• 한국인터넷방송통신학회논문지
• /
• 제21권4호
• /
• pp.183-188
• /
• 2021

협력 필터링 기반의 추천 시스템은 현재 다양한 분야의 상업용 시스템의 필수불가결한 기능으로서, 사용자들이 선호할만한 상품을 맞춤형으로 제공해 주는 유용한 서비스이다. 그러나, 사용자들의 평가 데이타가 불충분할 경우 선호상품의 예측이 부정확할 우려가 크다. 본 연구에서는 이러한 단점을 해결하기 위하여 단계적으로 상품의 평가치를 예측하는 방안을 제시한다. 각 단계에 해당하는 예측 방법의 적용 조건을 만족하지 못할 경우 다음 단계의 방법을 적용한다. 제안 방법의 성능 평가를 위해, 공개 데이터셋을 활용한 실험을 진행하였으며, 제안 방법은 여러 전통적 유사도 척도를 도입한 협력 필터링 시스템의 예측 성능과 정밀도 성능을 크게 향상시켰고, 평가데이터 희소성 해결을 위한 기존 방식들의 성능을 능가하는 결과를 보였다.

• 한국정보통신학회논문지
• /
• 제9권7호
• /
• pp.1569-1574
• /
• 2005

In this paper, I propose an intelligent credit rating system using a bankruptcy prediction model based on support vector machines (SVMs). SVMs are promising methods because they use a risk function consisting of the empirical error and a regularized term which is derived from the structural risk minimization principle. This study examines the feasibility of applying SVM in Predicting corporate bankruptcies by comparing it with other data mining techniques. In addition. this study presents architecture and prototype of intelligeht credit rating systems based on SVM models.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권2호
• /
• pp.119-124
• /
• 2016

According to the expansion of smartphone penetration and development of wearable device, personal context information can be easily collected. To use this information, the context aware recommender system has been actively studied. The key issue in this field is how to deal with the context information, as users are influenced by different contexts while rating items. But measuring the similarity among contexts is not a trivial task. To solve this problem, we propose context aware post-filtering to apply the context compensation. To be specific, we calculate the compensation for different context information by measuring their average. After reflecting the compensation of the rating data, the mechanism recommends the items to the user. Based on the item recommendation list, we recover the rating score considering the context information. To verify the effectiveness of the proposed method, we use the real movie rating dataset. Experimental evaluation shows that our proposed method outperforms several state-of-the-art approaches.

• KIEAE Journal
• /
• 제10권4호
• /
• pp.19-28
• /
• 2010

As design tools, building performance certification systems can be applied to provide adequate guidelines on design process to create environment-friendly buildings. Domestic certification systems of residential building took effect by doing supply to designers and contractors from affiliated organization of governments in the early 2000s. As a result, Building Energy Rating System, Apartment Performance Rating System, Green Homes and other means to promote green designs have been operated. International trends of applying certification systems were started in the early 1990s as forms of LEED in USGBC, BREEAM in BRE, GBTool Canada. These systems aim to evaluate building performance in line with the Climatic Change Convention and realize sustainable building design. In 2009, residential buildings accounted for the largest portion of the internal real estate market with 67.9 percent according to the National Statistical Office data. And for 18 years since 1991, apartments among constructed residential buildings have ranked top taking up 77.7% as of 2009. Apartment performance evaluations accordingly are to promote to constitution of improving tenant quality of life, the residential environment and saving energy and resources in the internal building market. The purpose of this study is to compare and analyze valuation bases of each sector in evaluation systems of residential buildings at home and abroad to upgrade current systems through reflecting the characteristics of residential buildings. Implementation of this study basically include comparison of valuation bases and partial analysis on properties of rating systems to suggest requisites for improvement in building performance certification.

• 한국초전도ㆍ저온공학회논문지
• /
• 제7권2호
• /
• pp.16-20
• /
• 2005

As power systems grow more complex and power demands increase, the fault current tends to gradually increase. In the near future, the fault current will exceed a circuit breaker rating for some substations, which is an especially important issue in the Seoul metropolitan area because of its highly meshed configuration. Currently, the Korean power system is regulated by changing the 154kV system configuration from a loop connection to a radial system, by splitting the bus where load balance can be achieved, and by upgrading the circuit breaker rating. A development project applying 154kV Superconducting Fault Current Limiter (SFCL) to 154kV transmission systems is proceeding with implementation slated for after 2010. In this paper, SFCL is applied to reduce the fault current in power systems according to two different application schemes and their technical impacts are evaluated. The results indicate that both application schemes can regulate the fault current under the rating of circuit breaker, however, applying SFCL to the bus-tie location is much more appropriate from an economic view point.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.721-739
• /
• 2023

Rating prediction is an important issue in recommender systems, and its accuracy affects the experience of the user and the revenue of the company. Traditional recommender systems use Factorization Machinesfor rating predictions and each feature is selected with the same weight. Thus, there are problems with inaccurate ratings and limited data representation. This study proposes a deep recommendation model based on self-attention Factorization (SAFMR) to solve these problems. This model uses Convolutional Neural Networks to extract features from user and item reviews. The obtained features are fed into self-attention mechanism Factorization Machines, where the self-attention network automatically learns the dependencies of the features and distinguishes the weights of the different features, thereby reducing the prediction error. The model was experimentally evaluated using six classes of dataset. We compared MSE, NDCG and time for several real datasets. The experiment demonstrated that the SAFMR model achieved excellent rating prediction results and recommendation correlations, thereby verifying the effectiveness of the model.

• 한국태양에너지학회:학술대회논문집
• /
• 한국태양에너지학회 2009년도 추계학술발표대회 논문집
• /
• pp.191-198
• /
• 2009

Many Countries are making nationwide efforts to reduce the energy consumption which causes greenhouse gas emissions and global warming problems. Energy performance assessments and certification systems have been in force to save energy consumption of residential buildings, and are anticipated to have strong effects through the systems. Korean Building Energy Efficiency Rating System is in its early stages and is considered that the additional upgrade is needed for the accurate assessment. Thus, in this study, the assessment methods of the Building Energy Efficiency Rating System of Korea and the SAP2005 of UK were compared and energy requirements of an actual residential building were calculated with two assessment methods, respectively. The strengths and shortcomings of two systems were analyzed and a way of improving Korean system was suggested.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.462-472
• /
• 2021

With an increase in the scale of recommender systems, users' rating data tend to be extremely sparse. Some methods have been utilized to alleviate this problem; nevertheless, it has not been satisfactorily solved yet. Therefore, we propose an effective pre-rating method based on users' dichotomous preferences and average ratings fusion. First, based on a user-item ratings matrix, a new user-item preference matrix was constructed to analyze and model user preferences. The items were then divided into two categories based on a parameterized dynamic threshold. The missing ratings for items that the user was not interested in were directly filled with the lowest user rating; otherwise, fusion ratings were utilized to fill the missing ratings. Further, an optimized parameter λ was introduced to adjust their weights. Finally, we verified our method on a standard dataset. The experimental results show that our method can effectively reduce the prediction error and improve the recommendation quality. As for its application, our method is effective, but not complicated.

• 한국정보시스템학회지:정보시스템연구
• /
• 제14권1호
• /
• pp.41-65
• /
• 2005

The credit ration is a significant area of financial management which is of major interest to practitioners, financial and credit analysts. The components of credit rating are identified decision models are developed to assess credit rating an the corresponding creditworthiness of firms an accurately ad possble. Although many early studies demonstrate a priori which of these techniques will be most effective to solve a specific classification problem. Recently, a number of studies have demonstrate that a hybrid model integration artificial intelligence approaches with other feature selection algorthms can be alternative methodologies for business classification problems. In this article, we propose a hybrid approach using rough set theory as an alternative methodology to select appropriate attributes for case-based reasoning. This model uses rough specific interest lies in lthe stable combining of both rough set theory to extract knowledge that can guide dffective retrevals of useful cases. Our specific interest lies in the stable combining of both rough set theory and case-based reasoning in the problem of corporate credit rating. In addition, we summarize backgrounds of applying integrated model in the field of corporate credit rating with a brief description of various credit rating methodologies.

• Journal of Information Processing Systems
• /
• 제1권1호
• /
• pp.22-26
• /
• 2005

In this paper, we classified the objectionable texts into four rates according to their harmfulness and proposed the hierarchical text rating system for objectionable documents. Since the documents in the same category have similarities in used words, expressions and structure of the document, the text rating system, which uses a single classification model, has low accuracy. To solve this problem, we separate objectionable documents into several subsets by using their properties, and then classify the subsets hierarchically. The proposed system consists of three layers. In each layer, we select features using the chi-square statistics, and then the weight of the features, which is calculated by using the TF-IDF weighting scheme, is used as an input of the non-linear SVM classifier. By means of a hierarchical scheme using the different features and the different number of features in each layer, we can characterize the objectionability of documents more effectively and expect to improve the performance of the rating system. We compared the performance of the proposed system and performance of several text rating systems and experimental results show that the proposed system can archive an excellent classification performance.