• The Journal of the Korea Contents Association
• /
• v.14 no.4
• /
• pp.407-417
• /
• 2014

An arirang is the most famous Korean folk song and was registered in UNESCO(Unitied Nations Educational, Scientific and cultural Organization) as an intangible cultural heritage in 2012. Most arirangs are composed of text and refrain parts. Genealogy of the arirang was classified in refrain patterns by using multiple sequence alignment algorithm. There are two different refrain patterns, slow and fast melodies. Of 106 arirangs, 38 and 68 arirangs contain fast and slow melodies, respectively. 73 arirangs and 104 their key words were extracted from bipartate arirang network that composed of arirangs, text works, and their relationships. The correlation among the arirangs was analyzed from the selected arirangs and key words by using pairwise comparison matrix. Also, analysis of correlation among the arirnags was performed by stepwise removal of the single degree nodes from the bipartate arirang network In this study, arirangs were analyzed in genealogy and correlation among arirangs by using informatic algorithm and network technology, in which arirang research will be constructed a stepping stone for the popularization and globalization of the arirangs.

• Journal of The Korean Association of Information Education
• /
• v.3 no.2
• /
• pp.72-84
• /
• 2000

Information retrieval system plays a key role in the information society to store digital documents with efficiency and to provide user with the information through the retrieval very fast. Especially, indexing is a prerequisite function for the information retrieval system in order to retrieve the information of the documents effectively which are saved in database. In this paper, we propose an indexing method using text partition. This method can retrieve educational documents in short processing time. We applied the suggested indexing method to real information retrieval system, and proved its excellent functions through the demonstration.

• Journal of the Korea Society for Simulation
• /
• v.11 no.3
• /
• pp.35-48
• /
• 2002

In the work presented here, we describe a method to extract TrueType features for supporting letter recognition. Even if variously existing document processing techniques have been challenged, almost few methods are capable of recognize a letter associated with its TrueType features supporting OCR free, which boost up fast processing time for image text retrieval. By reviewing the mechanism generating digital fonts and birth of TrueType, we realize that each TrueType is drawn by its contour of the glyph table. Hence, we are capable of deriving the segment with density for a letter with a specific TrueType, defined by the number of occurrence over a segment width. A certain number of occurrence appears frequently often due to the fixed segment width. We utilize letter recognition by comparing TrueType feature library of a letter with that from input word images. Experiments have been carried out to justify robustness of the proposed method showing acceptable results.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.521-526
• /
• 2017

Data format of Big data is diverse and vast, and its generation speed is very fast, requiring new management and analysis methods, not traditional data processing methods. Textual mining techniques can be used to extract useful information from unstructured text written in human language in online documents on social networks. Identifying trends in the message of politics, economy, and culture left behind in social media is a factor in understanding what topics they are interested in. In this study, text mining was performed on online news related to a given keyword using topic - oriented analysis technique. We use Latent Dirichiet Allocation (LDA) to extract information from web documents and analyze which subjects are interested in a given keyword, and which topics are related to which core values are related.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.43 no.3
• /
• pp.427-439
• /
• 2019

This study investigated the semantic network based on the focus of the fashion image and SNS text utilized by global SPA brands on the last seven years in terms of the quantity and quality of data generated by the fast-changing fashion trends and fashion content-based media environment. The research method relocated frequency, density and repetitive key words as well as visualized algorithms using the UCINET 6.347 program and the overall classification of the text related to fashion images on social networks used by global SPA brands. The conclusions of the study are as follows. A common aspect of global SPA brands is that by looking at the basis of text extraction on SNS, exposure through image of products is considered important for sales. The following is a discriminatory aspect of global SPA brands. First, ZARA consistently exposes marketing using a variety of professions and nationalities to SNS. Second, UNIQLO's correlation exposes its collaboration promotion to SNS while steadily exposing basic items. Third, in the case of H&M, some discriminatory results were found with other brands in connectivity with each cluster category that showed remarkably independent results.

• Journal of KIISE:Software and Applications
• /
• v.32 no.2
• /
• pp.85-98
• /
• 2005

Recently, a lot of researches about mobile vision using Personal Digital Assistant(PDA) has been attempted. Many CPUs for PDA are integer CPUs, which have no floating-computation component. It results in slow computation of the algorithms peformed by vision system or image processing, which have much floating-computation. In this paper, in order to resolve this weakness, we propose the Client(PDA)/server(PC) architecture which is connected to each other with a wireless LAN, and we construct the system with pipelining processing using two CPUs of the Client(PDA) and the Server(PC) in image sequence. The Client(PDA) extracts tentative text regions using Edge Density(ED). The Server(PC) uses both the Multi-1.aver Perceptron(MLP)-based texture classifier and Connected Component(CC)-based filtering for a definite text extraction based on the Client(PDA)'s tentativel99-y extracted results. The proposed method leads to not only efficient text extraction by using both the MLP and the CC, but also fast running time using Client(PDA)/server(PC) architecture with the pipelining processing.

• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.486-490
• /
• 1989

In this paper, a program controlling an auto-audio media - cassette deck - by a 16 bit personal computer is studied in order to execute audio and visual learning in CAI. The results of this study are as follows. 1. Audio and visual learning is executed efficiently in CAI. 2. Access rate of voice information to text/image information is about 98% and 60% in "play" and "fast forward" respectively. 3. In "fast forward", quality of a cassette tape affects voice information access rate in propotion to motor driving speed. 4. Synchronizing signal may be mistaken by defects of tape itself.

• Proceedings of the KIPE Conference
• /
• 2012.07a
• /
• pp.441-442
• /
• 2012

LabVIEW is faster than text language based program regarding development time and can monitor the output of data fast without the separate compiling work as the graphic-based graphical programming language. And, its coding is fast because it is designed by connecting the function with the wire and its has the merit of relatively intuitive UI. In this paper, data transmission and receiving between the program that is implemented in C language as CAN communication method that is strong against noise and used in power electronics application field variously and LabVIEW based program are explained. And, the design of LabVIEW based CAN communication program, data analysis and GUI screen composition that is convenient for monitoring are shown.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2005.08a
• /
• pp.71-78
• /
• 2005

빠르면서도 정확한 문서 자동분류를 위해서 자질값투표 기법과 문서측 자질선정 방식의 결합을 제안하였다. 자질값은 미리 학습된 분류자질과 분류범주간의 연관성을 뜻하는 것으로서, 자질값투표 기법은 분류대상 문서에 나타난 자질들의 자질값을 후보범주마다 합산하여 가장 높은 범주로 분류하는 것이다. 문서측 자질선정은 일반적인 분류자질선정과 달리 학습집단이 아닌 분류대상 문서의 자질 중 일부만을 선택하여 분류에 이용하는 방식이다. 이들을 결합하여 사용한 결과 실험환경에서는 나이브베이즈 분류기만큼 간단하고 빠르면서 SVM 분류기보다 좋은 성능을 보였다.

• The KIPS Transactions:PartC
• /
• v.9C no.2
• /
• pp.267-276
• /
• 2002

By using wireless terminal, User that want to transmit multimedia traffic as well as simple text and voice have a tendency to increase. This paper proposes a fast handoff protocol that is suitable transmission for real-tim of multimedia traffic by using modified local registration. The proposed protocol solves the Triangle Routing Protocol that is one of existing opened issues without modifying protocol of CN, and we propose the method that MN is able to received a packet by real-time, even if MN is being handoff. We compare fast handoff protocol proposed in this paper with existing method n the registration cost and data packet transmission cost. As a result, we showed that fast handoff protocol proposed in this paper outperforms existing method.