• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.9
• /
• pp.904-917
• /
• 2010

Much research on ontology has been done during the last decade in order to represent knowledge and connect data semantically in AI and Semantic Web areas. However, ontologies might be represented and defined in different ways depending on knowledge and intention of users. It causes heterogeneity problem that the same concept can be differently expressed. This paper introduces a XOB (XMDR-based Ontology Builder) system based on XMDR to resolve the problem. XOB creates ontologies by reusing classes and relations defined in XMDR. XOB therefore is able to either solve or minimize the heterogeneity problem among ontologies. This paper introduces the conceptual model and overall architecture of the proposed system XOB. This paper defines the process, algorithm, ontology generation rule that is required to create ontologies by using concepts registered in XMDR. Our proposal supports higher standardization than the previous approaches, and it provides many advantages such as consistent concept usage, easy semantic exchange, and so on. Therefore, XOB enables high-quality ontology creation and reduces cost for ontology integration and system development.

• Journal of Internet Computing and Services
• /
• v.20 no.2
• /
• pp.93-100
• /
• 2019

Recently, in various business fields, companies are concentrating on providing chatbot services to various environments by adding artificial intelligence to existing messenger platforms. Organizations in the field of job placement also require chatbot services to improve the quality of employment counseling services and to solve the problem of agent management. A text-based general chatbot classifies input user sentences into learned sentences and provides appropriate answers to users. Recently, user sentences inputted to chatbots are inputted as short texts due to the activation of social network services. Therefore, performance improvement of short text classification can contribute to improvement of chatbot service performance. In this paper, we propose T-EBOW (Translation-Extended Bag Of Words), which is a method to add translation information as well as concept information of existing researches in order to strengthen the short text classification for employment chatbot. The performance evaluation results of the T-EBOW applied to the machine learning classification model are superior to those of the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.115-123
• /
• 2021

Manufacturing execution system is a factory information system that handles production-related quality data as well as executes production plans of process unit for all resources in the production process on site. As the 4th industrial revolution, which maximizes an automation and connectivity with artificial intelligence, has become a hot topic, manufacturers are showing interest in building a smart factories, but enormous construction costs and unstandardized production processes are obstacles to smart factory construction. Therefore, this paper designs and implements a manufacturing execution system for building a smart factory in a deterioration factory. we propose a Web-based manufacturing execution system aiming at a smart factory at the basic level for steel wire processing. The proposed system will smoothly support interworking with the existing ERP system using REST APIs, and will consider extensibility so that it can be used in various devices and browsers. We will show practicality by implementing the proposed WoT-based manufacturing execution system.

• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.163-172
• /
• 2020

Recently, concepts of the Fourth Industrial Revolution technologies such as artificial intelligence, big data, and cloud computing have been introduced and the limits of individual or team development policies are being reviewed. Also, a lot of latest technology source codes have been opened to the public, and related studies are being conducted based on them. Meanwhile, the company is applying the strengths of the open source software development methodology to proprietary software development, and publicly announcing support for open source development methodology. In this paper, we introduced several software development methodology such as open source model, inner source model, and the similar DevOps model, which have been actively discussed recently, and compared their characteristics and components. Rather than claiming the excellence of a specific model, we argue that if the software development policy of an individual or affiliated organization is established according to each benefit, they will be able to achieve software quality improvement while satisfying customer requirements.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.92-98
• /
• 2022

Identifying defects in textiles is a key procedure for quality control. This study attempted to create a model that detects defects by analyzing the images of the fabrics. The models used in the study were deep learning-based VGGNet and ResNet, and the defect detection performance of the two models was compared and evaluated. The accuracy of the VGGNet and the ResNet model was 0.859 and 0.893, respectively, which showed the higher accuracy of the ResNet. In addition, the region of attention of the model was derived by using the Grad-CAM algorithm, an eXplainable Artificial Intelligence (XAI) technique, to find out the location of the region that the deep learning model recognized as a defect in the fabric image. As a result, it was confirmed that the region recognized by the deep learning model as a defect in the fabric was actually defective even with the naked eyes. The results of this study are expected to reduce the time and cost incurred in the fabric production process by utilizing deep learning-based artificial intelligence in the defect detection of the textile industry.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.457-460
• /
• 2021

대화 시스템은 인공지능과 사람이 자연어로 의사 소통을 하는 시스템으로 크게 목적 지향 대화와 일상대화 시스템으로 연구되고 있다. 목적 지향 대화 시스템의 경우 날씨 확인, 호텔 및 항공권 예약, 일정 관리 등의 사용자가 생활에 필요한 도메인들로 이루어져 있으며 각 도메인 별로 목적에 따른 시나리오들이 존재한다. 이러한 대화는 사용자에게 명확한 발화을 제공할 수 있으나 자연스러움은 떨어진다. 일상 대화의 경우 다양한 도메인이 존재하며, 시나리오가 존재하지 않기 때문에 사용자에게 자연스러운 발화를 제공할 수 있다. 또한 일상 대화의 경우 검색 기반이나 생성 기반으로 시스템이 개발되고 있다. 검색 기반의 경우 발화 쌍에 대한 데이터베이스가 필요하지만, 생성 기반의 경우 이러한 데이터베이스가 없이 모델의 Language Modeling (LM)으로 부터 생성된 발화에 의존한다. 따라서 모델의 성능에 따라 발화의 품질이 달라진다. 최근에는 사전학습 모델이 자연어처리 작업에서 높은 성능을 보이고 있으며, 일상 대화 도메인에서도 역시 높은 성능을 보이고 있다. 일상 대화에서 가장 높은 성능을 보이고 있는 사전학습 모델은 Auto Regressive 기반 생성모델이고, 한국어에서는 대표적으로 KoGPT2가 존재한다. 그러나, KoGPT2의 경우 문어체 데이터만 학습되어 있기 때문에 대화체에서는 낮은 성능을 보이고 있다. 본 논문에서는 대화체에서 높은 성능을 보이는 한국어 기반 KoDialoGPT2를 개발하였고, 기존의 KoGPT2보다 높은 성능을 보였다.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.139-152
• /
• 2022

Engineering's work area for plants is a technical area that directly affects productivity, performance, and quality throughout the lifecycle from planning, design, construction, operation and disposal. Using the different types of data that occur to make decisions is important not only in the subsequent process but also in terms of cyclical cost reduction. However, there is a lack of systems to manage and analyze these integrated data. In this paper, we developed a knowledge base-based plant engineering analysis platform that can manage and utilize data. The platform provides a knowledge base that preprocesses previously collected engineering data, and provides analysis and visualization to use it as reference data in AI models. Users can perform data analysis through the use of prior technology and accumulated knowledge through the platform and use visualization in decision-support and systematically manage construction that relied only on experience.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.4
• /
• pp.69-78
• /
• 2023

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.5
• /
• pp.47-53
• /
• 2023

With the advent of the 4th Industrial Revolution, diverse and a large amount of data has been accumulated now. The agricultural community has also collected environmental data that affects the growth of crops in smart farms or open fields with sensors. Environmental data has different features depending on where and when they are measured. Studies have been conducted using collected agricultural data to predict growth and yield with statistics and artificial intelligence. The results of these studies vary greatly depending on the data on which they are based. So, studies to enhance data quality have also been continuously conducted for performance improvement. A lot of data is required for high performance, but if there are outlier or missing values in the data, it can greatly affect the results even if the amount is sufficient. So, adjustment of outlier and missing values is essential in the data preprocessing. Therefore, this paper integrates data collected from actual farms and proposes a adjustment system for outlier and missing values based on it.

• Journal of the Society of Naval Architects of Korea
• /
• v.32 no.4
• /
• pp.136-141
• /
• 1995

Determination and optimization of proper welding condition are very important tasks to be directly related to weld quality and productivity. On this research the relationship between welding parameters and results is investigated systematically. Theoretical method, statistical analysis of experimental data and analysis of empirical knowledge are applied for this work. These results are represented by empirical equations, fuzzy rules and artificial intelligent knowledge forms in the knowledge base. The approximate reasoning of fuzzy expert system and the information in the knowledge base are used for recommendation of suitable welding condition, and optimization of welding parameter which is based on the evaluation of welding results by user.