• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.79-98
• /
• 2011

This paper proposes a semantic recommendation technique for a personalized e-commerce portal. Semantic recommendation is achieved by utilizing the attributes of products. The semantic similarity of the products is merged with the rating information of the products to provide an accurate recommendation. The recommendation technique also analyzes various attitudes of the customer to evaluate the implicit rating of products. Attitudes are classifies into three types such as "purchasing product", "adding product to shopping cart", and "viewing the product information." We implicitly track customer attitude to estimate the rating of products for recommending products. Also we implement a session validation process to identify the valid sessions that are highly important for giving an accurate recommendation. Our recommendation technique shows a high degree of accuracy as we use age groupings of customers with similar preferences. The experimental section shows that our proposed recommendation method outperforms well known collaborative filtering methods not only for the existing customer, but also for the new user with no previous purchase record.

• Journal of Korean Society of Transportation
• /
• v.25 no.3
• /
• pp.111-121
• /
• 2007

A transit assignment model can forecast the behaviors of transit users. thereby playing an important role In the evaluation of transit policies. Most existing transit assignment models are based on the models for passenger cars; therefore they cannot reflect the specific characteristics of transit modes. In addition most of the existing models are based on a single transit mode (bus or rail), and they cannot forecast the behaviors of transit users in a changing mass transportation system. The goal of this study is to overcome these problems with the exiting models and to develop a more realistic model. The newly developed model is based on mixed transit modes and is a stochastic model that can reflect the different preferences of each transit user for travel time and transfering. Data gathered from the Seoul metropolitan area's smart card are used to calibrate this model. This study is expected to be used for the evaluation of transportation policies and to attribute the development of transit revitalization strategies.

• Journal of the Korea Convergence Society
• /
• v.10 no.12
• /
• pp.243-250
• /
• 2019

With the popularization of online learning, mobile learning and blended learning model, augmented reality technology is increasingly widely applied in the field of education today. This article stresses the necessity of applying augmented reality to education by summarizing the current situation and advantages of augmented reality technology in education. Next, the author proposes a new education system-"AR+E education cloud platform system". Last, the author proposes several inspirations for the design of AR-based education software according to the observation and interview of the behaviors and preferences of the respondents.

• Proceedings of the Korean Association for Survey Research Conference
• /
• 2001.04a
• /
• pp.83-107
• /
• 2001

The contingent valuation method used survey questions to elicit people's preferences for public goods by finding out what they would be willing to pay for specified improvement in them. The method is thus aimed at eliciting their willingness to pay in money amounts. It circumvents the absence of markets for public goods by presenting consumers with hypothetical markets in which they have the opportunities to buy the good in question. The hypothetical markets may be modeled after either a private goods market or a political market. Respondents are presented with material, often in the course of a personal interview conducted face to face. An on-site survey was conducted to 1107 randomly selected P-mountain users using a dichotomous choice questionnaire for the contingent valuation method. Seventeen different bid sets were chosen ranging from the lowest bid of 300won to the highest bid of 2,100won to elicit a reasonable entrance fee in the suggested bid had been determined, and the expected value of willingness to pay was estimated using binary-logit model. The average public value of P-mountain per individual user was estimated to be 1,055.92won∼1,995.61won according to the binary-logit model. The economic value of this P-mountain which includes both use value and existence value can be determined by aggregating the average value giving total willingness to pay for the entire population, in this case 5.491 billion ∼ 10.377 billion.

• IE interfaces
• /
• v.18 no.3
• /
• pp.288-296
• /
• 2005

Many jobs and activities in our daily lives require squatting postures. The fore part includes housekeepers, farmers, and welders and the latter includes a wide variety of activities such as housekeeping; planting, cultivating and harvesting various agricultural products; grinding, welding, etc. It is speculated that prolonged squatting postures without any supporting stool would gradually cause musculoskeletal injuries to workers. This study is conducted to examine the proper height of stools according to the position of the working materials and to develop wearable stools for workers with squatting posture. Forty male and female subjects participated in the experiment to find the proper height of stools according to the position of the working materials. Subjects were asked to squat and work with 3 different working positions: floor level; ankle level; shank level of 3 different stool height conditions: 10cm height; 15cm height; and 20cm height. After 5 minutes of maintaining a squatting work posture while sitting on the different height stools, Likert summated rating method as well as pairwise ranking test was applied to evaluate the user preferences for provided stools under the conditions of different working positions. The results of statistical analysis show that the subjects preferred 10cm height stool for floor level, 15cm height stool for ankle level, 20cm height stool for knee level. We thus strongly recommend to use appropriate height stools in accordance with the different working positions. Moreover, a prototype wearable stool was designed such that workers with squatting posture do not need to move the stool while they are moving about. The purpose of developing wearable stool was to decrease the physical stress and hence promote worker's health who work with squatting posture.

• Journal of The Korean Association of Information Education
• /
• v.15 no.2
• /
• pp.219-226
• /
• 2011

Web personalization has focused on extracting web pages interesting to users, to help users searching wanted information efficiently on the web. One of the main methods to achieve this is by using queries, links and users' preferred words in the pages. In this study, we surveyed from the web users the features of pages that are considered important to themselves in selecting web pages. The survey results showed that the content of the pages is the most important. However, images and readability of the page are rated as high as the content for some users. Based on this result, we present a method for maintaining relative weights of major page features differently in the profile for each user, which is used for personalizing web search results. Performance of the proposed personalization method is analyzed to prove its superiority such that it yields as much as 1.5 times higher rate than the system utilizing both queries and preferred words and about 2.3 times higher rate than a generic search engine.

• Journal of Korea Multimedia Society
• /
• v.11 no.9
• /
• pp.1213-1226
• /
• 2008

A recommender system supports people in making recommendations finding a set of people who are likely to provide good recommendations for a given person, or deriving recommendations from implicit behavior such as browsing activity, buying patterns, and time on task. We proposed new recommender system which combined SOM(Self-Organizing Map) neural networks with the Collaborative filtering which most recommender systems hat applied First, we segmented user groups according to demographic characteristics and then we trained the SOM with people's preferences as ito inputs. Finally we applied the classic collaborative filtering to the clustering with similarity in which an recommendation seeker belonged to, and therefore we didn't have to apply the collaborative filtering to the whose data set. Experiments were run for EachMovies data set. The results indicated that the predictive accuracy was increased in terms of MAE(Mean-Absolute-Error).

• The KIPS Transactions:PartC
• /
• v.12C no.6 s.102
• /
• pp.799-808
• /
• 2005

This paper proposes low latency handover procedure for seamless connectivity and QoS support between wired (e.g. Ethernet) and wireless (e.g. WLAN, WiBro(802.16-compatible), CDMA) networks by the mobile-assisted and server-initiated handover strategy. It is assumed that the server decides the best target network considering network status and user preferences. In this algorithm a mobile terminal associates with the wireless link decided at the server In advance and receives CoA as well. When handover occurs without the prediction in wired networks, the server performs fast binding update using physical handover trigger through the MIH(media independent handover) function. As a result, a mobile terminal does not need to perform L2 and L3 handover during handover so that this procedure decreases handover latency and loss.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.11
• /
• pp.5627-5635
• /
• 2013

The purpose of this study was to determine factors of women's satisfaction of hospital environment following childbirth. Data were collected using a structured questionnaire from 783 women visited at 101 hospitals for delivery and frequencies, t-test, ANOVA, Pearson's correlation, and multiple regression analyses were performed. Women's satisfaction was significantly related with personal and environmental factors. Specifically, a kind of patient room, using a shared room regardless of their preference, using family delivery room, planned hospitalization, gestational week at delivery, and hospital locations significantly predicted the variance of women's satisfaction. Therefore, hospital user satisfaction should be carefully understood as a consequence of interaction of person and environment and the level of satisfaction can be represented by the degree of congruency between personal and environmental characteristics. Furthermore, healthcare providers should develop strategies to reduce gaps between personal preferences/will/control and environmental situations, contributing to women's satisfaction with hospital following childbirth.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1144-1153
• /
• 2016

Group recommendation analyzes the characteristics and tendency of a group rather than an individual and provides relevant information for the members of the group. Existing group recommendation methods merely consider the average and frequency of a preference. However, if the users' preferences have large deviations, it is difficult to provide satisfactory results for all users in the group, although the average and frequency values are high. To solve these problems, we propose a method that considers not only the average of a preference but also the deviation. The proposed method provides recommendations with high average values and low deviations for the preference, so it reflects the tendency of all group members better than existing group recommendation methods. Through a comparative experiment, we prove that the proposed method has better performance than existing methods, and verify that it has high performance in groups with a large number of members as well as in small groups.