Computer Aided Diagnosis Based on K-means Collaborative Filtering Algorithm

Feng Xue-yuan,Li Peng,Qiao Pei-li 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.4

In computer aided diagnosis (CAD) process, one of the most challenging problems is data sparsity, which leads to the diagnosis results are not reliable. This paper proposes a clustering collaborative filtering based algorithm to solve the problem of data sparsity. In this paper, we use k-means clustering algorithm to cluster the same type of patients, and then adopt collaborative filtering method to fill the missing data values for each cluster, in this way to reduce the complexity of similarity calculation of collaborative filtering. The proposed method makes full use of the information-sharing mechanism of "similar patient population" to predict and fill the missing values. A hepatitis dataset is used for evaluating the performance of the algorithm. Results indicate that the proposed algorithm has better performance for medical record data sparsity problem.

Performance Improvement of a Movie Recommendation System based on Personal Propensity and Secure Collaborative Filtering

Jeong, Woon-Hae,Kim, Se-Jun,Park, Doo-Soon,Kwak, Jin Korea Information Processing Society 2013 Journal of information processing systems Vol.9 No.1

There are many recommendation systems available to provide users with personalized services. Among them, the most frequently used in electronic commerce is 'collaborative filtering', which is a technique that provides a process of filtering customer information for the preparation of profiles and making recommendations of products that are expected to be preferred by other users, based on such information profiles. Collaborative filtering systems, however, have in their nature both technical issues such as sparsity, scalability, and transparency, as well as security issues in the collection of the information that becomes the basis for preparation of the profiles. In this paper, we suggest a movie recommendation system, based on the selection of optimal personal propensity variables and the utilization of a secure collaborating filtering system, in order to provide a solution to such sparsity and scalability issues. At the same time, we adopt 'push attack' principles to deal with the security vulnerability of collaborative filtering systems. Furthermore, we assess the system's applicability by using the open database MovieLens, and present a personal propensity framework for improvement in the performance of recommender systems. We successfully come up with a movie recommendation system through the selection of optimal personalization factors and the embodiment of a safe collaborative filtering system.

사용자 레퍼토리 기반 분산 병렬 협업 필터링을 위한 데이터 분배 방법 연구

Choelhan Moon,Seongjun Choe,Han Ki Son,Jun-Ki Min 한국차세대컴퓨팅학회 2021 한국차세대컴퓨팅학회 학술대회 Vol.2021 No.05

Collaborative filtering is a representative technique of a recommendation system. Collaborative filtering is a method of determining a recommendation target based on similarity between users or items. Distributed parallel collaborative filtering was proposed to speed up the computational speed of collaborative filtering. However, the data skewness problem caused by imbalanced data distribution still remains. Therefore, in this study, we proposed a data distribution and processing method based on the user taste repertoire analysis method to solve the data skewness problem caused by data distribution imbalance. So, the repertorie analysis is to analyze the range and number of areas of the services previously used by the users. In the proposed method, data is distributed based on the results of the repertorie analysis of the services previously used by the users. Our experiment distributing data of users based on the results of the repertoire analysis. It was shown that the performance was sufficiently usable as measuring RMSE and execution time.

Combining Neighborhood Based Collaborative Filtering with Tag Information for Personalized Recommendation

Xiaoyi Deng 보안공학연구지원센터 2016 International Journal of Multimedia and Ubiquitous Vol.11 No.9

Collaborative filtering recommendation is one of the most effective recommending techniques, which provide customers with suggestions according to their interests. However, neighborhood based collaborative filtering methods confront great challenges of data sparsity and lack of accessorial information in the context of big data. To address these problems, we propose a hybrid model combining tag information and neighborhood based collaborative filtering. A folksonomy network model based on tag information is proposed to analyze the tag relevance between different items. And tag relevance is incorporated into rating prediction of neighborhood based collaborative filtering for improving the recommendation accuracy. Experiments on MovieLens and Netflix datasets are carried out to evaluate the performance of our method. The results show that our method outperforms other methods and can improve recommending quality effectively.

Performance Improvement of a Movie Recommendation System based on Personal Propensity and Secure Collaborative Filtering

정운해,김세준,박두순,곽진 한국정보처리학회 2013 Journal of information processing systems Vol.9 No.1

There are many recommendation systems available to provide users with personalized services. Among them, the most frequently used in electronic commerce is ‘collaborative filtering’, which is a technique that provides a process of filtering customer information for the preparation of profiles and making recommendations of products that are expected to be preferred by other users, based on such information profiles. Collaborative filtering systems, however, have in their nature both technical issues such as sparsity, scalability, and transparency, as well as security issues in the collection of the information that becomes the basis for preparation of the profiles. In this paper, we suggest a movie recommendation system, based on the selection of optimal personal propensity variables and the utilization of a secure collaborating filtering system, in order to provide a solution to such sparsity and scalability issues. At the same time, we adopt ‘push attack’ principles to deal with the security vulnerability of collaborative filtering systems. Furthermore, we assess the system’s applicability by using the open database MovieLens, and present a personal propensity framework for improvement in the performance of recommender systems. We successfully come up with a movie recommendation system through the selection of optimal personalization factors and the embodiment of a safe collaborative filtering system

Item-network-based collaborative filtering: A personalized recommendation method based on a user's item network

Ha, T.,Lee, S. Pergamon Press 2017 Information processing & management Vol.53 No.5

Recommendation systems are becoming important with the increased availability of online services. A typical approach used in recommendations is collaborative filtering. However, because it largely relies on external relations, such as items-to-items or users-to-users, problems occur when the relations are biased or insufficient. Focusing on that limitation, we here suggest a new method, item-network-based collaborative filtering, which recommends items through four steps. First, the system constructs item networks based on users' item usage history and calculates three types of centrality: betweenness, closeness, and degree. Next, the system secures significant items based on the betweenness centrality of the items in each user's item network. Then, by using the closeness and degree centrality of the secured items, the algorithm predicts preference scores for items and their rank orders from each user's perspective. In the last step, the system organizes a recommendation list based on the predicted scores. To evaluate the performance of our system, we applied it to a sample dataset of 196 Last.fm users' listening history and compared the results with those from existing collaborative filtering methods. The results showed that the suggested method performed better than the basic item-based and user-based collaborative filtering methods in terms of Accuracy, Recall, and F1 scores for top-k recommendations. This indicates that an individual user's item relations can be utilized to remedy the problems occurring when the external relations are biased or insufficient.

아이템 연관성을 고려한 협력적 필터링 기반 추천시스템 개발

강호윤 ( Ho Yun Kang ),옥창수 ( Chang Soo Ok ) (주)엘지씨엔에스(구 LGCNS 엔트루정보기술연구소) 2015 Entrue Journal of Information Technology Vol.14 No.1

정보기술과 인터넷 기술의 발달로 전자상거래가 활성화되면서 추천시스템의 중요성이 증가하였다. 전자상거래에서 추천시스템은 사용자 개인 정보와 구매 이력을 통해 필요로 할 것이라 예상되는 상품을 사용자에게 추천해 준다. 추천시스템은 협력적 필터링과 군집모델, 그리고 검색 기반 방법 등 많은 연구가 수행되었다. 그러나 이러한 연구들은 상품 간의 연관성은 고려하지 않고 사용자 정보만을 가지고 상품을 추천해 주기 때문에 추천 상품의 정확도가 떨어진다. 본 연구에서는 이러한 문제점을 보안하기 위해 기존의 협력적 필터링 기법과 아마존에서 사용자고 있는 아이템 간 협력적 필터링 기법을 활용하여 혼합 추천시스템을 제안하고 이 추천시스템을 중소 제조기업을 위한 제조용 앱스토어에 적용한다. 본 연구에서 제안하는 추천시스템은 기존 연구에서 사용된 Recall과 Precision 두 척도의 조화평균 값으로 평가하였다. 평가 결과 제안한 추천시스템이 기존 협력적 필터링 보다 좀더 높은 정확도를 제공하는 것으로 나타났다. As glowing e-commerce markets, many websites for online shopping mall and B-to-B trading has emerged and, consequently, the websites need to differentiate themselves with their competitors. To obtain the goal e-commerce companies have considered recom-mender system as a business tool and the important of recommender system has increased. In e-commerce, recommender system help users find products which might be useful for user based on their personal and purchasing history information to acquire increase of sales and business superiority. Recommender system, collaborative filtering, cluster models, search-based methods, and many studies have been conducted. These studies, however, the quality of recommendation is relatively low, since those approaches consider user`s information only, without considering the correlation among products. In this study, in order to make up for these problems, a hybrid recommender system uti-lizing traditional collaborative filtering and item-to-item collaborative filtering is proposed. To demonstrate the effectiveness of the proposed algorithm is applied the manufacturing appstore (www.mfg-app.co.kr) and a user survey have conducted. The result of the analysis shows that our recommendation system is effective and provides more helpful recommendations to website users.

아이템 기반의 협업 필터링을 이용한 영화 추천 시스템 구현 및 비교

이준호,주경수 순천향대학교 부설 산업기술연구소 2017 순천향 산업기술연구소논문집 Vol.23 No.1

It is not easy for the user to find the information that is appropriate for the user among the suddenly increasing information in recent years. One of the ways to help individuals make decisions in such a lot of information is the recommendation system. Although there are many recommendation methods for such recommendation systems, a representative method is collaborative filtering. We implement a system that recommends movies, one of cultural contents, by using collaborative filtering algorithm based on user among collaborative filtering algorithms. Performance evaluations were made using the MovieLens 100k data set. After the performance evaluation, the results were compared with user - based collaborative filtering. In this paper, we also design and implement a movie recommendation system using the collaborative filtering algorithm of Arpache Mahout.

복합 필터링을 이용한 IPTV-VOD 프로그램 추천 시스템 연구

강용진,선철용,박규식 대한전자공학회 2010 電子工學會論文誌-SP (Signal processing) Vol.47 No.4

본 연구는 IPTV 환경에서 사용자의 취향에 맞는 VOD 프로그램을 추천할 수 있는 시스템을 새로이 제안하였다. 제안 시스템은 내용기반 필터링과 협업 필터링의 장․단점을 상호 보완한 복합 필터링에 의한 IPTV-VOD 프로그램 추천 시스템으로, 각 필터링 기법의 프로그램 선호도(program preference) 값을 단일 지표(single-scale)로 비교․평가할 수 있는 수단을 제공함으로써 실질적인 복합 필터링 추천 시스템을 구축하였다. 사용자의 프로그램 선호 취향을 나타내는 사용자 프로파일(user profile)은 사용자의 과거 프로그램 시청 이력뿐만 아니라 사용자와 유사한 이웃 사용자들의 취향을 1주일 단위로 갱신되는 프로그램 선호도와 중분류 선호도로 표현하였기 때문에 보다 정확한 프로그램 추천이 가능하다. 제안 시스템의 성능평가를 위해 시청률 조사기관인 닐슨리서치의 24주분 지상파 및 케이블 방송 시청 데이터를 IPTV 형식에 맞게 재구성하여 사용하였으며, 다양한 실험을 통해 그 실용성을 입증하였다. In this paper, a new program recommendation system is proposed to recommend user preferred VOD program in IPTV environment. A proposed system is implemented with hybrid filtering method that can cooperatively complements the shortcomings of the content-based filtering and collaborative filtering. For a user program preference, a single-scaled measure is designed so that the recommendation performance between content-based filtering and collaborative filtering is easily compared and reflected to final hybrid filtering procedure. In order to provide more accurate program recommendation, we use not only the user watching history, but also the user program preference and sub-genre program preference updated every week as a user preference profile. System performance is evaluated with modified IPTV data from real 24-weeks cable TV watching data provided by Nilson Research Corp. and it shows quite comparative quality of recommendation.

Word2Vec을 이용한 사용자기반 협업필터링의 예측 정확도 개선

강부식 한국지식정보기술학회 2018 한국지식정보기술학회 논문지 Vol.13 No.1

Word2Vec is a most popular method in text mining area, recently. It converts words to vectors using association among words in sentences. Similar words are nearly located in the vector space. Improving predictive accuracy of recommender algorithms is a major work in the area of recommender systems. User-based collaborative filtering recommends products using the information about product preference of Neighbors. This study proposed a method to compute user similarity using vectors of users by Word2Vec instead of using traditional method. In order to use Word2Vec, we separate sentences first, and then find corpus that is meaningful word set of the sentences. For using Word2Vec in user-based movie recommender, we find users that have seen same movies first, we substitute an user to a word and user list of a movie to corpus of one sentence. There can be several methods to compose the sentences in recommender systems. This study considers two methods, first method constructs a sentence per movie and second method can construct several sentences per movie. After sentence construction, it enters corpus of sentences into Word2Vec and computes vectors of users, and then computes user similarity by coefficient corelation method using the vectors of users. Using the similarity, it recommends products by user-based collaborative filtering. To validate, the proposed methods were applied to filmtrust dataset. The experimental results of repeating 10-fold cross validation three times showed that mean MAE of user-based collaborative filtering(wvCF3.0) applying Word2Vec improved the predictive accuracy greatly than that of conventional collaborative filtering method(uCF). Also, it showed that the sentence expansion method(wvCFthree) constructing several sentences per movie is better than the one sentence method(wvCF3.0) constructing one sentence per movie for improving the predictive accuracy. To test statistical significance between uCF and wvCF3.0, and between wvCF3.0 and wvCFthree, we experimented paired t-test and confirmed the statistical significance.