• 대한원격탐사학회지
• /
• 제37권1호
• /
• pp.41-55
• /
• 2021

To detect thunderstorms occurring in Korea, National Meteorological Satellite Center (NMSC) also introduced the rapid-development thunderstorm (RDT) algorithm developed by EUMETSAT. At NMCS, the H-RDT (HR) based on the Himawari-8 satellite and the K-RDT (KR) which combines the GK2A convection initiation output with the RDT were developed. In this study, we optimized the KR (KU) to improve the detection level of thunderstorms occurring in Korea. For this, we used all available data, such as GK2A/AMI, RADAR, lightning, and numerical model data from the recent two years (2019-2020). The machine learning of logistic regression and stepwise variable selection was used to optimize the KU algorithms. For considering the developing stages and duration time of thunderstorms, and data availability of GK2A/AMI, a total of 72 types of detection algorithms were developed. The level of detection of the KR, HR, and KU was evaluated qualitatively and quantitatively using lightning and RADAR data. Visual inspection using the lightning and RADAR data showed that all three algorithms detect thunderstorms that occurred in Korea well. However, the level of detection differs according to the lightning frequency and day/night, and the higher the frequency of lightning, the higher the detection level is. And the level of detection is generally higher at night than day. The quantitative verification of KU using lightning (RADAR) data showed that POD and FAR are 0.70 (0.34) and 0.57 (0.04), respectively. The verification results showed that the detection level of KU is slightly better than that of KR and HR.

• 융합신호처리학회논문지
• /
• 제22권2호
• /
• pp.85-90
• /
• 2021

운전자의 안전 운전을 위한 첨단 운전자 보조시스템(ADAS; Advanced Driver Assistance System)은 자율주행 자동차에서 중요한 연구 분야 가운데 하나이다. 특히, 이전에 자동차에 부착된 영상센서를 기반으로 한 ADAS 소프트웨어는 구축 비용이 저렴하고 그 활용도가 우수하다. 본 논문에서는 선행차의 주행 상황을 인지할 수 있는 선행 차량 후미등(Tail-Lamp)의 정지등(Break-Lamp) 영역을 검출하는 알고리즘을 제안한다. 제안하는 방법은 주행 영상으로부터 객체 추적에 우수한 성능을 보이고 있는 YOLO 기술을 이용하여 자동차 객체를 추출하고, 추출된 자동차 관심 영역의 HSV 영상을 이용하여 정지등의 밝기 변화 영역을 검출한다. 그 다음 검출된 각 정지등 후보 고립영역을 라벨링하여 후보 영역들 간의 모양 대칭성을 인지하는 선택적 주의집중 모델(Selective Attention Model)을 적용하여 정지등 영역을 검출한다. 제안한 알고리즘의 성능 평가를 위하여 다양한 주행 영상에 적용하여 실험한 결과 ADAS에 적용 가능한 성공적인 검출 결과를 보였다.

• 산업경영시스템학회지
• /
• 제43권4호
• /
• pp.133-141
• /
• 2020

Up to date cosmetic OEM/ODM (original equipment manufacturing/original development manufacturing) industry receives attention as a future growth engine due to steady growth. However, because of limited research and development capability, many companies have employed commercial management platforms specialized for large-sized companies; thus, overall system effectiveness and efficiency is low. Especially, MRP (material requirement planning) system introduced originally in 1970s is employed to calculate the requirement of the parts. However, dynamic nature of production lead time usually results in incorrect requirements. In addition, its algorithm does not consider the capability of the production resources. Also, because the commercial MRP system calculates all subcomponent for fixed period, the more goods have subcomponent, the slower calculation is. Therefore, conventional MRP system cannot respond complicated situation in time. In this study, we will suggest a new method that can respond to complicated situations resulting from short lead time and urgent production order in Korean cosmetic market. In particular, a distributed MRP system is proposed, that consists of multi-functional and operational modules, based on the characteristic of the BOM (bill of material). The distributed MRP system divides components (i.e. products and parts) into several fields and decrease the problem size; thus, we can respond to dynamically changed data any time. Through this solution, we can order components quickly, adjust schedules and planned quantity, and manage stocks reasonably. In addition, a prototype of the distributed MRP system is presented in this paper, in which ERP (enterprise resource planning) sever data is associated with an excel spreadsheet via MSsql. System user interface is implemented by a VBA (visual basic for applications) tool. According to a case study, response rate for delivery and planning achievement rate were enhanced about 20%, and inventory turnover was also decreased. Consequently, the proposed system improves overall profit.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1424-1436
• /
• 2020

Although huge progress has been made in current image segmentation work, there are still no efficient segmentation strategies for tree image which is taken from natural environment and contains complex background. To improve those problems, we propose a method for tree image segmentation combining adaptive mean shifting with image abstraction. Our approach perform better than others because it focuses mainly on the background of image and characteristics of the tree itself. First, we abstract the original tree image using bilateral filtering and image pyramid from multiple perspectives, which can reduce the influence of the background and tree canopy gaps on clustering. Spatial location and gray scale features are obtained by step detection and the insertion rule method, respectively. Bandwidths calculated by spatial location and gray scale features are then used to determine the size of the Gaussian kernel function and in the mean shift clustering. Furthermore, the flood fill method is employed to fill the results of clustering and highlight the region of interest. To prove the effectiveness of tree image abstractions on image clustering, we compared different abstraction levels and achieved the optimal clustering results. For our algorithm, the average segmentation accuracy (SA), over-segmentation rate (OR), and under-segmentation rate (UR) of the crown are 91.21%, 3.54%, and 9.85%, respectively. The average values of the trunk are 92.78%, 8.16%, and 7.93%, respectively. Comparing the results of our method experimentally with other popular tree image segmentation methods, our segmentation method get rid of human interaction and shows higher SA. Meanwhile, this work shows a promising application prospect on visual reconstruction and factors measurement of tree.

• 한국전산구조공학회논문집
• /
• 제35권5호
• /
• pp.259-266
• /
• 2022

본 논문에서는 프리팹 구조물의 품질관리를 위한 딥러닝 및 비전센서 기반의 조립 성능 평가 모델을 개발하였다. 조립부 검출을 위해 인코더-디코더 형식의 네트워크와 수용 영역 블록 합성곱 모듈을 적용한 딥러닝 모델을 사용하였다. 검출된 조립부 영역 내의 볼트홀을 검출하고, 볼트홀의 위치 값을 산정하여 k-근접 이웃 기반 모델을 사용하여 조립 품질을 평가하였다. 제안된 기법의 성능을 검증하기 위해 조립부 모형을 3D 프린팅을 이용하여 제작하여 조립부 검출 및 조립 성능 예측 모델의 성능을 검증하였다. 성능 검증 결과 높은 정밀도로 조립부를 검출하였으며, 검출된 조립부내의 볼트홀의 위치를 바탕으로 프리팹 구조물의 조립 성능을 5% 이하의 판별 오차로 평가할 수 있음을 확인하였다.

• 한국정보통신학회논문지
• /
• 제26권7호
• /
• pp.956-962
• /
• 2022

미만성 갑상샘 질환은 그 진단 기준이 모호하고 숙련자의 주관적인 진단에 따라 오류가 많이 발생한다. 초음파 영상에 영상처리기술을 적용하고 정량적 데이터를 추출하여 컴퓨터 보조 진단 시스템에 적용하게 되면 보다 정확하고 정략적인 진단이 가능하다. 본 논문에서는 갑상샘 질환 환자를 정상, 경도, 중등도로 분류된 초음파 영상에 GLCM 알고리즘을 적용하여 19개의 파라미터를 추출하였다. 이들 파라미터를 이용하여 인공신경망을 적용하여 미만성 갑상샘 초음파 영상을 분류하여 최종 96.9%의 분류율을 얻었다. 본 연구의 결과를 이용하여 갑상샘 질환의 진단에 있어 육안 판독에 따른 오류를 감소시키고, 미만성 갑상샘 질환 진단의 2차적인 수단으로 활용 가능할 것으로 기대된다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.251-266
• /
• 2022

Structural Health Monitoring (SHM) of critical infrastructure comprises a major pillar of maintenance management, shielding public safety and economic sustainability. Although SHM is usually associated with data-driven metrics and thresholds, expert judgement is essential, especially in cases where erroneous predictions can bear casualties or substantial economic loss. Considering that visual inspections are time consuming and potentially subjective, artificial-intelligence tools may be leveraged in order to minimize the inspection effort and provide objective outcomes. In this context, timely detection of sensor malfunctioning is crucial in preventing inaccurate assessment and false alarms. The present work introduces a sensor-fault detection and interpretation framework, based on the well-established support-vector machine scheme for anomaly detection, combined with a coalitional game-theory approach. The proposed framework is implemented in two datasets, provided along the 1st International Project Competition for Structural Health Monitoring (IPC-SHM 2020), comprising acceleration and cable-load measurements from two real cable-stayed bridges. The results demonstrate good predictive performance and highlight the potential for seamless adaption of the algorithm to intrinsically different data domains. For the first time, the term "decision trajectories", originating from the field of cognitive sciences, is introduced and applied in the context of SHM. This provides an intuitive and comprehensive illustration of the impact of individual features, along with an elaboration on feature dependencies that drive individual model predictions. Overall, the proposed framework provides an easy-to-train, application-agnostic and interpretable anomaly detector, which can be integrated into the preprocessing part of various SHM and condition-monitoring applications, offering a first screening of the sensor health prior to further analysis.

• 대한의용생체공학회:의공학회지
• /
• 제44권2호
• /
• pp.125-138
• /
• 2023

The development of AI systems for radiation therapy is important to improve the accuracy, effectiveness, and safety of cancer treatment. The current system has the disadvantage of monitoring patients using CCTV, which can cause errors and mistakes in the treatment process, which can lead to misalignment of radiation. Developed the PMRP system, an AI automation system that uses depth cameras to measure patient's fine movements, segment patient's body into parts, align Z values of depth cameras with Z values, and transmit measured feedback to positioning devices in real time, monitoring errors and treatments. The need for such a system began because the CCTV visual monitoring system could not detect fine movements, Z-direction movements, and body part movements, hindering improvement of radiation therapy performance and increasing the risk of side effects in normal tissues. This study could provide the development of a field of radiotherapy that lags in many parts of the world, along with the economic and social importance of developing an independent platform for radiotherapy devices. This study verified its effectiveness and efficiency with data through phantom experiments, and future studies aim to help improve treatment performance by improving the posture correction mechanism and correcting left and right up and down movements in real time.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.174-176
• /
• 2022

본 논문에서는인공지능(AI; Artificial Intelligence)알고리즘을 활용한 조음 장애 아동들의 '개인화된 맞춤형 학습' 모바일 애플리케이션을 제시한다. 조음과 관련된 빅데이터(Big Data)를 수집-정제-가공한 데이터 셋(Data Set)으로 학습자의 조음 상황 및 정도를 분석, 판단, 예측한다. 특히, 인공지능 활용 시 기존 애플리케이션에 비해 어떻게 개선되고 고도화할수 있는지를 UX/UI(GUI) 측면에서 바라보고 프로토타입 모델을 설계해 보았다. 지금까지 시각적 경험에 많이 치중해 있었다면, 이제는 데이터를 어떻게 가공하여 사용자에게 UX/UI(GUI) 경험을 제공할 수 있는지가 중요한 시점이다. 제시한 모바일 애플리케이션의 UX/UI(GUI)는 딥러닝(Deep Learning)의 CRNN(Convolution Recurrent Neural Network)과 Auto Encoder GPT-3 (Generative Pretrained Transformer)를 활용하여 학습자의 조음 정도와 상황에 맞게 제공하고자 하였다. 인공지능 알고리즘의 활용은 조음 장애 아동들에게 완성도 높은 학습환경을 제공하여 학습효과를 높일 수 있를 것이다. '개인화된 맞춤형 학습'으로 조음의 완성도를 높여서, 대화에 대한 두려움이나 불편함을 갖지 않길 바란다.

• 디지털산업정보학회논문지
• /
• 제18권1호
• /
• pp.55-64
• /
• 2022

This study analyzes the success factors of OTT original content through big data, and intends to suggest scenarios, casting, fun, and moving elements when producing the next work. In addition, I would like to offer suggestions for the success of 'Squid Game Season 2'. The success factor of 'Squid Game' through big data is first, it is a simple psychological experimental game. Second, it is a retro strategy. Third, modern visual beauty and color. Fourth, it is simple aesthetics. Fifth, it is the platform of OTT Netflix. Sixth, Netflix's video recommendation algorithm. Seventh, it induced Binge-Watch. Lastly, it can be said that the consensus was high as it was related to the time to think about 'death' and 'money' in a pandemic situation. The suggestions for 'Squid Game Season 2' are as follows. First, it is a fusion of famous traditional games of each country. Second, it is an AI-based planned MD product production and sales strategy. Third, it is casting based on artificial intelligence big data. Fourth, secondary copyright and copyright sales strategy. The limitations of this study were analyzed only through external data. Data inside the Netflix platform was not utilized. In this study, if AI big data is used not only in the OTT field but also in entertainment and film companies, it will be possible to discover better business models and generate stable profits.