• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.93-98
• /
• 2010

In this paper, we introduce a system that summarizes product evaluation through linguistic analysis to effectively utilize explosively increasing product reviews. Our system analyzes polarities of product reviews by product features, based on which customers evaluate each product like 'design' and 'material' for a skirt product category. The system shows to customers a graph as a review summary that represents percentages of positive and negative reviews. We build an opinion word dictionary for each product feature through context based automatic expansion with small seed words, and judge polarity of reviews by product features with the extracted dictionary. In experiment using product reviews from online shopping malls, our system shows average accuracy of 69.8% in extracting judgemental word dictionary and 81.8% in polarity resolution for each sentence.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.275-279
• /
• 2013

Recently, as multimedia information becomes popular, there are many studies to retrieve images based on images in the web. However, it is hard to find the matching images which users want to find because of various patterns in images. In this paper, we suggest an efficient images retrieval system based on images for finding products in internet shopping malls. We extract features for image retrieval by using SIFT (Scale Invariant Feature Transform) algorithm, repeat keypoint matching in various dimension by using PCA-SIFT, and find the image which users search for by combining them. To verify efficiency of the proposed method, we compare the performance of our approach with that of SIFT and PCA-SIFT by using images with various patterns. We verify that the proposed method shows the best distinction in the case that product labels are not included in images.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.6
• /
• pp.1129-1143
• /
• 2009

This paper proposes a recommendation system (Association Rule System for Targeting) which considers target which is not considered by previous Logistic Regression system, and proves that the efficiency of the recommendation system is better than that of the current and previous Apriori algorithm system. Also this study shows that the click and purchasing rate of the proposed Association Rule System for Targeting is much higher than those of current Apriori algorithm system after the purchasing campaign even though the open rate of the former is lower than that of the latter. In comparison with Logistic Regression methodology, this paper proves with experimental data that the purchasing effect of the proposed system for specific items is much higher in accuracy than that of current Apriori algorithm system even though the purchasing rate of current Apriori algorithm system is higher in whole shopping malls than that of the proposed Association Rule System for Targeting.

• Journal of the Korean Society of Costume
• /
• v.66 no.3
• /
• pp.75-92
• /
• 2016

The purpose of this study was to prove how sociocultural perspective of obesity, differences in consumers' perception of body and attitudes of accepting obesity affected individuals' clothing behaviors through cross-cultural studies. The data collected were composed of 612 Korean and US consumers in the 20's and 30's that had experiences in purchasing plus-size products. The results were as follows. First, BMI index was lower in Korean consumers than the US consumers, but Korean consumers received more stress from being overweight compared to the US consumers, and had a more negative attitude about their body. Second, although Korean consumers had lower BMI index and degrees of obesity than US consumers, they were severely stressed by obesity and were found to have a higher level of dissatisfaction with their bodies. Third, Korean consumers responded more sensitively to obesity and had a tendency to display a more negative attitude regarding obesity, and a more passive dependence on clothing. Forth, differences in the body shape were reflected even in wearing evaluation, and US consumers showed a more positive attitude toward evaluations of size suitability and fitness. Fifth, the plus-size market for Korean consumers was still not active, and most products purchased were generic brands obtained from online shopping malls through the Internet. However, in the case of the US, in which the ratio of obese people is high and the plus-size market is growing, consumers were purchasing plus-size brands through various distribution online and offline channels. Sixth, Korean consumers were less satisfied than US consumers with shops, sizes and fitness; however, they were more satisfied with design factors. Finally, it is expected that this study can offer practical implications for marketers and product developers running plus-size market for young obese consumers in their 20 and 30s.

• Archives of design research
• /
• v.16 no.3
• /
• pp.273-280
• /
• 2003

Priming Effect, as a part of "Contextual Effect" is the phenomenon that pre-searched product information influences consecutive product evaluation. "Priming Effect" is different from other types of "Contextual Effects" in that pre-searched information doesn't have an direct effect on product evaluation, but an indirect effect which means that pre-searched information influences interpretation of consecutive product evaluation. On the previous theoretical background, this study investigated that how visual images can influence consumer preference and product choice, introducing concept of priming effects into the design of on-line shopping malls. This experiment adopted the digital cameras as the experimental stimulus target products and designed the individual web pages by priming the attributes of price and size. In result of analysis, the difference of product preference by priming attributes was proved to be statistically significant. In this reason, suggesting the background of commercial web page can be the significant factor in choosing products, the priming effects introduced into the design can be positively employed in online advertising.mployed in online advertising.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.131-147
• /
• 2020

RFID (Radio Frequency Identification) identifies a specific object by radio signals. As the tag provides a unique ID for the purpose of identification, RFID technology effectively solves the ambiguity and occlusion problem that challenges the laser or camera-based approach. This paper proposes an approach to track a moving object based on the integration of RFID and laser ranging information using a particle filter. To be precise, we split laser scan points into different clusters which contain the potential moving objects and calculate the radial velocity of each cluster. The velocity information is compared with the radial velocity estimated from RFID phase difference. In order to achieve the positioning of the moving object, we select a number of K best matching clusters to update the weights of the particle filter. To further improve the positioning accuracy, we incorporate RFID signal strength information into the particle filter using a pre-trained sensor model. The proposed approach is tested on a SCITOS service robot under different types of tags and various human velocities. The results show that fusion of signal strength and laser ranging information has significantly increased the positioning accuracy when compared to radial velocity matching-based or signal strength-based approaches. The proposed approach provides a solution for human machine interaction and object tracking, which has potential applications in many fields for example supermarkets, libraries, shopping malls, and exhibitions.

• Journal of Fashion Business
• /
• v.18 no.6
• /
• pp.38-56
• /
• 2014

This study compared the flared skirts on 3D simulation and in real to show diverse forms in women's clothing depending on the body's gait and motion. By finding the problems, we suggested the possible methods for utilizing the 3D simulation in the clothing industry. First, the 3D simulation of flared skirts showed similar forms of appearance according to the flare length and volume. However, virtually formed drape shape was even in size and spacing, whereas it was not even in real. Second, according to the results of appearance test on the length and flare volume at $90^{\circ}$ and $180^{\circ}$, both real and 3D simulation skirts were evaluated to have outstanding appearances regardless of the skirt length. However, as the flares volume increased, the skirts with longer length were evaluated to have superior appearances compared to the skirts of shorter length. Third, it showed higher resemblance between the real and virtual simulation, when the skirt had less flare and as the skirt length shortened. However, it showed greater difference between the real and virtual simulation when flare volume and length increased. The length and volume of the skirt and the physical properties of the material are predicted to be different between the real and virtual simulation. However, they usually are similar in forms, so it is believed possible to use for predicting the design's silhouette or the feel when it is worn. This method can be applied on internet shopping malls, which can possibly reduce unnecessary time and expenses.

• Journal of Korea Multimedia Society
• /
• v.7 no.2
• /
• pp.145-155
• /
• 2004

It is very important for Internet searching systems to have user-friendly and rapid searching functions at the managers'point of view. The former finds optimized input parameters to support the various searching requirements of user. The latter has fast searching results which are effectively normalized to various input parameters having different attributes. In this paper we basically focus on optimized database construction not only to have searching functions with multiple attributes to support maximal various input requirements of the user but also to have more rapid searching functions. For this research, we suggest a modified association algorithm that takes into consideration to the support and confidence that is the criteria of the association mining rule in order to reflect the searching characteristics of internet shopping malls. We also propose the model management systems for rapid searching functions. The following results are from a processed simulation: the more the number of searching transactions of the users increase, the less the total relative average searching time becomes.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.1109-1113
• /
• 2009

Exchange of data between users and system is made by users' inputting their information into HTML input forms like when signing up in websites or buying in online shopping malls. If users make a mistake of inputting their information, the system gives an error message in order for users to correct their mistakes. Although ISO recommends immediate feedback, Bargas et al. gave a report that feedback in all after filling forms out is more usable than feedback one by one when inputting data online. We made a comparative experiment on usability under each case of feedback one by one and feedback in all. The result is immediate feedback is more usable and satisfactory. The analysis of data resulted that immediate feedback produced fewer error and gets higher subjective ratings.

• Journal of Environmental Science International
• /
• v.7 no.6
• /
• pp.745-751
• /
• 1998

The well-mixed room model has been traditionally used to predict the concentrations of contaminants in indoor environments. However, this is inappropriate because the flow fields in many indoor environments distribute contaminants non-uniformly, due to imperfect air mixing. Thus, some means used to describe an imperfectly mixed room are needed. The simplest model that accounts for imperfect air mixing is a two-zone model. Therefore, this study on development of computer program far the two-zone model is carried out to propose techniques of estimating the concentration of contaminants in the room. To do this, an important consideration is to divide a room into two-zone, i.e. the lower and upper zone assuming that the air and contaminants are well mixed within each zone. And between the zones the air recirculation is characterized through the air exchange parameter. By this basic assumption, the equations for the conservation of mass are derived for each zone. These equations are solved by using the computational technique. The language used to develope the program is a VISUAL BASIC. The value of air exchange coefficient($f_12$) is the most difficult to forecast when the concentrations of contaminants in an imperfectly mixed room are estimated by the two-zone model. But, as the value of $f_12$ increases, the air exchange between each zone increases. When the value of $f_12$ is approximately 15, the concentrations in both zone approach each other, and the entire room may be approximately treated as a single well-mixed room. Therefore, this study is available for designing of the ventilation to improve the air quality of indoor environments. Also, the two-zone model produces the theoretical base which may be extended to the theory for the multi-zone model, that will be contributed to estimate the air pollution in large enclosures, such as shopping malls, atria buildings, atria terminals, and covered sports stadia.