• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.134-136
• /
• 2012

u-City 환경에서 사용자 맞춤형 국토정보를 제공하기 위해 대용량의 데이터를 효과적으로 분석할 수 있는 데이터마이닝 기법이 적용되고 있다. 따라서 이 논문에서는 데이터마이닝 기법 중 연관분류기법을 적용하여 사용자 맞춤형 관광명소 추천 시스템을 개발하였다. 특히, CPFP-tree를 이용하여 빈발항목집합 탐사에 대한 시간을 단축하였으며, 연관분류를 통해 보다 높은 정확도로 결과를 예측 및 분류할 수 있게 하였다. 제시한 시스템은 공간정보에 대해 사용자 맞춤 서비스를 제공할 수 있음을 보였으며, 다양한 시나리오 적용을 통해 맞춤형 국토정보화 기술의 기반이 될 수 있다.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.255-262
• /
• 2020

Recently, medical tourism is recognized as a high value-added industry because of its longer period of stay and higher expenditure than general tourism. In particular, although the number of medical tourists visiting Korea is increasing, the perception of Korean medical services is low. The purpose of this paper is to develop the app which, based on medical tourism type, recommends tourism destinations. Additionally, this proposed app can expand general tourism as well. It can provide tourists with medical information easily by sorting types tourists. Besides, as medical tourists normally stay long, we can take the advantage of post-treatment time. This app collects medical information data and tourist destination data, and categorizes the types of medical tourists into four categories: disease medical tourism, traditional medical tourism, cosmetic medical tourism, and recreational medical tourism. It provides medical information according to each type and recommends customized tourist destinations. User-based collaborative filtering is applied for tourist destination recommendations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.818-820
• /
• 2022

The keyword 'healing' is essential to the competitive society and culture of Koreans. In addition, as the time at home increases due to COVID-19, the demand for indoor healing services has increased. Therefore, this thesis analyzes the user's facial expression so that people can receive various 'customized' healing services indoors, and based on this, provides lighting, ASMR, video recommendation service, and facial expression recording service.The user's expression was analyzed by applying the ensemble algorithm to the expression prediction results of various CNN models after extracting only the face through object detection from the image taken by the user.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.705-708
• /
• 2023

본 논문은 사용자의 피부 상태에 따라 사용자에게 적합한 화장품을 소개해주는 화장품 추천 웹 쇼핑몰, "PBTI"를 개발한다. 요즘 유행하는 성격 유형 설문조사인 MBTI에서 영감을 받아 피부 유형과 퍼스널 컬러를 검사하고 이를 기반으로 화장품을 추천하는 온라인 쇼핑몰 웹사이트를 제작하게 되었다. 바우만 교수의 피부 유형 지표를 바탕으로 제작된 질문을 통해 사용자들의 피부 유형을 검사하고 해당 피부 유형 결과에 따른 상품을 추천해주는 알고리즘이 탑재되어 사용자에게 맞는 상품을 추천해준다. 텐서플로우 기반의 인공지능을 탑재하여 퍼스널컬러 테스트를 제작하였다. PBTI의 이러한 무료 테스트 서비스 제공은 다른 온라인 뷰티 쇼핑몰과 극명한 차별점을 만들고, 쇼핑몰 매출을 크게 증대시킬 것으로 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.669-671
• /
• 2023

정보 폭증으로 인한 정보 필터링 어려움을 해결하기 위한 추천 시스템의 중요성이 강조되고 있다. 특히 취업 구직자가 어떤 기업에 지원해야 하는지 혼란스러워하는 문제가 증가하고 있다. 이에 본 연구에서는 교육 기관에 등록된 학생 데이터를 활용하여 각 개인에게 적합한 기업을 추천해주는 맞춤형 기업 추천 시스템을 제안하고자 한다. 다양한 유사도 함수를 적용하여 비교한 결과, 코사인 유사도(Cosine similarity)를 활용한 추천 시스템이 가장 높은 정확도를 보였으며, 이러한 연구는 취업 관련 결정을 지원하는 데 중요한 역할을 할 것으로 기대된다.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.357-363
• /
• 2021

In general, people choose clothes to wear when they go out, referring to real-time weather and temperature. However, it is difficult for an individual to use real-time weather information and his or her temperature sensitivity information to choose the right clothes from among the clothes he or she owns. Existing clothing recommendation systems developed to help with these problems have problems recommending clothes that are not clearly set in the clothing category and are not in the possession of the user. In addition, user-specific temperature sensitivity is not taken into account, resulting in inappropriate clothing recommendations for users. To solve these problems, this study developed a system that determines and registers clothing categories for the clothing owned by the user, and recommends customized clothing for each user by considering temperature sensitivity and real-time weather information. In the case of weather information, not only weather information such as temperature and wind direction, but also clothes based on temperature sensitivity were recommended based on the calculation of temperature sensitivities. A satisfaction survey of 65 university students was conducted to assess the system. As a result, 80% of the respondents were satisfied with the recommended clothing, indicating that the satisfaction of the system was good. Therefore, it is expected that this system will be highly utilized in real life as it will be recommended based on clothes owned by individuals, reflecting individual temperature sensitivity.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.27-46
• /
• 2023

Research on restaurant recommender systems has been proposed due to the development of the food service industry and the increasing demand for restaurants. Existing restaurant recommendation studies extracted consumer preference information through quantitative information or online review sensitivity analysis, but there is a limitation that it cannot reflect consumer semantic preference information. In addition, there is a lack of recommendation research that reflects the detailed attributes of restaurants. To solve this problem, this study proposed a model that can learn the interaction between consumer preferences and restaurant attributes by applying deep learning techniques. First, the convolutional neural network was applied to online reviews to extract semantic preference information from consumers, and embedded techniques were applied to restaurant information to extract detailed attributes of restaurants. Finally, the interaction between consumer preference and restaurant attributes was learned through the element-wise products to predict the consumer preference rating. Experiments using an online review of Yelp.com to evaluate the performance of the proposed model in this study confirmed that the proposed model in this study showed excellent recommendation performance. By proposing a customized restaurant recommendation system using big data from the restaurant industry, this study expects to provide various academic and practical implications.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Journal of Internet Computing and Services
• /
• v.17 no.1
• /
• pp.15-21
• /
• 2016

Under the flag of creative economy, Korea government is now releasing public data in order to develop or provide a range of services. In this paper, we develop a customized trip navigation system to recommend a trip itinerary based on integration of open government data and personal tourist data. The system uses case-based reasoning (CBR) to provide a personalized trip navigation service. The main difference between existing trip information systems and ours is that our system can offers a user-oriented information service. In addition, our system supports Turn-key style contents provision to maximize convenience. Our system can be a good example of the way in which open government data can be used to design a new service.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.443-450
• /
• 2018

Due to the improvement of quality of life, health care is a main concern of modern people, and the demand for healthcare system is increasing naturally. However, it is difficult to provide customized wellness information suitable for a specific user because there are various medical information on the Internet and it is difficult to estimate the reliability of the information. In this study, we propose a user - centered service that can provide customized service suitable for users rather than simple search function by classifying big data as text mining and providing personalized medical information. We built a big data system and measured the data processing time while increasing the Hadoop slave node for efficient big data analysis. It is confirmed that it is efficient to build big data system than existing system.