• Journal of Digital Convergence
• /
• v.16 no.3
• /
• pp.145-156
• /
• 2018

Unlike the past, when distributors distributed games through retail stores, they are now selling digital content, which is based on online distribution channels. This study analyzes the effects of eWOM (electronic Word of Mouth) on sales volume of game sold on Steam, an online digital content distribution channel. Recently, data mining techniques based on Big Data have been studied. In this study, emotion index of eWOM is derived by emotional analysis which is a text mining technique that can analyze the emotion of each review among factors of eWOM. Emotional analysis utilizes Naive Bayes and SVM classifier and calculates the emotion index through the SVM classifier with high accuracy. Regression analysis is performed on the dependent variable, sales variation, using the emotion index, the number of reviews of each game, the size of eWOM, and the user score of each game, which is a rating of eWOM. Regression analysis revealed that the size of the independent variable eWOM and the emotion index of the eWOM were influential on the dependent variable, sales variation. This study suggests the factors of eWOM that affect the sales volume when Korean game companies enter overseas markets based on steam.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.883-885
• /
• 2005

지지 벡터 기계(Support Vector Machine: SVM)를 이용한 다중부류 분류기법이 최근 활발히 연구되고 있다. SVM은 이진분류기이기 때문에 다중부류 분류를 위해서 다수의 분류기를 구성하고 이들을 효과적으로 결합하는 방법이 필요하다. 본 논문에서는 기존의 정적인 다중분류기 결합 방법과는 달리 포섭구조의 분류모델을 확률에 따라 동적으로 구성하는 방법을 제안한다. 확률적 분류기인 나이브 베이즈 분류기(NB)를 이용하여 입력된 샘플의 각 클래스에 대한 확률을 계산하고, OVA (One-Vs-All) 전략으로 구축된 다중의 SVM을 획득된 확률에 따라 포섭구조로 구성한다. 제안하는 방법은 OVA SVM에서 발생하는 중의적인 상황을 효과적으로 처리하여 고성능의 분류를 수행한다. 본 논문에서는 지문분류 문제에서 대표적인 NIST-4 지문 데이터베이스를 대상으로 제안하는 방법을 적용하여 $1.8\%$의 거부율에서 $90.8\%$의 분류율을 획득하였으며, 기존의 결합 방법인 다수결 투표(Majority vote), 승자독식(Winner-takes-all), 행동지식공간 (Behavior knowledge space), 결정템플릿(Decision template) 등보다 높은 성능을 확인하였다.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.581-587
• /
• 2013

In this paper, we propose a method of sentiment classification which uses Levenshtein distance. We generate BOW(Bag-Of-Word) applying Levenshtein daistance in sentiment features and used it as the training set. Then the machine learning algorithms we used were SVMs(Support Vector Machines) and NB(Naive Bayes). As the data set, we gather 2,385 reviews of movies from an online movie community (Daum movie service). From the collected reviews, we pick sentiment words up manually and sorted 778 words. In the experiment, we perform the machine learning using previously generated BOW which was applied Levenshtein distance in sentiment words and then we evaluate the performance of classifier by a method, 10-fold-cross validation. As the result of evaluation, we got 85.46% using Multinomial Naive Bayes as the accuracy when the Levenshtein distance was 3. According to the result of the experiment, we proved that it is less affected to performance of the classification in spelling errors in documents.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.37-39
• /
• 2006

지지 벡터 기계(Support Vector Machine; SVM)는 기본적으로 이진분류를 위해 고안되었지만, 최근 다양한 분류기 생성전략과 결합전략이 고안되어 다중부류 분류에도 적용되고 있다. 본 논문에서는 OVR(One-Vs-Rest) 전략으로 생성된 SVM을 NB(Naive Bayes) 분류기를 이용하여 동적으로 구성함으로써, OVR SVM을 이용한 다중부류 분류 시스템에서 자주 발생하는 동점을 효과적으로 해결하는 방법은 제안한다. 이 방법을 유전발현 데이터를 이용한 다중부류 암 분류에 적용하였는데, 고차원의 데이터로부터 NB 분류기 구축에 유용한 유전자를 선택하기 위해 Pearson 상관계수를 사용하였다. 14개의 암 유형과 16,063개의 유전발현 수준을 가지는 대표적인 다중부류 암 분류 데이터인 GCM 암 데이터에 적용하여 제안하는 방법의 유용성을 확인하였다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.47 no.10
• /
• pp.738-746
• /
• 2019

Instead of hydraulic actuation systems, an electromechanical actuation system is more efficient in terms of weight, cost, and test evaluation in the thrust vector control of the 7-ton gimbal engine used in the Korea Space Launch Vehicle-II(KSLV-II) $3^{rd}$ stage. The electromechanical actuator is a kind of servo actuator with position feedback and uses a BLDC motor that can operate at high vacuum. In the case of the gimballed rocket engine, a synthetic resonance phenomenon may occur due to a combination of a vibration mode of the actuator itself, a bending mode of the launcher structure, and an inertial load of the gimbals engine. When the synthetic resonance occurs, the control of the rocket attitude becomes unstable. Therefore, the requirements for the stiffness have been applied in consideration of the gimbal engine characteristics, the support structure, and the actuating system. For the 7-ton gimbal engine of the KSLV-II $3^{rd}$ stage, the stiffness requirement of the actuation system is $3.94{\times}10^7N/m$, and the direct drive type electromechanical actuator is designed to satisfy this requirement. In this paper, an equivalent stiffness analysis model of a direct drive electromechanical actuator designed based on the stiffness requirements is proposed and verified by experimental results.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.4
• /
• pp.328-341
• /
• 2017

In the control actuator system of a launch vehicle based on thrust vectoring, the interaction between electro-mechanical position servo and inertial load are combined with the dynamic characteristics of the flexible vehicle support to generate synthetic resonance. This occurred resonance is fed back to the attitude control system and can influence stability of launch vehicle. In this study, we proposed a simulation model to analyze synthetic resonance of electro-mechanical actuation system for thrust vector control and explained the results of simulation and test using dynamic force feedback control which improves dynamic characteristics of servo actuation system by reducing synthetic resonance.

• Annual Conference on Human and Language Technology
• /
• 2003.10d
• /
• pp.7-13
• /
• 2003

인터넷을 통해 생성, 전달되는 문서 량이 급격히 많아짐에 따라, 정보의 접근을 용이하게 하기 위한 문서의 자동 분류 기능이 절실히 요구되고 있다. SVM(Support Vector Machine)은 최근에 문서 분류에 널리 쓰이고 있는 기법으로 다른 분류기에 비하여 좋은 성능을 보여주고 있다. 하지만 SVM은 현재까지 주로 비 계층 평탄화(flat)된 분류 응용에 효과적으로 적용되어 왔다. 이와 달리 본 논문은 문서 분류에 있어서 최종 분류 class를 한번에 출력하는 비 계층 분류보다는, 비슷한 성질을 갖는 class의 집합을 계층적 구조로 묶어 분류하는 계층적 분류 기법이 보다 사람이 이해하기 쉽고 사용하기 편리하며 더 효과적이라는 것을 보이고, 실험을 통해 계층적 분류를 위한 효과적인 SVM분류기를 개발하여 비 계층 분류보다 좋은 분류 성능을 보여 줄 수 있음을 확인한다.

• Applied Chemistry for Engineering
• /
• v.18 no.1
• /
• pp.94-97
• /
• 2007

Carbon nanotubes and nanowires were prepared by methane pyrolysis over Pd(5)/SPK catalyst by changing oxygen molar ratio in a fixed bed flow reactor under atmospheric condition and also analyzed by SEM and TEM. When the $CH_4/O_2$ molar ratio was 1, carbons were not almost deposited on the catalyst bed support, but when it was 2, carbons were deposited as much as plugging reactor. TEM and SEM images for the deposited carbons showed a number of single-walled carbon nanotubes and carbon nanowires. The growth mechanism of carbon nanotubes produced on the catalyst surface was the tip growth mode. It should be played an important role in carbon nanotubes and nanowires produced on the catalyst bed support to formate the carbon growth velocity vectors and nuclei of ring structure of carbon nanowires. SPK carrier was $N_2$ isotherm of IV type with mesopores, and excellent in the thermal stability.

• Journal of KIISE:Software and Applications
• /
• v.32 no.10
• /
• pp.984-989
• /
• 2005

This study aims to identify grammatical relations (GRs) in Korean sentences. The key task is to find the GRs in sentences in terms of such GR categories as subject, object, and adverbial. To overcome this problem, we are fared with the many ambiguities. We propose a statistical model, which resolves the grammatical relational ambiguity first, and then finds correct noun phrases (NPs) arguments of given verb phrases (VP) by using the probabilities of the GRs given NPs and VPs in sentences. The proposed model uses the characteristics of the Korean language such as distance, no-crossing and case property. We attempt to estimate the probabilities of GR given an NP and a VP with Support Vector Machines (SVM) classifiers. Through an experiment with a tree and GR tagged corpus for training the model, we achieved an overall accuracy of $84.8\%,\;94.1\%,\;and\;84.8\%$ in identifying subject, object, and adverbial relations in sentences, respectively.

• Journal of the Korean Society for information Management
• /
• v.25 no.4
• /
• pp.227-243
• /
• 2008

This study investigates an event detection method with the aim of generating an event-focused news summary from a set of news articles on a certain event using a multi-document summarization technique. The event detection method first classifies news articles into the event related topic categories by employing a SVM classifier and then creates event clusters containing news articles on an event by a modified single pass clustering algorithm. The clustering algorithm applies a time penalty function as well as cluster partitioning to enhance the clustering performance. It was found that the event detection method proposed in this study showed a satisfactory performance in terms of both the F-measure and the detection cost.