• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.217-225
• /
• 2017

Recently, the interest in predicting hot topics has grown significantly as it has become more important to find and analyze meaningful information from a large amount of data flowing in social networking services. Existing hot topic detection schemes do not consider a temporal property, so they are not suitable to predict hot topics that are rapidly issued in a changing society. This paper proposes a hot topic prediction scheme that uses a modified TF-IDF in social networking environments. The modified TF-IDF extracts a candidate set of keywords that are momentarily issued. The proposed scheme then calculates the hot topic prediction scores by assigning weights considering user influence and professionality to extract the candidate keywords. The superiority of the proposed scheme is shown by comparing it to an existing detection scheme. In addition, to show whether or not it predicts hot topics correctly, we evaluate its quality with Korean news articles from Naver.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.178-186
• /
• 2018

Subject classification of thesis units is essential to serve scholarly information deliverables. However, to date, there is a journal-based topic classification, and there are not many article-level subject classification services. In the case of academic papers among domestic works, subject classification can be a more important information because it can cover a larger area of service and can provide service by setting a range. However, the problem of classifying themes by field requires the hands of experts in various fields, and various methods of verification are needed to increase accuracy. In this paper, we try to classify topics using the unsupervised learning algorithm to find the correct answer in the unknown state and compare the results of the subject classification algorithms using the coherence and perplexity. The unsupervised learning algorithms are a well-known Hierarchical Dirichlet Process (HDP), Latent Dirichlet Allocation (LDA) and Latent Semantic Indexing (LSI) algorithm.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.2
• /
• pp.263-277
• /
• 2020

Children's use of the Internet is growing. Each company collects children's personal information. However, it is also difficult for children to recognize the concept of personal information. In this study, based on the analysis of newspaper children's personal information leakage, we investigated the occurrence of personal information leakage in children through ground theory, one of qualitative research methods used in the social science field. The ground theory is thought to be able to derive a causal relationship by identifying the leakage of children's personal information. As a result of the study, it was collected through the consent of the legal representative, but depending on the situation, the consent process was not performed. Even with the consent, it was found that due to insufficient measure to protect personal information, various situation(criminal damage, anxiety, embarrassment, anger, etc.) occurred the legal representative. As a result, children's personal information collection providers paid fines according to the situation.

• Journal of Internet Computing and Services
• /
• v.21 no.1
• /
• pp.1-15
• /
• 2020

This study explores reasonable alternatives to internet interconnection policy. Due to the development of information and communication technology, patterns of the Internet usage are changing rapidly, including increase of video streaming services. For this reason, there is a lively discussion of the Internet interconnection policy, which integrates various Internet service operators into one ecosystem. We conducted an Analytic Hierarchy Process(AHP) analysis with 16 experts in government/public, and academic sectors, and alternative selection criteria and their corresponding alternatives and detailed tasks were evaluated. According to the results, the most important alternative selection criteria was a "fair charge against foreign service operators", and the most desirable alternative was "partial revise". Moreover, the experts responded that "reassessment of the principle of the charge" is the most urgent task to improve the Internet interconnection policy.

• The Bulletin of The Korean Astronomical Society
• /
• v.35 no.1
• /
• pp.84.1-84.1
• /
• 2010

2009 세계 천문의 해(International Year of Astronomy 2009, IYA2009) 한국조직위원회는 지난 1년간 148개 참가국의 일원으로 다양한 활동을 펼쳤다. IYA2009 활동은 강연, 별 축제와 같은 고전적인 이벤트로부터 시, 수필, 에세이, 음악, 미술, 만화, 영화, 대회, 인터넷 생중계, 플래시 동영상과 같이 새롭게 시도된 프로그램에 이르기까지 다양하게 기획, 운영되었다. 또한 우리는 시민천문대와 과학관, 미술관은 물론, 지하철, 기차역, 시청, 놀이공원, 쇼핑몰, 백화점, 병원, 그리고 경찰서에 이르기까지, 기존의 전통적인 전시공간을 벗어나 다양한 장소에서 전시회와 동영상 상영을 시도했다. 우리는 지난 1년간 90여 종의 행사를 410여 회에 걸쳐 진행했으며, 총 11,700,000여 명의 일반 시민과 학생들이 2009 세계 천문의 해에 참여한 것으로 추산하고 있다. IYA2009는 강연 200여 회, 전시 80여 회, 공연 15회, 학회 7회 등으로 요약할 수 있으며, 공식책자 4종, 도록 3종이 발간되었다. 관련 보도자료는 40 차례 배포했으며, 그 결과 2,500여 건이 언론을 통해 보도되었고, 총 248편의 연재기사가 실렸다. 2009 세계 천문의 해 한국조직위원회 공식 웹진 '이야진' 접속자는 999,890명, 총 페이지 뷰 건수는 131,963,473을 기록했다.

• Journal of KIISE:Software and Applications
• /
• v.26 no.10
• /
• pp.1247-1259
• /
• 1999

본 논문에서는 한국어 문장형성원리를 간결하게 제시할 수 있도록 X-바 이론의 중심어 개념을 도입한 한국어 자질기반 문법을 제안한다. 제안하는 문법은 어절에 관계없이 나타나는 한국어의 문법현상을 명확히 설명할 수 있도록 어절 대신 형태소를 기본단위로 한다. 그리고, 한국어의 구문범주가 지닌 의미정보와 기능정보를 자질을 이용하여 독립적으로 표현하며, 구문범주간의 결합관계를 바탕으로 하는 자질연산을 수행하여 문장을 분석한다. 또한, 한국어의 부분자유어순과 생략현상에 대해 견고하게 분석할 수 있도록 자질연산을 이진결합중심의 CNF(Chomsky Normal Form)로 제한한다. 이렇게 구성된 한국어 자질기반 문법은 규칙을 직관적이고도 간단하게 기술하며, 한국어의 다양한 문장들을 견고하게 분석한다. SERI Test Suites 97과 신문기사에서 746문장을 추출하여 실험한 결과 94%~99%의 적용율을 보였다.Abstract In this paper, we propose a Korean feature-based grammar(KFG) which adopts the X-bar theoretic notion of headedness for a precise representation of Korean syntactic structure. In order to explain various language phenomena in a given sentence, we use not the word but the morpheme as a constituent unit of KFG. We use features manifesting both the syntactic information and the semantic information of Korean syntactic categories, and feature operations based on the association relationship between two categories. In addition, we restrict feature operations to CNF(Chomsky Normal Form) binary form, which provides a robust representation for properties in Korean such as the frequent ellipsis and the partial free-order. The KFG is intuitive, simple, and versatile in representing most Korean sentences. The experimental result shows 94%~99% coverage on 746 sentences extracted from SERI Test Suites 97 and newspaper sentences.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.674-679
• /
• 2017

In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.14 no.4
• /
• pp.260-264
• /
• 1981

The purpose of the present study is to measure the sound spectrum of the underwater noise generated by a stern trawler M/S Saebada (2,275 GT, 3600 ps) in the various operational conditions. Underwater noises were recorded by a hydrophone (B & K 8100) and analyses were made rising a digital frequency analyzer (B & K 2131) and level recorder (B & K 2370). The predominant frequency range was 100-500 Hz, and maximum sound pressure level was 121 dB(re. $1{\mu}Pa$). Underwater noise level increased with the increased speed of the vessel. Sound pressure level measured in the course of astern cruising was higher than that measured in the course of ahead cruising and also the noise spectrums were different in these two cases. At the time of cruising the underwater noise was higher than 10 dB compared to those values measured at the time at rest with only engine operation. The underwater noise of the vessel was mainly due to the main engine revolution of the propeller and the vibration of hull.

• Journal of KIISE
• /
• v.43 no.9
• /
• pp.1008-1014
• /
• 2016

Data such as Twitter, Facebook, and customer reviews belong to the informal document group, whereas, newspapers that have grammar correction step belong to the formal document group. Finding consistent rules or patterns in informal documents is difficult, as compared to formal documents. Hence, there is a need for additional approaches to improve informal document analysis. In this study, we classified Twitter data, a representative informal document, into ten categories. To improve performance, we revised and expanded features based on LDA(Latent Dirichlet allocation) word distribution. Using LDA top-ranked words, the other words were separated or bundled, and the feature set was thus expanded repeatedly. Finally, we conducted document classification with the expanded features. Experimental results indicated that the proposed method improved the micro-averaged F1-score of 7.11%p, as compared to the results before the feature expansion step.

• Korean Journal of Food Science and Technology
• /
• v.10 no.1
• /
• pp.57-62
• /
• 1978

The morphology and chemical properties of bracken (Pteridium aquilinum) root starch were investigated. The starch granules were mainly sphere and cocoon with the diameter of $5-12\mu$. Polarized micrograph indicated that the starch granule had a hilum at the center of granule, showing a crossed-birefringence. X-ray diffraction pattern demonstrated that the granules showed B-type. The density of the starch was 1.49 and the amylose content was 22%. The ferricyanide number and alkali number were 0.292 and 11.03, respectively. Proximate analysis showed that the starch contained 0.52% lipid, 0.63% ash and 150ppm phosphorus of which over 80% were found in the amylopectin fraction. The iodine affinity and molecular weight of amylose were 16.1 and 83,000 respectively. The degree of branching and glucose units per segment of amylopectin were 3.7% and 27, respectively.