• Smart Media Journal
• /
• v.13 no.2
• /
• pp.85-94
• /
• 2024

Artificial Intelligence of Things (AIoT), which combines AI and the Internet of Things (IoT), has recently gained popularity. Deep neural networks (DNNs) have achieved great success in many applications. Deploying complex AI models on embedded boards, nevertheless, may be challenging due to computational limitations or intelligent model complexity. This paper focuses on an AIoT-based system for smart sewing automation using edge devices. Our technique included developing a detection model and a decision tree for a sufficient testing scenario. YOLOv5 set the stage for our defective sewing stitches detection model, to detect anomalies and classify the sewing patterns. According to the experimental testing, the proposed approach achieved a perfect score with accuracy and F1score of 1.0, False Positive Rate (FPR), False Negative Rate (FNR) of 0, and a speed of 0.07 seconds with file size 2.43MB.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.302-313
• /
• 2023

This paper aims to develop a framework that can fully automate the quality management of training data used in large-scale Artificial Intelligence (AI) models built by the Ministry of Science and ICT (MSIT) in the 'AI Hub Data Dam' project, which has invested more than 1 trillion won since 2017. Autonomous driving technology using AI has achieved excellent performance through many studies, but it requires a large amount of high-quality data to train the model. Moreover, it is still difficult for humans to directly inspect the processed data and prove it is valid, and a model trained with erroneous data can cause fatal problems in real life. This paper presents a dataset reconstruction framework that removes abnormal data from the constructed dataset and introduces strategies to improve the performance of AI models by reconstructing them into a reliable dataset to increase the efficiency of model training. The framework's validity was verified through an experiment on the autonomous driving dataset published through the AI Hub of the National Information Society Agency (NIA). As a result, it was confirmed that it could be rebuilt as a reliable dataset from which abnormal data has been removed.

• Journal of The Korean Association of Information Education
• /
• v.25 no.3
• /
• pp.449-457
• /
• 2021

Ministry of education recently announced to implement AI curriculum in elementary, middle school and highschool from 2025 which will include programing, basic AI principal and AI Ethics, and the media is releasing articles that have reservations on it. This study is focused on analyzing the perspective of elementary teachers - who are going to be in charge of AI education - on the implementation of AI education in elementary schools and the teachers are divided into two groups of 'software-experienced' and 'software-inexperienced' in relation to software training background. The results showed that 100% of the 'software-experienced' teachers agreed on implementing AI education and 80% of 'software-inexperienced' teachers also showed positive perspective on it. Among the reasons that 20% of 'software-inexperienced' teachers had negative perspective on AI education, it was highly rated that existing home economics subject covers fulfilling amount of software education. Both 'software-experienced' and 'software-inexperienced' teachers chose grade 5 and 6 as the most appropriate age for software education and considered one class per a week as the most appropriate amount of AI class. In terms of the subject format, 75% of the 'software-experienced' teachers chose the idea that software education has to be an independent school subject which will include AI education. Also, 54% of the 'software-inexperienced' teachers chose the ideas either AI education should be an independent subject or software education should be an independent subject which will include AI education. The preference of the content of AI education appeared in order of basic AI programing, principles of AI and AI Ethics.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.5
• /
• pp.15-23
• /
• 2020

Automated driving car is drawing attention as a seminal service representing 4th industrial revolution era based on 5G network, AI, IOT and sensor technology. automated driving car is expected to evolve into the final level which does not require driver's input. Drivers are able to consume new additional time in private space. Many industries started to compete to control these time and space. Media industry is expecting quite big change due to the introduction of automated driving cars. This research examines the impact of the media industry and social & institutional issues of automated driving cars based on depth interviews of experts. The introduction of automated driving cars is giving new opportunity for media industry as contents provider. Telcos and IT corporations are expected to compete each other to get the control of infotainment systems of automated driving cars. The reform of current regulations regarding car driving is pointed as important task to protect private information and the introduction of automated driving cars.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.257-266
• /
• 2023

The aim of this study is to use media big data to understand the characteristics and changes in technology that prevents wandering and missing for dementia patients as well as supports safe walking since 1990 until recently. BigKinds as a media big data was used to conduct an analysis in two stages. In the results, first, the media reports began to be reported in the early 2000s, and it increased after 2014. Second, regarding to the characteristics of changes in technology and device utilization, there has been a change to advanced technology that combines AI and IoT, focusing on GPS. Drone has recently increased in media report, however problems of personal information security need to be resolved. Third, technology development focused on location identification by police and guardians. Based on the results, technology development and community cooperation for dementia patient were discussed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1102-1103
• /
• 2023

안전모 착용 여부를 확인하는 객체 탐지 모델을 물류 현장에서 활용하기 위해서는 안전모를 착용한 경우와 착용하지 않은 경우를 정확하게 탐지해야 한다. 하지만 학습 데이터가 안전모를 착용한 클래스와 착용하지 않은 클래스 간 불균형이 존재하는 경우 해당 데이터만으로는 태스크에 맞게 학습이됐다고 보긴 힘들다. 본 연구는 데이터 증강 기법 적용 시 임의의 데이터에 증강을 적용하는 대신 상대적으로 적은 안전모를 착용하지 않은 클래스를 포함하는 이미지에 대하여 데이터 증강 기법을 적용하였다. 여러 데이터 증강 기법 중 Rotation, Gaussian Noise, 객체를 기준으로 한 Crop을 직접 구현 및 적용하여 객체 탐지 모델인 YOLOv5의 성능을 효과적으로 높이며 더욱 강건한 모델을 개발하는 방법을 제안한다.

• Smart Media Journal
• /
• v.7 no.1
• /
• pp.45-51
• /
• 2018

Avian influenza (AI) is notorious for its rapid infection rate, and has a serious impact on consumers and producers alike, especially in poultry farms. The AI outbreak, which occurred nationwide at the end of 2016, devastated the livestock farming industries. As a result, the prices of eggs and egg products had skyrocketed, and the event was reported by the media with heavy emphasis. The purpose of this study was to investigate the correlation between the egg price fluctuation and the keyword changes in online news articles reflecting social issues. To this end, we analyzed 682 cases of AI-related online news articles for fourteen weeks from November 2016 in South Korea. The results of this study are expected to contribute to understanding the relationship between the actual price of eggs and the keywords from news articles related to social issues.

• International Journal of Advanced Culture Technology
• /
• v.7 no.2
• /
• pp.195-200
• /
• 2019

Media art, which is a combination of media technology and art, is making a lot of progress in combination with AI, IoT and VR. This paper aims to meet people's needs by creating a video that simulates the dance moves of an object that users admire by using media art that features interactive interactions between users and works. The project proposed a universal image synthesis system that minimizes equipment constraints by utilizing a deep running-based Skeleton estimation system and one of the deep-running neural network structures, rather than a Kinect-based Skeleton image. The results of the experiment showed that the images implemented through the deep learning system were successful in generating the same results as the user did when they actually danced through inference and synthesis of motion that they did not actually behave.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.145-147
• /
• 2022

본 논문에서는 훼손되어 식별할 수 없는 탑 이미지를 비롯해 낮은 해상도의 탑 이미지를 개선하기 위해 우리는 탑 이미지의 화질 개선을 인공지능을 이용하여 빠르게 개선을 해 보고자 한다. 최근에 Generative Adversarial Networks(GANS) 알고리즘에서 SrGAN 알고리즘이 나오면서 이미지 생성, 이미지 복원, 해상도 변화 분야가 지속해서 발전하고 있다. 이에 본 연구에서는 다양한 GAN 알고리즘을 화질 개선에 적용해 보았다. 탑 이미지에 GAN 알고리즘 중 SrGan을 적용하였으며 실험한 결과 Srgan 알고리즘은 학습이 진행되었으며, 낮은 해상도의 탑 이미지가 높은 해상도, 초고해상도 이미지가 생성되는 것을 확인했다.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.115-122
• /
• 2021

This study attempted to examine how Personalization Advertising and Customization Advertising strategies affect consumers' Aad among AI-based Programmatic Advertising strategies that have been actively conducted recently. To this end, the relationship between two advertising strategies, the transportation, the overall emotional experience that occurs when acting, and Aad was examined structurally. As a result of a survey of 110 general people, Personalization Advertising had a negative influence on consumers' transportation, and the Customization Advertising strategy had a positive influence. In addition, transportation had a positive influence on the Aad. These results suggest the needs to actively induce consumers into Customization advertising situation, rather than the company's mechanical analysis and exposure-oriented advertising strategy.