• Korean Journal of Artificial Intelligence
• /
• v.12 no.4
• /
• pp.27-33
• /
• 2024

Various techniques are being researched to effectively detect forest fires. Among them, techniques using object detection models can monitor forest fires over wide areas 24 hours a day. However, detecting forest fires early with traditional object detection models is a very challenging task. While they show decent accuracy for thick smoke and large fires, they show low accuracy for faint smoke and small fires, and frequently generate false positives for lights that are like fires. In this paper, to solve these problems, we focus on leveraging local characteristics such as contours and textures of fire and smoke, which are crucial for accurate detection. Based on this approach, we propose EDAM (Edge driven Attention Module) that performs enhancement by richly utilizing contour and texture information of fire and smoke. EDAM extracts important edge information to generate feature maps with emphasized contour and texture information, and based on this map, performs Attention Mechanism to emphasize key characteristics of smoke and fire. Through this mechanism, the overall model performance was improved, with AP_sincreasing from 0.154 to 0.204 and AP_0.5 from 0.779 to 0.784, resulting in a significant improvement in AP_svalue to 32.47%. In practice, the model applying this technique showed excellent inference speed while greatly improving detection performance for small objects compared to existing models and reduced false positive rates for building and street light illumination in nighttime environments that are easily mistaken for fire.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.4
• /
• pp.126-138
• /
• 2017

Recently, the national interest in environment is increasing and for dealing with water environment-related issues swiftly and accurately, the demand to facilitate the analysis of water environment data using a GIS is growing. To meet such growing demands, a spatial network data-based stream network analysis map(Korean Reach File; KRF) supporting spatial analysis of water environment data was developed and is being provided. However, there is a difficulty in delineating catchment areas, which are the basis of supplying spatial data including relevant information frequently required by the users such as establishing remediation measures against water pollution accidents. Therefore, in this study, the development of a computer program was made. The development process included steps such as designing a delineation method, and developing an algorithm and modules. DEM(Digital Elevation Model) and FDR(Flow Direction) were used as the major data to automatically delineate catchment areas. The algorithm for the delineation of catchment areas was developed through three stages; catchment area grid extraction, boundary point extraction, and boundary line division. Also, an add-in catchment area delineation module, based on ArcGIS from ESRI, was developed in the consideration of productivity and utility of the program. Using the developed program, the catchment areas were delineated and they were compared to the catchment areas currently used by the government. The results showed that the catchment areas were delineated efficiently using the digital elevation data. Especially, in the regions with clear topographical slopes, they were delineated accurately and swiftly. Although in some regions with flat fields of paddles and downtowns or well-organized drainage facilities, the catchment areas were not segmented accurately, the program definitely reduce the processing time to delineate existing catchment areas. In the future, more efforts should be made to enhance current algorithm to facilitate the use of the higher precision of digital elevation data, and furthermore reducing the calculation time for processing large data volume.

• Korean Journal of Remote Sensing
• /
• v.34 no.3
• /
• pp.439-450
• /
• 2018

The lineament is a linear or curved terrain element to discriminate adjacent geological structures in each other. It has been widely used for analysis of geology, mineral exploration, natural disasters, and earthquake, etc. In the past, the lineament has been extracted using cartographic map or field survey. However, it is possible to extract more efficiently the lineament for a very wide area thanks to development of remote sensing technique. Remotely sensed observation by aircraft, satellite, or digital elevation model (DEM) has been used for visual recognition for manual lineament extraction. Automatic approaches using computer science have been proposed to extract lineament more objectively. In this study, we evaluate the characteristics of lineament which is automatically extracted with respect to difference of spatial resolution of DEM. We utilized two types of DEM: one is Shuttle Radar Topography Mission (SRTM) with spatial resolution of about 90 m (3 arc sec), and the other is the latest world DEM of TerraSAR-X add-on for Global DEM with 12 m spatial resolution. In addition, a global DEM was resampled to produce a DEM with a spatial resolution of 30 m (1 arc sec). The shaded relief map was constructed considering various sun elevation and solar azimuth angle. In order to extract lineament automatically, we used the LINE module in PCI Geomatica software. We found that predominant direction of the extracted lineament is about $N15-25^{\circ}E$ (NNE), regardless of spatial resolution of DEM. However, more fine and detailed lineament were extracted using higher spatial resolution of DEM. The result shows that the lineament density is proportional to the spatial resolution of DEM. Thus, the DEM with appropriate spatial resolution should be selected according to the purpose of the study.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.10-17
• /
• 2020

Recently, the liquefaction phenomenon was first discovered in Korea due to a magnitude 5.4 earthquake that occurred in Pohang, Gyeonsangbuk-do. When liquefaction occurs, some of the water and sand are ejected to the ground, producing a space, which leads to various dangerous situations, such as ground subsidence, building collapse, and sinkhole generation. Recently, the necessity of producing a liquefaction risk map in Korea has increased to grasp potential liquefaction areas in advance. Therefore, this study examined the drilling information from the national geotechnical information DB center at the Ministry of Land, Infrastructure, and Transport to produce a liquefaction risk map, and developed a module to implement functions for basic data modeling and 3D analysis based on drilling information database extraction and information. Through this study, effective interlocking technology of the integrated database of national land information was obtained, and three-dimensional information was generated for each stage of liquefaction risk analysis, such as soil resistance value and a liquefaction risk map. In the future, the technology developed in this study can be used as a comprehensive decision support technology for establishing a foundation for building 3D liquefaction information and for establishing a response system of liquefaction.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.321-328
• /
• 2014

In this paper, we present a MapReduce-based mobility pattern mining system which can predict efficiently the next place of mobile users. It learns the mobility pattern model of each user, represented by Hidden Markov Models(HMM), from a large-scale trajectory dataset, and then predicts the next place for the user to visit by applying the learned models to the current trajectory. Our system consists of two parts: the back-end part, in which the mobility pattern models are learned for individual users, and the front-end part, where the next place for a certain user to visit is predicted based on the mobility pattern models. While the back-end part comprises of three distinct MapReduce modules for POI extraction, trajectory transformation, and mobility pattern model learning, the front-end part has two different modules for candidate route generation and next place prediction. Map and reduce functions of each module in our system were designed to utilize the underlying Hadoop infrastructure enough to maximize the parallel processing. We performed experiments to evaluate the performance of the proposed system by using a large-scale open benchmark dataset, GeoLife, and then could make sure of high performance of our system as results of the experiments.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.1077-1081
• /
• 2008

Soil and Water Assessment Tool(SWAT) 모형은 DEM(Digital Elevation Model)을 사용하여 지형인자를 추출하고 이를 바탕으로 수문 및 수질 모의가 이루어진다. 지형인자의 추출시 DEM 격자크기에 따라 상이한 결과를 초래할 수 있다. 그리하여 정확한 수문 및 수질 모델링에 있어 가능한 고해상도의 DEM을 사용하도록 권장하고 있다. 그러나 넓은 유역에서의 적용시 고해상도 DEM 사용에 따른 컴퓨터 처리 용량과 프로그램 실행 시 소요되는 시간상의 문제는 그 효율성에 있어서 문제시될 수 있다. 그리하여 본 연구에서는 소양강댐, 임하댐 유역을 대상으로 SWAT 모형에서 저해상도 DEM 사용으로 고해상도 DEM의 지형인자를 추출하여 자동 입력될 수 있는 모듈을 개발 적용하였다. 본 연구의 결과 소양강댐 유역을 대상으로 격자크기 20m DEM과 100m DEM을 사용하였을 때 연평균 유사량이 83.8%의 큰 차이가 발생한 반면 격자크기의 20m DEM과 본 모듈을 적용하여 20m DEM의 지형인자로 자동 보정된 100m DEM을 사용하였을 때의 연평균 유사량이 4.4%로 차이가 상당히 줄어든 것을 볼 수 있었다. 임하댐 유역의 경우는 격자크기 10m DEM과 100m DEM을 사용하였을 때 연평균 유사량이 43.4% 큰 차이가 발생하였다. 반면 격자크기 10m DEM과 본 모듈을 적용하여 10m DEM의 지형인자로 자동 보정된 100m DEM을 사용하였을 때의 연평균 유사량이 0.3%로 차이가 크게 줄어든 것을 확인 할 수 있었다. 또한 본 모듈의 검정을 위해 소양강댐 유역의 지형 자료와 유사한 충주댐 유역을 대상으로 본 모듈을 적용하여 검정을 실시하였다. 그 결과 연간 평균 유사량이 격자크기 20m와 100m의 DEM을 이용하였을 때 98.7%의 큰 차이가 발생한 반면 격자크기 20m와 본 모듈을 적용하여 보정된 경사도 값의 100m DEM을 사용하였을 때 20.7%로 차이가 크게 줄어든 것을 볼 수 있었다. 그리하여 본 연구의 결과를 통해 SWAT 모형에서의 개선된 지형인자 추출 방식을 사용하여 저해상도의 DEM 사용으로 고해상도 DEM 사용의 효과를 볼 수 있을 것이고 이로 인해 넓은 유역에서 저해상도 DEM 사용으로 컴퓨터 사용용량과 프로그램 지연 시간을 줄일 수 있을 것으로 판단된다. 향후 여러 유역을 대상으로 보정, 검정하여 보다 정확하고 통합적으로 적용될 수 있는 모듈의 개선이 필요할 것으로 사료된다.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.11
• /
• pp.1034-1046
• /
• 2011

In this paper, a design and fabrication of 40 W power amplifier for the X-band using load-pull measurement of GaN HEMT chip are presented. The adopted active device for power amplifier is GaN HEMT chip of TriQuint company, which is recently released. Pre-matched fixtures are designed in test jig, because the impedance range of load-pull tuner is limited at measuring frequency. Essentially required 2-port S-parameters of the fixtures for extraction optimal input and output impedances is obtained by the presented newly method. The method is verified in comparison of the extracted optimal impedances with data sheet. The impedance matching circuit for power amplifier is designed based on EM co-simulation using the optimal impedances. The fabricated power amplifier with 15${\times}$17.8 $mm^2$ shows the efficiency above 35 %, the power gain of 8.7~8.3 dB and the output power of 46.7~46.3 dBm at 9~9.5 GHz with pulsed-driving width of 10 usec and duty of 10 %.

• The Journal of Engineering Geology
• /
• v.10 no.2
• /
• pp.52-74
• /
• 2000

The basement rock of upper stream of Keum River Valley consists of Precambrian gneiss which is resistant to weathering. That of mid and lower stream valley, however, is mainly composed of Mesozoic granites which are vulnerable to weathering. The upstream part of Geum River Basin is typified by the deeply-incised and steep meandering streams, whereas mid and lower part is characterized by wide floodplain and gently dipping river bottom toward the Yellow Sea. In particular flooding deposits, in which are imprinted a number of repetitions of erosion and sedimentation during the Holocene, are widely distributed in the lower stream of Geum River Basin. For understanding of erosions in the mid and lower stream of Geum River Basin, the rate of erosion of each small basins were estimated by using the data of field survey, erosional experiments and GIS ananlysis. It was revealed that erosion rate appeared highest in granite areas, and overall areas, in this field survey were represented by relatively high erosion rates. By implemeatation of remote sensing and imagery data, the temporal changes of river bed sediments for about last 11 years were successfully monitored. Observed as an important phenomenon is that the river bed has been risen since 1994 when an embankment (Dyke) was constructed in the estuarine river mouth. From the results derived from the detailed river bed topographical map made in this investigation, the sedimentation of the lower river basin is considered to be deposited with about 5 cm/year for the last 11 years. Based on this river bed profile analysis by HEC-6 module, it is predicted that Geum River bed of Ganggyeong area is continuously rising up in general until 2004. Although extraction of a large amount of aggregates from Gongju to Ganggyung areas, the Ganggyung lower stream shows the distinct sedimentation. Therefore, it is interpreted that the active erosions of tributary basins Geum drainage basins can affect general river bed rising changes of Geum River.

• Journal of Biomedical Engineering Research
• /
• v.24 no.3
• /
• pp.183-192
• /
• 2003

A transformation methode of the chromaticity coordinates was proposed to calibrate the measured data obtained by a urine analysis system which implemented in our previous study. Generally. the reacted color of a reagent strip by urine analysis system often exhibit the color distortions due to nonlinear characteristics of the various devices that is the optic module mechanism. hardware, and surround circumstance. A color correction method for minimizing the color distortion play a few role in maintaining high accuracy and reproduction of the urine analysis system. In this work, we used the compensation method such as the shading correction, the characteristic curve extraction of RGB color by means of third order spline interpolation, and linear transformation using a reference color. In addition, 1931 CIE XYZ color space was used to compensate the color of the measured data by a standard reference system as colorimeter. A compensation matrix was obtained so that the output values of the urine analysis system is nearly equal to that of a standard reference system for identical color sample. Color correction obtained by a urine analysis system which implemented in our previous study exhibited a good color accuracy when it was compared with the reference data. Observed result from an experiments on ten items or a urinalysis strip that color difference or between two urine analysis system was 1.28.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.45-51
• /
• 2021

With the development of deep learning, semantic segmentation methods are being studied in various fields. There is a problem that segmenation accuracy drops in fields that require accuracy such as medical image analysis. In this paper, we improved PSPNet, which is a deep learning based segmentation method to minimized the loss of features during semantic segmentation. Conventional deep learning based segmentation methods result in lower resolution and loss of object features during feature extraction and compression. Due to these losses, the edge and the internal information of the object are lost, and there is a problem that the accuracy at the time of object segmentation is lowered. To solve these problems, we improved PSPNet, which is a semantic segmentation model. The multi-scale attention proposed to the conventional PSPNet was added to prevent feature loss of objects. The feature purification process was performed by applying the attention method to the conventional PPM module. By suppressing unnecessary feature information, eadg and texture information was improved. The proposed method trained on the Cityscapes dataset and use the segmentation index MIoU for quantitative evaluation. As a result of the experiment, the segmentation accuracy was improved by about 1.5% compared to the conventional PSPNet.