• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.953-964
• /
• 2020

Ever since media contents took over the world, the importance of typography has increased, and the influence of fonts has be n recognized. Nevertheless, the current Hangul font system is very poor and is provided passively, so it is practically impossible to understand and utilize all the shape characteristics of more than six thousand Hangul fonts. In this paper, the characteristics of Hangul font shapes were selected based on the Hangul structure of similar fonts. The stroke element detection training was performed by fine tuning Faster R-CNN Inception v2, one of the deep learning object detection models. We also propose a system that automatically extracts the stroke element characteristics from characters by introducing an automatic extraction algorithm. In comparison to the previous research which showed poor accuracy while using SVM(Support Vector Machine) and Sliding Window Algorithm, the proposed system in this paper has shown the result of 10 % accuracy to properly detect and extract stroke elements from various fonts. In conclusion, if the stroke element characteristics based on the Hangul structural information extracted through the system are used for similar classification, problems such as copyright will be solved in an era when typography's competitiveness becomes stronger, and an automated process will be provided to users for more convenience.

• Korean Journal of Social Welfare
• /
• v.65 no.4
• /
• pp.221-243
• /
• 2013

The purpose of the study was to investigate the effect of organizational and care worker factors on client violence occurring at nursing homes in Korea, and to provide an empirical basis on which to draw strategies for prevention and reduction of client violence. A survey was conducted on 253 care workers from 23 nursing homes located in 16 regions nationwide, and multiple regression models were analyzed to examine the effect of worker demographic variables, education and experience, work related characteristics, working conditions, and organizational risk management system on client violence. The respondents reported their experience of violence from the most frequent to the least in the order of physical, verbal, others, property damage, and sexual in nature; only half of their employers were implementing an organizational risk management system. In the regression analysis on client violence of all types combined, risk management procedures and supervisor leadership were found statistically signifiant. Based on these results, implications were discussed for agency efforts in improving risk management procedures and leadership training of supervisors.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.103-111
• /
• 2020

Liver cancer is the most fatal cancer that occurs worldwide. In order to diagnose liver cancer, the patient's physical condition was checked by using a CT technique using radiation. Segmentation was needed to diagnose the liver on the patient's abdominal CT scan, which the radiologists had to do manually, which caused tremendous time and human mistakes. In order to automate, researchers attempted segmentation using image segmentation algorithms in computer vision field, but it was still time-consuming because of the interactive based and the setting value. To reduce time and to get more accurate segmentation, researchers have begun to attempt to segment the liver in CT images using CNNs, which show significant performance in various computer vision fields. The pixel value, or numerical value, of the CT image is called the Hounsfield Unit (HU) value, which is a relative representation of the transmittance of radiation, and usually ranges from about -2000 to 2000. In general, deep learning researchers reduce or limit this range and use it for training to remove noise and focus on the target organ. Here, we observed that the range of HU values was limited in many studies but different in various liver segmentation studies, and assumed that performance could vary depending on the HU range. In this paper, we propose the possibility of considering HU value range as a hyper parameter. U-Net and ResUNet were used to compare and experiment with different HU range limit preprocessing of CHAOS dataset under limited conditions. As a result, it was confirmed that the results are different depending on the HU range. This proves that the range limiting the HU value itself can be a hyper parameter, which means that there are HU ranges that can provide optimal performance for various models.

• Communications for Statistical Applications and Methods
• /
• v.17 no.5
• /
• pp.697-712
• /
• 2010

This paper is concerned with the statistical analysis and development of stochastic models for the demand for life insurance policy loans. For these, firstly the characteristics of the regression trend, periodicity and dependence of the monthly demand for life insurance policy loans are investigated by a statistical analysis of the monthly demand data for the years 1999 through 2008. Secondly, the causal relationships between the demand for life insurance policy loans and the economic variables including unemployment rate and inflation rate for the period are investigated. The results show that inflation rate is main factor influencing policy loan demands. The overall evidence, however, failed to establish unidirectional causality relationships between the demand series and the other variables under study. Finally, based on these, univariate time series model and transfer function model where the demand series is related to one input series are derived, respectively, for the prediction of the demand for life insurance policy loans. A statistical procedure for using the model to predict the demand for life insurance policy loans is also proposed.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.59-64
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to chose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state- action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem. we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL)as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• The KIPS Transactions:PartB
• /
• v.17B no.2
• /
• pp.139-148
• /
• 2010

This paper shows a reinforcement post-processing method and feedback algorithm for improvement of assigning method in classification. Especially, we focused on complex documents that are generally considered to be hard to classify. A basis factors in traditional classification system are training methodology, classification models and features of documents. The classification problem of the documents containing shared features and multiple meanings, should be deeply mined or analyzed than general formatted data. To address the problems of these document, we proposed a method to expand classification scheme using decision boundary detected automatically in our previous studies. The assigning method that a document simply decides to the top ranked category, is a main factor that we focus on. In this paper, we propose a post-processing method and feedback algorithm to analyze the relevance of ranked list. In experiments, we applied our post-processing method and one time feedback algorithm to complex documents. The experimental results show that our system does not need to change the classification algorithm itself to improve the accuracy and flexibility.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.9
• /
• pp.3841-3848
• /
• 2012

The process of an analysis of alternatives(AoA) attempts to select the best and balanced solution among a set of multiple candidate solutions under the constraints of cost, schedule, performance and risk(CSPR). The traditional AoA for the acquisition of a new weapon system has usually centered on the sequence of the requirement analysis, design synthesis, and cost estimation. An improved process for AoA is developed in this paper based on a multi-objective decision-making method, which is intended to be applied in the design concept refinement and material solution analysis stage for the acquisition of naval surface ships. The presentation of the proposed AoA approach is then followed by a case study for the next generation multi-purpose training ship based on the principles of systems engineering and also using the models of the effectiveness measure, cost estimation, and risk assessments.

• Tunnel and Underground Space
• /
• v.28 no.3
• /
• pp.277-291
• /
• 2018

LSTM (Long Short-Term Memory) algorithm which is a kind of recurrent neural network was used to establish a model to predict the stress-strain curve of an material under uniaxial compression. The model was established from the stress-strain data from uniaxial compression tests of silica-gypsum specimens. After training the model, it can predict the behavior of the material up to the failure state by using an early stage of stress-strain curve whose stress is very low. Because the LSTM neural network predict a value by using the previous state of data and proceed forward step by step, a higher error was found at the prediction of higher stress state due to the accumulation of error. However, this model generally predict the stress-strain curve with high accuracy. The accuracy of both LSTM and tangential prediction models increased with increased length of input data, while a difference in performance between them decreased as the amount of input data increased. LSTM model showed relatively superior performance to the tangential prediction when only few input data was given, which enhanced the necessity for application of the model.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.3 no.2
• /
• pp.1-29
• /
• 2008

The objective of this study is to develop new entrepreneurship education program and to enhance the program by applying new program. First, this paper examined domestic studies for preceding research on entrepreneurship education, and did foreign studies as theoretical background based on the examination. And this paper drew new models for entrepreneurship education program by analyzing education program from American and Japanese graduate school of entrepreneurship. The model of entrepreneurship education program was drawn by theoretical range, educational system and practical model, and presented reform measures by applying that on the Graduate School of Entrepreneurship. The range of entrepreneurship education program is defined from the moment when an entrepreneur decided to his entrepreneurship to initial growth stage, and should educate specific knowledge required to the development of companies and measures against potential problems on the way to growth it. An entrepreneurship training program should be organized curriculum by the growth stages of company.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.6
• /
• pp.900-911
• /
• 2015

In this paper, 3D face recognition model is designed by using Polynomial based RBFNN(Radial Basis Function Neural Network) and PNN(Polynomial Neural Network). Also recognition rate is performed by this model. In existing 2D face recognition model, the degradation of recognition rate may occur in external environments such as face features using a brightness of the video. So 3D face recognition is performed by using 3D scanner for improving disadvantage of 2D face recognition. In the preprocessing part, obtained 3D face images for the variation of each pose are changed as front image by using pose compensation. The depth data of face image shape is extracted by using Multiple point signature. And whole area of face depth information is obtained by using the tip of a nose as a reference point. Parameter optimization is carried out with the aid of both ABC(Artificial Bee Colony) and PSO(Particle Swarm Optimization) for effective training and recognition. Experimental data for face recognition is built up by the face images of students and researchers in IC&CI Lab of Suwon University. By using the images of 3D face extracted in IC&CI Lab. the performance of 3D face recognition is evaluated and compared according to two types of models as well as point signature method based on two kinds of depth data information.