• ETRI Journal
• /
• 제33권5호
• /
• pp.720-730
• /
• 2011

Opinion mining involves the analysis of customer opinions using product reviews and provides meaningful information including the polarity of the opinions. In opinion mining, feature extraction is important since the customers do not normally express their product opinions holistically but separately according to its individual features. However, previous research on feature-based opinion mining has not had good results due to drawbacks, such as selecting a feature considering only syntactical grammar information or treating features with similar meanings as different. To solve these problems, this paper proposes an enhanced feature extraction and refinement method called FEROM that effectively extracts correct features from review data by exploiting both grammatical properties and semantic characteristics of feature words and refines the features by recognizing and merging similar ones. A series of experiments performed on actual online review data demonstrated that FEROM is highly effective at extracting and refining features for analyzing customer review data and eventually contributes to accurate and functional opinion mining.

• 정보처리학회논문지B
• /
• 제16B권6호
• /
• pp.497-502
• /
• 2009

본 논문에서는 상품평의 효율적인 분석을 위한 평가 항목 추출 시스템을 제안한다. 시스템은 크게 상품평 수집-보정과 평가 항목 추출의 두 단계로 구성된다. 상품평 수집-보정에서는 인터넷 쇼핑몰에서 상품평을 수집하고 상품평 특유의 구어체 표현과 맞춤법 오류 등을 처리한다. 평가 항목 추출에서는 스커트 상품 카테고리의 경우 ‘사이즈', ‘스타일'과 같이 상품을 평가하는 기준이 되는 항목을 상품평과 인터넷 상의 웹 문서를 활용하여 자동으로 추출한다. 상품평에 나타나는 명사들을 평가 항목 후보로 설정하고, 각 후보 명사의 상품평에서의 어휘 통계인 내부연관도와, 후보 명사와 상품 카테고리명의 웹 문서에서의 공기 빈도에 기반하여 계산된 외부연관도를 결합하여 상품과 평가 항목 후보의 연관도를 계산한다. 본 논문의 평가 항목 추출 방식은 평균 재현율 90%를 보여 기존 연구보다 우수한 결과를 보였다.

• Smart Structures and Systems
• /
• 제29권6호
• /
• pp.767-775
• /
• 2022

Metal additive manufacturing (AM), also known as metal three-dimensional (3D) printing, produces 3D metal products by repeatedly adding and solidifying metal materials layer by layer. During the metal AM process, products experience repeated local melting and cooling using a laser or electron beam, resulting in product defects, such as warpage, cracks, and internal pores. Such defects adversely affect the final product. This paper proposes the in situ monitoring-based warpage prediction of metal AM products with experimental feature extraction. The temperature profile of the metal AM substrate during the process was experimentally collected. Time-domain features were extracted from the temperature profile, and their relationships to the warpage mechanism were investigated. The standard deviation showed a significant linear correlation with warpage. The findings from this study are expected to contribute to optimizing process parameters for metal AM warpage reduction.

• 한국전자거래학회지
• /
• 제22권1호
• /
• pp.65-87
• /
• 2017

온라인 쇼핑몰에서 상품에 대한 사용자 리뷰와 평점을 분석하여 상품의 특징을 자동으로 추출하고 평점이 어떤 특징에 의해 부여된 것인지 판단하여 각 특징에 분배하여 점수화함으로써 상품의 특징을 파악할 수 있는 방법을 제안한다. 기존 방식은 상품 구매 여부를 결정하기 위해서 많은 리뷰와 평점을 읽는데 시간을 허비하거나, 상품의 장단점을 파악하기 어려울 뿐더러 상품에 부여된 평점이 어떠한 특징에 의해서 부여되었는지 알 수 없는 구조로 되어있다. 따라서 본 논문에서는 이러한 문제를 해소하기 위하여 사용자 리뷰에서 상품의 특징을 자동으로 추출하고 각 특징별 평점을 전체 평점에서 자동으로 분배 계산하여 보여주는 방법을 제안한다. 제안하는 방법은 상품별 리뷰와 평점을 수집하여 형태소 분석을 수행하고 이를 통해 상품의 특징과 이에 대한 감성어를 추출한다. 또한, 상품의 특징을 파악할 수 있도록 각 특징에 대한 가중치를 특징이 출현한 문장의 극성을 판단하여 부여하는 방법을 기술한다. 실험을 통하여 얻은 결과와 기존 방법을 비교하는 설문조사를 통하여 제안하는 방법의 유용성을 입증하였고, 상품 리뷰 전문가의 분석과 실험의 결과를 비교함으로써 타당성을 입증하였다.

• 한국컴퓨터정보학회논문지
• /
• 제21권5호
• /
• pp.119-126
• /
• 2016

Software maintenance becomes extremely difficult, especially caused by multiple versions in project-based or customer-oriented software development methodology. For reducing the maintenance cost, reengineering to software product line can be a solution to the software which either is a family of products nevertheless little different functionalities or are customized for each different customer's requirement. At an initial stage of the reengineering, the most important activity in software product line is feature extraction with respect to commonality and variability from the existing system due to verifying functional coverage. Several researchers have studied to extract features. They considered only a single version in a single product. However, this is an obstacle to classify the commonality and variability of features. Therefore, we propose a method for systematically extracting features from source code and its change history considering several versions of the existing system. It enables us to represent functionalities reflecting developer's intention, and to clarify the rationale of variation.

• 한국CDE학회논문집
• /
• 제12권4호
• /
• pp.245-254
• /
• 2007

This research proposed feature extraction algorithms as an input of STEP Ap214 data, and feature parameterization process to simplify further design change and maintenance. The procedure starts with suppression of blend faces of an input solid model to generate its simplified model, where both constant and variable-radius blends are considered. Most existing cell decomposition algorithms utilize concave edges, and they usually require complex procedures and computing time in recomposing the cells. The proposed algorithm using reference features, however, was found to be more efficient through testing with a few sample cases. In addition, the algorithm is able to recognize depression features, which is another strong point compared to the existing cell decomposition approaches. The proposed algorithm was implemented on a commercial CAD system and tested with selected industrial product models, along with parameterization of recognized features for further design change.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.316-326
• /
• 2022

The prompt development in the field of video is the outbreak of online services which replaces the television media within a shorter period in gaining popularity. The online videos are encouraged more in use due to the captions displayed along with the scenes for better understandability. Not only entertainment media but other marketing companies and organizations are utilizing videos along with captions for their product promotions. The need for captions is enabled for its usage in many ways for hearing impaired and non-native people. Research is continued in an automatic display of the appropriate messages for the videos uploaded in shows, movies, educational videos, online classes, websites, etc. This paper focuses on two concerns namely the first part dealing with the machine learning method for preprocessing the videos into frames and resizing, the resized frames are classified into multiple actions after feature extraction. For the feature extraction statistical method, GLCM and Hu moments are used. The second part deals with the deep learning method where the CNN architecture is used to acquire the results. Finally both the results are compared to find the best accuracy where CNN proves to give top accuracy of 96.10% in classification.

• 한국컴퓨터정보학회논문지
• /
• 제17권9호
• /
• pp.39-47
• /
• 2012

일반적으로 사람들은 특정 상품에 관한 의견을 표현할 때 그 상품이 갖는 개별속성에 대해 긍부정 성향을 표시한다. 어떤 경우에는 상품이 갖는 동질의 개별 속성에 대해 포괄적으로 긍부정 성향을 표현하거나 상품 자체에 대해 표현하기도 한다. 따라서 의견검색 분야에서 추출 대상이 되는 의견 속성명에는 상품의 개별 속성명, 이 개별 속성들을 포함하는 전체어, 그리고 상품명이 존재한다. 그러나 의견 대상을 상품명이나 전체어로 표현할 때, 경우에 따라 의견문장 표면에 나타나는 속성명과 의견 작성자가 의도한 실제 대상이 일치하지 않을 수도 있다. 본 논문에서는 의견문장으로부터 의견 대상을 추출하는 방법을 제시한다. 무엇보다 우리는 의도한 대상과 일치하지 않는 속성명으로부터 의도한 대상을 추출하기 위한 새로운 방법을 제안한다. 제시하는 방법에서는 단어간 의존관계를 이용하여 의견속성 후보쌍을 추출하고, 추출된 후보쌍들 중 의견 대상과 일반적으로 빈번히 불일치하는 속성명을 선택한다. 선택된 속성명을 작성자가 의도한 개별속성으로 변경한 뒤, 이를 포함한 전체 의견속성 후보쌍들로부터 적합한 의견속성을 추출하기 위해 사람들이 관심 있어할만한 순으로 재배열하게 된다.

• 산업경영시스템학회지
• /
• 제22권49호
• /
• pp.11-21
• /
• 1999

The purpose of this study is to present the method to select optimal size for the industrial products which are closely related to human's body size. For this purpose, human factors such as body characteristics, body features, and preference in product selection which needs to be considered in setting standards were analyzed. This analysis is to select optimal size to minimize losses caused by the difference of size between demand by the customers and supply from the manufacturers. Using loss function, repetitive calculation process algorithm by using bisearch method was applied in selecting the sizes of demand and supply which minimize the total expected losses. For cumulative normal distribution probability, IMSL routine DNORDF was used. In case study, comparison has been made between the result which was calculated using presented algorithm and the results calculated by the process currently used by KS and ISO by measuring aged women's body size in human factors side and sorting them through the factor analysis and cluster analysis for feature factor extraction. Thus, they can be used as a basis for establishing industrial product standards.

• 한국자기공명학회논문지
• /
• 제24권4호
• /
• pp.96-103
• /
• 2020

A new NMR method to monitor solvent-localized NMR signals in the two-phase liquid system is suggested. This method based on intermolecular single-quantum coherence (iSQC). Here, we exploited the feature of the local action of distant dipolar field (DDF) effect in order to filter out specific NMR signals dissolved in different solvents. This solvent specific iSQC spectroscopy was carried out on a model two-phase liquid system (D-glucose in water/palmitic acid in chloroform), and showed solvent-localized NMR signals. We believe our approaches might be useful in metabolic analysis such as two-phase liquid extraction scheme for labile chemical species.