• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.617-624
• /
• 2001

With the proliferation of E-Commerce, product informations and services are provided to customers diversely. Thus customers want a software agent that can retrieve and recommend goods satisfying various purchase conditions as well as price. In this paper, we present a MAS (multi-agent system) for book information retrieval and recommendation in E-Commerce. User's preference is reflected in the MAS using the profile which is taken by user. The proposed MAS is composed of individual agents that support information retrieval, information recommendation, user interface, and web robots and a coordination agent which performs information sharing and job management between individual agents. Our goal is to design and implement this multi-agent system on a Windows NT server. Owing to the workflow management of the coordination agent, we can remove redundant information retrievals of web robots. From the results, we could provide customers various purchase conditions for several online bookstores in real-time.

• The Journal of Society for e-Business Studies
• /
• v.19 no.4
• /
• pp.21-30
• /
• 2014

Personalized data of users at social network service can be used as a new resource for providing personalized nutrition information. Although providing personalized information for nutrition using social data, there are a few studies on providing personalized nutrition information with customized user preference based on social network service. The purpose of this study is to implement the clustering of data analysis with collected personal data of Facebook users. To find out the method for providing personalized information, this study described an effective method for providing nutrition information by analyzing web posting on Facebook that can be called a typical social network service. According to the result from clustering, sodium and sugars were important variables from diet of user. Furthermore, the importance of elements of user's diet has some differences according to vendor/manufactures.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.57-65
• /
• 2022

Gyeongsangnam-do has been operating Bravo-taxi, a Gyeongnam-type DRT using taxi vehicles, since 2017 to guarantee the right of mobility for residents who live in areas lacking public transportation. This research investigated and analyzed changes in users' awareness over two years from beginning of Bravo-taxi operation in Gyeongsangnam-do, which started operating Bravo-taxis in 2017, targeting sites lacking public transportation. Through this study, the positive effects of taxi-type DRT were confirmed, such as improving the mobility of residents in areas underprivileged by public transportation, reducing required time for trips, and increasing preference for Bravo-taxis compared to existing buses. On the other hand, problems with the current Bravo-taxi system were also identified. In some areas, it was found that there were not enough coupons for Bravo-taxis, or in the case of Bravo-taxis operating at fixed times, the user's desired time and operating time did not match, resulting in lower satisfaction. The results of this research are expected to be utilized as basic data for service continuity of taxi-type DRT in operation by other local governments.

• Journal of Korean Society of Transportation
• /
• v.30 no.2
• /
• pp.43-52
• /
• 2012

A lane departure warning system (LDWS) is an effective technology-based countermeasure for preventing traffic crashes as it provides warning information to drivers. Understanding the characteristics of perception and satisfaction levels on LDWS is fundamental for deriving better performance and functionality enhancements of the system. The purpose of this study is to evaluate the user satisfaction of LDWS. A survey to collect user perception and user preference data was conducted. Both cross-tabulation analysis and binary logistic regression technique were adopted to identify the factors affecting user satisfaction for LDWS. The results revealed that the accuracy and timeliness of warning information was significant for evaluating the effectiveness of LDWS. In particular, the warning accuracy at a curve segment on the road was the most dominant factor affecting user satisfaction. The outcome of this study would be valuable in evaluating and designing LDWS functionalities.

• Journal of Korean Institute of Industrial Engineers
• /
• v.34 no.1
• /
• pp.66-78
• /
• 2008

In the past, Manufacturers used to determine the quality of products, but the trend of today's market becomesmore into customer-driven. As a result, demands from customers are becoming more diverse and complicated,and most companies are obligated to meet their needs. As one of the effort to achieve their satisfaction,companies are now emphasizing activities to find out what customers specifically want and extract voice ofcustomer(VOC). This study attempts to develop an ergonomic product development process as a method tomaximally reflect the VOC. In order to meet this goal, ergonomic design guidelines, which are possible to beclassified according that user's human characteristics, will be recommended. Even now, there are numerousdesign guidelines already existing in the ergonomics literature. However, it is not realistically feasible to reviewall of those guidelines, and some of them are even conflicting with each other. Therefore, in this paper, theproduct development process, which prioritizes the human characteristics that reflect customer needs and appliesthe design guidelines that meet the most important ones, will be suggested. Finally, the research was described toshow the validity of the product development process through an example of a mobile phone development case.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.46 no.6
• /
• pp.1074-1087
• /
• 2022

This study reports an optimization of a 3D printed wrist brace (WB) for various tilting angles (0°, 45°, 90°) of the re-entrant (RE) pattern and thickness (2 mm, 4 mm) using thermoplastic polyurethane (TPU) filaments and thermoplastic elastomer (TPE) filaments. The actual printing time, weight, Poisson's ratio, and tensile property of the manufactured samples were analyzed. The results confirmed that the actual printing time and weight increased with increasing thickness, regardless of the filament type. All tilting angles of the WB showed a negative Poisson's ratio (NPR), the largest of which appeared at 90°. The results of the tensile property analysis showed that a 90° tilting angle also had the largest value of elongation and stress. From these results, we conclude that the most suitable wrist brace is one in which the actual printing time is low, the weight is minimized to a thickness of 2 mm, and the tilting angle of the RE pattern is 90° for good shock absorption. The choice of filaments may be decided upon according to the user's preference, since the TPU is stiff and the TPE is elastic.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.1-18
• /
• 2015

Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

• Journal of Digital Contents Society
• /
• v.19 no.5
• /
• pp.871-880
• /
• 2018

Recently, the technology of recommendation of POI (Point of Interest) related technology is getting attention with the increase of big data related to consumers. Previous studies on POI recommendation systems have been limited to specific data sets. The problem is that if the study is carried out with this particular dataset, it may be suitable for the particular dataset. Therefore, this study analyzes the similarity and correlation between stores using the user visit data obtained from the integrated sensor installed in Seoul and Songjeong roads. Based on the results of the analysis, we study the preference prediction system which recommends the stores that new users are interested in. As a result of the experiment, various similarity and correlation analysis were carried out to obtain a list of relevant stores and a list of stores with low relevance. In addition, we performed a comparative experiment on the preference prediction accuracy under various conditions. As a result, it was confirmed that the jacquard similarity based item collaboration filtering method has higher accuracy than other methods.

• Korean Institute of Interior Design Journal
• /
• v.14 no.4 s.51
• /
• pp.87-94
• /
• 2005

Lately due to the sudden growth of the construction of an apartment complex in domestic market, many construction companies are eager to provide various public facilities to increase the apartment distribution rate. An introduction of a fitness center is popularized as a part of such development. There has been a continuing development in a private fitness based on analyzing the user's data. However a public fitness is quite different from the private in terms of a user's classification, preference rate, the pattern of use, and location which requires a different facility plan. Nevertheless, all these days a public fitness in an apartment house has been developed without a specific facility plan based on relevant materials. It is worried that such development would cause the facilities not to function as appropriate resident facilities and sink to idle ones. Therefore the purpose of this paper is to make the standard considered in facility planning in future and the base to guide an applying method. In the paper the present condition of fitness centers inside apartment houses has been compared to analyze the progress of the existing facilities and the appropriateness of the organization and the structure division. The result of the research shows that public resident facilities is not the place to perform passive role for fixed activities but one to form a community through the human relationship based on the facility. Therefore a fitness center inside the apartment complex have to be designed to provide service and leisure space as one of main community facilities for residents. To obtain this purpose, when choosing facilities of an apartment complex, first of all the residents' standard of living, apartment size, residents' distinction rate of age and sex, the needs of the times should be fully considered Secondly, the size of each facility space have to be decided based on the practical data analysis in facility use such as space preference, average staying time. Also, future living culture requires the change of the function and space according to the change of social values, so continuing research and data analysis are required to related to fitness center inside an apartment complex in order to present systematic approaching method and the paper will be expected to be a little step toward it.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.1-10
• /
• 2013

Personalization aims to provide customized contents to each user by using the user's personal preferences. In this sense, the core parts of personalization are regarded as recommendation technologies, which can recommend the proper contents or products to each user according to his/her preference. Prior studies have proposed novel recommendation technologies because they recognized the importance of recommender systems. Among several recommendation technologies, collaborative filtering (CF) has been actively studied and applied in real-world applications. The CF, however, often suffers sparsity or scalability problems. Prior research also recognized the importance of these two problems and therefore proposed many solutions. Many prior studies, however, suffered from problems, such as requiring additional time and cost for solving the limitations by utilizing additional information from other sources besides the existing user-item matrix. This study proposes a novel implicit rating approach for collaborative filtering in order to mitigate the sparsity problem as well as to enhance the performance of recommender systems. In this study, we propose the methods of reducing the sparsity problem through supplementing the user-item matrix based on the implicit rating approach, which measures the trust level among users via the existing user-item matrix. This study provides the preliminary experimental results for testing the usefulness of the proposed model.