• Journal of applied mathematics & informatics
• /
• v.41 no.3
• /
• pp.553-567
• /
• 2023

There are real life situations in our lives where the things are changing continuously or from time to time. It is a very important problem for one whether to continue the existing relationship or to form a new one after some occasions. That is, people, companies, cities, countries, etc. may change their opinion or position rapidly. In this work, we think of the problem of changing relationships from a mathematical point of view and think of an answer. In some sense, we comment these changes as power changes. Our number theoretical model will be based on this idea. Using the convolution sum of the restricted divisor function E, we obtain the answer to this problem.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.775-778
• /
• 2021

악성 댓글은 언어폭력이며 사이버 범죄의 일종으로 인터넷상에서 상대방이 올린 글에 비방이나 험담을 하는 악의적인 댓글을 말한다. 악성 댓글을 단순히 차단하는 다른 프로그램들과는 달리 해당 영상의 악성 댓글의 비율을 알려주고 악플러들의 닉네임과 그 빈도를 나타내주는 것으로 차별화를 두었다. 따라서 많은 유튜버들이 겪는 악성 댓글 문제들을 탐지하여 유튜브에 달리는 악성 댓글들을 탐지하고 시각화하여 제공한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.864-867
• /
• 2021

뉴스, SNS 등의 인터넷 댓글은 익명으로 의견을 자유롭게 개진할 수 있는 반면 댓글의 익명성을 악용하여 비방이나 험담을 하는 악성 댓글이 여러 분야에서 사회적 문제가 되고 있다. 해당 문제를 해결하기 위해 AI를 활용한 댓글 분류 알고리즘을 개발하려는 많은 노력들이 이루어지고 있지만, 댓글 분류 모델에 사용되는 AI는 오버피팅의 문제로 인해 댓글 분류에 대한 정확도가 떨어지는 문제점을 가지고 있다. 이에 본 연구에서는 크라우드소싱을 활용하여 오버피팅으로 인한 악성 댓글 분류 및 판단 정확도 저하 문제를 개선한 크라우드소싱 기반 딥러닝 분류 알고리즘(Deep Learning Classification Algorithm Based on Crowdsourcing: DCAC)과 해당 알고리즘을 사용한 시스템을 제안한다. 또한, 실험을 통해 오버피팅으로 낮아진 판단 정확도를 증가시키는 데 제안된 방법이 도움이 되는 것을 확인하였다.

• Animal Systematics, Evolution and Diversity
• /
• v.39 no.4
• /
• pp.289-294
• /
• 2023

We discovered a halacarid mite species, Isobactrus tuberculatus Abé, 1996, inhabiting marine plastic debris on the coast of Jeju Island, Korea. The key characteristics of these Korean specimens were consistent with those in the original description of specimens from Hokkaido, Japan, including the presence of tuberculate membranous cuticles between the anterior and posterior dorsal plates, fusion of the posterior epimeral plates I and II, tibia II with a bipectinate seta, tibiae III and IV each with five setae, and a pair of subgenital setae in females. However, two small morphological differences were noted: the distance between the anterior and posterior dorsal plates was shorter than that in Japanese specimens, and the location of dorsal seta-2 was closer to the anterior dorsal plate in Korean specimens. We herein provide detailed illustrations of I. tuberculatus, based on the Korean specimens, with a brief taxonomic comment on the similarities among allied congeneric species. The genus Isobactrus is first reported in Korea.

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.119-133
• /
• 2020

Recently, as famous YouTubers produce and broadcast videos that receive sponsorship and advertising such as indirect advertising (PPL), a so-called 'back advertising' controversy continues, and not only famous YouTubers but also entertainers are caught up in the issue. It is causing confusion among the public in Korea. This study attempts to find out the public's reaction before and after the controversy of 'back advertising' by YouTubers through comment analysis. Specifically, among text analysis using R programs, we intend to analyze the issue through various methods such as word cloud, qgraph analysis, LDA, and word2vec analysis, a deep learning technique. The target of the analysis was to analyze the channels of three YouTubers who belonged to the controversy of the 'back advertising' YouTuber and uploaded the 'Apology video'. The 5 most recent videos of Muk-bang YouTuber Moon Bok-hee, who has a similar content disposition to SussTV's Han Hye-yeon stylist, which was controversial, and Yang Pang, a YouTuber who showed various contents (August 09, 2020) Criterion and her first 5 videos uploaded were reviewed. As a result of the study, most of the comments that showed positive reactions before the controversy, but after the controversy, it was found that negative reactions accounted for most of the comments. Therefore, this study examines the degree of change of the public about influencers through comments after the controversy over 'back advertising' through various analysis using R program. This research also devises various measures to prevent the occurrence of back advertising of influencers in the future.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.89-96
• /
• 2018

In online communities, a large number of participants can exchange their opinion using replies without time and space restrictions. While the online space provides quick and free communication, it also easily triggers unnecessary quarrels and conflicts. The network established on the discussion participants is an important cue to analyze the confrontation and predict serious disputes. In this paper, we present a quantitative measure for polarity observed on the discussion network built from reply exchanges in online communities. The proposed method uses the comment exchange information to establish the user interaction network graph, computes its maximum spanning tree, and then performs vertex coloring to assign two colors to each node in order to divide the discussion participants into two subsets. Using the proportion of the comment exchanges across the partitioned user subsets, we compute the polarity measure, and quantify how discussion participants are bipolarized. Using experimental results, we demonstrate the effectiveness of our method for detecting polarization and show participants of a specific discussion subject tend to be divided into two camps when they debate.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.103-110
• /
• 2023

With the spread of the Internet, anonymous communities emerged along with the activation of communities for communication between people, and many users are doing harm to others, such as posting aggressive posts and leaving comments using anonymity. In the past, administrators directly checked posts and comments, then deleted and blocked them, but as the number of community users increased, they reached a level that managers could not continue to monitor. Initially, word filtering techniques were used to prevent malicious writing from being posted in a form that could not post or comment if a specific word was included, but they avoided filtering in a bypassed form, such as using similar words. As a way to solve this problem, deep learning was used to monitor posts posted by users in real-time, but recently, the community uses words that can only be understood by the community or from a human perspective, not from a general Korean word. There are various types and forms of characters, making it difficult to learn everything in the artificial intelligence model. Therefore, in this paper, we proposes a preprocessing technique in which each character of a sentence is imaged using a CNN model that learns the consonants, vowel and spacing images of Korean word and converts characters that can only be understood from a human perspective into characters predicted by the CNN model. As a result of the experiment, it was confirmed that the performance of the LSTM, BiLSTM and CNN-BiLSTM models increased by 3.2%, 3.3%, and 4.88%, respectively, through the proposed preprocessing technique.

• Journal of Engineering Education Research
• /
• v.19 no.1
• /
• pp.54-60
• /
• 2016

This paper was built for an activation of a merged education and development of non-subject, new type creative merged education program having effectivities. This program is disciplined a kind of flipped learning and camp program of 2 nights and 3 days. Given a problem which big enough and open-ended problem, multidisciplinary team that composed with engineering and design major students works the capstone design project. For ordinary engineering design process, 'how can we make?' was important. But in this program 'what can we make?' is more serious question. Our program was pursuing an creative idea that can induce innovation. Teaching or interference of professors was minimized and then students solve the problem theirselves by long time and liberal brainstorming. Last products is not real goods and only a proposal for manufacturing. Finally, the results are presented using ppt and board. After not only professors but also students of other teams can ask a question, resolve and comment on that proposal. The benefits of this program are that inner members of university take a whole process from planning and working to last evaluation. Besides economic benefit, they can secure an infrastructure for development of creative merged education program by running for several times and so can improve the program continuously. For an aspect of students, they can respond to recently highlighted creative experiences that required for recruitment.

• Environmental and Resource Economics Review
• /
• v.7 no.2
• /
• pp.87-109
• /
• 1998

1989년 미국 환경청(Environmental Protection Agency : EPA)은 유독물질통제법(Toxic Substances Control Act : TSCA)에 의해 석면을 함유하고 있는 일부 제품의 제조, 수업, 가공 및 판매를 세 단계로 나누어 금지하였다. 본 논문은 석면규제를 금지여부결정과 금지우선순위결정으로 구분하여 각 결정에 내재된 EPA의 의사결정요인들을 추론한다. 특히 본 논문은 Magat et al.(1986), Asch and Seneca(1989), Cropper et al.(1992)이 EPA의 의사결정요인들로 제시한 내부신호(internal signals, 비용과 편익의 추정치)와 외부신호(external signals, 외부집단의 참여)를 석면규제에 적용하여 이들의 역할을 고찰한다. 한편 본 논문은 규제에 의해 영향을 받는 이익집단들이 EPA의 의견수렴기간(comment period) 동안에 제출한 의견서(written comments)가 외부신호를 나타낸다고 가정한다. Probit 모형으로 추정된 금지여부결정에 있어 EPA는 TSCA의 규정을 준수하여 비용과 편익을 균형하였고, 기업과 환경보호단체의 참여도 EPA의 의사 결정에 영향을 미쳤다. 즉, 어떤 제품의 금지에 소요되는 비용이 많으면 그 제품이 금지될 확률이 작았고, 그 제품의 금지를 반대하는 기업의 의견서가 많으면 그 제품이 금지될 확률이 작았다. 그러나 외부신호가 포함된 모형에서 내부 신호의 통계적 유의성이 낮아지는 문제가 나타났다. 한편 추정결과는 금지로 인해 감소된 암 한 건에 대한 EPA의 암묵적인(implicit) 평가가 5,000만 달러가 넘는다는 것을 보여 준다. Ordered Probit 모형으로 추정된 금지우선순위결정에 있어, 편익의 단위당 비용이 작을수록, 그리고 그 제품의 금지를 찬성하는 환경보호단체의 의견서가 많을수록 그 제품은 보다 이른 단계에서 금지되었다. 이 경우 외부신호의 계수의 통계적 유의성은 높은 반면 내부신호의 계수의 통계적 유의성은 상대적으로 낮았다.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.5
• /
• pp.319-324
• /
• 2014

Web applications make life more convenient. Many web applications have several kinds of user input (e.g. personal information, a user's comment of commercial goods, etc.) for the activities. On the other hand, there are a range of vulnerabilities in the input functions of Web applications. Malicious actions can be attempted using the free accessibility of many web applications. Attacks by the exploitation of these input vulnerabilities can be achieved by injecting malicious web code; it enables one to perform a variety of illegal actions, such as SQL Injection Attacks (SQLIAs) and Cross Site Scripting (XSS). These actions come down to theft, replacing personal information, or phishing. The existing solutions use a parser for the code, are limited to fixed and very small patterns, and are difficult to adapt to variations. A machine learning method can give leverage to cover a far broader range of malicious web code and is easy to adapt to variations and changes. Therefore, this paper suggests the adaptable classification of malicious web code by machine learning approaches for detecting the exploitation user inputs. The approach usually identifies the "looks-like malicious" code for real malicious code. More detailed classification using sequence information is also introduced. The precision for the "looks-like malicious code" is 99% and for the precise classification with sequence is 90%.