• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.55-58
• /
• 2024

최근 각 기업의 AI 면접시스템 도입이 증가하고 있으며, AI 면접에 대한 실효성 논란 또한 많은 상황이다. 본 논문에서는 AI 면접 과정에서 지원자를 평가하는 방식을 시각, 음성, 자연어처리 3영역에서 구현함으로써, 면접 지원자를 다방면으로 분석 방법론의 적절성에 대해 평가하고자 한다. 첫째, 시각적 측면에서, 면접 지원자의 감정을 인식하기 위해, 합성곱 신경망(CNN) 기법을 활용해, 지원자 얼굴에서 6가지 감정을 인식했으며, 지원자가 카메라를 응시하고 있는지를 시계열로 도출하였다. 이를 통해 지원자가 면접에 임하는 태도와 특히 얼굴에서 드러나는 감정을 분석하는 데 주력했다. 둘째, 시각적 효과만으로 면접자의 태도를 파악하는 데 한계가 있기 때문에, 지원자 음성을 주파수로 환산해 특성을 추출하고, Bidirectional LSTM을 활용해 훈련해 지원자 음성에 따른 6가지 감정을 추출했다. 셋째, 지원자의 발언 내용과 관련해 맥락적 의미를 파악해 지원자의 상태를 파악하기 위해, 음성을 STT(Speech-to-Text) 기법을 이용하여 텍스트로 변환하고, 사용 단어의 빈도를 분석하여 지원자의 언어 습관을 파악했다. 이와 함께, 지원자의 발언 내용에 대한 감정 분석을 위해 KoBERT 모델을 적용했으며, 지원자의 성격, 태도, 직무에 대한 이해도를 파악하기 위해 객관적인 평가지표를 제작하여 적용했다. 논문의 분석 결과 AI 면접의 다면적 평가시스템의 적절성과 관련해, 시각화 부분에서는 상당 부분 정확도가 객관적으로 입증되었다고 판단된다. 음성에서 감정분석 분야는 면접자가 제한된 시간에 모든 유형의 감정을 드러내지 않고, 또 유사한 톤의 말이 진행되다 보니 특정 감정을 나타내는 주파수가 다소 집중되는 현상이 나타났다. 마지막으로 자연어처리 영역은 면접자의 발언에서 나오는 말투, 특정 단어의 빈도수를 넘어, 전체적인 맥락과 느낌을 이해할 수 있는 자연어처리 분석모델의 필요성이 더욱 커졌음을 판단했다.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.285-294
• /
• 2024

This study aims to enhance learners' creative and integrative thinking through the use of a practical music education program, facilitating high-quality artistic activities and the integration of various disciplines. To achieve this, a practical music education program incorporating the PDIE model was designed, and the content validity of the developed program was verified. Through this process, We have researched and described methodologies for multidisciplinary research that can be applied in practical music education. This paper focuses on the fourth session of the study, which deals with the creative and integrative education of practical music and mathematics. The mathematical theory of interest in this research is the Fibonacci sequence, fundamental to the golden ratio in art. The goal is to enable balanced and high-quality creative activities through learning and applying the Fibonacci sequence. Additionally, to verify the validity and effectiveness of the instructional plan, including the one used in the 15-week course, we have detailed the participants involved in the content validation, the procedures of the research, the research tools used, and the methods for collecting and analyzing various data. Through this, We have confirmed the potential of creative and integrative education in higher practical music education and sought to develop educational methodologies for cultivating various creative talents in subsequent research.

• Journal of The Korean Association For Science Education
• /
• v.34 no.2
• /
• pp.63-78
• /
• 2014

Integrative STEM education is an engineering design-based learning approach that purposefully integrates the content and process of STEM disciplines and can extend its concept to integration with other school subjects. This study was part of fundamental research to develop an integrative STEM education program based on the science inquiry process. The specific objectives of this study were to review relevant literature related to STEM education, analyze the key elements and value of STEM education, develop an integrative STEM education model based on the science inquiry process, and suggest an exemplary program. This study conducted a systematic literature review to confirm key elements for integrative STEM education and finally constructed the integrative STEM education model through analyzing key inquiry processes extracted from prior studies. This model turned out to be valid because the average CVR value obtained from expert group was 0.78. The integrative STEM education model based on the science inquiry process consisted of two perspectives of the content and inquiry process. The content can contain science, technology, engineering, and liberal arts/artistic topics that students can learn in a real world context/problem. Also, the inquiry process is a problem-solving process that contains design and construction and is based on the science inquiry. It could integrate the technological/engineering problem solving process and/or mathematical problem solving process. Students can improve their interest in STEM subjects by analyzing real world problems, designing possible solutions, and implementing the best design as well as acquire knowledge, inquiry methods, and skills systematically. In addition, the developed programs could be utilized in schools to enhance students' understanding of STEM disciplines and interest in mathematics and science. The programs could be used as a basis for fostering convergence literacy and cultivating integrated and design-based problem-solving ability.

• Journal of Internet Computing and Services
• /
• v.21 no.1
• /
• pp.169-178
• /
• 2020

The reductions of troops/human resources, and improvement in combat power have made Korean Department of Defense actively adapt 4th Industrial Revolution technology (Artificial Intelligence, Big Data). The defense information system has been developed in various ways according to the task and the uniqueness of each military. In order to take full advantage of the 4th Industrial Revolution technology, it is necessary to improve the closed defense datamanagement system.However, the establishment and usage of data standards in all information systems for the utilization of defense big data and artificial intelligence has limitations due to security issues, business characteristics of each military, anddifficulty in standardizing large-scale systems. Based on the interworking requirements of each system, data sharing is limited through direct linkage through interoperability agreement between systems. In order to implement smart defense using the 4th Industrial Revolution technology, it is urgent to prepare a system that can share defense data and make good use of it. To technically support the defense, it is critical to develop Multi Repository Meta-Data Management (MRMM) that supports systematic standard management of defense data that manages enterprise standard and standard mapping for each system and promotes data interoperability through linkage between standards which obeys the Defense Interoperability Management Development Guidelines. We introduced MRMM, and implemented by using vocabulary similarity using machine learning and statistical approach. Based on MRMM, We expect to simplify the standardization integration of all military databases using artificial intelligence and bigdata. This will lead to huge reduction of defense budget while increasing combat power for implementing smart defense.

• The Journal of Korean Philosophical History
• /
• no.31
• /
• pp.347-374
• /
• 2011

Along with Hujiwara Seika(藤原惺窩), Hayashi Razan(林羅山) is called the founder of the Japanese Confucianism in the Eto(江戶) era. And it is necessary for us to grasp that how Razan understand the theory of I-Ki(理氣論), then we can investigate the characteristics of his thought. In ordinary, people understand that the theory of I-Ki, as a completed view of the world, is integration of the structure of theory of the neo-Confucianism. So a certain thinker's ideological attitude is determined according to how people understand the theory. And then we can grasp the structure of his view of the world and human. Therefore, the purpose of this paper is to study how Razan had understanded the I(理) and Ki(氣). In spite of a scholar of Zhu Xi(朱熹), Razan didn't accept Zhu's view of I-Ki, he seem to lean toward the view of Wang Yangmings'(王陽明) in the his early learning days. But that doesn't mean he is a scholar of doctrine of Wang Yangming. When he meets the logical contradiction under the process of investigating the problem of Sein and Sollen, he just only to explain it with logic of Ki(氣) which is closed by mind. Meanwhile if we suppose I(理) is pure goodness and there is no things outside of I(理), if so Razan doubts about that where is the root of evil and he try to investigate the answer. In his latter years, Razan takes Zhu Xi's doctrine again get out of the mental attitude to the view of I-Ki(理氣). The outcome of precedent study about Razan points a fact that Razan needs a little more digging into the ieda of 'Fact and Sollen' which had been the reason of ideal confusion of him. But his ideal confusion is not the point of issue. Point is that Razan had understanded I-Ki(理氣) with monistic of Shim(心) in his early years. As a result, that bring about the outcome which exclude ontological thinking, and had come to grips with aspects of Sollen of all things in understanding of the doctrine of Zhu Xi. And I think that is the clue to understanding of Razan's learning.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.201-220
• /
• 2019

Fake news has emerged as a significant issue over the last few years, igniting discussions and research on how to solve this problem. In particular, studies on automated fact-checking and fake news detection using artificial intelligence and text analysis techniques have drawn attention. Fake news detection research entails a form of document classification; thus, document classification techniques have been widely used in this type of research. However, document summarization techniques have been inconspicuous in this field. At the same time, automatic news summarization services have become popular, and a recent study found that the use of news summarized through abstractive summarization has strengthened the predictive performance of fake news detection models. Therefore, the need to study the integration of document summarization technology in the domestic news data environment has become evident. In order to examine the effect of extractive summarization on the fake news detection model, we first summarized news articles through extractive summarization. Second, we created a summarized news-based detection model. Finally, we compared our model with the full-text-based detection model. The study found that BPN(Back Propagation Neural Network) and SVM(Support Vector Machine) did not exhibit a large difference in performance; however, for DT(Decision Tree), the full-text-based model demonstrated a somewhat better performance. In the case of LR(Logistic Regression), our model exhibited the superior performance. Nonetheless, the results did not show a statistically significant difference between our model and the full-text-based model. Therefore, when the summary is applied, at least the core information of the fake news is preserved, and the LR-based model can confirm the possibility of performance improvement. This study features an experimental application of extractive summarization in fake news detection research by employing various machine-learning algorithms. The study's limitations are, essentially, the relatively small amount of data and the lack of comparison between various summarization technologies. Therefore, an in-depth analysis that applies various analytical techniques to a larger data volume would be helpful in the future.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.427-434
• /
• 2022

This study aims to develop design elements for cultural convergence between rehabilitation for individuals with developmental disabilities and lifelong education for individuals with disabilities, which is a key area in the practical support system for independent life support for individuals with developmental disabilities. As for the research method, a procedure for conducting FGI by forming two teams for professors majoring in special education and rehabilitation science was formed. The research was presented in three upper categories (universal cultural convergence elements, field-centered cultural convergence elements, and policy-centered cultural convergence elements) that should be designed for cultural convergence between rehabilitation for individuals with developmental disabilities and lifelong education for individuals with disabilities. In addition, subcategories were specifically composed for each upper category. First, as a universal cultural element, "open creative convergence" was presented in principle, which can be explained as a principle of exploring and practicing the validity of convergence between related fields for rehabilitation for individuals with developmental disabilities and lifelong education for individuals with disabilities. Second, field-centered cultural factors included development of joint practice model between fields of rehabilitation science and special education, subject matter education knowledge and skills, teaching and learning methods, learning career roadmaps, employment and job career development roadmaps, and the formation of an independent life development history certification system. Third, as policy-centered cultural elements, the formation of a curriculum integration composition system between local related institutions, the establishment of a qualification development path for coordinator-professional teacher-type personnel, and the organizational systematization between school-center types were presented. The study concluded that independent life support for individuals with developmental disabilities should not only be guaranteed for the entire life of adulthood, but also a lifelong education for individuals with disabilities based rehabilitation support system for individuals with developmental disabilities should be established through cultural convergence.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Journal of Service Research and Studies
• /
• v.14 no.1
• /
• pp.13-26
• /
• 2024

Multi-modal generation is the process of generating results based on a variety of information, such as text, images, and audio. With the rapid development of AI technology, there is a growing number of multi-modal based systems that synthesize different types of data to produce results. In this paper, we present an AI system that uses speech and text recognition to describe a person and generate a montage image. While the existing montage generation technology is based on the appearance of Westerners, the montage generation system developed in this paper learns a model based on Korean facial features. Therefore, it is possible to create more accurate and effective Korean montage images based on multi-modal voice and text specific to Korean. Since the developed montage generation app can be utilized as a draft montage, it can dramatically reduce the manual labor of existing montage production personnel. For this purpose, we utilized persona-based virtual person montage data provided by the AI-Hub of the National Information Society Agency. AI-Hub is an AI integration platform aimed at providing a one-stop service by building artificial intelligence learning data necessary for the development of AI technology and services. The image generation system was implemented using VQGAN, a deep learning model used to generate high-resolution images, and the KoDALLE model, a Korean-based image generation model. It can be confirmed that the learned AI model creates a montage image of a face that is very similar to what was described using voice and text. To verify the practicality of the developed montage generation app, 10 testers used it and more than 70% responded that they were satisfied. The montage generator can be used in various fields, such as criminal detection, to describe and image facial features.

• Cartoon and Animation Studies
• /
• s.49
• /
• pp.359-382
• /
• 2017

Content is the complex of art and technology of trend, so it is important to experience different technologies for content education. Today, many non-profit organizations plan and operate numbers of programs for disabilities, low-income, and minority families to enhance the quality of life and the realization of social integration. These programs are limited to museums and galleries, not so pro-actively in progressing. Various contend education is necessary to the expansion of cultural exchange for the culturally alienated area. Naver is running an outreach program named . It is an experience-based outreach program where current cartoon / webtoon writers come directly to the school to inform students about the basic story of comics and comic techniques. However, the fact that the is not centered on the marginalized area but is centered on the Seoul Gyeonggi area, has the limitation that they can not benefit from a wide range of programs because they have a space limit of 'school', and, has a spatial limitation that the experience of the work is excluded. 'Outreach programs in marginalized areas' must be reorganized into a fluid dimension, not a fixed, single-system program. You should be able to experience and experience your work by directly using various professional equipment of comics based on your capacity and experience, local culture, religion, and society. These program participants will gain the effect of attractive and effective learning with empathy with their comic experience. Meanings of Comics content outreach program are following: First, the rich cultural archive can be used efficiently by providing various contents to existing outreach programs with the educational limitation of museums and galleries. Second, Comics contents can be enjoyed as a part of our life by understanding diversity and technology of contents. Third, because it is the program of expertise' participation, it can remodel, and restructure the severed experience in remote areas for the continuous growth and development, and furthermore, it can enhance the understanding of society.