their performances such as number of parameters, loss score, precision and recall. We experiment them in the bottom-up method of human pose estimation system by adapted the pose parsing module of openpose. Our experimental results show that the backbone method using VGG network outperforms the Resent network with fewer parameter, lower loss score and higher accuracy of precision and recall.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.9
• /
• pp.1591-1598
• /
• 2008

Z. Cao had proposed NFRM(new fuzzy reasoning method) which infers in detail using relation matrix. In spite of the small inference rules, it shows good performance than mamdani's fuzzy inference method. In this paper, we propose Z. Cao's fuzzy inference method with learning ability which is used a gradient descent method in order to improve the performances. It is hard to determine the relation matrix elements by trial and error method. Because this method is needed many hours and effort. Simulation results are applied nonlinear systems show that the proposed inference method using a gradient descent method has good performances.