• Knowledge Management Research
• /
• v.16 no.4
• /
• pp.69-87
• /
• 2015

Given the huge number of data produced by its users, SNS is a great source of customer insights. Since viral trends in SNS reflect customers' direct feedback, companies can draw out highly meaningful business insights when such data is effectively analyzed and managed. However, while the importance of understanding SNS big data keeps growing, the methods for analyzing atypical data such as SNS postings for business insights over product has not been well studied. This study aims to demonstrate the way to exploit topic modeling method to support marketing strategy generation and therefore leverage business process. First, we conducted topic modeling analysis for twitter data of Apple and Samsung smartphones. Then we comparatively examined the analysis results to draw meaningful market insights about each smartphone product. Finally, we draw out a strategic marketing recommendation for each smartphone brand based on the findings.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.430-433
• /
• 2018

딥러닝 모델의 성능 향상을 위해 적은 데이터를 증가시킬 수 있는 연구들이 필요하다. 이미지의 경우 회전, 이동, 반전등의 연산으로 쉽게 데이터를 증가시킬 수 있지만 자연어는 그렇지 않다. 그러나 최근 딥러닝 생성 모델의 발전으로 기존 자연어 데이터를 생성 모델을 통해 양을 늘려 실험하는 연구들이 많이 시도되었다. 본 논문에서는 문장 데이터 생성을 위한 VAE, 문장 분류를 위한 CNN이 결합된 모델을 한국어 영화평 데이터에 적용하여 기존 모델보다 0.146% 높은 86.736%의 정확도를 기록하였다.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.623-626
• /
• 2018

한국어 학습에 대한 관심이 전 세계적으로 높아짐에 따라 한국어 학습을 위한 다양한 프로그램들이 등장하고 있다. 한국어가 모국어가 아닌 외국인들의 한국어 학습을 위해서는 단어 학습이 기초가 되어야 하며, 단어 학습에서는 다양한 예문들이 필수적이다. 기존의 학습 시스템에서는 말뭉치에 있는 문장들을 예문으로 제시하는 기능을 제공하지만, 이 경우 한정적이고 반복된 문장만을 제공하는 문제를 가진다. 본 논문에서는 사용자가 학습하고자 하는 단어를 입력하면 해당 단어 단어를 포함하는 한국어 문장을 자동 생성하여 제공하는 시스템을 제안한다. 시스템에서는 언어 모델의 제어가 비교적 쉬운 마르코프체인을 활용한다.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2001.10a
• /
• pp.1-9
• /
• 2001

scale genomic and postgenomic data means that many of the challenges in biomedical research are now challenges in computational sciences and information technology. The informatics revolutions both in clinical informatics and bioinformatics will change the current paradigm of biomedical sciences and practice of clinical medicine, including diagnostics, therapeutics, and prognostics. Postgenome informatics, powered by high throughput technologies and genomic-scale databases, is likely to transform our biomedical understanding forever much the same way that biochemistry did a generation ago. In this talk, 1 will describe how these technologies will in pact biomedical research and clinical care, emphasizing recent advances in biochip-based functional genomics. Basic data preprocessing with normalization and filtering, primary pattern analysis, and machine teaming algorithms will be presented. Issues of integrated biochip informatics technologies including multivariate data projection, gene-metabolic pathway mapping, automated biomolecular annotation, text mining of factual and literature databases, and integrated management of biomolecular databases will be discussed. Each step will be given with real examples from ongoing research activities in the context of clinical relevance. Issues of linking molecular genotype and clinical phenotype information will be discussed.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.2 s.150
• /
• pp.198-206
• /
• 2006

Hypertext is a web form consisted of HTML(hypertext markup language) which is used in Internet. Hypertext in costume is the product of modem industrial society. Hypertext is not a mechanical technique that enlarges external capacity of human beings. It is rather a motif that extends the internal ability of human beings. It brings about the social innovation by extending the expression realm of costume and providing the various views of recognition. This study regards costume not as an artistic work but as a text which interacts in the open relationship of human body, society and culture and causes dynamic generation of meaning. This study distinguishes Plasticitic Characteristics of Hypertext in Costume with intertextuality, rhizome, interactivity in the structural characteristics of hypertext which is a typical trait of digital culture of openness and variousness. In conclusion, this study clarified plasticitic value of modem costume, which expresses vague isms and the pargidm of multi-typed culture most sensitively and condretley, and expressional forms in relation with the structural characteristics of hypertext.

• Proceedings of the KSME Conference
• /
• 2008.11a
• /
• pp.1647-1650
• /
• 2008

The moyamoya disease is a type of cerebrovascular disease which produces thin abnormal blood vessels like haze in the brain base because the end of internal carotid artery which supplies about 80% of blood is blocked. Regarding this moyamoya disease, the shearing stress and thrombus generation are mentioned as its main causes. This study three-dimensionally implemented the ICA, ACA, and MCA parts of the cerebrovascular configuration related to the moyamoya disease, and analyzed the hydrodynamic phenomenon with the commercial program ADINA. In particular, the correlations between shearing stress and speed distribution according to the branch angle of ACA and MCA. A numerical analysis found that the greater the branch angle of ACA and MCA, the lower the shearing stress and the greater the stationary area of the flow.. Put Abstract text here.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.4
• /
• pp.5-23
• /
• 2014

This study reports the first step in the Classification-based Search and Knowledge Discovery (CSKD) project, which aims to combine information organization and retrieval approaches for building digital library applications. In this study, we explored the generation and application of a faceted vocabulary as a potential mechanism to enhance knowledge discovery. The faceted vocabulary construction process revealed some heuristics that can be refined in follow-up studies to further automate the creation of faceted classification structure, while our concept search application demonstrated the utility and potential of integrating classification-based approach with retrieval-based approach. Integration of text- and classification-based methods as outlined in this paper combines the strengths of two vastly different approaches to information discovery by constructing and utilizing a flexible information organization scheme from an existing classification structure.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1034-1047
• /
• 2020

The personal authentication technique is an essential tool in this complex and modern digital information society. Traditionally, the most general mechanism of personal authentication was using alphanumeric passwords. However, passwords that are hard to guess or to break, are often hard to remember. There are demands for a technology capable of replacing the text-based password system. Graphical passwords can be an alternative, but it is vulnerable to shoulder-surfing attacks. This paper looks through a number of recently developed graphical password systems and introduces a personal authentication system using a machine learning technique with electroencephalography (EEG) signals as a new type of personal authentication system which is easier for a person to use and more difficult for others to steal than other preexisting authentication systems.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.521-524
• /
• 1988

This paper describes BSDL(Behavioral/Structural Description Language), CDTF(Control Data Text File) and state synthesizer built for use in ICSC(InCheon Silicon Compiler). BSDL describes structral and behaviral specifications of an ASIC(Application Specific IC) for digital system design. ICSC's paser generates CDTF consists of if-then-else, arithmetic and data transfer statement according to each BSDL statement. State synthesizer generates CCG(Control Constraint Graph) in consideration of execution of statement and generates VCG (Variable Constraint Graph) in consideration use of variable generation and use of variable. Also, it involves allocating algorithm operation nodes in the data path and the control path to machine states with minimum state number and as small area as possible.

• Proceedings of the Zoological Society Korea Conference
• /
• 2000.10a
• /
• pp.244.2-245
• /
• 2000

No Abstract, See Full Text