• 한국소프트웨어감정평가학회 논문지
• /
• 제17권1호
• /
• pp.59-66
• /
• 2021

Recently, conceptual information model is changing fast, and these changes are coming about as a result of individual tendency, social cultural, new circumstances and societal shifts within big data environment. Despite the data is growing more and more, now is the time to commit ourselves to the development of renewable, invaluable information of social/live commerce. Because we have problems with various insoluble data, we propose about deep learning prediction model-based object classification in social commerce of big data environment. Accordingly, it is an increased need of social commerce platform capable of handling high volumes of multiple items by users. Consequently, responding to rapid changes in users is a very significant by deep learning. Namely, promptly meet the needs of the times, and a widespread growth in big data environment with the goal of realizing in this paper.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.334-337
• /
• 2019

본 연구에서는 딥러닝을 통해 스스로 사용자의 행동 습관 데이터를 학습하고, 상황에 맞춰 실내 환경을 조성할 수 있는 시스템을 구성하였다. 정보 수집 시스템은 데이터 수집 서버와 각종 센서 노드로 구성되며, 모은 데이터에 따라 환경을 조성한다. 사진 분석은 Google Inception v3를, 행동 유추는 직접 설계한 2차 DNN을 사용했다. 모의 데이터로 DNN 학습을 진행한 결과 98.4%의 정확도로 충분히 상황 유추가 가능함을 입증할 수 있었다.

• 한국태양에너지학회 논문집
• /
• 제29권2호
• /
• pp.14-21
• /
• 2009

Recently, alternative energy resources have emerged considerably due to the high oil prices and environment problems. Deep sea water that is one of the natural energy sources can be one of the attractive solutions to reduce the environment problems, and there are already a few examples in some developed countries. In this study, cooling system of deep sea water using heat exchangers of two hotels, located in near Haeundae Bay in Busan, have been analyzed on the quantity of electricity and gas use comparison between existing cooling system and deep seawater cooling system by using E-Quest simulation program. The results of the study showed that the Hotel A approximately saves 370 millions won per year, and the Hotel B saves 248 millions won per year. It means that the cooling system by using deep sea water has great worth to reduce the ratio of fuel sources.

• 로봇학회논문지
• /
• 제14권1호
• /
• pp.8-13
• /
• 2019

Visual place recognition is widely researched area in robotics, as it is one of the elemental requirements for autonomous navigation, simultaneous localization and mapping for mobile robots. However, place recognition in changing environment is a challenging problem since a same place look different according to the time, weather, and seasons. This paper presents a feature extraction method using a deep convolutional auto-encoder to recognize places under severe appearance changes. Given database and query image sequences from different environments, the convolutional auto-encoder is trained to predict the images of the desired environment. The training process is performed by minimizing the loss function between the predicted image and the desired image. After finishing the training process, the encoding part of the structure transforms an input image to a low dimensional latent representation, and it can be used as a condition-invariant feature for recognizing places in changing environment. Experiments were conducted to prove the effective of the proposed method, and the results showed that our method outperformed than existing methods.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.63-71
• /
• 2024

Deep reinforcement learning (RL) significantly influences autonomous vehicle development by optimizing decision-making and adaptation to complex driving environments through simulation-based training. In deep RL, an activation function is used, and various activation functions have been proposed, but their performance varies greatly depending on the application environment. Therefore, finding the optimal activation function according to the environment is important for effective learning. In this paper, we analyzed nine commonly used activation functions for RL to compare and evaluate which activation function is most effective when using deep RL for autonomous vehicles to learn highway merging. To do this, we built a performance evaluation environment and compared the average reward of each activation function. The results showed that the highest reward was achieved using Mish, and the lowest using SELU. The difference in reward between the two activation functions was 10.3%.

• Journal of Astronomy and Space Sciences
• /
• 제41권2호
• /
• pp.61-78
• /
• 2024

This study developed a real-time spacecraft pose estimation algorithm that combined a deep learning model and the least-squares method. Pose estimation in space is crucial for automatic rendezvous docking and inter-spacecraft communication. Owing to the difficulty in training deep learning models in space, we showed that actual experimental results could be predicted through software simulations on the ground. We integrated deep learning with nonlinear least squares (NLS) to predict the pose from a single spacecraft image in real time. We constructed a virtual environment capable of mass-producing synthetic images to train a deep learning model. This study proposed a method for training a deep learning model using pure synthetic images. Further, a visual-based real-time estimation system suitable for use in a flight testbed was constructed. Consequently, it was verified that the hardware experimental results could be predicted from software simulations with the same environment and relative distance. This study showed that a deep learning model trained using only synthetic images can be sufficiently applied to real images. Thus, this study proposed a real-time pose estimation software for automatic docking and demonstrated that the method constructed with only synthetic data was applicable in space.

• 지능정보연구
• /
• 제26권4호
• /
• pp.27-65
• /
• 2020

많은 정보통신기술 기업들은 자체적으로 개발한 인공지능 기술을 오픈소스로 공개하였다. 예를 들어, 구글의 TensorFlow, 페이스북의 PyTorch, 마이크로소프트의 CNTK 등 여러 기업들은 자신들의 인공지능 기술들을 공개하고 있다. 이처럼 대중에게 딥러닝 오픈소스 소프트웨어를 공개함으로써 개발자 커뮤니티와의 관계와 인공지능 생태계를 강화하고, 사용자들의 실험, 적용, 개선을 얻을 수 있다. 이에 따라 머신러닝 분야는 급속히 성장하고 있고, 개발자들 또한 여러가지 학습 알고리즘을 재생산하여 각 영역에 활용하고 있다. 하지만 오픈소스 소프트웨어에 대한 다양한 분석들이 이루어진 데 반해, 실제 산업현장에서 딥러닝 오픈소스 소프트웨어를 개발하거나 활용하는데 유용한 연구 결과는 미흡한 실정이다. 따라서 본 연구에서는 딥러닝 프레임워크 사례연구를 통해 해당 프레임워크의 도입 전략을 도출하고자 한다. 기술-조직-환경 프레임워크를 기반으로 기존의 오픈 소스 소프트웨어 도입과 관련된 연구들을 리뷰하고, 이를 바탕으로 두 기업의 성공 사례와 한 기업의 실패 사례를 포함한 총 3 가지 기업의 도입 사례 분석을 통해 딥러닝 프레임워크 도입을 위한 중요한 5가지 성공 요인을 도출하였다: 팀 내 개발자의 지식과 전문성, 하드웨어(GPU) 환경, 데이터 전사 협력 체계, 딥러닝 프레임워크 플랫폼, 딥러닝 프레임워크 도구 서비스. 그리고 도출한 성공 요인을 실현하기 위한 딥러닝 프레임워크의 단계적 도입 전략을 제안하였다: 프로젝트 문제 정의, 딥러닝 방법론이 적합한 기법인지 확인, 딥러닝 프레임워크가 적합한 도구인지 확인, 기업의 딥러닝 프레임워크 사용, 기업의 딥러닝 프레임워크 확산. 본 연구를 통해 각 산업과 사업의 니즈에 따라, 딥러닝 프레임워크를 개발하거나 활용하고자 하는 기업에게 전략적인 시사점을 제공할 수 있을 것이라 기대된다.

• 한국지하수토양환경학회:학술대회논문집
• /
• 한국지하수토양환경학회 2004년도 임시총회 및 추계학술발표회
• /
• pp.453-454
• /
• 2004

Hydrogeochemical and isotopic characteristics were investigated for groundwater of Tertiary basin in southeastern part of Korea where deep drilling is in progress for geothermal investigation. According to geology, aquifer was distinguished as alluvial, tertiary sedimentary bedrock (bedrock groundwater), and fractured volcanic rock (deep groundwater). Groundwater of each aquifer is distinctively separated in Eh-pH conditions and concentrations of Cl, F, B and HCO$_3$. Deep groundwater has very low level 3H and 14C whereas alluvial groundwater has those of recent precipitation level. However one of deep groundwater show mixed characteristics in terms of hydrochemistry which indicates effect of pumping. Deep groundwater have temperature of 38 to 43$^{\circ}C$ whereas bedrock and alluvial groundwater have temperature less than 2$0^{\circ}C$. Fractured basement rock aquifer has different hydrogeologicalsetting from bedrock and alluvial aquifer considering hydrogeochemical and isotopic characteristics, and temperature.

• 로봇학회논문지
• /
• 제14권2호
• /
• pp.139-149
• /
• 2019

In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments.

• 드라이브 ㆍ 컨트롤
• /
• 제19권3호
• /
• pp.9-15
• /
• 2022

This paper proposes a method for constructing and verifying datasets used in deep learning technology, to prevent safety accidents in automated construction machinery or autonomous vehicles. Although open datasets for developing image recognition technologies are challenging to meet requirements desired by users, this study proposes the interface of virtual simulators to facilitate the creation of training datasets desired by users. The pixel-level training image dataset was verified by creating scenarios, including various road types and objects in a virtual environment. Detecting an object from an image may interfere with the accurate path determination due to occlusion areas covered by another object. Thus, we construct a database, for developing an occlusion area detection algorithm in a virtual environment. Additionally, we present the possibility of its use as a deep learning dataset to calculate a grid map, that enables path search considering occlusion areas. Custom datasets are built using the RDBMS system.