• Journal of Wetlands Research
• /
• v.21 no.4
• /
• pp.305-311
• /
• 2019

Recently, global climate change causes abnormal weather and disaster countermeasures do not provide sufficient defense and mitigation because they were established according to the historical climate condition. Repeated torrential rains, in particular, are causing damage even in the robust urban flood defense system. Therefore, in this study, the change of runoff considering the spatial distribution of rainfall and urban characteristics was analyzed. For rainfall concentrated in small catchment, rainfall in the watershed must be accurately measured. This study is based on the rainfall data observed with Automated Surface Observing System (ASOS) and Automatic Weather Stations (AWS) provided by the Seoul Meteorological Administration. Effluent from the pumping station was estimated using the EPA-SWMM model and compared and analyzed. Catchments with rainwater pumping station are small with large portion of impermeable areas. Thus, when the ASOS data where is located from from the chatchment, runoff is often calculated using rainfall data that is different from rainfall in the catchment. In this study, the difference between rainfall data observed in the AWS near the catchment and ASOS away from the catchment was calculated. It was found that accurate rainfall should be used to operate rainwater pumping stations or forecast urban flooding floods. In addition, the results of this study may be helpful for estimating design rainfall and runoff calculation.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.63-71
• /
• 2020

In this paper, we propose a fire detection technology using YOLOv3 and EfficientDet, the most reliable artificial intelligence detection algorithm recently, an alert service that simultaneously transmits four kinds of notifications: text, web, app and e-mail, and an AWS system that links fire detection and notification service. There are two types of our highly accurate fire detection algorithms; the fire detection model based on YOLOv3, which operates locally, used more than 2000 fire data and learned through data augmentation, and the EfficientDet, which operates in the cloud, has conducted transfer learning on the pretrained model. Four types of notification services were established using AWS service and FCM service; in the case of the web, app, and mail, notifications were received immediately after notification transmission, and in the case of the text messaging system through the base station, the delay time was fast enough within one second. We proved the accuracy of our fire detection technology through fire detection experiments using the fire video, and we also measured the time of fire detection and notification service to check detecting time and notification time. Our AI fire detection and notification service system in this paper is expected to be more accurate and faster than past fire detection systems, which will greatly help secure golden time in the event of fire accidents.

• Journal of Wetlands Research
• /
• v.14 no.3
• /
• pp.385-397
• /
• 2012

A grid based physically distributed model analyzes rainfall-runoff using physical parameters and grid-typed spatial and hydrological data. This study have developed a real time runoff modelling system using GRM RT(Grid based Rainfall-runoff Model Real Time) which is a real time flow analysis module in GRM, a grid based physically distributed rainfall-runoff model. Weather radar data received in real time are calibrated by using real time AWS from Korea Meteorological Administration(KMA), and they are applied to real time runoff modeling. And the runoff model is calibrated by using observed discharges from a water level gauge in real time. This study have designed and implemented the databases necessary to construct the real time runoff modelling system, and established the process of a real time runoff modelling. And the performances of the developed system have been evaluated. The system have been applied to Nerinheon watershed located in the upstream of Soyanggang Dam and the application results are evaluated.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.11
• /
• pp.305-310
• /
• 2021

Artificial intelligence technology in the medical field initially focused on analysis and algorithm development, but it is gradually changing to web application development for service as a product. This paper describes a Urinary Stone segmentation model in abdominal CT images and an artificial intelligence web application based on it. To implement this, a model was developed using U-Net, a fully-convolutional network-based model of the end-to-end method proposed for the purpose of image segmentation in the medical imaging field. And for web service development, it was developed based on AWS cloud using a Python-based micro web framework called Flask. Finally, the result predicted by the urolithiasis segmentation model by model serving is shown as the result of performing the AI web application service. We expect that our proposed AI web application service will be utilized for screening test.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.4
• /
• pp.3-15
• /
• 2000

In this paper we present a new image denoising filter that can suppress additive noise components while preserving signal components in the wavelet domain. The proposed filter, which we call an adaptive wavelet shrinkage(AWS) filter, is composed of two operators: the wavelet killing operator and the adaptive shrinkage operator. Each operator is selected based on the threshold value which is estimated adaptively by using the local statistics of the wavelet coefficients. In the wavelet killing operation, the small wavelet coefficients below the threshold value are replaced by zero to suppress noise components in the wavelet domain. The adaptive shrinkage operator attenuates noise components from the wavelet components above the threshold value adaptively. The experimental results show that the proposed filter is more effective than the other methods in preserving signal components while suppressing noise.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.880-881
• /
• 2016

디지털액자가 고전적 액자의 향취를 주며 또한 사진을 바꿀 수 있는 기능도 제공하지만 아직 새 흐름이 되는 못했다. 그 이유는 비싼 가격과 사진을 전송하기가 불편하기 때문이다. 우리는 디지털 액자로 사진 전송을 쉽게 하고, 거기에 더하여 위젯과 보안 기능을 추가하는 연구를 하였다. 사진 전송을 위하여 AWS(Amazon Web Service) 서버를 사용하는데 AWS 서버는 언제 어디서나 원할 때면 사진을 WiFi로 전송할 수 있게 한다. 이는 현재 사용하는 USB나 SD 카드를 이용하여 디지털 사진을 전송하는 것보다 훨씬 편리하다. 우리의 디지털 액자를 사용하면 다른 사람과 사진 교환이 쉽고 따라서 가족, 친구, 동료 사이의 친밀감도 쉽게 높일 수 있다.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.31-37
• /
• 2020

Last year's Goseong-Sokcho forest fires have highlighted the limitations of extinguishing work for night-time forest fire and the importance of quick identification for information on the spread of forest fire. However, it is not easy to find services that take into account the characteristics of forest fires, as most existing disaster-related mobile applications and research assume various disaster situations rather than just forest fire situations. Therefore, a system that can provide information quickly is needed, taking into account the characteristics of forest fires and the limitations of extinguishing work. In this paper, we propose evacuation route guidance services that bypass areas where fire has already spread, supplement existing methods of extinguishing work, and provide general information on forest fire situations in real time, by putting drones into forest fire situations. It has been implemented to automate image analysis using the Rekognition service of Amazon Web Service (AWS), and the results of fire detection and the T Map API guide the evacuation path. It is expected that the results of this paper will allow efficient and rapid rescue and extinguishing work to be carried out, and further reduce the damage of human life caused by forest fires.

• Journal of Environmental Science International
• /
• v.14 no.6
• /
• pp.555-563
• /
• 2005

This study presents the characteristics of nocturnal inversion layer and their effect on the concentration variations of surface air pollutants using tethersonde and automatic weather station (AWS, 2 layer tower) system in Ulsan during 2003, The method for the distinction of inversion intensity was decided based on the sum of nocturnal temperature gradient. As the results, there was a close correlation (correlation coefficient of 0,76) between the maximum inversion height obtained from tethersonde and the sum of nocturnal temperature gradient. The air pollutant concentration was also directly proportional to the inversion intensity. When the inversion intensity was strong in the nighttime, ozone $(O_3)$ concentration was lower, while nitrogen dioxide $(NO_2)$ concentration was higher. The carbon monoxide (CO) concentration was gradually higher according to the nocturnal inversion intensity, whereas sulfur dioxide $(SO_2)$ concentration was relatively constant. In addition, we found that there was no correlation between the inversion intensity and TSP concentration.

• Journal of Environmental Science International
• /
• v.27 no.11
• /
• pp.1155-1167
• /
• 2018

We developed a small sensor observation system (SSOS) at a relatively low cost to observe the atmospheric boundary layer. The accuracy of the SSOS sensor was compared with that of the automatic weather system (AWS) and meteorological tower at the Korea Meteorological Administration (KMA). Comparisons between SSOS sensors and KMA sensors were carried out by dividing into ground and lower atmosphere. As a result of comparing the raw data of the SSOS sensor with the raw data of AWS and the observation tower by applying the root-mean-square-error to the error, the corresponding values were within the error tolerance range (KMA meteorological reference point: humidity ${\pm}5%$, atmospheric pressure ${\pm}0.5hPa$, temperature ${\pm}0.5^{\circ}C$. In the case of humidity, even if the altitude changed, it tends to be underestimated. In the case of temperature, when the altitude rose to 40 m above the ground, the value changed from underestimation to overestimation. However, it can be confirmed that the errors are within the KMA's permissible range after correction.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.21-24
• /
• 2020

대용량의 데이터를 시각적 요소를 활용하여 눈으로 볼 수 있도록 하는 데이터 시각화에 대한 관심이 꾸준히 증가하고 있다. 데이터 시각화는 데이터의 전처리를 거쳐 차원 축소를 하여 데이터의 분포를 시각적으로 확인할 수 있다. 공개된 데이터 셋은 캐글(kaggle), 아마존 AWS 데이터셋(Amazon AWS datasets), UC 얼바인 머신러닝 저장소(UC irvine machine learning repository)등 다양하다. 본 논문에서는 UCI의 화학 가스의 데이터셋을 이용하여 딥러닝을 이용하여 다양한 환경 및 조건에서의 학습을 통한 데이터분석 및 학습 결과가 좋을 경우와 그렇지 않을 경우의 마지막 레이어의 특징 벡터를 시각화하여 직관적인 결과를 확인 가능 하도록 하였다. 또한 다차원 입력 데이터를 시각화 함으로써 시각화 된 결과가 딥러닝의 학습결과와 연관이 있는지를 확인 한다.