• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권12호
• /
• pp.553-564
• /
• 2014

본 논문은 지금까지의 소셜미디어 분석과 분석보고서 생성의 세 가지 문제점을 해결하기 위해서 소셜 빅데이터 마이닝에 기반한 이슈분석보고서 자동 생성 시스템을 제안한다. 세 가지 문제점은 분석의 고립성, 전문가의 주관성과 고비용에 기인한 정보의 폐쇄성이다. 시스템은 자연언어 질의분석, 이슈분석, 소셜 빅데이터 분석, 소셜 빅데이터 상관성분석과 자동 보고서 생성으로 구성된다. 생성된 보고서의 유용성을 평가하기 위해, 본 논문에서는 리커트척도를 사용하였고, 빅데이터 분석 전문가 2명이 평가하였다. 평가결과는 리커트 척도 평가에서 보고서의 품질이 비교적 유용하고 신뢰할 수 있는 것으로 평가되었다. 보고서 생성의 저비용, 소셜 빅데이터의 상관성 분석과 소셜 빅데이터 분석의 객관성 때문에, 제안된 시스템이 소셜 빅데이터 분석의 대중화를 선도할 것으로 기대된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 추계학술대회 논문집 학회본부 A
• /
• pp.113-115
• /
• 2000

So far, it was very difficult to simulate the dispersed generation system including PV generation system using EMTP or EMTDC because the source of the dispersed generation system has a particular VI characteristic equation. In this paper, a novel simulation method of PV generation system has proposed and a new solar cell component for EMTDC is also developed. The VI characteristic equation of solar cell is used in order to realize the solar generation system in EMTDC simulation. Consequently the simulation of PV power generation system using field data is realized and acceptable results, which show close match between the real data of PV panel and the simulated data, were obtained.

• Journal of Information Technology Applications and Management
• /
• 제30권6호
• /
• pp.143-155
• /
• 2023

Procedural generation methods based on physical-based materials generate data by algorithms rather than manual through combinations with artist-generated assets based on computer-generated randomness algorithms. For this reason, the procedural generation method is mainly used to produce textures of 3D models in the field of computer graphics because it is easy to obtain the desired quality with little data. This study is a study on physical-based materials and procedural generation methods based on them. Physical-based materials are divided into Metallic/Roughness workflows and Specific/Glossiness workflows. These two methods produce the same results, which are more accurate based on the law of conservation of energy. The procedural generation method allows a natural texture to be obtained very quickly by texturing through a combination of a computer-generated random algorithm and an artist-generated asset based on various maps.

• Communications for Statistical Applications and Methods
• /
• 제30권6호
• /
• pp.589-603
• /
• 2023

Deep generative models target to infer the underlying true data distribution, and it leads to a huge success in generating fake-but-realistic data. Regarding such a perspective, the data attributes can be a crucial factor in the data generation process since non-existent counterfactual samples can be generated by altering certain factors. For example, we can generate new portrait images by flipping the gender attribute or altering the hair color attributes. This paper proposes counterfactual disentangled variational autoencoder generative adversarial networks (CDVAE-GAN), specialized for data attribute level counterfactual data generation. The structure of the proposed CDVAE-GAN consists of variational autoencoders and generative adversarial networks. Specifically, we adopt a Gaussian variational autoencoder to extract low-dimensional disentangled data features and auxiliary Bernoulli latent variables to model the data attributes separately. Also, we utilize a generative adversarial network to generate data with high fidelity. By enjoying the benefits of the variational autoencoder with the additional Bernoulli latent variables and the generative adversarial network, the proposed CDVAE-GAN can control the data attributes, and it enables producing counterfactual data. Our experimental result on the CelebA dataset qualitatively shows that the generated samples from CDVAE-GAN are realistic. Also, the quantitative results support that the proposed model can produce data that can deceive other machine learning classifiers with the altered data attributes.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권12호
• /
• pp.882-891
• /
• 2010

테스트 데이터를 자동으로 생성하기 위한 동적 테스트 데이터 생성에 관한 많은 연구가 이루어졌다. 동적 테스트 데이터 생성 방법은 가공 테스트 대상 프로그램(SUT; Software Under Test)을 실행시켜 기존의 테스트 데이터의 적합도를 평가하고, 평가된 적합도 값과 최적의 알고리즘을 이용하여 새로운 테스트 데이터를 생성하는 방법이다. 최근에 전역 최적화 알고리즘을 이용한 동적 테스트 데이터 생성에 관한 많은 연구가 이루어져 왔고, 이 알고리즘을 통해서 테스트 대상 프로그램 (SUT)의 커버리지를 높일 수 있는 데이터를 생성할 수 있다는 것이 실험적으로 밝혀졌다. 그러나 최적화 알고리즘은 오랜 연산 시간이 필요하기 때문에, 이를 이용한 방법은 테스트 데이터를 생성하기 위해 많은 시간이 걸린다는 단점이 있다. 본 논문에서는 최적화 알고리즘을 이용한 동적 테스트 데이터 생성의 시간을 줄이기 위하여, 최적화 알고리즘의 절차 중 적합도 평가 시간을 줄이는 방법을 제안한다. 이를 위하여 SUT의 테스트 목표 경로로 부터 생성된 적합도 평가 프로그램(FEP)을 정의하고, 가공 SUT 실행하는 대신 소개된 FEP를 이용한 적합도 평가 방법을 제안하고 'ConGA'라는 도구를 구현한다. 그리고 C언어로 작성된 프로그램을 'ConGA'를 이용하여, 테스트 데이터 생성 효율성을 확인하였다. 이 실험을 통하여 제안된 방법이 기존의 방법보다 테스트 데이터 생성에 걸린 시간을 평균적으로 약 20% 줄인 것을 확인할 수 있었다.

• 유통과학연구
• /
• 제17권10호
• /
• pp.61-71
• /
• 2019

Purpose - This study aims to explore the impact of factors on Korean consumer goods purchase decision of Vietnam's Generation Z. Research design, data, and methodology - A mixed research method was utilized in this study including focus group, in-depth interview, pilot study, and official study. The conceptual model and hypothesis were tested using data collected cross-sectional by questionnaire, from a sample of 439 respondents, by both electronic and paper surveys with non-probability and convenience sampling. The SPSS 20 and AMOS 20 software were employed to analyze the data. Results - Results showed that Vietnam's Generation Z was strongly impacted by social media, Hallyu, country of origin, social norms, and perceived usefulness. Besides, Korean consumer goods purchase decision of Vietnam's Generation Z also were impacted by intermediary factors such as trust, social norms, product involvement, perceived quality, perceived usefulness, attitude, and buying intention. There were differences in factors affecting the purchase decision of the boy and girl Generation Z group. Conclusions - The factors impacting on Korean consumer goods decision of Vietnam's Generation Z are very important for Korean firms and government. The findings provide Korean firms opportunity for appropriate to be carried out factors impacting Korean consumer goods to generation Z in Vietnam successful.

• 한국철도학회논문집
• /
• 제18권5호
• /
• pp.481-488
• /
• 2015

현재 통행발생량 산정 등 교통계획 정보의 생성 체계가 기존 조사 중심 체계에서 외부 데이터를 접목하여 조사 비용을 저감시키고 정확성을 높이는 방향으로 전환되고 있다. 우리나라는 인구보다 많은 휴대전화가 보급되어 있기 때문에 이로부터 구축된 무선통신 자료는 교통계획에 매우 유용한 정보를 줄 수 있을 것이다. 본 연구에서는 이동통신사에서 제공하는 수도권 지역 성 연령별 유동인구 자료로부터 교통계획의 중요한 자료인 통행발생량을 산정하기 위한 방안을 제시하고 이를 KTDB의 통행발생량과 상관성 분석을 통하여 자료의 활용 가능성을 확인하였다. 그 결과 무선통신 자료를 이용한 통행발생량 추정은 기존의 KTDB에서 구축한 직접 조사 방식 기반에 의한 결과와 매우 높은 상관관계를 가지는 것으로 분석되었다.

• 한국BIM학회 논문집
• /
• 제10권4호
• /
• pp.11-21
• /
• 2020

With increasing interest and research on smart cities, there is also an increasing number of studies on urban facilities that can be built within smart cities. According to these studies, smart cities' urban facilities are likely to become high value-added industries. However, the concept of smart city is not clear because it involves various fields. Therefore, in this study, the definition of Next-Generation(N.G) Smart City Facilities with Digital Twin and Digital Chain is carried out through a multidisciplinary approach. Based on this, Next-Generation Smart City Facilities will be divided into High Value-Added Products and Big Data Platforms. Subsequently, the definition of the Digital Chain containing the data flow of the entire process built through the construction of the Digital Twin proceeds. The definitions derived are applied to the Next-Generation Noise Barrier Tunnel to ensure that data is exchanged at the Digital Twin stage, and to review the proposed configuration of the Digital Chain and Data Flow in this study. The platform definition and Digital Chain of Next-Generation Smart City Facilities proposed in this study suggest that it can affect not only the aspects of data management that are currently in the spotlight, but also the manufacturing industry as a whole.

• Journal of Construction Engineering and Project Management
• /
• 제3권3호
• /
• pp.23-34
• /
• 2013

As climate change and environmental pollution become one of the biggest global issues today, new renewable energy, especially solar photovoltaic (PV) system, is getting great attention as a sustainable energy source. However, initial investment cost of PV system is considerable, and thus, it is crucial to predict electricity generation accurately before installation of the system. This study analyzes the loss ratio of solar photovoltaic electricity generation from the actual PV system monitoring data to predict electricity generation more accurately in advance. This study is carried out with the following five steps: (i) Data collection of actual electricity generation from PV system and the related information; (ii) Calculation of simulation-based electricity generation; (iii) Comparative analysis between actual electricity generation and simulation-based electricity generation based on the seasonality; (iv) Stochastic approach by defining probability distribution of loss ratio between actual electricity generation and simulation-based electricity generation ; and (v) Case study by conducting Monte-Carlo Simulation (MCS) based on the probability distribution function of loss ratio. The results of this study could be used (i) to estimate electricity generation from PV system more accurately before installation of the system, (ii) to establish the optimal maintenance strategy for the different application fields and the different season, and (iii) to conduct feasibility study on investment at the level of life cycle.

• 국제학술발표논문집
• /
• The 5th International Conference on Construction Engineering and Project Management
• /
• pp.375-385
• /
• 2013

As climate change and environmental pollution become one of the biggest global issues today, new renewable energy, especially solar photovoltaic (PV) system, is getting great attention as a sustainable energy source. However, initial investment cost of PV system is considerable, and thus, it is crucial to predict electricity generation accurately before installation of the system. This study analyzes the loss ratio of solar photovoltaic electricity generation from the actual PV system monitoring data to predict electricity generation more accurately in advance. This study is carried out with the following five steps: (i) Data collection of actual electricity generation from PV system and the related information; (ii) Calculation of simulation-based electricity generation; (iii) Comparative analysis between actual electricity generation and simulation-based electricity generation based on the seasonality; (iv) Stochastic approach by defining probability distribution of loss ratio between actual electricity generation and simulation-based electricity generation ; and (v) Case study by conducting Monte-Carlo Simulation (MCS) based on the probability distribution function of loss ratio. The results of this study could be used (i) to estimate electricity generation from PV system more accurately before installation of the system, (ii) to establish the optimal maintenance strategy for the different application fields and the different season, and (iii) to conduct feasibility study on investment at the level of life cycle.