• Asian Journal for Public Opinion Research
• /
• v.9 no.1
• /
• pp.48-82
• /
• 2021

This research article attempts to understand the current situation of fake news on social media in India. The study focused on four characteristics of fake news based on four research questions: subject matter, presentation elements of fake news, debunking tool(s) or technique(s) used, and the social media site on which the fake news story was shared. A systematic sampling method was used to select a sample of 90 debunked fake news stories from two Indian fact-checking websites, Alt News and Factly, from December 2019 to February 2020. A content analysis of the four characteristics of fake news stories was carefully analyzed, classified, coded, and presented. The results show that most of the fake news stories were related to politics in India. The majority of the fake news was shared via a video with text in which narrative was changed to mislead users. For the largest number of debunked fake news stories, information from official or primary sources, such as reports, data, statements, announcements, or updates were used to debunk false claims.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.203-206
• /
• 2022

본 논문에서는 생성된 이미지에 대한 YOLO 모델의 객체 인식의 성능을 확인하고 사례를 연구하는 것을 목적으로 한다. 최근 영상 처리 기술이 발전함에 따라 적대적 공격의 위험성이 증가하고, 이로 인해 객체 인식의 성능이 현저히 떨어질 수 있는 문제가 발생하고 있다. 본 연구에서는 앞서 언급한 문제를 해결하기 위해 text-to-image 모델을 활용하여 기존에 존재하지 않는 새로운 이미지를 생성하고, 생성된 이미지에 대한 객체 인식을 사례 별로 연구한다. 총 8가지의 동물 카테고리로 분류한 후 객체 인식 성능을 확인한 결과 86.46%의 정확도로 바운딩 박스를 생성하였고, 동물에 대한 116개의 60.41%의 정확도를 보여주었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.179-182
• /
• 2022

최근 코로나 19 팬더믹 이후 원격근무의 확대와 더불어 랜섬웨어 팬더믹이 심화하고 있다. 현재 안티바이러스 백신 업체들이 랜섬웨어에 대응하고자 노력하고 있지만, 기존의 파일 시그니처 기반 정적분석은 패킹의 다양화, 난독화, 변종 혹은 신종 랜섬웨어의 등장 앞에 무력화될 수 있고, 실제로 랜섬웨어의 피해 규모 지속 증가가 이를 설명한다. 본 논문에서는 기계학습을 기반으로 한 단일 분석만을 이용하여 탐지모델에 적용하는 것이 아닌 정적 분석 정보(.text Section Opcode)와 동적 분석 정보(Native API)를 추출하고 유사도를 바탕으로 연관성을 찾아 결합하여 기계학습에 적용하는 탐지모델을 제안한다.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.24-29
• /
• 2023

In this paper, we propose a real-time bus arrival notification system using deep learning to guarantee movement rights for the visually impaired. In modern society, by using location information of public transportation, users can quickly obtain information about public transportation and use public transportation easily. However, since the existing public transportation information system is a visual system, the visually impaired cannot use it. In Korea, various laws have been amended since the 'Act on the Promotion of Transportation for the Vulnerable' was enacted in June 2012 as the Act on the Movement Rights of the Blind, but the visually impaired are experiencing inconvenience in using public transportation. In particular, from the standpoint of the visually impaired, it is impossible to determine whether the bus is coming soon, is coming now, or has already arrived with the current system. In this paper, we use deep learning technology to learn bus numbers and identify upcoming bus numbers. Finally, we propose a method to notify the visually impaired by voice that the bus is coming by using TTS technology.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.91-96
• /
• 2021

조기 위험 검출은 실시간으로 들어오는 텍스트를 순차적으로 처리하면서 해당 대화에 위험이 있는지 조기에 분류하는 작업으로, 정확도 저하를 최소화하는 동시에 가능한 한 빨리 대화를 분류하는 것을 목적으로 한다. 이러한, 조기 위험 검출은 온라인 그루밍 검출, 보이스 피싱 검출과 같은 다양한 영역에 활용될 수 있다. 이에, 본 논문에서는 조기 위험 검출 문제를 정의하고, 이를 평가할 수 있는 데이터 셋과 Latency F1 평가 지표를 소개한다. 또한, 점진적 문장 분류 모듈과 위험 검출 결정 모듈로 구성된 점진적 조기 텍스트 분류 시스템을 제안한다. 점진적 문장 분류 모듈은 이전 문장들에 대한 메모리 벡터와 현재 문장 벡터를 통해 현재까지의 대화를 분류한다. 위험 검출 결정 모듈은 softmax 분류 점수와 강화학습을 기반으로 하여 Read 또는 Stop 판단을 내린다. 결정 모듈이 Stop 판단을 내리면, 현재까지의 대화에 대한 분류 결과를 전체 대화의 분류 결과로 간주하고 작업을 종료한다. 해당 시스템은 micro F1과 Latency F1 지표 각각에서 0.9684와 0.8918로 높은 검출 정확성 및 검출 신속성을 달성하였다.

• Smart Media Journal
• /
• v.12 no.10
• /
• pp.38-46
• /
• 2023

Farming activities are transforming from traditional skill-based agriculture into knowledge-based and technology-driven digital agriculture. The use of intelligent information and communication technology introduces the idea of smart farming that enables farmers to collect weather data, monitor crop growth remotely and detect crop diseases easily. The introduction of Plantix, a pest and disease management tool in the form of a mobile application has allowed farmers to identify pests and diseases of the crop using their mobile devices. Hence, this study collected the reviews of Plantix to explore the response of the users on the Google Play Store towards the application through Latent Dirichlet Allocation (LDA) topic modeling. Results indicate four latent topics in the reviews: two positive evaluations (compliments, appreciation) and two suggestions (plant options, recommendations). We found the users suggested the application to additional plant options and additional features that might help the farmers with their difficulties. In addition, the application is expected to benefit the farmer more by having an early alert of diseases to farmers and providing various substitutes and a list of components for the remedial measures.

• Archives of Plastic Surgery
• /
• v.51 no.2
• /
• pp.196-201
• /
• 2024

Nevus lipomatosus superficialis (NLS) is a hamartoma of adipose tissue, rarely reported in the past 100 years. We treated one case, and we conducted a systematic review of the literature. A 41-year-old man presented with a cutaneous multinodular lesion in the posterior region near the right auricle. The lesion was excised and examined histopathologically. To review the literature, we searched PubMed with the keyword "NLS." The search was limited to articles written in English and whose full text was available. We analyzed the following data: year of report, nation of corresponding author, sex of patient, age at onset, duration of disease, location of lesion, type of lesion, associated symptoms, pathological findings, and treatment. Of 158 relevant articles in PubMed, 112 fulfilled our inclusion criteria; these referred to a total of 149 cases (cases with insufficient clinical information were excluded). In rare cases, the diagnosis of NLS was confirmed when the lesion coexisted with sebaceous trichofolliculoma and Demodex infestation. Clinical awareness for NLS has increased recently. NLS is an indolent and asymptomatic benign neoplasm that may exhibit malignant behavior in terms of huge lesion size and specific anatomical location. Early detection and curative treatment should be promoted.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.61-68
• /
• 2024

In this paper, Generative AI is a technology that creates various forms of content such as text, images, and music, and is being utilized across different fields. In the security sector, generative AI is poised to open up new possibilities in various areas including security vulnerability analysis, malware detection and analysis, and the creation and improvement of security policies. This paper presents a guide for identifying vulnerabilities and secure coding using ChatGPT for security vulnerability analysis and prediction, considering the application of generative AI in the security domain. While generative AI offers innovative possibilities in the security field, it is essential to continuously pursue research and development to ensure safe and effective utilization of generative AI through in-depth consideration of ethical and legal issues accompanying technological advancements.

• The Journal of Society for e-Business Studies
• /
• v.18 no.4
• /
• pp.315-326
• /
• 2013

Users in social media post various types of opinions such as product reviews and movie reviews. It is a common trend that customers get assistance from the opinions in making their decisions. However, as opinion usage grows, distorted feedbacks also have increased. For example, exaggerated positive opinions are posted for promoting target products. So are negative opinions which are far from common evaluations. Finding these biased opinions becomes important to keep social media reliable. Techniques of opinion mining (or sentiment analysis) have been developed to determine sentiment polarity of opinionated documents. These techniques can be utilized for finding the biased opinions. However, the previous techniques have some drawback. They categorize the text into only positive and negative, and they also need a large amount of training data to build the classifier. In this paper, we propose methods for discovering the biased opinions which are skewed from the overall common opinions. The methods are based on angle based outlier detection and personalized PageRank, which can be applied without training data. We analyze the performance of the proposed techniques by presenting experimental results on a movie review dataset.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.4
• /
• pp.55-61
• /
• 2024

Recently, the number of aging concrete structures is steadily increasing. This is because many of these structures are reaching their expected lifespan. Such structures require accurate inspections and persistent maintenance. Otherwise, their original functions and performance may degrade, potentially leading to safety accidents. Therefore, research on objective inspection technologies using deep learning and computer vision is actively being conducted. High-resolution images can accurately observe not only micro cracks but also spalling and exposed rebar, and deep learning enables automated detection. High detection performance in deep learning is only guaranteed with diverse and numerous training datasets. However, surface damage to concrete is not commonly captured in images, resulting in a lack of training data. To overcome this limitation, this study proposed a method for generating concrete surface damage images, including cracks, spalling, and exposed rebar, using stable diffusion. This method synthesizes new damage images by paired text and image data. For this purpose, a training dataset of 678 images was secured, and fine-tuning was performed through low-rank adaptation. The quality of the generated images was compared according to three base models of stable diffusion. As a result, a method to synthesize the most diverse and high-quality concrete damage images was developed. This research is expected to address the issue of data scarcity and contribute to improving the accuracy of deep learning-based damage detection algorithms in the future.