• Journal of the Korea Society of Computer and Information
• /
• v.12 no.6
• /
• pp.287-295
• /
• 2007

This paper proposes a novel data editing techniques with genetic algorithm (GA) in case-based reasoning (CBR) for the prediction of Korea Stock Price Index (KOSPI). CBR has been widely used in various areas because of its convenience and strength in compelax problem solving. Nonetheless, compared to other machine teaming techniques, CBR has been criticized because of its low prediction accuracy. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However. designing a good matching and retrieval mechanism for CBR system is still a controversial research issue. In this paper, the GA optimizes simultaneously feature weights and a selection task for relevant instances for achieving good matching and retrieval in a CBR system. This study applies the proposed model to stock market analysis. Experimental results show that the GA approach is a promising method for data editing in CBR.

• Convergence Security Journal
• /
• v.12 no.4
• /
• pp.85-90
• /
• 2012

DES is a 64-bit binary, and each block is divided into units of time are encrypted through an encryption algorithm. The same key as the symmetric algorithm for encryption and decryption algorithms are used. Conversely, when decryption keys, and some differences may apply. The key length of 64 bits are represented by two ten thousand an d two 56-bit is actually being used as the key remaining 8 bits are used as parity check bits. The 64-bit block and 56-bit encryption key that is based on a total of 16 times 16 modifier and spread through the chaos is completed. DES algorithm was chosen on the strength of the password is questionable because the most widely available commercially, but has been used. In addition to the basic DES algorithm adopted in the future in the field by a considerable period are expected to continue to take advantage of the DES algorithm effectively measures are expected to be in the field note.

• Journal of Navigation and Port Research
• /
• v.28 no.3
• /
• pp.193-198
• /
• 2004

In this paper, we estimate the difference of port preference and attributed importance by diving subjects of the survey into internal and external shipping companies considered as the main customers of port. From the results of conjoint analysis, it is found that there are differences in preference between domestic shipping companies and foreign ones. The difference in port preference shows; foreign shipping companies mark Shanghai port in the first place in the preference of transshipment port, while domestic shipping companies prefer Busan port. Similar results are applied to preference of rolling port. The result of the survey means it is necessary to group shipping company, when port is analyzed, because the port preference is subject to wether internal or external shipping companies. Also, it implies target marketing strategies should continuously be needed in order to maintain Busan port's preference gaining advantage over other ports and major target would be shipping companies.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.135-146
• /
• 2010

In this paper, we propose an Recommendation System for supporting self-directed learning on e-learning marketplace. The key idea of this system is recommendation system using revised collaborative filtering to support marketplace. Exisiting collaborative filtering method consists of 3 stages as preparing low data, building familiar customer group by selecting nearest neighbor, creating recommendation list. This study designs recommendation system to support self-directed learning by using collaborative filtering added nearest neighbor learning course that considered industry and learning level. This service helps to select right learning course to learner in industry. Recommendation System can be built by many method and to recommend the service content including explicit properties using revised collaborative filtering method can solve limitations in existing content recommendation.

• Journal of Korea Game Society
• /
• v.15 no.3
• /
• pp.63-78
• /
• 2015

This study explored parental mediation strategies of children's online gaming and their relevant variables which could influence on them. A survey to 379 parents with elementary, middle, highschool, and college aged children revealed 7 distinctive parental mediation strategies of children's online gaming, that is, 'instructive', 'co-playing', 'rule-based', 'restrictive', 'technological', 'government regulation-dependent', and 'active guidance' mediation. Also, the results showed that there was significant relation between the parental mediation strategies, characteristics of parents, and characteristics of children. This study holds its significance in identifying the parental mediation types reflecting media characteristics of online games and Korean social and cultural context.

• The Journal of the Korea Contents Association
• /
• v.17 no.5
• /
• pp.174-181
• /
• 2017

Colors that stimulate human emotions in everyday life are one of the important factors in animation production. The research on color has been actively carried out in relation to the importance and nature mainly for animation production. However, researches that investigated different views for specific color by geographic characteristics are rare. Therefore, information was collected through questionnaire survey and empirical analysis was conducted using SPSS statistical package to analyze preference of Korean and Chinese people for the Chinese traditional colors. The analysis results showed that both Korean and Chinese groups preferred red color among Chinese traditional colors. This preference for red was statistically significant in both groups, indicating that the intensity of preference for red was different even though Korean and Chinese equally preferred red. Furthermore, among 10 red colors, the preferred red was different between Chinese and Korean. Based on these results, it is suggested that the color should be selected considering the characteristics of the intended market for Chinese animation production and the personality of the viewers who watch the animation products.

• Journal of the Korean Dietetic Association
• /
• v.25 no.4
• /
• pp.257-268
• /
• 2019

This study provides basic data on how stress impacts the processed convenience foods purchase attitudes and the selection attributes of housewives. The stress consists of 3 factors, which were housework stress, family relation stress and economic stress. The processed convenience food purchase attitude consisted of 2 factors, which were peripheral influence purchase and conviction purchase. The processed convenience food selection attribute consisted of 4 factors, which were quality, convenience, packaging and price. Factor loading confirmation and reliability test were conducted, and the reliability was confirmed with Cronbach's alpha coefficients for all the factors exceeding 0.5. The high stress levels showed significantly high stress factors of housework, family relations and economic stress (P<0.001). The high stress group was shown to make purchases by recognizing peripheral influences (P<0.01). When the selection properties of processed convenience foods depending on different stress levels were examined, it was revealed that among the three groups, the low stress group least considered the price aspect (P<0.01). After deducting the factors, AMOS (Analysis of Moment Structure) was used to conduct the confirmatory factor analysis for verifying validity. The structural equation model was used to determine the path coefficient. From the processed convenience foods purchase attitude, the peripheral influence purchase had significantly positive (+) effects on convenience (P<0.05). Also, conviction purchase was shown to have significantly positive (+) effects on quality (P<0.05). Housework and family relation stress were shown to have negative (-) effects on processed convenience foods selection attribute, and economic stress was shown to have positive (+) effects, although no significant relationships were revealed.

• Knowledge Management Research
• /
• v.22 no.3
• /
• pp.55-73
• /
• 2021

The sharing economy is considered as a collaborative consumption which enables customers to share unused resources. This study investigated the key factors affecting consumer loyalty in the context of sharing accommodation. Emotions, perceived value and self-image consistency were posited as key antecedents of enhancing customer loyalty. Authentic experience, home amenities, and price fairness were also considered as Airbnb's selection attributes. Airbnb was selected a survey target because it is the largest company in the domain of shared accommodation market. The research model was analyzed for 294 Airbnb customer through structural equation models. Additionally, this paper examine Airbnb customers' experiences by topic modelling method posted on the Naver blog. Based on the understanding of the key factors affecting customer loyalty to sharing accommodation, the analysis results contribute to establish effective marketing and operation strategies by enhancing customer experience.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.4
• /
• pp.785-794
• /
• 2019

Recently Deep Learning technology, one of the fourth industrial revolution technologies, is used to identify the hidden meaning of network data that is difficult to detect in the security arena and to predict attacks. Property and quality analysis of data sources are required before selecting the deep learning algorithm to be used for intrusion detection. This is because it affects the detection method depending on the contamination of the data used for learning. Therefore, the characteristics of the data should be identified and the characteristics selected. In this paper, the characteristics of malware were analyzed using network data set and the effect of each feature on performance was analyzed when the deep learning model was applied. The traffic classification experiment was conducted on the comparison of characteristics according to network characteristics and 96.52% accuracy was classified based on the selected characteristics.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.161-168
• /
• 2019

The purpose of this study analyze consumer usage characteristics and product development guide of electronic pen based on TAM theory(Davies, 1989). Research methods apply contents analysis(qualitative research) and Activity/Inactivity analysis of main consumer participation. Research results are as follows. Active consumer indicated 30-49 age, male, office job and research fellow. And they suggested stable power supply system, App connected pen function extension, add the modified pen function, advanced data recognition of pen, advanced take note ability and stable grip feeling of pen, selected line width, synchronization improvement with other smart device and charging function. These result indicated the importance product improvement diffusion factor of early market to main market. The future research of electric pen focused on different product strategy between electric pen and smart device connected electric pen.