• 한국인터넷방송통신학회논문지
• /
• 제23권4호
• /
• pp.9-15
• /
• 2023

기존의 단순 통계 기반 추천 시스템은 학생들의 수강 이력 데이터만을 활용하기 때문에 선호하는 수업을 찾는 것에 많은 어려움을 겪고 있다. 이를 해결하기 위해, 본 연구에서는 심층 강화학습 기반의 개인화된 전공과목 추천 시스템을 제안한다. 이 시스템은 학생의 학과, 학년, 수강 이력 등의 정형 데이터를 기반으로 학생들 간의 유사도를 측정하며, 이를 통해 각 전공과목에 대한 정보와 학생들의 강의 평가를 종합적으로 고려하여 가장 적합한 전공과목을 추천한다. 본 논문에서는 이 DRL 기반의 추천 시스템을 통해 대학생들이 전공과목을 선택하는 데에 유용한 정보를 제공하며, 이를 통계 기반 추천 시스템과 비교하였을 때 더 우수한 성능을 보여주는 것을 확인하였다. 시뮬레이션 결과, 심층 강화학습 기반의 추천 시스템은 통계 기반 추천 시스템에 비해 수강 과목 예측률에서 약 20%의 성능 향상을 보였다. 이러한 결과를 바탕으로, 학생들의 강의 평가를 반영하여 개인화된 과목 추천을 제공하는 새로운 시스템을 제안한다. 이 시스템은 학생들이 자신의 선호와 목표에 맞는 전공과목을 찾는 데에 큰 도움이 될 것으로 기대한다.

• 한국지능시스템학회논문지
• /
• 제19권2호
• /
• pp.242-247
• /
• 2009

지능형 추천 시스템은 사용자의 요청에 응답하는 수동적인 시스템이 아닌 사용자가 원하는 서비스를 제안하는 시스템으로서 최근 콘텐츠 서비스 분야에 많이 개발되고 있다. 이러한 지능형 추천 시스템은 콘텐츠 개인화 서비스에 응용되고 있으며 대표적인 추천기법으로 내용기반과 협업적 필터링 기법이 있다. 본 연구에서는 협업적 필터링 및 퍼지 시스템을 이용하여 추천 시스템의 기반 기술인 예측 시스템을 제안하였다. 제안한 예측 시스템은 사용자의 과거 영화평가 정보를 바탕으로 영화에 대한 평가점수를 예측한다. 영화평가 예측시스템의 성능은 영화 평가점수의 실제값과 예측값의 오차를 RMSE(root mean square error) 방법으로 계산한 후 기존의 영화평가 시스템 RMSE 값과 비교하여 평가하였다. 본 연구를 통해 제안한 영화평가 예측시스템이 추천 시스템의 기반 기술로서 활용이 가능하고 다른 멀티미디어 컨텐츠 서비스 추천에도 응용이 가능할 것으로 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3798-3814
• /
• 2022

Social recommendation algorithm can alleviate data sparsity and cold start problems in recommendation system by integrated social information. Among them, matrix-based decomposition algorithms are the most widely used and studied. Such algorithms use dot product operations to calculate the similarity between users and items, which ignores user's potential preferences, reduces algorithms' recommendation accuracy. This deficiency can be avoided by a metric learning-based social recommendation algorithm, which learns the distance between user embedding vectors and item embedding vectors instead of vector dot-product operations. However, previous works provide no theoretical explanation for its plausibility. Moreover, most works focus on the indirect impact of social friends on user's preferences, ignoring the direct impact on user's rating preferences, which is the influence of user rating preferences. To solve these problems, this study proposes a user bias drift social recommendation algorithm based on metric learning (BDML). The main work of this paper is as follows: (1) the process of introducing metric learning in the social recommendation scenario is introduced in the form of equations, and explained the reason why metric learning can replace the click operation; (2) a new user bias is constructed to simultaneously model the impact of social relationships on user's ratings preferences and user's preferences; Experimental results on two datasets show that the BDML algorithm proposed in this study has better recommendation accuracy compared with other comparison algorithms, and will be able to guarantee the recommendation effect in a more sparse dataset.

• 한국컴퓨터정보학회논문지
• /
• 제18권2호
• /
• pp.107-116
• /
• 2013

본 연구에서는 소셜 음악 사이트에서 사용자들이 음악 아이템을 청취한 횟수와 생성한 태그 정보를 혼합하여 음악을 추천하는 시스템을 제안한다. 현재, 상용화된 음악 추천 시스템들은 주로 사용자의 청취 습관과 외부적인 선호도 입력값을 기반으로 음악을 추천하고 있다. 그러나 이 방식은 아직 음악을 청취한 사용자가 많지 않은 새로운 음악이나 청취 정보가 없는 새로운 사용자의 경우 추천하는 데 어려움이 있다. 이 문제를 해결하기 위해서 본 논문에서는 사용자가 선정한 키워드를 아이템에 부여하는 협업 태깅으로 생성된 태그 정보를 활용하였다. 태그의 의미를 파악하여 감정 표현의 정도에 따라 가중치를 부여한 뒤, 태그 점수와 청취 횟수를 혼합하여 음악 아이템의 선호도를 산출하였다. 이를 기반으로 사용자 프로파일을 생성하고 협업 필터링 알고리즘을 수행하였다. 제안하는 추천 방법의 효율성을 평가하기 위해서, 청취 습관 기반 추천, 태그 점수 기반 추천, 하이브리드 추천 방법의 세 가지 추천 방법에 대해서 정확도, 재현율, 그리고 F-measure를 계산하였다. 실험 결과에 대해 통계적 검증을 시행한 결과, 하이브리드 추천 방법이 다른 두 가지 방식보다 통계적으로 유의한 차이를 보여 성능이 우수한 것으로 나타났다.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.1-7
• /
• 2020

As the demand for health screening increases, there is a need for efficient design of screening items. We build machine learning models for health screening and recommend screening items to provide personalized health care service. When offline, a synthetic data set is generated based on guidelines and clinical results from institutions, and a machine learning model for each screening item is generated. When online, the recommendation server provides a recommendation list of screening items in real time using the customer's health condition and machine learning models. As a result of the performance analysis, the accuracy of the learning model was close to 100%, and server response time was less than 1 second to serve 1,000 users simultaneously. This paper provides an adaptive and automatic recommendation in response to changes in the new screening environment.

• 인터넷정보학회논문지
• /
• 제19권3호
• /
• pp.7-14
• /
• 2018

As SNS(Social Network Service) becomes a part of our life, new information can be derived through various information provided by SNS. Through the public timeline analysis of SNS, we can extract the latest tour trends for the public and the intimacy through the social relationship analysis in the SNS. The extracted intimacy can also be used to make the personalized recommendation by adding the weights to friends with high intimacy. We apply SNS elements such as analyzed latest trends and intimacy to item-based collaborative filtering techniques to achieve better accuracy and satisfaction than existing travel recommendation services in a new way. In this paper, we propose a social travel recommendation system using item - based collaborative filtering.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제7권3호
• /
• pp.165-170
• /
• 2007

Recommendation systems provide users with proper services using context information being input from many sensors occasionally under ubiquitous computing environment. But in case there isn't sufficient context information for service recommendation in spite of much context information, there can be problems of resulting in inexact result. In addition, in the quantification step to use context information, there are problems of classifying context information inexactly because of using an absolute classification course. In this paper, we solved the problem of lack of necessary context information for service recommendation by using dynamic profile information. We also improved the problem of absolute classification by using a relative classification of context information in quantification step. As the result of experiments, expectation preference degree was improved by 7.5% as compared with collaborative filtering methods using an absolute quantification method where context information of P2P mobile agent is used.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.2903-2923
• /
• 2023

Knowledge recommendation is a type of recommendation system that recommends knowledge content to users in order to satisfy their needs. Although using graph neural networks to extract data features is an effective method for solving the recommendation problem, there is information loss when modeling real-world problems because an edge in a graph structure can only be associated with two nodes. Because one super-edge in the hypergraph structure can be connected with several nodes and the effectiveness of knowledge graph for knowledge expression, a dual-channel hypergraph convolutional neural network model (DCHC) based on hypergraph structure and knowledge graph is proposed. The model divides user data and knowledge data into user subhypergraph and knowledge subhypergraph, respectively, and extracts user data features by dual-channel hypergraph convolution and knowledge data features by combining with knowledge graph technology, and finally generates recommendation results based on the obtained user embedding and knowledge embedding. The performance of DCHC model is higher than the comparative model under AUC and F1 evaluation indicators, comparative experiments with the baseline also demonstrate the validity of DCHC model.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2007년도 학술대회 1부
• /
• pp.268-273
• /
• 2007

In this paper, we present effective methods for automatic music recommendation system which automatically recommend music by signal processing technology. Conventional music recommendation system use users’ music downloading pattern, but the method does not consider acoustic characteristics of music. Sometimes, similarities between music are used to find similar music for recommendation in some method. However, the feature used for calculating similarities is not highly related to music characteristics at the system. Thus, our proposed method use high-level music characteristics such as rhythm pattern, timbre characteristics, and the lyrics. In addition, our proposed method store features of music, which individuals queried, to recommend music based on individual taste. Experiments show the proposed method find similar music more effectively than a conventional method. The experimental results also show that the proposed method could be used for real-time application since the processing time for calculating similarities between music, and recommending music are fast enough to be applicable for commercial purpose.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.267-269
• /
• 2019

There are many recommendation systems offer an effort to get better preciseness the information to the users. In order to further improve more accuracy, the social network analysis method which is used to analyze data to community detection in social networks was introduced in the recommendation system and the result shows this method is improving more accuracy. In this paper, we propose a movie recommendation system using social network analysis and normalized discounted cumulative gain with the best accuracy. To estimate the performance, the collaborative filtering using the k nearest neighbor method, the social network analysis with collaborative filtering method and the proposed method are used to evaluate the MovieLens data. The performance outputs show that the proposed method get better the accuracy of the movie recommendation system than any other methods used in this experiment.