• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• Asia pacific journal of information systems
• /
• 제6권2호
• /
• pp.125-148
• /
• 1996

This paper is primarily focused on the function of model management systems such as higher level representations and buildings of optimization models using them, especially in the area of the telecommunication network models. This research attempts to provide the model builders an intuitive language-namely higher level representation-using five distinctivenesses : Objective, Node, Link, Topological Constraint including five components, and Decision. The paper elaborates all components included in each of distinctivenesses extracted from structural characteristics of typical telecommunication network models. Higher level representations represented with five distinctivenesses should be converted into base level representations which are employed for semantic representations of linear and integer programming problems in knowledge: assisted optimization modeling system(UNIK-OPT). Furthermore, for formulating the network model using higher level representations, the reasoning process is proposed. A system called UNIK-NET is developed to implement the approach proposed in this research, and the system is illustrated with an example of the network model.

• 디지털산업정보학회논문지
• /
• 제5권2호
• /
• pp.1-11
• /
• 2009

This study presents HCWS algorithm for researcher grouping on a weighted researcher network. The weights represent intensity of connections among researchers based on the number of co-authors and the number of co-authored research papers. To confirm the validity of the proposed technique, this study conducted an experimentation on about 80 research papers. As a consequence, it is proved that HCWS algorithm is able to bring about more realistic clustering compared with HCS algorithm which presents semantic relations among researchers in simple connections. In addition, it is found that HCWS algorithm can address the problems of existing HCS algorithm; researchers are disconnected since their connections are classified as weak even though they are strong, and vise versa. The technique described in this research paper can be applied to efficiently establish social networks of researchers considering relations such as collaboration histories among researchers or to create communities of researchers.

• 경영과학
• /
• 제14권1호
• /
• pp.205-227
• /
• 1997

Higher level representation splay an important role in model management systems. The role is to make decision makers friendly represent their problem using the representations. In this research, we address higher level representations including five distinctivenesses: Objective, Node, Link, Topological Constraint including five components, and Decision, Therefore, it is developed a system called HLRNET that implements the building procedure of network models using structural knowledge and object data The paper particularly elaborates all components included in each of distinctiveness extracted from structural characteristics of a lot of telecommunication network models. Higher level representations represented with five destinctivenesses should be converted into base level representations which are employed for semantic representations of linear and integer programming problems in a knowledge-assisted optimization modeling system. The system is illustrated with an example of the local access network model.

• 한국IT서비스학회지
• /
• 제13권2호
• /
• pp.173-184
• /
• 2014

As social network services has become one of the most successful web-based business, recommendation in social network sites that assist people to choose various products and services is also widely adopted. Collaborative Filtering is one of the most widely adopted recommendation approaches, but recommendation technique that use explicit or implicit social network information from social networks has become proposed in recent research works. In this paper, we reviewed and compared research works about recommendation using social network analysis and collaborative filtering in social network sites. As the results of the analysis, we suggested the trends and implications for future research of recommendation in SNSs. It is expected that graph-based analysis on the semantic social network and systematic comparative analysis on the performances of social filtering and collaborative filtering are required.

• 전기전자학회논문지
• /
• 제11권4호
• /
• pp.279-282
• /
• 2007

In this paper, we introduce the general way for producing context information to support context-aware applications. It can fetch raw data from the service environments, translate it to reasonable context information, and provide to multiple applications. It is designed originally for the ubiquitous computing middleware and based on the ontology processing model. Automated service applications can use this system as the form of libraries or of web services for deciding its semantic cause of action.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 1994년도 제6회 한글 및 한국어정보처리 학술대회
• /
• pp.326-332
• /
• 1994

본 연구에서는 중사전 규모의 현대국어사전에서 약 5,000 개의 표제항목의 뜻풀이 8,000여 항에 사용된 어휘를 분석한 결과를 제시하였다. 분석 결과 명사류의 의미구조에서 최상위계층에 속하는 것들이 사전의 뜻풀이에 자주 사용됨을 확인할 수 있었고, 아울러 뜻풀이에 사용되는 단어들이 어느 정도 통제된 상태임을 알 수 있었다. 그러나 표제항목과 뜻풀이에 사용된 단어들 사이의 관계만을 바탕으로 해서는 의미망을 구축하기 어려웠는데, 그것은 국어사전에서의 뜻풀이가 지니고 있는 구조적 문제에서 기인하는 것이다. 즉 일부 한자어의 경우에는 명사로 정의되지 않으며, 그 결과 표제명사와 뜻풀이에 사용된 명사 사이의 관계를 바탕으로 한 의미망의 구축에 포함되지 않는 것이다. 또한 순환적 뜻풀이의 경우 역시 의미망 구축에 장애요소로 작용함을 밝혔다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2011년도 한국컴퓨터종합학술대회논문집 Vol.38 No.1(C)
• /
• pp.266-268
• /
• 2011

스마트폰을 비롯한 모바일 기기에 내장된 다양한 센서들로부터 수집되는 개인의 일상에 대한 정보인 모바일 라이프로그를 관리하고 검색하는 다양한 연구가 진행되고 있다. 기존에는 에피소딕 메모리 형태로 저장된 모바일 라이프로그 상에서 사용자가 과거 정보를 찾고 회상하는 방법이 일반적으로 사용되었다. 이러한 방법에서는 사용자가 원하는 데이터를 찾기 위해서는 정확하고 충분한 데이터를 사전에 알고 있어야 한다. 하지만 사람은 처음부터 완전한 정보를 가지고 검색을 하는 것이 아니고 검색을 수행하면서 데이터간의 연관도를 바탕으로 추가적인 정보를 떠올리는 연관 검색을 수행한다. 본 논문에서는 연관도 기반 검색을 위해 인지구조를 바탕으로 모바일 라이프로그를 표현하는 시맨틱 네트워크를 자동으로 생성하는 방법을 제안한다. 정의된 구조를 바탕으로 네트워크를 구성하고 관계의 빈도수와 가중치 공유를 통하여 관계의 가중치를 학습한다. 구성된 시맨틱 네트워크상에서 활성화 확산을 기반으로 연관 검색을 수행함으로 방법의 유용성을 입증하였다.

• 감성과학
• /
• 제8권1호
• /
• pp.1-7
• /
• 2005

This paper reports several emotion detecting methods based on various attributes of human voice. These methods have been developed at our Engineering Systems Laboratory. It is noted that, in all of the proposed methods, only prosodic information in voice is used for emotion recognition and semantic information in voice is not used. Different types of neural networks(NNs) are used for detection depending on the type of voice parameters. Earlier approaches separately used linear prediction coefficients(LPCs) and time series data of pitch but they were combined in later studies. The proposed methods are explained first and then evaluation experiments of individual methods and their performances in emotion detection are presented and compared.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2115-2127
• /
• 2021

Although significant progress has been made in synthesizing visually realistic face images by Generative Adversarial Networks (GANs), there still lacks effective approaches to provide fine-grained control over the generation process for semantic facial attribute editing. In this work, we propose a novel cross channel self-attention based generative adversarial network (CCA-GAN), which weights the importance of multiple channels of features and archives pixel-level feature alignment and conversion, to reduce the impact on irrelevant attributes while editing the target attributes. Evaluation results show that CCA-GAN outperforms state-of-the-art models on the CelebA dataset, reducing Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) by 15~28% and 25~100%, respectively. Furthermore, visualization of generated samples confirms the effect of disentanglement of the proposed model.