• 한국IT서비스학회지
• /
• 제16권3호
• /
• pp.113-125
• /
• 2017

Customers have been affected by others' opinions when they make a purchase. Thanks to the development of technologies, people are sharing their experiences such as reviews or ratings through online or social network services, However, although ratings are intuitive information for others, many reviews include only texts without ratings. Also, because of huge amount of reviews, customers and companies can't read all of them so they are hard to evaluate to a product without ratings. Therefore, in this study, we propose a methodology to predict ratings based on reviews for a product. In a methodology, we first estimate the topic-review matrix using the Latent Dirichlet Allocation technic which is widely used in topic modeling. Next, we predict ratings based on the topic-review matrix using the artificial neural network model which is based on the backpropagation algorithm. Through experiments with actual reviews, we find that our methodology can predict ratings based on customers' reviews. And our methodology performs better with reviews which include certain opinions. As a result, our study can be used for customers and companies that want to know exactly a product with ratings. Moreover, we hope that our study leads to the implementation of future studies that combine machine learning and topic modeling.

• 한국지형학회지
• /
• 제20권1호
• /
• pp.21-33
• /
• 2013

이 연구에서는 접근이 어렵고 범위가 광대하여 많은 시간과 비용이 소요되는 산지습지의 현장조사 대상범위를 줄이고 작업의 효율성을 높이기 위해 산지 습지 위치와 지형 및 기타 GIS 정보 사이의 관계를 확률로 표현하는 Weight of Evidence 기법을 적용하여 산지습지 가능지역을 추출하였다. 이를 위하여 영남지역을 대상으로 산지습지와 관련된 경사 분포, 곡률 분포, 식생지수 분포, 습윤지수 분포, 토양 배수등급 분포 등 공간 데이터베이스를 구축하고 이를 기존 산지습지 위치와의 상관관계를 통하여 Weight of Evidence를 구하였다. 우도비를 통하여 산지습지 가능성에 대한 각 요인의 등급을 분석한 결과 경사도, 곡률, 식생지수, 습윤지수가 낮을수록, 토양 배수등급이 양호한 곳에 산지습지 분포 가능성이 높은 것으로 나타났다. 산지습지가능성도 작성을 위하여 각 요인의 등급에 대하여 Weight of Evidence 가중치를 부여하고 GIS 중첩분석을 실시하여 산지습지가능지수를 산출하였다. 그리고 검증을 위하여 산지습지 가능지수 등급구간에 대한 산지습지 위치 포함 누적비율을 표시한 성공확률곡선을 작성하고 면적비율을 계산한 결과 75.48%로서 상당히 높은 예측정확도를 나타내었다.

• 한국지반공학회논문집
• /
• 제35권9호
• /
• pp.37-45
• /
• 2019

터널 굴착 시 신속한 막장면 상태 파악 및 적절한 지보패턴 결정은 터널 붕락사고의 예방 및 안정적인 굴진에 매우 중요하다. 본 연구에서는 딥러닝 기법을 활용하여 막장면 상태에 따른 암반상태 분류를 신속하게 결정할 수 있는 기술을 개발하였으며, CNN 기법을 이용한 암반상태 분류방법 및 예측 정확도 개선 방법 등을 제시하고 있다. 수 만개의 이미지가 사전 학습된 VGG16 모델을 알고리즘으로 적용하였고, 1,469개의 터널 막장면 이미지에 대한 학습을 통하여 5개 등급으로 암반상태를 분류하였다. 본 연구에서의 예측 정확도는 최대 83.9% 수준을 나타내었으며, 향후 추가적인 이미지 축적을 통해 암반상태 평가자에 따른 편차를 줄인 객관적이고 정량적 암반상태 분류방법으로 활용 가능할 것으로 판단된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2948-2966
• /
• 2014

To promote recommendation services through prediction quality, some privacy-preserving collaborative filtering solutions are proposed to make e-commerce parties collaborate on partitioned data. It is almost probable that two parties hold ratings for the same users and items simultaneously; however, existing two-party privacy-preserving collaborative filtering solutions do not cover such overlaps. Since rating values and rated items are confidential, overlapping ratings make privacy-preservation more challenging. This study examines how to estimate predictions privately based on partitioned data with overlapped entries between two e-commerce companies. We consider both user-based and item-based collaborative filtering approaches and propose novel privacy-preserving collaborative filtering schemes in this sense. We also evaluate our schemes using real movie dataset, and the empirical outcomes show that the parties can promote collaborative services using our schemes.

• 수산해양교육연구
• /
• 제20권1호
• /
• pp.36-45
• /
• 2008

The purpose of this study was to explore new fisheries-related jobs in the future. The study is based on a thorough literature review and in-depth interviews with experts in the fisheries industry. The major findings of the study were as follows: First, new fisheries-related jobs that surpass the fitness rating of 90% and earn more than 3 on the prospect scale are expected to be found mostly in professional fishery sectors. In the production and processing sectors, fishery quality control manager, marine product cooks, and raw fish cooks looked most promising. In the fishery marketing and distribution section, on the other hand, marine tour consultants, marine product distribution consultants, underwater guides, online marine product traders, marine sports consultants, and marine safety specialists ranked high on the list.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 A
• /
• pp.58-60
• /
• 1999

This paper presents dynamic performance prediction using Matlab / simulink after parameter estimation of synchronous reluctance motor considering iron loss. Test motor is 3 phase SynRM with the segmental rotor, rating power is 0.175KW. Experiment equipment is consists of testing motor, dynamometer, vector invertor dynamocontroller, and power analyser. The stator iron loss and rotor iron loss are modelled by additional windings on three-phase winding axis. These windings are transformed into d-q axis, and are represented as equivalent eddy current windings. P-Q circle diagram method and single phase standstill method are used to measure motor parameters considering iron loss.

• 아동학회지
• /
• 제17권2호
• /
• pp.181-193
• /
• 1996

The purpose of this study was: (1) to examine relationships between social development and day care quality, child-care experience and family characteristics, and (2) to investigate the explainability of those related variables for social development. Subjects for this study were 252 4-year-old children and their mothers from 32 day care centers in Seoul. Harms & Clifford's Early Childhood Environment Rating Scale was used to measure the quality of day care. The main results were as follows: (1) Day care quality, child-care experience and family characteristics were significantly related to social development. (2) Child's gender, months of age, mother's child rearing attitude, the length of child-care experience, overall quality of day care, and group size significantly predicted social development. 33％ of the variance of social development was explained by these variables. The relative influence of these variables to the prediction of social development was about the same.

• Journal of the Korean Data and Information Science Society
• /
• 제17권3호
• /
• pp.775-784
• /
• 2006

This study is to investigate the effect of the number of co-rated users to the MAE. User based collaborative algorithm generally uses similarity weight to compute the relation of active user and other users. The original estimation algorithm of the GroupLens used the Pearson's correlation coefficient, soon after other researchers used various weighting. The Pearson’s correlation coefficient and Vector similarity, which is used in the field of information retrieval, are commonly used to the estimation algorithm. In prediction, we analyze the effect of the number of co-rated users on the user based recommender system.

• 한국컴퓨터정보학회논문지
• /
• 제23권12호
• /
• pp.219-226
• /
• 2018

Collaborative filtering has been most popular approach to recommend items in online recommender systems. However, collaborative filtering is known to suffer from data sparsity problem. As a simple way to overcome this problem in literature, Jaccard index has been adopted to combine with the existing similarity measures. We analyze performance of such combination in various data environments. We also find optimal weights of factors in the combination using a genetic algorithm to formulate a similarity measure. Furthermore, optimal weights are searched for each user independently, in order to reflect each user's different rating behavior. Performance of the resulting personalized similarity measure is examined using two datasets with different data characteristics. It presents overall superiority to previous measures in terms of recommendation and prediction qualities regardless of the characteristics of the data environment.

• 한국농림기상학회:학술대회논문집
• /
• 한국농림기상학회 2015년도 하계 학술발표논문집
• /
• pp.126-130
• /
• 2015