• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.77-83
• /
• 2022

As users' needs for customized services increase, the service provision method is changing from a vertical structural service provision method to a horizontal structural service provision method. This paradigm shift has led to a change from the way existing users find the content they want to find and provide customized needs of users by content providers. With the recent development of smartphones and various AI technologies, demand for providing seamless services such as smartphones is increasing in automobiles. However, it is difficult to provide services in line with changes in this service paradigm because automobile services provide services centered on finished car manufacturers rather than individually providing services tailored to user needs. In this paper, we develop a Node-RED-based dynamic vehicle service simulation tool so that users can use the service they want in cars. The simulation tool developed provides a simulation environment for services authored by the user using NodeRed by writing, registering, and using NodeRed.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.3
• /
• pp.245-251
• /
• 2023

Facial expression recognition plays a significant role in understanding human emotional states. With the advancement of AI and computer vision technologies, extensive research has been conducted in various fields, including improving customer service, medical diagnosis, and assessing learners' understanding in education. In this study, we develop a model that can infer emotions in real-time from a webcam using transfer learning with TensorFlow.js and MobileNet. While existing studies focus on achieving high accuracy using deep learning models, these models often require substantial resources due to their complex structure and computational demands. Consequently, there is a growing interest in developing lightweight deep learning models and transfer learning methods for restricted environments such as web browsers and edge devices. By employing MobileNet as the base model and performing transfer learning, our study develops a deep learning transfer model utilizing JavaScript-based TensorFlow.js, which can predict emotions in real-time using facial input from a webcam. This transfer model provides a foundation for implementing facial expression recognition in resource-constrained environments such as web and mobile applications, enabling its application in various industries.

• The Journal of Information Systems
• /
• v.32 no.2
• /
• pp.87-108
• /
• 2023

Purpose The main purpose of this study is to improve fake news detection performance by using video information to overcome the limitations of extant text- and image-oriented studies that do not reflect the latest news consumption trend. Design/methodology/approach This study collected video clips and related information including news scripts, speakers' facial expression, and video metadata from YouTube to develop fake news detection model. Based on the collected data, seven combinations of related information (i.e. scripts, video metadata, facial expression, scripts and video metadata, scripts and facial expression, and scripts, video metadata, and facial expression) were used as an input for taining and evaluation. The input data was analyzed using six models such as support vector machine and deep neural network. The area under the curve(AUC) was used to evaluate the performance of classification model. Findings The results showed that the ACU and accuracy values of three features combination (scripts, video metadata, and facial expression) were the highest in logistic regression, naïve bayes, and deep neural network models. This result implied that the fake news detection could be improved by using video information(video metadata and facial expression). Sample size of this study was relatively small. The generalizablity of the results would be enhanced with a larger sample size.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.873-879
• /
• 2022

In the future, AI and the metaverse are becoming so powerful that their application areas and influences are swallowing up the world. The advertising field is no exception, and it is becoming more important to predict, analyze, and strategize these future changes. In order to study the future change of advertising according to the development of artificial intelligence and metaverse, literature research related to the development of artificial intelligence and metaverse technology and the resulting change in the advertising environment, in-depth interviews with future and advertising experts, and Delphi technique research method I want to study change. First, through this study, we would like to examine the opinions of experts through in-depth interviews on the development of artificial intelligence and metaverse technology and the changes in the advertising sector in the post-coronavirus era of civilizational transformation. In addition, the Delphi technique is used to determine how important the change is by future advertising technology area, future advertising media area, future advertising form area, future advertising effect area, future advertising application area, and future advertising process area, and at what point in the future it will change. In addition, we want to study how the future advertising form will change in detail. Also, based on this, we would like to propose a countermeasure for the advertising industry.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.983-991
• /
• 2019

This study aims to analyze movies which contain various stories according to the size of their shots. To achieve this, it is needed to classify dataset according to the shot size, such as extreme close-up shots, close-up shots, medium shots, full shots, and long shots. However, a typical video storytelling is mainly composed of close-up shots, medium shots, full shots, and long shots, it is not an easy task to construct an appropriate dataset for extreme close-up shots. To solve this, we propose an image cropping method based on the region of interest (ROI) detection. In this paper, we use the face detection and saliency detection to estimate the ROI. By cropping the ROI of close-up images, we generate extreme close-up images. The dataset which is enriched by proposed method is utilized to construct a model for classifying shots based on its size. The study can help to analyze the emotional changes of characters in video stories and to predict how the composition of the story changes over time. If AI is used more actively in the future in entertainment fields, it is expected to affect the automatic adjustment and creation of characters, dialogue, and image editing.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.2
• /
• pp.211-219
• /
• 2019

Accomplishing information system, techniques, methodology have been studied continuously and give much help to auditors who are using them. Additionally audit report which is the conclusion of accomplishing ISA(information system audit), has law of a basis and phase with ITA/EA Law(Electronic Government Law). This paper is for better quality of ISA report. But it has more errors about sentence and Grammatical structures. In this paper, to achieve quality improvement objectives, it is necessary to recognize the importance of an audit report by investigating on objectives, functionality, structures and usability of a report firstly, and a legal basis, the presence of report next. Several types of audit reports were chosen and the reports errors were divided into several categories and analyzed. After grasping reasons of those errors, the methods for fixing those errors and check-lists model was provided. And based on that foundation, the effectiveness validation about real audit reports was performed. The necessity for efforts to improve the quality of audit reports was emphasized and further research subject(AI Automatic tool) of this paper conclusion. We also expect this paper to be useful for the organization to improve on ISA in the future.

• Journal of the Korea Convergence Society
• /
• v.13 no.4
• /
• pp.233-244
• /
• 2022

One of the most noteworthy topics in recent corporate management is ESG(Environmental, Social, Governance). Although there are many companies that have declared ESG management, KT has declared full-fledged ESG management in 2021 and is sharing its sustainable management strategy with stakeholders. In addition, KT is strengthening ESG management by issuing ESG bonds for the first time in the domestic ICT industry. At a time when the information technology industry became more important due to COVID-19, this study attempted to examine KT's ESG management goals and strategies by dividing them into environmental, social, and governance areas. KT was aiming to achieve environmental integrity through 'environmental management', 'green competence', 'energy resources', and 'eco-friendly projects' in the environmental field. In addition, in the social field, genuine creating social value was pursued through 'social contribution', 'co-growth', and 'human rights management'. Finally, in the governance area, it was aiming for a transparent corporate management system to pursue economic reliability through 'ethics and compliance' and 'risk management'. In particular, KT was promoting its own ESG management by promoting strategies to solve environmental and social problems using AI and BigData technologies based on the characteristics of a digital platform company. This study aims to derive implications for ESG strategy establishment and ESG management development direction through KT's ESG management case in relation to ESG management, which has emerged as a hot topic.

• Trans-
• /
• v.13
• /
• pp.35-58
• /
• 2022

This study predicts the paradigm shift that the development of artificial intelligence technology will bring to the production of music content, and suggests that works created through collaboration between artificial intelligence and humans can have artistic value as finished products. Anyone can easily produce music content using artificial intelligence composition programs, and it has become an opportunity to inspire artists with various attempts and creative ideas. Although artificial intelligence technology provides convenience in human life and benefits a lot in the efficient aspect of work, it is difficult to escape the perception of data-based pattern music in the art field so far. Pattern music with many quantitative elements is not recognized as a complete creation due to the absence of abstract symbolism or meaning pursued by art. However, it predicts that if qualitative elements such as emotions and creativity are given to artificial intelligence music through human collaboration, it can be recognized as a complete work of art. The development of artificial intelligence technology increases access to culture and art from the public, and it can be expected that anyone can enjoy it as well as aesthetic experiences. In addition, various contents can be produced by improving individual digital literacy, and it is an opportunity to share and communicate with others. As such, artificial intelligence technology serves as a medium connecting the public with culture and art, and is narrowing the gap between humans and technology through art activities. Along with this cultural phenomenon, we predict the possibility of research on the production of artificial intelligence music contents with artistic value and the development of various convergence and complex art contents using artificial intelligence technology in the future.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.4
• /
• pp.5-24
• /
• 2021

The purpose of this study was to investigate and analyze the operating conditions of lecture contents in contactless online classes for University students. First, as a result of analyzing the responses of 93 respondents, 93.3% of the respondents took real-time online lectures (47.7%) or recorded video lectures (45.6%). Second, as a result of analyzing the contents used as textbooks, it was found that e-books (materials) and paper books (materials) were used together (36.6%), or e-books or electronic materials (36.6% and 37.6% respectively) were used in both liberal arts (47.3%) and major subjects (39.8%). In addition to textbooks, both major subjects and liberal arts highly used web materials (47.6% and 40.5% respectively) and YouTube materials (33.3% and 48.0% respectively) as external materials. Third, both liberal arts and major subjects used 'electronic files in the form of PPT or text organized and written by instructors' (62.9% and 58.1% respectively), 'internet materials' (16.7% and 19% respectively) and 'paper book or materials' (10.4% and 12.3% respectively) to share lecture contents. For the screen displayed lecture contents, 93.5% of the respondents satisfied in major subjects, and 90.2% of the respondents satisfied in liberal arts. These results suggest developing multimedia-based lecture contents and an evaluation solution capable of real-time exam supervision, developing a task management system capable of AI-based plagiarism search, task guidance, and task evaluation, and institutionalizing a solution to copyright problems for electronicizing lecture materials so that lectures can be given in the ubiquitous environment.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.936-939
• /
• 2022

As air combat system technologies developed in recent years, the development of air defense systems is required. In the operating concept of the anti-aircraft defense system, selecting an appropriate armament for the target is one of the system's capabilities in efficiently responding to threats using limited anti-aircraft power. Much of the flying threat identification relies on the operator's visual identification. However, there are many limitations in visually discriminating a flying object maneuvering high speed from a distance. In addition, as the demand for unmanned and intelligent weapon systems on the modern battlefield increases, it is essential to develop a technology that automatically identifies and classifies the aircraft instead of the operator's visual identification. Although some examples of weapon system identification with deep learning-based models by collecting video data for tanks and warships have been presented, aerial vehicle identification is still lacking. Therefore, in this paper, we present a model for classifying fighters, helicopters, and drones using a convolutional neural network model and analyze the performance of the presented model.