• KIPS Transactions on Software and Data Engineering
• /
• v.13 no.1
• /
• pp.17-27
• /
• 2024

Video frame interpolation is an important technique used in the field of video and media, as it increases the continuity of motion and enables smooth playback of videos. In the study of video frame interpolation using deep learning, Kernel Based Method captures local changes well, but has limitations in handling global changes. In this paper, we propose a new U-Net structure that applies feature map differentiation and two directions to focus on capturing major changes to generate intermediate frames more accurately while reducing the number of parameters. Experimental results show that the proposed structure outperforms the existing model by up to 0.3 in PSNR with about 61% fewer parameters on common datasets such as Vimeo, Middle-burry, and a new YouTube dataset. Code is available at https://github.com/Go-MinSeong/SF-AdaCoF.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.1
• /
• pp.21-29
• /
• 2024

With the development of ICT and network, security management of IT infrastructure that has grown in size is becoming very difficult. Many companies and public institutions are having difficulty managing system and network security. In addition, as the complexity of hardware and software grows, it is becoming almost impossible for a person to manage all security. Therefore, AI is essential for network security management. However, since it is very dangerous to operate an attack model in a real network environment, cybersecurity emulation research was conducted through reinforcement learning by implementing a real-life network environment. To this end, this study applied reinforcement learning to the network environment, and as the learning progressed, the agent accurately identified the vulnerability of the network. When a network vulnerability is detected through AI, automated customized response becomes possible.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.23-30
• /
• 2024

In this paper, we propose a deep learning-based personalized senior care service application. The proposed application uses Speech to Text technology to convert the user's speech into text and uses it as input to Autogen, an interactive multi-agent large-scale language model developed by Microsoft, for user convenience. Autogen uses data from previous conversations between the senior and ChatBot to understand the other user's intent and respond to the response, and then uses a back-end agent to create a wish list, a shared calendar, and a greeting message with the other user's voice through a deep learning model for voice cloning. Additionally, the application can perform home IoT services with SKT's AI speaker (NUGU). The proposed application is expected to contribute to future AI-based senior care technology.

• 한국기계연구소 소보
• /
• s.17
• /
• pp.111-123
• /
• 1987

Two dimensional computer simulation of solidification behavior using FDM as simulation tool was applied to AI-bronze casting. By the comparison of computer simulation with the experimental results, it was showed that the final shrinkage position and solidification time are good accordance with results of computer simulation. It is expected that this software will be widely applied to casting design or rise ring for directional solidification.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1988.10a
• /
• pp.1-6
• /
• 1988

In this study, the current progress in computational structural engineering and research trends are discussed. The development of new finite elements, error analysis and adaptive mesh generation, material constitutive model, boundary element methods, structural optimal design, hardware/software, AI application and expert systems are particularly emphasized. The rapid development in computer technologies provides good environment for the technical advancement in computational structural engineering.

• International Journal of Advanced Culture Technology
• /
• v.6 no.4
• /
• pp.303-308
• /
• 2018

Demand is increasing rapidly in recent years than supply to machine learning professionals. To alleviate this gap, user-friendly machine learning software that can be used by non-specialists has emerged, which is Machine Learning-as-a-Service(MLaaS). MLaaS provides services that enable businesses to easily leverage ML capabilities without expertise. In this paper, we will compare and analyze features, interfaces, supporting programming language, ML framework, and Machine Learning services of MLaaS, to help companies easily use ML service.

• Journal of Multimedia Information System
• /
• v.8 no.3
• /
• pp.183-190
• /
• 2021

In this paper, we implement a system for a fund recommendation based on the investment propensity and for a future fund price prediction. The investment propensity is classified by scoring user responses to series of questions. The proposed system recommends the funds with a suitable risk rating to the investment propensity of the user. The future fund prices are predicted by Prophet model which is one of the machine learning methods for time series data prediction. Prophet model predicts future fund prices by learning the parameters related to trend changes. The prediction by Prophet model is simple and fast because the temporal dependency for predicting the time-series data can be removed. We implement web pages for the fund recommendation and for the future fund price prediction.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.51-52
• /
• 2019

본 연구는 영화에 대한 정량적 분석을 위해 MRCNN을 활용한 영화 속 등장인물의 얼굴 면적을 검출하였다. MRCNN을 선택한 이유는 기존 얼굴 인식 시스템이 갖는 한계(뒷모습, 누워있는 모습의 측정 오류)의 개선과 면밀한 계산을 하고자 함이었다. 영화 한편에서 주인공과 상대주인공이 함께 등장한 씬을 선별한 726개의 이미지 중 496개의 이미지가 마스킹이 됨으로서 68%의 성능을 보였다. 반면에 230개의 이미지 파일에서는 다소 문제가 발견되어 32%의 오차가 발생했다. 오차를 개선하기 위해서 주요 인물을 학습시킨 뒤 마스킹을 씌우는 작업을 함으로써 현 확률보다 높은 확률로 정상적으로 이미지가 추출될 수 있도록 시험해 볼 것이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.85-87
• /
• 2022

고품질 코드를 위한 정적 분석은 아직도 매우 필요한 영역이며, 또한 코드의 가시화는 개발자들에게 코드의 복잡한 모듈에 대한 가이드에 필요하다. 기존의 코드 가시화는 정적 분석의 코드 내부 정보들을 DB 테이블화 및 품질 지표(CK Metrics, Coupling, # function Calls, Bed smell) 질의어화, 그리고 추출된 정보를 가시화하는 것에만 초점을 두었다. 문제는 코드 내부 정보(Class, method, parameters, etc) 테이블들에 대한 join 연산 시 엄청난 시간과 리소스가 소모된다. 이 문제를 해결하기 위해, 우리는 테이블 설계의 정규화를 제안한다. 또한 필요한 품질 지표의 질의를 통해 코드 내부 정보 추출하여 데이터 및 제어 복잡 모듈을 식별하여 refactoring 를 가이드 한다. 앞으로는 이 부분의 AI learning 을 통해 bad/good program 을 식별을 기대한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.857-859
• /
• 2022

본 연구는 인공지능 기반의 전력 수요 데이터 예측 모델을 구축하고 이를 최종적으로 웹의 형태로 구현하는 것을 목표로 하였다. 기상청 데이터의 기후 요소를 매개변수로 삼아 전력 수요를 예측하고, 그 결과를 가시적으로 시각화하는 것까지의 전 과정을 최대한 간결하게 진행하였다. 추후 한층 더 발전된 모델을 구축할 수 있다면, 전력시장의 효율성과 경제성을 향상시켜 불필요한 에너지 낭비를 미연에 방지할 수 있을 것이라고 기대한다. 나아가 시스템 상용화를 위해 계속 연구 활동에 정진할 수 있을 것이다.