• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.1051-1052
• /
• 2024

코로나19 이후 비대면 커뮤니케이션의 확산과 메신저의 발달로 인해 말하기 공포가 증가하여, 진단 및 치료를 위한 임상적 대화 훈련 해결책의 필요성이 높아지고 있다. 인공지능(AI)과의 말하기 시뮬레이션을 통해 사회불안장애 진단 및 솔루션 제공이 가능한 플랫폼 개발을 목표로 한다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.388-389
• /
• 2022

Recently, AI (Artificial Intelligence) has been applied to various technologies such as automatic driving, robot and smart communication. Currently, AI system is developed by software-based method using tensor flow, and GPU (Graphic Processing Unit) is employed for processing unit. However, if software-based method employing GPU is used for AI applications, there is a problem that we can not change the internal circuit of processing unit. In this method, if high-level jobs are required for AI system, we need high-performance GPU, therefore, we have to change GPU or graphic card to perform the jobs. In this work, we developed a CNN-based FPGA (Field Programmable Gate Array) chip to solve this problem.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.57-58
• /
• 2022

Sleep apnea (SA) is a common chronic sleep disorder that disrupts breathing during sleep. Clinically, the standard for diagnosing SA involves nocturnal polysomnography (PSG). However, this requires expert human intervention and considerable time, which limits the availability of SA diagnoses in public health sectors. Therefore, ECG-based methods for SA detection have been proposed to automate the PSG procedure and reduce its discomfort. We propose a preprocessing method to convert the one-dimensional time series of ECG into two-dimensional images using the Gramian Angular Field (GAF) algorithm, extract temporal features, and use a two-dimensional convolutional neural network for classification. The results of this study demonstrated that the proposed method can perform SA detection with specificity, sensitivity, accuracy, and area under the curve (AUC) of 88.89%, 81.50%, 86.11%, and 0.85, respectively. Our experimental results show that SA is successfully classified by extracting preprocessing transforms with temporal features.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.28 no.4
• /
• pp.133-142
• /
• 2023

In this paper, we built a data-driven artificial intelligence model using RNN-LSTM (Recurrent Neural Networks-Long Short-Term Memory) to predict the Lorenz system, and examined the possibility of whether this model can replace chaotic dynamic models. We confirmed that the data-driven model reflects the chaotic nature of the Lorenz system, where a small error in the initial conditions produces fundamentally different results, and the system moves around two stable poles, repeating the transition process, the characteristic of "deterministic non-periodic flow", and simulates the bifurcation phenomenon. We also demonstrated the advantage of adjusting integration time intervals to reduce computational resources in data-driven models. Thus, we anticipate expanding the applicability of data-driven artificial intelligence models through future research on refining data-driven models and data assimilation techniques for data-driven models.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.35-44
• /
• 2021

Recent advances in the 4th Industrial Revolution have accelerated the change of the working environment, such that the paradigm of education has been shifted in accordance with career education including the free semester system and the high school credit system. While the purpose of those systems is students' self-motivated career exploration, educational limitations for teachers and students exist due to the rapid change of the information on education. Also, education technology research to tackle these limitations is relatively insufficient. To this end, this study first defines three requirements that education technologies for the career education system should consider. Then, through data-driven artificial intelligence technology, this study proposes a data system and an artificial intelligence recommendation model that incorporates the topics for career exploration, courses, and majors in one scheme. Finally, this study demonstrates that the set-based artificial intelligence model shows satisfactory performances on recommending career education contents such as courses and majors, and further confirms that the actual application of this system in the educational field is acceptable.

• Water for future
• /
• v.54 no.12
• /
• pp.8-14
• /
• 2021

• Journal of Korea Technology Innovation Society
• /
• v.22 no.2
• /
• pp.242-264
• /
• 2019

This study focuses on considering the factors affecting the user intention to adopt an intelligent service - A.I. speaker services. Currently there can be a considerable difference between the expectation and the realized diffusion of IT-based intelligent services. This study aims to find out this gap based on the idea of diver previous researches including TAM and UTAUT studies and to identify the direct and indirect effects of diverse factors such as security issues, perceived time pressure, service innovativeness, and the experience of these IT-based intelligent services. And this study considers the expected impact of perceived time pressure factor on the user acceptance of A.I. speaker services. In analysis results, not only the traditional factors such as the perceived usefulness and the hedonic/utilitarian motives but also the perceived time pressure, the perceived security issues, and the experience of the services should be considered as meaningful factors to affect the users adopting A.I. speaker services.

• Journal of Korean Library and Information Science Society
• /
• v.53 no.1
• /
• pp.231-263
• /
• 2022

The understanding and capability to utilize artificial intelligence (AI) incorporated technology has become a required basic skillset for the people living in today's information age, and various members of the university have also increasingly become aware of the need for AI education. Amidst such shifting societal demands, both domestic and international university libraries have recognized the users' need for educational content centered on AI, but a user-centered service that aims to provide personalized recommendations of digital AI educational content is yet to become available. It is critical while the demand for AI education amongst university students is progressively growing that university libraries acquire a clear understanding of user intention towards an AI educational content recommender system and the potential factors contributing to its success. This study intended to ascertain the factors affecting acceptance of such system, using the Extended Technology Acceptance Model with added variables - innovativeness, self-efficacy, social influence, system quality and task-technology fit - in addition to perceived usefulness, perceived ease of use, and intention to use. Quantitative research was conducted via online research surveys for university students, and quantitative research was conducted through written interviews of university librarians. Results show that all groups, regardless of gender, year, or major, have the intention to use the AI-related Educational Content Recommendation System, with the task suitability factor being the most dominant variant to affect use intention. University librarians have also expressed agreement about the necessity of the recommendation system, and presented budget and content quality issues as realistic restrictions of the aforementioned system.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.379-384
• /
• 2022

관계 추출은 두 개체 간의 관계를 식별하는 작업이며, 비정형 텍스트를 구조화시키는 역할을 하는 작업 중 하나이다. 현재 관계 추출에서 다양한 모델에 대한 연구들이 진행되고 있지만, 한국어 관계 추출 모델에 대한 연구는 영어에 비해 부족하다. 따라서 본 논문에서는 NE(Named Entity)태그 정보가 반영된 TEM(Typed Entity Marker)과 의존 구문 그래프를 이용한 한국어 관계 추출 모델을 제안한다. 모델의 학습과 평가 말뭉치는 KLUE에서 제공하는 관계 추출 학습 말뭉치를 사용하였다. 실험 결과 제안 모델이 68.57%의 F1 점수로 실험 모델 중 가장 높은 성능을 보여 NE태그와 구문 정보가 관계 추출 성능을 향상시킬 수 있음을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.528-531
• /
• 2021

띄어쓰기에 대한 오류는 한국어 처리 전반에 영향을 주므로 자동 띄어쓰기는 필수적인 요소이다. 글쓴이의 대부분은 띄어쓰기 오류를 범하지 않으므로 글쓴이의 의도가 띄어쓰기 시스템에 반영되어야 한다. 그러나 대부분의 자동 띄어쓰기 시스템은 모든 띄어쓰기 정보를 제거하고 새로이 공백문자를 추가하는 방법으로 띄어쓰기를 수행한다. 이런 문제를 완화하기 위해서 본 논문에서는 기계학습에서 글쓴이의 의도가 반영된 자질을 추가하는 방법을 제안한다. 실험을 위해서 CRFs(Conditional Random Fields)를 사용하여 기존 시스템과 사용자의 의도를 반영한 띄어쓰기 시스템과의 성능을 비교하고 분석한다.