• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.78-78
• /
• 2021

영상유속분석법은 비접촉식으로 유속을 측정하는 방법으로 특히 홍수시 하천의 표면유속을 안전하게 계측할 수 있어서 경제적이고 안전한 하천유속 측정 방법 중 하나이다. STIV는 영상의 휘도 정보를 시간 방향으로 나열하여 작성된 STI(Space-Time Image)에 나타나는 패턴의 기울기를 이용하여 유속을 산정하는 방법이다. 특히 STIV(Space-Time Image Velocimetry)는 기존 입자군의 상호상관법에 기초한 입자영상유속계와 달리 표식자의 유무와 상관없이 유속을 측정할 수 있어 적용성과 안정성이 확보된다. 하지만 영상의 상태가 불량한 경우 정확한 유속 측정이 난해하며 야간에는 별도의 조명 추가 및 태풍과 같은 악기상에서는 빗방울이 카메라에 맺히거나 수면의 진동, 구조물의 진동에 의한 영상의 상태가 불량하게 되어 측정 정도가 떨어진다. 이처럼 영상을 이용한 유속 계측에 있어 다양한 연구 및 기술개발이 요구되는 시점이다. 따라서 본 연구에서는 영상을 이용한 정확한 유속측정을 위해 STIV와 인공지능을 융합하여 정확한 유속 평가를 목적으로 한다. 우선 기존 STI에 의한 기울기 추정방법을 확장하여 딥러닝(CNN)에 의한 기울기 추정방법을 도입하였다. CNN은 일반적으로 이미지의 특성을 추출하는데 유용한 방법으로서 STI의 2차원 Fourier변환 이미지를 사용하여 패턴의 기울기를 감지하도록 학습하였고 적용 결과 기울기에 대한 인식율은 매우 양호하였으며 이를 이용한 실제 관측 영상에 적용한 결과 유속에 대한 정밀도도 매우 양호하게 나타났다. 또한 딥러닝을 적용한 STIV는 노이즈(진동, 화면 불량 등)가 있는 영상에서도 안정적으로 유속을 산정할 수 있으며 전파유속계를 이용한 실제 하천의 표면유속 관측치와 비교 검토 결과 매우 양호하게 유속을 평가하고 있는 것으로 나타났다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.463-465
• /
• 2021

Currently, the inspection method printed on food packages and boxes is to sample only a few products and inspect them with human eyes. Such a sampling inspection has the limitation that only a small number of products can be inspected. Therefore, accurate inspection using a camera is required. This paper proposes a deep learning object recognition technology model, which is an artificial intelligence technology, as a method for detecting the defects of expiration date printed on the product packaging. Using the Faster R-CNN (region convolution neural network) model, the color images, converted gray images, and converted binary images of the printed expiration date are trained and then tested, and each detection rates are compared. The detection performance of expiration date printed on the package by the proposed method showed the same detection performance as that of conventional vision-based inspection system.

• Smart Media Journal
• /
• v.12 no.5
• /
• pp.65-72
• /
• 2023

Smart Farm means creating new value in various fields related to agriculture, including not only agricultural production but also distribution and consumption through the convergence of agriculture and ICT. In Korea, a rental smart farm is created to spread smart agriculture, and a smart farm big data platform is established to promote data collection and utilization. It is pushing for digital transformation of agricultural products distribution from production areas to consumption areas, such as expanding smart APCs, operating online exchanges, and digitizing wholesale market transaction information. As such, although agricultural data is generated according to characteristics from various sources, it is only used as a service using statistics and standardized data. This is because there are limitations due to distributed data collection from agriculture to production, distribution, and consumption, and it is difficult to collect and process various types of data from various sources. Therefore, in this paper, we analyze the current state of domestic agricultural data collection and sharing for digital agriculture and propose a data collection and linkage method for artificial intelligence services. And, using the proposed data, we propose a deep learning-based environmental factor recommendation method.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.21-30
• /
• 2024

This research aims to design a system capable of generating real web pages based on deep learning and big data, in three stages. First, a classification system was established based on the industry type and functionality of e-commerce websites. Second, the types of components of web pages were systematically categorized. Third, the entire web page auto-generation system, applicable for deep learning, was designed. By re-engineering the deep learning model, which was trained with actual industrial data, to analyze and automatically generate existing websites, a directly usable solution for the field was proposed. This research is expected to contribute technically and policy-wise to the field of generative AI-based complete website creation and industrial sectors.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.1001-1004
• /
• 2021

Pain is an unpleasant experience for the patient. The recognition and assessment of pain help tailor the treatment to the patient, and they are also challenging in the medical. In this paper, we propose an approach for pain recognition through a deep neural network applied to pre-processed physiological. The proposed approach applies the idea of shortcut connections to concatenate the spatial information of a convolutional neural network and the temporal information of a recurrent neural network. In addition, our proposed approach applies the attention mechanism and achieves competitive performance on the BioVid Heat Pain dataset.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.2
• /
• pp.134-142
• /
• 2022

As industry and technology go through advancement, it is hard to search new materials which satisfy various standards through conventional trial-and-error based research methods. Crystal Graph Convolutional Neural Network(CGCNN) is a neural network which uses material's features as train data, and predicts the material properties(formation energy, bandgap, etc.) much faster than first-principles calculation. This report introduces how to train the CGCNN model which predicts the formation energy using open database. It is anticipated that with a simple programming skill, readers could construct a model using their data and purpose. Developing machine learning model for materials science is going to help researchers who should explore large chemical and structural space to discover materials efficiently.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.559-562
• /
• 2024

자연어 기반의 분류모델을 개발할 때 높은 성능을 획득하기 위해서는 데이터의 품질이 중요한 요소이다. 특히 무역상품 국제 분류체계 HS-CODE에서 상품명을 기반으로 HS코드를 분류할 때, 라벨링 된 데이터의 품질에 의해서 분류모델의 성능이 좌우된다. 하지만 현실적으로 확보 가능한 데이터셋에는 데이터 라벨링 오류나 데이터로 활용하기에 특징점이 부족한 데이터들이 다수 존재하기도 한다. 본 연구에서는 분류모델 학습 데이터의 정제 방법론으로, 딥러닝 기반 노이즈 검출 알고리즘을 제안한다. 분류 대상의 특징점이 분류 경계값 주변에 존재한다면 분류하기 모호한 노이즈 데이터일 가능성이 높다고 가정하고, 해당 노이즈 데이터를 검출하는 방법으로 딥러닝 기술을 활용한다. 해당 경계값 노이즈 검출 알고리즘으로 데이터를 정제한 뒤 학습모델의 성능비교 결과, 기존 대비 우수한 분류 정확도를 기록하였다.

• Journal of Auto-vehicle Safety Association
• /
• v.16 no.1
• /
• pp.29-34
• /
• 2024

This paper presents a multi-label lane detection method for autonomous vehicles based on deep learning. The proposed algorithm can detect two types of lanes: center lane and normal lane. The algorithm uses a convolution neural network with an encoder-decoder architecture to extract features from input images and produce a multi-label heatmap for predicting lane's label. This architecture has the potential to detect more diverse types of lanes in that it can add the number of labels by extending the heatmap's dimension. The proposed algorithm was tested on an OpenLane dataset and achieved 85 Frames Per Second (FPS) in end to-end inference time. The results demonstrate the usability and computational efficiency of the proposed algorithm for the lane detection in autonomous vehicles.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.125-134
• /
• 2022

This paper implements an AR manual for a vehicle that can be used even in the vehicle interior space where it is difficult to apply the augmentation method of AR content, which is mainly used, and applies a deep learning model to improve the augmentation matching between real space and virtual objects. Through deep learning, the logo of the steering wheel is recognized regardless of the position, angle, and inclination, and 3D interior space coordinates are generated based on this, and the virtual button is precisely augmented on the actual vehicle parts. Based on the same learning model, the function to recognize the main warning light symbols of the vehicle is also implemented to increase the functionality and usability as an AR manual for vehicles.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.9
• /
• pp.273-282
• /
• 2023

Recently, various technologies such as logistics automation and port operations automation with ICT technology are being developed to build smart ports. However, there is a lack of technology development for port safety and safety accident prevention. This paper proposes an AI-based shipping container loading safety management system for the prevention of safety accidents at container loading fields in ports. The system consists of an AI-based shipping container safety accident risk classification and storage function and a real-time safety accident monitoring function. The system monitors the accident risk at the site in real-time and can prevent container collapse accidents. The proposed system is developed as a prototype, and the system is ecaluated by direct application in a port.