• Journal of the Korean Data and Information Science Society
• /
• 제22권1호
• /
• pp.19-27
• /
• 2011

온라인 사용자에게 선택의 어려움을 줄여주고 사용의도를 높이기 위해 만들어진 것이 추천시스템이다. 추천시스템은 정보검색과 정보필터링을 용이하게 하고, 정보 과잉의 문제를 해결하는 데에 많은 도움을 주고 있다. 본 연구의 목적은 웹 상점을 이용하는 사용자들의 클릭스트림 데이터를 분석하여 데이터 인접성의 차이를 확인하고, 이를 통해 상품추천을 제안하고자 하는 데에 있다. 본 연구에서 제안하는 추천시스템의 성과를 검증하기 위하여 실험을 통해 알아본 결과, 추천시스템 적용 전보다 적용 후에 사용자들의 구매 의도는 높아졌고 탐색시간은 줄어들었다.

• 지능정보연구
• /
• 제9권3호
• /
• pp.177-191
• /
• 2003

상품추천시스템은 고객들에게 추천 상품 리스트를 만들어 고객들이 구매 가능성이 있는 상품을 쉽게 찾도록 도와주는 개인화 된 정보필터링 기술이다 협업 필터링(collaborative filtering)이 가장 성공적인 상품추천 기법으로 알려져 있으며 많이 이용되고 있다. 그러나, 인터넷 쇼핑몰에서 관리하는 상품과 고객의 수가 급속히 증가하면서 협업필터링에 기반 한 상품추천 시스템은 입력데이터의 희박성(Sparsity) 문제와 시스템 확장성(Scalability) 문제가 노출되고 있다. 따라서 본 연구에서는 협업필터링 기반 상품추천시스템의 상품추천 효과 및 성능을 개선하기 위해 웹 마이닝과 군집분석 기법에 기반을 둔 개인별 상품추천 방법론을 개발한다. 또한 실제 인터넷 쇼핑몰에서 개인별로 상품을 추천할 때 개발된 상품추천 방법론을 적용하여 다른 기존 상품추천 방법론과 실험적으로 비교함으로써 개발 방법론의 효과 및 성능을 검증한다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.1075-1087
• /
• 2020

Aviation ICT technology is a convergence technology between aviation and electronics, and has a wide variety of applications, including navigation and education. Among them, in the field of aerial pilot training, there are many problems such as the possibility of accidents during training and the lack of coping skills for various situations. This raises the need for a simulated pilot training system similar to actual training. In this paper, pilot training data were collected in pilot training system using VR/AR to increase immersion in flight training, and Customized Pilot Training Platform with Collaborative Deep Learning in VR/AR Environment that can recommend effective training courses to pilots is proposed. To verify the accuracy of the recommendation, the performance of the proposed collaborative deep learning algorithm with the existing recommendation algorithm was evaluated, and the flight test score was measured based on the pilot's training data base, and the deviations of each result were compared. The proposed service platform can expect more reliable recommendation results than previous studies, and the user survey for verification showed high satisfaction.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권2호
• /
• pp.113-119
• /
• 2020

Numerous tourist-related data produced on the Internet contain not only simple tourist information but also diverse ideas and opinions from users. In order to derive meaningful information about tourist sites from such big data, the social network analysis of tourist keywords can identify the frequency of keywords and the relationship between keywords. Thus, it is possible to make recommendations more suitable for users by utilizing the clear recommendation criteria of tourist attractions and the relationship between tourist attractions. In this paper, a recommendation system was designed based on tourist site information through big data social network analysis. Based on user personality information, the types of tourism suitable for users are classified through deep learning and the network analysis among tourist keywords is conducted to identify the relationship between tourist attractions belonging to the type of tourism. Tour information for related tourist attractions shown on SNS and blogs will be recommended through tagging.

• 한국식생활문화학회지
• /
• 제32권5호
• /
• pp.421-436
• /
• 2017

This study was conducted to examine the effects of Chinese perceptions of quality attributes on customer's satisfaction, revisit intention and recommendation intention for coffee shops in Beijing, China. Subjects of this study included 200 customers who had visited a coffee shop at least once during the last year. Statistical analyses were performed using SPSS v23.0 and AMOS v21.0. In this study, the majority of customers visited a coffee shop once or twice a week with friends. Respondents preferred tall-sized warm coffee in the store. The coffee shop quality attributes of were derived from five exploratory factors identified upon analysis of 30 observational variables. It was important to maintain and strengthen the quality attributes of coffee shops in this area because IPA(Importance Performance Analysis) analysis showed that "Doing great, keep it well" part was a desirable area because it had high importance and performance. Finally, path analysis revealed that customer satisfaction was influenced by employee attitude and affected revisit intention and recommendation intention.

• 한국조리학회지
• /
• 제14권3호
• /
• pp.123-135
• /
• 2008

The purpose of this study is to investigate the priority order in the factors influencing college choice of students who are majoring in culinary art in Chungcheong-do. For the study, we set the decision-making factors of upper hierarchies and nineteen bottom hierarchies based on the literature review and employed the analytical hierarchical process(AHP). As a result, the first considering factor among 4 upper hierarchies for college choice was the educational environments of the department(0.378). The next came in the order named as follows: college and university grade(0.263), the educational environments of colleges or universities(0.244), recommendation(0.115). The first considering factor among the educational environments of the department was the aptitude for the major(0.323). The first considering factor in college and university grade was the entrance competitive rate(0.397). The first considering factors among the educational environments of the colleges or universities were scholarships and tuition fees(0.325). The first considering factor in recommendation was the recommendation of a high school teacher(0.295). This results of this study will contribute to the development of colleges and universities under the turbulent changes of educational environments.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1346-1357
• /
• 2021

The drone technology, which is receiving a lot of attention due to the 4th industrial revolution, requires an Unmanned Aerial Vehicles'(UAVs) flight path search algorithm for automatic operation and driver assistance. Various studies related to flight path prediction and recommendation algorithms are being actively conducted, and many studies using the A-Star algorithm are typically performed. In this paper, we propose an Optimal 3D Flight Path Recommendation System for unmanned aerial vehicles. The proposed system was implemented and simulated in Unity 3D, and by indicating the meaning of the route using three different colors, such as planned route, the recommended route, and the current route were compared each other. And obstacle response experiments were conducted to cope with bad weather. It is expected that the proposed system will provide an improved user experience compared to the existing system through accurate and real-time adaptive path prediction in a 3D mixed reality environment.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권3호
• /
• pp.155-162
• /
• 2021

With the global COVID-19 pandemic, the tourism sector and all consumption have contracted with the untact era. Wine will also be sold and developed in various ways non-face-to-face in the future. Therefore, it is necessary to develop apps and web servers that focus on health in the era of single-person households and non-face-to-face. This study used facial recognition data based on photos of adult men and women in their 40s and 50s to analyze the Sasang constitution through a mobile app and web server, and suggested wine recommendations suitable for their constitution. First, the user's body information is entered. And through the facial recognition mobile app, recommend the right wine after analyzing the body type. if it's not like the first recommended wine, it is configured to receive another wine recommendation. In the future, the number of single-person households will increase further, and in the age of well-being, wine recommendations that fit my body will be useful. Wine recommendation suitable for Sasang constitution will be a useful mobile application to manage personal healt

• International Journal of Computer Science & Network Security
• /
• 제22권8호
• /
• pp.175-186
• /
• 2022

This research article develops an Arabic books' recommendation system, which is based on the content similarity that assists users to search for the right book and predict the appropriate and suitable books pertaining to their literary style. In fact, the system directs its users toward books, which can meet their needs from a large dataset of Information. Further, this system makes its predictions based on a set of data that is gathered from different books and converts it to vectors by using the TF-IDF system. After that, the recommendation algorithms such as the cosine similarity, the sequence matcher similarity, and the semantic similarity aggregate data to produce an efficient and effective recommendation. This approach is advantageous in recommending previously unrated books to users with unique interests. It is found to be proven from the obtained results that the results of the cosine similarity of the full content of books, the results of the sequence matcher similarity of Arabic titles of the books, and the results of the semantic similarity of English titles of the books are the best obtained results, and extremely close to the average of the result related to the human assigned/annotated similarity. Flask web application is developed with a simple interface to show the recommended Arabic books by using cosine similarity, sequence matcher similarity, and semantic similarity algorithms with all experiments that are conducted.

• 지능정보연구
• /
• 제28권1호
• /
• pp.311-328
• /
• 2022

정보통신기술 발달로 스마트폰이 보급되면서, 온라인 쇼핑몰 서비스는 컴퓨터가 아닌 모바일로도 사용이 가능해졌다. 그로 인해 온라인 쇼핑몰 서비스를 이용하는 사용자는 급격히 증가하게 되고, 거래되는 제품의 종류 또한 방대해지고 있다. 따라서 기업은 이익을 최대화하기 위해서는 사용자가 관심을 가질만한 정보를 제공해주는 것이 중요하다. 이를 위해 사용자의 과거 행동 데이터나 행동 구매 기록을 기반으로 사용자에게 필요한 정보 또는 제품을 제시하는 것을 추천 시스템이라 한다. 현재 추천 서비스를 제공하는 대표적인 해외 기업으로는 Netflix, Amazon, YouTube 등이 있다. 최근 이러한 전자상거래 사이트에서는 사용자가 해당 제품에 대한 리뷰가 유용한지에 대해 투표할 수 있는 기능을 제공하고 있다. 이를 통해, 사용자는 유용하다고 판단되는 제품에 대한 리뷰와 평점을 참고하여 구매 의사결정을 내린다. 따라서 본 연구에서는 제품에 대한 평점과 리뷰의 유용성 정보 간의 상관관계를 파악하고, 리뷰의 유용성 정보를 추천 시스템에 반영하여 추천 성능을 확인하고자 한다. 또한 대부분의 사용자들은 만족한 제품에만 평점을 부여하는 경향이 있고 제품에 대한 평점이 높을수록 구매 의도가 높아지는 경향이 있다. 따라서 전통적인 협업 필터링 기법에 모든 평점을 반영한 결과와 4점과 5점 평점만을 반영한 추천 성능 결과를 비교하고자 한다. 이를 위해 본 연구에서는 Amazon에서 수집한 전자 제품 데이터를 사용하였으며, 실험 결과는 평점과 리뷰 유용성 정보 간 상관관계가 있는 것으로 확인되었다. 또한 모든 평점과 4점과 5점 평점만을 추천 시스템에 반영하여 추천 성능을 비교한 결과, 4점과 5점 평점만을 추천 시스템에 반영한 결과의 추천 성능이 더 높게 나타났다. 그리고 리뷰 유용성 정보를 추천 시스템에 반영한 결과는 리뷰가 유용할수록 추천 성능은 높게 나타나는 것으로 확인하였다. 따라서 이러한 실험 결과는 향후 개인화 추천 서비스의 성능 향상에 기여하고, 전자상거래 사이트에 시사점을 제공할 수 있을 것으로 본다.