• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.165-170
• /
• 2024

This study aims to verify the accuracy of the air quality management system in Yangju City using an artificial intelligence (AI) evaluation model. The consistency and reliability of fine dust data were assessed by comparing public data from the Ministry of Environment with data from Yangju City's air quality management system. To this end, we analyzed the completeness, uniqueness, validity, consistency, accuracy, and integrity of the data. Exploratory statistical analysis was employed to compare data consistency. The results of the AI-based data quality index evaluation revealed no statistically significant differences between the two datasets. Among AI-based algorithms, the random forest model demonstrated the highest predictive accuracy, with its performance evaluated through ROC curves and AUC. Notably, the random forest model was identified as a valuable tool for optimizing the air quality management system. This study confirms that the reliability and suitability of fine dust data can be effectively assessed using AI-based model performance evaluation, contributing to the advancement of air quality management strategies.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.1088-1089
• /
• 2024

본 연구는 농인의 언어권 보장을 위한 한국어-한국수어 번역 프로그램의 필요성을 제기하고 있다. 이를 위해 KoBART 모델을 활용하여 한국어 텍스트를 한국수어로 효과적으로 변환한다. ControlNet을 통해 수어 영상에서 손의 위치와 제스처를 정밀하게 추출하여 Stable Diffusion 모델을 제공함으로써 고해상도의 아바타 영상을 생성한다. 이러한 기술을 바탕으로 개발된 애플리케이션은 사용자가 음성을 입력하면 이를 텍스트로 변환하고, 변환된 텍스트에 대응하는 수어 영상을 순차적으로 재생하여 농인의 의사소통을 보다 원활하게 지원한다.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.12
• /
• pp.125-134
• /
• 2019

As the limitations of the passive recognition domain, which is not guaranteed transparency of the operation process, AI technology has a vulnerability that depends on the data. Human error is inherent because raw data for artificial intelligence learning must be processed and inspected manually to secure data quality for the advancement of AI learning. In this study, we examine the necessity of learning data management before machine learning by analyzing inaccurate cases of AI learning data and cyber security attack method through the approach from cyber security perspective. In order to verify the learning data integrity, this paper presents the direction of data-preserving artificial intelligence system, a blockchain-based learning data environment model. The proposed method is expected to prevent the threats such as cyber attack and data corruption in providing and using data in the open network for data processing and raw data collection.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.19-24
• /
• 2024

The future military combat environment is rapidly expanding the role and importance of artificial intelligence (AI) in defense, aligning with the current trends of declining military populations and evolving dynamics. Particularly, in the civilian sector, AI development has surged into new domains based on foundation models, such as OpenAI's Chat-GPT, categorized as Super-Giant AI or Hyperscale AI. The U.S. Department of Defense has organized Task Force Lima under the Chief Digital and AI Office (CDAO) to conduct research on the application of Large Language Models (LLM) and generative AI. Advanced military nations like China and Israel are also actively researching the integration of Super-Giant AI into their military capabilities. Consequently, there is a growing need for research within our military regarding the potential applications and fields of application for Super-Giant AI in weapon systems. In this paper, we compare the characteristics and pros and cons of specialized AI and Super-Giant AI (Foundation Models) and explore new application areas for Super-Giant AI in weapon systems. Anticipating future application areas and potential challenges, this research aims to provide insights into effectively integrating Super-Giant Artificial Intelligence into defense operations. It is expected to contribute to the development of military capabilities, policy formulation, and international security strategies in the era of advanced artificial intelligence.

• Communications of Mathematical Education
• /
• v.38 no.1
• /
• pp.49-67
• /
• 2024

Recent interest in the diverse applications of artificial intelligence (AI) language models has highlighted the need to explore didactical uses in mathematics education. AI language models, capable of natural language processing, show promise in solving mathematical word problems. This study tested the capability of ChatGPT, an AI language model, to solve word problems from elementary school textbooks, and analyzed both the solutions and errors made. The results showed that the AI language model achieved an accuracy rate of 81.08%, with errors in problem comprehension, equation formulation, and calculation. Based on this analysis of solution processes and error types, the study suggests implications for the didactical application of AI language models in education.

• Education of Primary School Mathematics
• /
• v.26 no.3
• /
• pp.163-180
• /
• 2023

This study aimed to investigate the factors influencing the intentions of elementary school teachers to use artificial intelligence (AI) in mathematics lessons and to identify the essential prerequisites for the effective implementation of AI in mathematics education. To achieve this purpose, we examined the structural relationship between elementary school teachers' TPACK(Technological Pedagogical Content Knowledge) and the TAM(Technology Acceptance Model) using structural equation model. The findings of the study indicated that elementary school teachers' TPACK regarding the use of AI in mathematics instruction had a direct and significant impact on their perceived ease of use and perceived usefulness of AI. In other words, when teachers possessed a higher level of TPACK competency in utilizing AI in mathematics classes, they found it easier to incorporate AI technology and recognized it as a valuable tool to enhance students' mathematics learning experience. In addition, perceived ease of use and perceived usefulness directly influenced the attitudes of elementary school teachers towards the integration of AI in mathematics education. When teachers perceived AI as easy to use in their mathematics lessons, they were more likely to recognize its usefulness and develop a positive attitude towards its application in the classroom. Perceived ease of use, perceived usefulness, and attitude towards AI integration in mathematics classes had a direct impact on the intentions of elementary school teachers to use AI in their mathematics instruction. As teachers perceived AI as easy to use, valuable, and developed a positive attitude towards its incorporation, their intention to utilize AI in mathematics education increased. In conclusion, this study shed light on the factors influencing elementary school teachers' intentions to use AI in mathematics classes. It revealed that teachers' TPACK plays a crucial role in facilitating the integration of AI in mathematics education. Additionally, the study emphasized the significance of enhancing teachers' awareness of the advantages and convenience of using AI in mathematics instruction to foster positive attitudes and intentions towards its implementation. By understanding these factors, educational stakeholders can develop strategies to effectively promote the utilization of AI in mathematics education, ultimately enhancing students' learning outcomes.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.642-643
• /
• 2023

피트니스 분야 인공지능 서비스의 성능 개선을 AI모델 개발이 아닌 데이터셋의 품질 개선을 통해 접근하는 방식을 제안하고, 데이터품질의 성능을 평가하는 것을 목적으로 한다. 데이터 설계는 각 분야 전문가 10명이 참여하였고, 단일 시점 영상을 이용한 운동동작 자동 분류에 사용된 모델은 Google의 MediaPipe 모델을 사용하였다. 팔굽혀펴기의 운동동작인식 정확도는 100%로 나타났으나 팔꿉치의 각도 15° 이하였을 때 동작의 횟수를 인식하지 않았고 이 결과 값에 대해 피트니스 전문가의 의견과 불일치하였다. 향후 연구에서는 동작인식의 분류뿐만 아니라 운동량을 연결하여 분석할 수 있는 시스템이 필요하다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.619-620
• /
• 2023

본 논문에서는 AI 모델이 노출될 수 있는 적대적 공격을 연구한 논문이다. AI 쳇봇이 적대적 공격에 노출됨에 따라 최근 보안 침해 사례가 다수 발생하고 있다. 이에 대해 본 논문에서는 적대적 공격이 무엇인지 조사하고 적대적 공격에 대응하거나 사전에 방어하는 방안을 연구하고자 한다. 적대적 공격의 종류 4가지와 대응 방안을 조사하고, AI 모델의 보안 중요성을 강조하고 있다. 또한, 이런 적대적 공격을 방어할 수 있도록 대응 방안을 추가로 조사해야 한다고 결론을 내리고 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.107-108
• /
• 2023

본 논문에서는 교량의 변위를 IoT 장치를 이용하여 실시간 측정하고 추출된 데이터를 이용하여 교량의 이상징후를 AI 기반으로 진단 및 모니터링 하는 방법을 제안한다. AI 모델 학습 학습을 위해서 비정상 상태의 교량이 필요하지만, 실제 교량에 인위적으로 비정상 상태를 만들 수 없으므로, 탄성 받침을 이용하여 모의 교량을 제작하였다. 탄성 받침을 이용하여 제작에 반영 및 모의교량에 적합한 모의 차량도 제작하여 정상적 데이터와 비정상적 데이터를 수집하였다. 수집된 데이터를 전처리 과정을 통해 AI 분석을 통해 교량의 이상 징후를 진단 및 모니터링하였으며, 제안 모델을 실험한 결과 96.7%의 정확도가 도출되었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.325-327
• /
• 2024

국내외에서 AI기반 의료 솔루션 시장은 빠른 속도로 확장 중이며 이에 따른 다양한 의학 분야에서 많은 기법을 통한 의료 AI 시스템이 등장하고 있다. 그러나 기존 다양한 AI 연구가 이뤄짐에도 아직 중환자의 징후 예측에는 많은 어려움이 있다. 또한, 중환자의 경우 현재 의료진만으로 모든 환자를 필요한 시기에 진료하기엔 어려움이 있고 환자 상태 조기 예측이 필수적임을 관련 다양한 의학 기사를 통해 쉽게 인지할 수 있다. 본 연구에서는 위와 같은 문제점을 해결하고자 중환자의 진료 결과 데이터를 활용하여 환자의 진료 후 상태를 예측하는 모델을 생성하였다. '용인시산업진흥원'에서 제공하는 60만여 건에 달하는 환자 데이터를 수집하여, 중환자 상태 징후를 조기에 예측할 수 있는 머신러닝/딥러닝 기반 알고리즘으로 구현한 여러 모델에 대해 비교했을 때 딥러닝(DNN) 기반 모델이 약 92%의 분류 정확도를 측정할 수 있었다.