• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.750-762
• /
• 2019

The importance of the call center as a contact point for the enterprise is growing. However, call centers have difficulty with their operating agents due to the agents' lack of knowledge and owing to frequent agent turnover due to downturns in the business, which causes deterioration in the quality of customer service. Therefore, through an N-bank call center case study, we developed a system to reduce the burden of keeping up business knowledge and to improve customer service quality. It is a "real-time agent advisor" system that provides agents with answers to customer questions in real time by combining AI technology for speech recognition, natural language processing, and questions & answers for existing call center information systems, such as a private branch exchange (PBX) and computer telephony integration (CTI). As a result of the case study, we confirmed that the speech recognition system for real-time call analysis and the corpus construction method improves the natural speech processing performance of the query response system. Especially with name entity recognition (NER), the accuracy of the corpus learning improved by 31%. Also, after applying the agent advisor system, the positive feedback rate of agents about the answers from the agent advisor was 93.1%, which proved the system is helpful to the agents.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.107-117
• /
• 2019

In the era of SNS, many people relies on it to express their emotions about various kinds of products and services. Therefore, for the companies eagerly seeking to investigate how their products and services are perceived in the market, emotion mining tasks using dataset from SNSs become important much more than ever. Basically, emotion mining is a branch of sentiment analysis which is based on BOW (bag-of-words) and TF-IDF. However, there are few studies on the emotion mining which adopt feature selection (FS) methods to look for optimal set of features ensuring better results. In this sense, this study aims to propose FS methods to conduct emotion mining tasks more effectively with better outcomes. This study uses Twitter and SemEval2007 dataset for the sake of emotion mining experiments. We applied three FS methods such as CFS (Correlation based FS), IG (Information Gain), and ReliefF. Emotion mining results were obtained from applying the selected features to nine classifiers. When applying DT (decision tree) to Tweet dataset, accuracy increases with CFS, IG, and ReliefF methods. When applying LR (logistic regression) to SemEval2007 dataset, accuracy increases with ReliefF method.

• Fire Science and Engineering
• /
• v.33 no.1
• /
• pp.121-129
• /
• 2019

In Korea, life safety assessment through simulation are mandatory in performance-based design. Generally, there are three types of methods for simulation-based life safety assessments: the non-coupling method that compares available safe egress time (ASET) and required safe egress time (RSET) at a specific point through conducting fire and assessment simulations independently; the semi-coupling method that compares fire and evacuation simulation results by overlaying the result screens; and the coupling method that compares the results of fire effect simulation to an evacuation simulation. Of these methods, all designers in South Korea have used the only non-coupling method. In the non-coupling method, it is important to determine the location of a specific point to compare ASET and RSET. However, without any defined regulation, setting the location is determined based on the designer's experience and knowledge. The number of specific locations and the locations themselves differ with each designer, which can produce contrasting results in a life safety assessment. Therefore, this study conducted a life safety assessment based on the three methods (non-coupling, semi-coupling and coupling) and compared each of the results. Furthermore this study suggests a improvement way in particular for the computer simulation.

• International Journal of Computer Science & Network Security
• /
• v.22 no.1
• /
• pp.113-120
• /
• 2022

Information technologies in higher education are the basis for solving the tasks set by monitoring the quality of higher education. The directions of aplying information technologies which are used the most nowadays have been listed. The issues that should be addressed by monitoring the quality of higher education with the use of information technology have been listed. The functional basis for building a monitoring system is the cyclical stages: Observation; Orientation; Decision; Action. The monitoring system's considered cyclicity ensures that the concept of independent functioning of the monitoring system's subsystems is implemented.. It also ensures real-time task execution and information availability for all levels of the system's hierarchy of vertical and horizontal links, with the ability to restrict access. The educational branch uses information and computer technologies to monitor research results, which are realized in: scientific, reference, and educational output; electronic resources; state standards of education; analytical materials; materials for state reports; expert inferences on current issues of education and science; normative legal documents; state and sectoral programs; conference recommendations; informational, bibliographic, abstract, review publications; digests. The quality of Ukrainian scientists' scientific work is measured using a variety of bibliographic markers. The most common is the citation index. In order to carry out high-quality systematization of information and computer monitoring technologies, the classification has been carried out on the basis of certain features: (processual support for implementation by publishing, distributing and using the results of research work). The advantages and disadvantages of using web-based resources and services as information technology tools have been discussed. A set of indicators disclosed in the article evaluates the effectiveness of any means or method of observation and control over the object of monitoring. The use of information technology for monitoring and evaluating higher education is feasible and widespread in Ukrainian education, and it encourages the adoption of e-learning. The functional elements that stand out in the information-analytical monitoring system have been disclosed.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.33-42
• /
• 2022

In this paper, we proposed a deep learning model based on multi-scale dilated convolution feature fusion for the segmentation of black ice region in road image to send black ice warning to drivers in real time. In the proposed multi-scale dilated convolution feature fusion network, different dilated ratio convolutions are connected in parallel in the encoder blocks, and different dilated ratios are used in different resolution feature maps, and multi-layer feature information are fused together. The multi-scale dilated convolution feature fusion improves the performance by diversifying and expending the receptive field of the network and by preserving detailed space information and enhancing the effectiveness of diated convolutions. The performance of the proposed network model was gradually improved with the increase of the number of dilated convolution branch. The mIoU value of the proposed method is 96.46%, which was higher than the existing networks such as U-Net, FCN, PSPNet, ENet, LinkNet. The parameter was 1,858K, which was 6 times smaller than the existing LinkNet model. From the experimental results of Jetson Nano, the FPS of the proposed method was 3.63, which can realize segmentation of black ice field in real time.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.6
• /
• pp.1100-1109
• /
• 2022

Herein, a case study was conducted on the bilge pumping performance of a 24,000TEU class container ship with an overall length of 400m. Although the bilge system of the 24,000TEU class container ship was designed in accordance with the rule requirements of the Classification Society, the bilge system did not satisfy the 2 m/s requirements of SOLAS Reg.II-1/35-1 under the rated flow rate and maximum flow rate conditions of the bilge pump installed in the ship. In particular, assumptions were made that No.1 ~ No.4 cargo holds were flooded and filled entirely by sea water and the evaluation of bilge pumping performance had been performed for No.1 ~ No.4 cargo holds. According to the evaulation results of the, the mean water velocity at the main bilge pipe for No.2, No.3, and No.4 cargo holds did not meet the 2 m/s criterion. To resolve this problem, in this study, the branch bilge pipe in each cargo hold was changed from 150A to 200A and the mean water velocity at the main bilge pipe for No.2, No.3, and No.4 was calculated as 2.479m/s, 2.476m/s, and 2.459m/s, respectively.

• Journal of the Korean Society of Floral Art and Design
• /
• no.45
• /
• pp.13-29
• /
• 2021

Under the recognition that the technological system of traditional flower design in Korea has been passed down from the past to the present, we extracted the type of design form from the flower decoration of the Joseon Dynasty, analyzed the expression technique, and examined the relationship with the modern traditional flower decoration in this study. As a result, most of the flower design works of the Joseon Dynasty mainly expressed one focal point at the central starting point. One central branch line was mainly used, and cut leaves were mainly used as the base material. Similar to the Joseon Dynasty, one central starting point and a base made of leaves are mainly used In modern flower design. In the frequency of use by expression technique, the stem exposure technique was used the most, and cut flowers and cut stems were used at a similar frequency in all techniques. As plant materials, cut flowers and cut stems were mainly used. In addition, non-plant materials such as feathers, fans, and brushes were also used for decoration. In conclusion, it can be seen that traditional flower decorations in Korea were systematically established in the Joseon Dynasty in terms of expression techniques and high-level flower design works were made. In the future, it will be necessary to study the history of our flower designs in more diverse ways and to develop modern flower designs while preserving historical traditions.

• Journal of Conservation Science
• /
• v.38 no.3
• /
• pp.234-242
• /
• 2022

The study aimed to investigate the split casting method based on the recreation of the iron-seated Buddha (ISB) statue (number 1971) in the Chuncheon Museum. The statue was designed using three-dimensional scan data and reduced to half-size. Using the existing research results, the ISB statue was created by mold production and split casting. The mold was prepared by mixing sand and clay at a ratio of 3:4 and 1:3 on the outside and inside, respectively, and then casting was done. Various casting defects were observed in the ISB casting and similar shapes were seen. The casting defects included veining or finning, misrun, open or external shrinkage, surface or subsurface blowholes, surface pinholes, and shift. The microstructures were identified as branch-shaped dendrite and pearlite organizations, and black graphite was observed between the cementite organizations. The study findings may be relevant in exploring traditional casting and manufacturing techniques of ISB and may aid in the production of the original form of ISB.

• The Korean Journal of Franchise Management
• /
• v.9 no.4
• /
• pp.7-19
• /
• 2018

Purpose - Recently, global management in Korea franchise industry is becoming an important keyword. As an important branch market, Chinese market plays a major role not only by making experience of the competitiveness among global brands which offers a foothold to become a top global brand, but also by actualizing an economies of scale in production, sales, etc. Therefore, it is necessary to identify key successful factor influencing customer evaluation and responses of Korean franchise restaurant targeting Chinese consumers in China context. The purpose of this study is to examine the effects for Korean franchise restaurant selection attributes on perceived value, customer satisfaction and customer loyalty in Chinese context with SmartPLS 3 and Artifical Neural Network(ANN). Research design, data, and methodology - For these purposes, the authors developed several hypotheses. A questionnaire survey was conducted on the panel of online survey companies for Chinese consumers who have visited Korean franchise restaurants. A total of 404 data were analyzed using structural equation modeling(SEM) and artifical neural network(ANN) with SPSS 22.0 and SmartPLS 3.0. Result - The findings of this study are as follows: First, the alternative model findings show that facilities & atmosphere, employee service, and menu influenced on utilitarian value, customer satisfaction, and customer loyalty directly. Second, employee service influenced on customer satisfaction. Third, menu influenced on hedonic value. Fourth, brand reputation influenced on utilitarian value. Fifth, hedonic value increase customer satisfaction and customer loyalty. Sixth, hedonic value increase customer loyalty. Seventh, customer increase customer loyalty. And, the ANN analysis shows that utilitarian value is the first most important factor influencing customer satisfaction, followed by hedonic value, facilities & atmosphere, menu and employee service. However, the ANN analysis shows that customer satisfaction is the first most important factor influencing customer loyalty, followed by utilitarian value, hedonic value, brand reputation, menu, and employee service. Conclusions - This study provides practical implications for enhancing customer satisfaction and customer loyalty by applying the ANN technique that complements the limitations of the linear structural relationship analysis using the proposed model and the alternative model. In other words, the SEM-ANN model provides guidelines on how Korean franchise restaurants should formulate facilities & atmosphere, employee service, and menu mix strategies in China. In addition, ANN 's analysis shows that restaurant brand reputation plays a pivotal role in increasing customer loyalty. The fact suggests that Korean franchise companies should establish their domestic brand reputation prior to their entry into overseas markets such as China.

• 한국노년학
• /
• v.29 no.1
• /
• pp.177-194
• /
• 2009

Korea government has launched long-term care insurance from 2008. However, one of the most important issues, whether or not providing cash benefit, is still unresolved. In this paper, in order to provide policy guidelines for the long-term care insurance, I attempt to estimate the Willingness-To-Accept (WTA) of the cash subsidy for informal care by using Double Bounded Dichotomous Choice method, a branch of Contingent Valuation Method (CVM). In doing so, I also estimated the determinants of the preference for cash benefit. Data were obtained from face-to-face survey interviews with 300 informal care-givers at three major general hospitals in Seoul, Korea. The questionnaire was constructed with two scenarios (mild/severe symptom). The results from logistic regression analyses and the estimation of WTA indicate that informal care-givers are willing to accept the cash benefit as low as 628 thousands won for mild fragile elderly and 1,072 thousands won for severe fragile elderly. The strength of this paper is that I estimated the WTA of the cash benefit by reflecting the changes in preferences of informal care-givers. The analytic results from the this paper suggest that the cash benefit in long-term care insurance is indispensible in achieving the goal of the long-term care system.