• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.93-99
• /
• 2006

Ontology is an indispensable component in intelligent and semantic processing of knowledge and information, such as in semantic web. Ontology is considered to be constructed generally on the basis of taxonomy of human concepts about the world. However. as human concepts are unstructured and obscure, ontology construction based on the taxonomy of human concepts cannot be realized systematically furthermore automatically. So, we try to do this from the relation among linguistic symbols regarded representing human concepts, in short, words. We show the similarity between taxonomy of human concepts and relation among words. And we propose a methodology to construct and generate automatically ontologies from these relations mon words and a series of algorithm to convert these relations into ontologies. This paper presents the process and concrete application of this methodology.

• Journal of Korean Society of Archives and Records Management
• /
• v.20 no.4
• /
• pp.1-17
• /
• 2020

Along with the development of information technology, the digitalization of archives has also been accelerating. However, digital archives have limitations in effectively searching, interlinking, and understanding records. In response to these issues, this study proposes a knowledge graph that represents comprehensive relationships among heterogeneous entities in digital archives. In this case, the knowledge graph organizes resources in the archives on the Korean financial crisis of 1997 by transforming them into named entities that can be discovered by machines. In particular, the study investigates and creates an overview of the characteristics of the archives on the Korean financial crisis as a digital archive. All resources on the archives are described as entities that have relationships with other entities using semantic vocabularies, such as Records in Contexts-Ontology (RiC-O). Moreover, the knowledge graph of the Korean Financial Crisis of 1997 is represented by resource description framework (RDF) vocabularies, a machine-readable format. Compared to conventional digital archives, the knowledge graph enables users to retrieve a specific entity with its semantic information and discover its relationships with other entities. As a result, the knowledge graph can be used for semantic search and various intelligent services.

• Journal of the Ergonomics Society of Korea
• /
• v.31 no.4
• /
• pp.507-513
• /
• 2012

Objective: This study developed a hierarchy of conditions of applications(devices), situations and functions which are applicable to gesture interface. Background: Gesture interface is one of the promising interfaces for our natural and intuitive interaction with intelligent machines and environments. Although there were many studies related to developing new gesture-based devices and gesture interfaces, it was little known which applications, situations and functions are applicable to gesture interface. Method: This study searched about 120 papers relevant to designing and applying gesture interfaces and vocabulary to find the gesture applicable conditions of applications, situations and functions. The conditions which were extracted from 16 closely-related papers were rearranged, and a hierarchy of them was developed to evaluate the applicability of applications, situations and functions to gesture interface. Results: This study summarized 10, 10 and 6 conditions of applications, situations and functions, respectively. In addition, the gesture applicable condition hierarchy of applications, situation and functions were developed based on the semantic similarity, ordering and serial or parallel relationship among them. Conclusion: This study collected gesture applicable conditions of application, situation and functions, and a hierarchy of them was developed to evaluate the applicability of gesture interface. Application: The gesture applicable conditions and hierarchy can be used in developing a framework and detailed criteria to evaluate applicability of applications situations and functions. Moreover, it can enable for designers of gesture interface and vocabulary to determine applications, situations and functions which are applicable to gesture interface.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.2
• /
• pp.48-55
• /
• 2020

Recently, a study of prognosis and health management (PHM) was conducted to diagnose failure and predict the life of air craft engine parts using sensor data. PHM is a framework that provides individualized solutions for managing system health. This study predicted the remaining useful life (RUL) of aeroengine using degradation data collected by sensors provided by the IEEE 2008 PHM Conference Challenge. There are 218 engine sensor data that has initial wear and production deviations. It was difficult to determine the characteristics of the engine parts since the system and domain-specific information was not provided. Each engine has a different cycle, making it difficult to use time series models. Therefore, this analysis was performed using machine learning algorithms rather than statistical time series models. The machine learning algorithms used were a random forest, gradient boost tree analysis and XG boost. A sliding window was applied to develop RUL predictions. We compared model performance before and after applying the sliding window, and proposed a data preprocessing method to develop RUL predictions. The model was evaluated by R-square scores and root mean squares error (RMSE). It was shown that the XG boost model of the random split method using the sliding window preprocessing approach has the best predictive performance.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.453-460
• /
• 2005

P2P(Peer to Peer) 기술은 잠재적 능력에도 불구하고 컨텐츠의 저작권문제와 보안문제 등으로 인하여 많은 사람들이 충분히 활용하지 못하고 있다. 본 연구는 인터넷 사용자(개인)와 소규모 서버를 운영하는 조직들이 정보 제공, 분배, 공유의 정보시스템 구조를 자신들의 목적에 맞게 자유롭게 만들 수 있는 프레임워크인 오픈웨어 (Openware)의 개발에 관한 것이다. 오픈웨어는 P2P기반 시스템으로 다음과 같은 특징올 갖는다. 1) 다수의 서버와 클라이언트로 이루어지는 구조로, 사용자의 목적에 맞게 집중형 혹은 분산형 구조를 자유롭게 혼합하여 정보시스템을 구성 할 수 있다. 이러한 정보 구조의 유연성은 다양한 형태의 협업(개인과 개인, 개인과 그룹, 그룹과 그룹)이 요구되는 응용 시스템의 기반을 제공한다. 2) 데이터 관점에서 오픈웨어는 개인이 데이터베이스를 손쉽게 생성, 관리 할 수 있고, 자신의, 데이터 혹은 데이터베이스 구조를 다른 사람이나 그룹과 공유 하거나 통합 할 수 있다. 3) 데이터 통신면에서 오픈웨어는 HTTP(HyperText Transfer Protocol) 프로토콜만을 사용하는 웹 기반 시스템으로 인터넷에 연결 되어있는 누구와도 오픈웨어를 통해 협업이 가능하다. 4) 소프트웨어 이름에서 알 수 있듯이 오픈웨어는 Java, JSP, Apache, Resin등 공개소프트어로 만들어져 있고, 오픈웨어 자체도 공개소프트웨어이다. 오픈웨어는 개인과 그룹의 흠페이지 생성과 관리, 파일 공유 기능이 구현 되어있고, 데이터베이스 공유, 통합 기능을 이용하여 개인이나 그룹의 주소록관리, 일정관리 등이 가능하다. 오픈웨어는 사용자 흑은 개발자가 다양한 형태의 응용컴포넌트를 자유롭게 등록하여 기능을 추가 할 수 있는 확장성올 제공하고 있어서, 앞으로 e-메일, 매신저, 전자결재, 지식관리시스템, 인터넷 방송 시스템의 기반 구조 역할을 할 수 있다. 현재 오픈웨어에 적용하기 위한 P2P 기반의 지능형 BPM(Business Process Management)에 관한 연구와 X인터넷 기술을 이용한 RIA (Rich Internet Application) 기반 웹인터페이스 연구를 진행하고 있다.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.139-148
• /
• 2006

In the collaborative product design environment, the communication between designers is important to capture design intents and to share a common view among the different but semantically similar terms. The Semantic Web supports integrated and uniform access to information sources and services as well as intelligent applications by the explicit representation of the semantics buried in ontology. Ontologies provide a source of shared and precisely defined terms that can be used to describe web resources and improve their accessibility to automated processes. Therefore, employing ontologies on assembly modeling makes assembly knowledge accurate and machine interpretable. In this paper, we propose a framework of semantic assembly modeling using ontologies to share design information. An assembly modeling ontology plays as a formal, explicit specification of a shared conceptualization of assembly design modeling. In this paper, implicit assembly constraints are explicitly represented using OWL (Web Ontology Language) and SWRL (Semantic Web Rule Language). The assembly ontology also captures design rationale including joint intent and spatial relationships.

• Journal of Intelligence and Information Systems
• /
• v.13 no.4
• /
• pp.121-135
• /
• 2007

Constraint directed scheduling techniques, representing problem constraints explicitly and constructing schedules by constrained heuristic search, have been successfully applied to real world scheduling problems that require satisfying a wide variety of constraints. However, there has been little basic research on the representation and optimization of the objective value of a schedule in the constraint directed scheduling literature. In particular, the cost objective is very crucial for enterprise decision making to analyze the effects of alternative business plans not only from operational shop floor scheduling but also through strategic resource planning. This paper aims to explicitly represent and optimize the total cost of a schedule including the tardiness and inventory costs while satisfying non-relaxable constraints such as resource capacity and temporal constraints. Within the cost based scheduling framework, a cost propagation algorithm is presented to update cost information throughout temporal constraints within the same job.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.3
• /
• pp.50-63
• /
• 2021

There has been a steady rate of accident in Coal Thermal Power Plants which have relatively higher chance of mortality. However, neither the systematic view of safety management nor the methodology such as safety factors or system requirements are yet to be studied in detail. Therefore, this study aims to propose a methodology to preemptively deal with safety issues and to secure fact focused responsibility in safety. It consists of two main parts. First, the Safety Measurement Index(SMI) with total 50 factors is proposed by analyzing the key factors that contribute to safety accidents based on failure mode and effect analysis (FMEA) and quality function deployment (QFD). To analyze the safety requirements, index presented by major countries and organizations are discussed. Second, main features of intelligent CCTV are studied to determine their relative importance for the framework of Smart Safety Management System (SSMS). Main features are discussed with four technological steps. Also, QFD was held to analyze to analyze how key technologies deal with Quality Measurement Index(QMI). The research results of this study reveal that scientific approaches could be utilized in integrating CCTV technologies into a smart safety management system in the era of Industry 4.0. Moreover, this reasearch provides an specific approach or methodology for dealing with safety management in Coal Thermal Power Plant.

• Healthcare Informatics Research
• /
• v.24 no.4
• /
• pp.309-316
• /
• 2018

Objectives: Both the valence and arousal components of affect are important considerations when managing mental healthcare because they are associated with affective and physiological responses. Research on arousal and valence analysis, which uses images, texts, and physiological signals that employ deep learning, is actively underway; research investigating how to improve the recognition rate is needed. The goal of this research was to design a deep learning framework and model to classify arousal and valence, indicating positive and negative degrees of emotion as high or low. Methods: The proposed arousal and valence classification model to analyze the affective state was tested using data from 40 channels provided by a dataset for emotion analysis using electrocardiography (EEG), physiological, and video signals (the DEAP dataset). Experiments were based on 10 selected featured central and peripheral nervous system data points, using long short-term memory (LSTM) as a deep learning method. Results: The arousal and valence were classified and visualized on a two-dimensional coordinate plane. Profiles were designed depending on the number of hidden layers, nodes, and hyperparameters according to the error rate. The experimental results show an arousal and valence classification model accuracy of 74.65 and 78%, respectively. The proposed model performed better than previous other models. Conclusions: The proposed model appears to be effective in analyzing arousal and valence; specifically, it is expected that affective analysis using physiological signals based on LSTM will be possible without manual feature extraction. In a future study, the classification model will be adopted in mental healthcare management systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.