• The Journal of the Korea Contents Association
• /
• v.13 no.7
• /
• pp.379-385
• /
• 2013

On the internet, the rating scores assigned by customers are considered as the preference information of themselves and thus, these can be used efficiently in the customer profile generation process of recommender system. However, since anyone is free to assign a score that has a biased rating, using this without any filtering can exhibit a reliability problem. In this study, we suggest the methodology that measures the reliability of rating scores and then applies them to the customer profile creation process. Unlikely to some related studies which measure the reliability on the user level, we measure the reliability on the individual rating score level. Experimental results show that prediction accuracy of recommender system can be enhanced when ratings with higher reliability are selectively used for the customer profile configuration.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.3
• /
• pp.91-95
• /
• 2010

Using artificial neural network to use a search preference based on the user's information, the ranking of search results that will enable flexible searches can be improved. After trained in several different queries by other users in the past, the actual search results in order to better reflect the use of artificial neural networks to neural network learning. In order to change the weights constantly moving backward in the network to change weights of backpropagation algorithm. In this study, however, the initial training, performance data, look for increasing the number of lessons that can be overfitted. In this paper, we have optimized a lot of objects that have a strong advantage to apply genetic algorithms to the relevant page of the search rankings flexible as an object to the URL list on a random selection method is proposed for the study.

• Korean Institute of Interior Design Journal
• /
• v.24 no.5
• /
• pp.99-107
• /
• 2015

The purpose of this study is to analyze the change of visual stimulus of users to the space through the experiment of EEG and the satisfaction of users depends on the lighting. To do that, the results measured with EEG experiment focusing on Beta ${\beta}$ were compared to each other to figure out difference in the changes of the activation of human brain on lighting's situation as the lighting off and on in the same space. The difference in the results was verified according to the characteristic of users which classified with 4 types of the spatial sensitivities. The results of this study are as following. Firstly, the spacial sensitivity of user is to communicate well with the different senses with stimulus through interaction among the elements. At this time, the brain plays a major role in build the spacial sensitivity of users as the place to make form. Secondly, there are the differences in the activation of brain depends on lighting situation even in the same space. The stimulus into the brain became generally stronger in images with lighting on than off. Especially, the response in the occipital lobe which connected with the visual center turn out strongly in the image of 'modern natural'. Because the visual stimulus interact well with the bright color, the reflectional texture and the rough texture painted the dark color. Thirdly, the satisfaction of users changed with lighting in the space. But we could know that the satisfaction of users isn't be related to the visual stimulus through the results of this study. Finally, there isn't the difference in the activation degree of brain according to the characteristic which are preference of users into 4 types of the spatial sensitivity through the results came from ANCOVA(analysis of covariance) with SPSS Program 22.

• The KIPS Transactions:PartD
• /
• v.17D no.1
• /
• pp.17-24
• /
• 2010

Recently, there has been growing interest in skyline queries. Most of works for skyline queries assume that the data do not have null value. However, when we input data through the Web or with other different tools, there exist incomplete data with null values. As a result, several skyline processing techniques for incomplete data have been proposed. However, available skyline query techniques for incomplete data do not consider the environments that coexist complete data and incomplete data since these techniques deal with the incomplete data only. In this paper, we propose a novel skyline group processing technique which evaluates skyline queries for the environments that coexist complete data and incomplete data. To do this, we introduce the top-k(g) skyline group query which searches g skyline groups with respect to the user's dimensional preference. In our experimental study, we show efficiency of our proposed technique.

• Korean Institute of Interior Design Journal
• /
• v.21 no.5
• /
• pp.85-97
• /
• 2012

This study is aimed to identify the color characteristics of the current Korean Brand Apartment, focused on the color of kitchens and dining rooms in the cyber model houses. The Brands which were selected for this study ranked from first to fifth in the contractor ranking and now account for 64 percent of the apartments in sale in Seoul and Gyeonggi Province. In addition, the size between $99m^2$ and $165m^2$ were selected, because it was most preferred at the 2011 survey for user preference on the size of apartment. As this study is for the colors shown on the monintor, colors were extracted from the images of web site with L*, a*, b*. And then, they were converted to Munsell values through computer program, which values were used to identify the color characteristics of hue, tone and to apply the theory of Moon Spencer. The result of the study on the color characteristics of the kitchen and dining room of the five brands' apartments is as follows. Regarding the color use, most of the brands used Y and YR color while as the accent color, P, PB and G were used. This result of main color use for hue was same as the guideline by the literature review, but color for tone showed the difference between brands and the difference between sizes. Next, regarding the color combination, first ambiguity of color harmony was shown the most. And the larger the size was, the more the contrast of color harmony was shown. It means that the color tone had close relation with the sizes of households.

• Journal of Digital Convergence
• /
• v.17 no.6
• /
• pp.349-354
• /
• 2019

The purpose of this study is to measure and analyze color image scale when viewing the public objects installed in Kongju National University and the installation environment, and preferred colors and color image scale in the color planning. The research was conducted with the analysis of the sculpture installed in the school and the questionnaire for the students. As a result of the study, suggestions were made for points to be considered for user's perception of environmental sculptures in the school and when constructing the sculpture. This study approaches the color of the public environment sculpture installed in the school academically, and proposes factors to be considered in the color planning stage in the future. Therefore, it is expected that this study will provide appropriate guidelines for the installation and planning of the sculpture in the school.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.518-519
• /
• 2014

The smartphone of pen input device makes a stage appearance by the development of the latest technology. Such smartphone chooses both touch method using hand and pen input device simultaneously. This research try to conduct usability evaluation in order to find the user's preference between pen input and touch input method. We recruit five novices and five expert for it. We presented all participants the task of touch input and pen input in series. This research conducts the unstructured interview after doing tasks as a pilot study. As a result, we found that it was influenced according to the feature of the task. However, most of the participants prefer to do touch method overall. Specially the result of this research reveals that the novice group prefers the pen input method. We expect to suggest the design guideline for product development to extend pen input method in smartphone.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.29-56
• /
• 2021

Recently, various types of products have been launched with the rapid growth of the e-commerce market. As a result, many users face information overload problems, which is time-consuming in the purchasing decision-making process. Therefore, the importance of a personalized recommendation service that can provide customized products and services to users is emerging. For example, global companies such as Netflix, Amazon, and Google have introduced personalized recommendation services to support users' purchasing decisions. Accordingly, the user's information search cost can reduce which can positively affect the company's sales increase. The existing personalized recommendation service research applied Collaborative Filtering (CF) technique predicts user preference mainly use quantified information. However, the recommendation performance may have decreased if only use quantitative information. To improve the problems of such existing studies, many studies using reviews to enhance recommendation performance. However, reviews contain factors that hinder purchasing decisions, such as advertising content, false comments, meaningless or irrelevant content. When providing recommendation service uses a review that includes these factors can lead to decrease recommendation performance. Therefore, we proposed a novel recommendation methodology through CNN-based review usefulness score prediction to improve these problems. The results show that the proposed methodology has better prediction performance than the recommendation method considering all existing preference ratings. In addition, the results suggest that can enhance the performance of traditional CF when the information on review usefulness reflects in the personalized recommendation service.

• Journal of the Korean Society for Library and Information Science
• /
• v.50 no.3
• /
• pp.113-132
• /
• 2016

Positioning technique which has been widely used for making marketing strategy by analyzing customer's image also has been used for public and test-taker's image analysis about public facilities, entrepreneurs, universities. This study analyze image of library and Information science students who trying to find a job in library fields about diverse types of library and information centers by Positioning technique. As a result of Similarity cognition analysis by multidimensional Scaling and K-means clustering, it was found that students recognize that public, national, university, school library are similar, on the other hand, portal company and special library are different from those types. In the jobs, user service jobs and technical service jobs are recognized as separated clusters, and cultural program job is also recognized dissimilarly from those clusters. By the way, images about work satisfaction and stability of employment shows high in national library; high wage shows high in portal company; employee's growth potential shows high in special library; job importance shows high in reference service jobs; difficulty shows high in content's job. Anyway, in the workplace selection, almost students regard stability of employment as top priorities, accordingly they prefers public library at most. Such a preference concentration tendency is strongly appeared in local university students than in metropolitan area students as a result of Pearson's chi-square test.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.7
• /
• pp.1075-1081
• /
• 2013

Twitter, Facebook, and KakaoStory are the major SNS in Korea. Social knowledge production is being produced by those services from numerous collaboration and co-participation in those SNS. Wikipedia or Naver JishikIN service was regarded as the representative product of collective knowledge production during the wired internet era. However now at the wireless internet era centered with smart phones, various forms of collective knowledge production would be achieved by connecting to SNS in real-time. In this thesis, the survey data of collective knowledge production for users of three SNS have been compared and analyzed. The difference of the collective knowledge production mechanism among Twitter, Facebook and KakaoStory has been studied and compared through three variables: the motivation of collective knowledge production, the preference of collective knowledge production model, and collective knowledge production cultural perception. As a result of the analysis of the discriminant factors for three SNS user groups, it turns out that the diversity-toward usage motivation, personal contribution motivation, and collective knowledge production tendency perception are the most influential variables. This thesis is of significance in that it unites the value of social science such as social capital and collective knowledge production from the viewpoint of computer science and opens the new chapter of collective knowledge production with the real-time SNS of wireless internet from the wired internet.