• Journal of Information Processing Systems
• /
• 제15권3호
• /
• pp.464-477
• /
• 2019

With the sustained and rapid development of new energy sources, the demand for electric energy is increasing day by day. However, China's energy distribution is not balanced, and the construction of transmission lines is in a serious lag behind the improvement of generating capacity. So there is an urgent need to increase the utilization of transmission capacity. The transmission capacity is mainly limited by the maximum allowable operating temperature of conductor. At present, the evaluation of transmission capacity mostly adopts the static thermal rating (STR) method under severe environment. Dynamic thermal rating (DTR) technique can improve the utilization of transmission capacity to a certain extent. In this paper, the meteorological parameters affecting the conductor temperature are analyzed with the IEEE standard thermal equivalent equation of overhead transmission lines, and the real load capacity of 220 kV transmission line is calculated with 7-year actual meteorological data in Weihai. Finally, the thermal load capacity of DTR relative to STR under given confidence is analyzed. By identifying the key parameters that affect the thermal rating and analyzing the relevant environmental parameters that affect the conductor temperature, this paper provides a theoretical basis for the wind power grid integration and grid intelligence. The results show that the thermal load potential of transmission lines can be effectively excavated by DTR, which provides a theoretical basis for improving the absorptive capacity of power grid.

• 지능정보연구
• /
• 제28권2호
• /
• pp.171-189
• /
• 2022

온라인 리뷰는 소비자의 구매 의사결정 과정에서 중요한 역할을 담당하고 있으므로 소비자에게 유용하고 신뢰성이 있는 리뷰를 제공하는 것이 중요하다. 기존의 온라인 리뷰 유용성 예측 관련 연구는 주로 온라인 리뷰의 텍스트와 평점 정보 간의 일관성을 바탕으로 리뷰 유용성을 예측하였다. 그러나 기존 연구는 평점 정보를 스칼라로 표현했기 때문에 표현 수용력이 제한적이거나 평점 정보와 리뷰 텍스트 정보와의 상호작용을 제한적으로 학습하는 한계가 존재한다. 본 연구에서는 기존 연구의 한계점을 보완하기 위해 리뷰 텍스트와 평점 정보 간의 상호작용을 효과적으로 학습할 수 있는 CNN-RHP(CNN based Review Helpfulness Prediction) 모델을 제안하였다. 먼저, 리뷰 텍스트의 의미론적 특성을 추출하기 위해 multi-channel CNN을 적용하였다. 다음으로, 평점 정보는 텍스트 특성과 동일한 차원을 나타내는 독립된 고차원 임베딩 특성 벡터로 변환하였다. 최종적으로 요소별(Element-wise) 연산을 통해 리뷰 텍스트와 평점 정보 간의 일관성을 학습하였다. 본 연구에서는 제안된 CNN-RHP 모델의 성능을 평가하기 위해 Amazom.com에서 수집된 온라인 소비자 리뷰를 사용하였다. 실험 결과, 본 연구에서 제안한 CNN-RHP 모델이 기존 연구에서 제안된 여러 모델과 비교했을 때 우수한 예측 성능을 나타내는 것을 확인하였다. 본 연구의 결과는 온라인 전자상거래 플랫폼에서 소비자들에게 리뷰 유용성 예측 서비스를 제공할 때 유의미한 시사점을 제공할 수 있다.

• 한국정보기술학회 영문논문지
• /
• 제9권2호
• /
• pp.41-54
• /
• 2019

The cinema circuit is facing a digital, network, and mobile age, which expands non-theater accessibility to movies. Application platforms are situated as the most competitive business model that provide digital content such as games, music, books, and movies. Consumers can acquire content-related information not just offline, but online as well. Therefore, item information provided by application platforms is required. The information provided by application platforms consists of richly descriptive information such as storyline summary, consumer reviews, and related articles, while non-descriptive normative information covers data such as sales ranking, release date, genre, rental or purchase cost, domestic/foreign classification, consumer rating, number of consumer ratings, film rating, and so on. In this study, we surveyed and analyzed statistically the correlation between real-time sales ranking and other comparable non-descriptive information.

• 대한정형도수물리치료학회지
• /
• 제8권2호
• /
• pp.19-29
• /
• 2002

Objectives: This study was to analysis of pain using visual analogue scale and self rating anxiety scale questionnaire. Methods: Questionnaire were completed by 83 adult patients of department relation to pain in hospitals of Daegu from June 20, to August 10, 2001. The information was used to estimate multiple regression for the pain and anxiety scale related factors association. Results: Women visual analogue scale 4.6 scores of mean was higher than man 4.3 scores. Man self rating anxiety scale 30.2 scores of mean was higher than women 26.8 scores. The scores of 6 months above was discomfort 51.8, 1 month below was mild 22.1%, 2-3 months was discomfort 10.5%, and 4-5 months was discomfort 9.3% in association between present pain index and duration. Conclusion: Visual analogue scale scores was significantly associated with frequency of present pain index. Self rating anxiety scale scores was significantly associated with frequency of occupation and present pain index.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2310-2332
• /
• 2020

In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.

• Asia pacific journal of information systems
• /
• 제20권2호
• /
• pp.23-37
• /
• 2010

Conventional Support Vector Machines (SVMs) have been utilized as classifiers for binary classification problems. However, certain real world problems, including corporate bond rating, cannot be addressed by binary classifiers because these are multi-class problems. For this reason, numerous studies have attempted to transform the original SVM into a multiclass classifier. These studies, however, have only considered nominal classification problems. Thus, these approaches have been limited by the existence of multiclass classification problems where classes are not nominal but ordinal in real world, such as corporate bond rating and multiclass customer classification. In this study, we adopt a novel multiclass SVM which can address ordinal classification problems using ordinal pairwise partitioning (OPP). The proposed model in our study may use fewer classifiers, but it classifies more accurately because it considers the characteristics of the order of the classes. Although it can be applied to all kinds of ordinal multiclass classification problems, most prior studies have applied it to finance area like bond rating. Thus, this study applies it to a real world customer level classification case for implementing customer relationship management. The result shows that the ordinal multiclass SVM model may also be effective for customer level classification.

• 디지털산업정보학회논문지
• /
• 제19권1호
• /
• pp.91-107
• /
• 2023

With the recent expansion of the commerce ecosystem, a large number of user evaluations have been produced. Accordingly, attempts to create business insights using user evaluation data have been actively made. However, since user evaluation can change after the user experiences the product, it is difficult to say that the analysis based only on reviews immediately after purchase fully reflects the user's evaluation of the product. Moreover, studies conducted so far on user evaluation have overlooked the fact that the length of time a user has used a product can affect the user's product evaluation. Therefore, in this study, we build a model that predicts the direction of change in the user's rating after use from the user's rating and reviews immediately after purchase. In particular, the proposed model reflects the product's period of use in predicting the change direction of the star rating. However, since the posterior information on the duration of product use cannot be used as input in the inference process, we propose a structure that utilizes information about the product's period of use using an auxiliary classifier. As a result of an experiment using 599,889 user evaluation data collected from the shopping platform 'N' company, we confirmed that the proposed model performed better than the existing model in terms of accuracy.

• 인터넷정보학회논문지
• /
• 제18권3호
• /
• pp.19-28
• /
• 2017

협업적 필터링(CF)은 사용자와 상품간의 관계를 해석하여 특정 사용자에게 상품을 추천 해주는 시스템이다. CF 모델은 컨텐츠 등 다른 추가 정보 없이 평점 데이터만으로 사용자에게 상품을 추천해 줄 수 있다는 장점이 있다. 하지만 사용자는 전체 상품의 극히 일부분만을 소비하고 상품을 소비한 후에도 평점을 부여하지 않는 경우가 매우 많다. 이는 관찰된 평점의 수가 매우 적으며 사용자 평점 행렬이 매우 희박함을 의미한다. 이러한 평점 데이터의 희박성은 CF의 성능을 끌어올리는데 문제를 야기한다. 본 논문에서는 CF 모델 중 하나인 잠재 요인 모델(특히 SVD)의 성능을 끌어올리는데 집중한다. SVD에 상품 유사도 정보와 상품 동시 발생(co occurrence) 정보를 포함시킨 새로운 모델을 제안한다. 평점 데이터로부터 얻어지는 유사도와 동시 발생 정보는 상품 잠재 요인에 대한 잠재 공간상의 표현력을 높여주어 기존방법보다 Recall은 약 16%, Precision과 NDCG는 각각 8%, 7% 상승하였다. 본 논문에서 제안하는 방법이 향후 다른 추천 시스템과 결합하면 기존의 방법보다 더 좋은 성능을 보여줄 것이다.

• Smart Structures and Systems
• /
• 제13권6호
• /
• pp.901-925
• /
• 2014

The reliability of a Bridge management System depends on the quality of visual inspection and the reliable estimation of bridge condition rating. However, the current practices of visual inspection have been identified with several limitations, such as: they are time-consuming, provide incomplete information, and their reliance on inspectors' experience. To overcome such limitations, this paper presents an approach of automating the prediction of condition rating for bridges based on digital image analysis. The proposed methodology encompasses image acquisition, development of 3D visualization model, image processing, and condition rating model. Under this method, scaling defect in concrete bridge components is considered as a candidate defect and the guidelines in the Ontario Structure Inspection Manual (OSIM) have been adopted for developing and testing the proposed method. The automated algorithms for scaling depth prediction and mapping of condition ratings are based on training of back propagation neural networks. The result of developed models showed better prediction capability of condition rating over the existing methods such as, Naïve Bayes Classifiers and Bagged Decision Tree.

• 한국주거학회논문집
• /
• 제20권6호
• /
• pp.57-65
• /
• 2009

In Korea, Housing Performance Rating Indication System was first adopted in 2006. Main purpose of the System is on developing criteria which can systematically measure the level of housing performance. Among the five categories of Housing Performance Rating Indication System, Repair Convenience is closely related to Remodeling which has been widely recognized as an alternative to the building reconstruction. Especially, as the actual housing supply level in Korea is reaching almost 100%, it is crucial to expand Long-life Housing through the effective maintenance and management. In addition, consumers should have an access to the performance ratings of apartment buildings on which they can rely on in choosing their own housings. And for construction companies, a performance code enacted by government will provide them with a standard that they can utilize in determining performance level of buildings that they build. This study examines data which has been obtained from the recent application of Housing Performance Rating Indication System and Repair Convenience category is main concern. Findings from the study will provide vital information in improving current Housing Performance Rating Indication System.