• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.182-186
• /
• 2003

일반적으로 영상은 공간, 분광 및 시간 해상력을 바탕으로 고해상과 저해상 영상으로 구분된다. 최근 IKONOS 와 QuickBird 등 공간해상력이 1m 이하인 위성 영상들이 국내에 공급되어 바야흐로 고해상 위성영상을 이용한 다양한 활용분야들이 연구되고 있다. 이에 반하여 고분광해상력을 갖는 하이퍼스펙트럴 영상에 대한 연구는 미흡한 실정이다. 국제적으로는 항공기탑재 센서들을 이용한 다양하고 광범위한 조사분석 연구가 이루어지고 있으나, 국내에서는 장비와 관심의 부재로 인하여 초기적인 연구 단계에 있는 실정이다 하이퍼스펙트럴 센서는 환경, 지질, 목표물 인식 분야에 있어 많은 관심을 받고 있으며 위성탑재 초다중분광센서가 운용되기 시작하면서 연구의 활성화가 더욱 기대되고 있다. 본 연구에서는 EO-1 위성의 Hyperion 센서 데이터를 이용하여 노이즈 제거를 위한 영상 전처리 과정을 실시하고 분광특성에 따른 무감독 분류를 통한 인덱싱 기법과 널리 알려진 분광 라이브러리를 활용한 대상물, 특히 인공지물 추출 기법을 실험하였다. 이를 위하여 MNF(Maximum/Minimum Noise Filtering) 변환 및 분광 매칭(Spectral Matching) 기법, 분광 라이브러리 처리 등을 수행하였다. 결과의 비교를 위하여 동일 지역의 Landsat ETM+ 데이터를 이용하여 상호비교를 통한 검증작업으로서 그 성과를 판단하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.324-326
• /
• 2012

기계 학습에서 입력 데이터의 차원을 줄이는 문제(dimension reduction)는 매우 중요한 문제 중의 하나이다. 입력 변수의 차원이 늘어남에 따라 처리해야하는 연산의 수와 계산 복잡도가 급격히 늘어나기 때문이다. 이를 해결하기 위하여 다수의 기계 학습 알고리즘은 명시적으로 차원을 줄이거나(feature selection), 데이터에 약간의 연산을 가하여 차원이 작은 새로운 입력 데이터를 만든다(feature extraction). 반면 사람이 여러 종류의 고차원 센서 데이터를 입력받아 빠른 시간 안에 정확하게 정보를 처리할 수 있는 가장 큰 이유 중 하나는 실시간으로 판단하여 가장 필요한 정보에 집중하기 때문이다. 본 연구는 사람의 정보 처리 과정을 기계 학습 알고리즘에 반영하여, 집중도를 이용하여 효율적으로 데이터를 처리하는 방법을 제시한다. 이 성질을 시각 하이퍼네트워크 모델에 반영하여, 효율적으로 고차원 입력 데이터를 다루는 방법을 제안한다. 실험에서는 시각 하이퍼네트워크를 이용하여 고차원의 이미지 데이터에서 행동을 분류하였다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.1
• /
• pp.56-70
• /
• 2017

In this study, multi-image information for the central Taewha River basin was used to develop and analyze a distribution map of non-point pollution sources. The data were collected using a hyper-sensor (image), aerial photography, and a field spectro-radiometer. An image correction process was performed for each image to develop an ortho-image. In addition, the spectra from the field spectro-radiometer measurements were analyzed for each classification to create land cover and distribution maps of non-point pollutant sources. In the western region of the Taewha River basin, where most of the forest and agricultural land is distributed, the distribution map showed generated loads for BOD($kg/km^2{\times}day$) of 1.0 - 2.3, for TN($kg/km^2{\times}day$) of 0.06 - 9.44, and for TP($kg/km^2{\times}day$) of 0.03 - 0.24, which were low load distributions. In the eastern region where urbanization is in progress, the BOD, TN, and TP were 85.9, 13.69, and 2.76, respectively and these showed relatively high load distributions when the land use was classified by plot.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.05a
• /
• pp.339-344
• /
• 2005

하이퍼스펙트럴 데이터의 효과적인 분석을 위해 밴드 추출(Feature Extraction)이나 밴드선택(Feature Selection)에 대한 연구가 최근 많이 이루어지고 있다. 본 연구는 상대적으로 많은 밴드를 가지는 하이퍼스펙트럴 영상을 식생지수(Vegetation Index)와 같은 특수한 목적에 적용하기 위해 같은 파장대의 밴드를 조합(Band Aggregation)하여 Landsat ETM+ 영상 밴드와 동일한 영상 생성을 목적으로 한다. 이를 위해 NASA에서 제공하는 밴드별 분광특성 자료를 이용하여 밴드 조합을 위한 가중치 계산식에 적용하였으며, 밴드 선택을 위한 유효 파장대를 추출해 보았다 데이터 간 편차를 줄이기 위해 실제 1분 간격으로 촬영된 동일지역의 Hyperion과 ETM+ 영상을 사용하여 알고리즘에 적용하였고, 그 결과를 영상 간 상관계수와 NDVI 영상을 이용하여 비교 분석하였다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.3
• /
• pp.63-71
• /
• 2013

This study calculated vegetation indexes such as SR, NDVI, SAVI, and LAI to figure out correlations regarding vegetation by using high resolution KOMPSAT-2 images and LANDSAT images based on the forest biomass distribution map that utilized field survey data, satellite images and LiDAR data and then analyzed correlations between their values and forest biomass. The analysis results reveal that the vegetation indexes of high resolution KOMPSAT-2 images had higher correlations than those of LANDSAT images and that NDVI recorded high correlations among the vegetation indexes. In addition, the study analyzed the characteristics of hyperspectral images by using the COMIS of STSAT-3 and Hyperion images of a similar sensor, EO-1, and further the usability of biomass estimation in hyperspectral images by comparing vegetation index, which had relatively high correlations with biomass, with the vegetation indexes of LANDSAT with the same GSD conditions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.450-453
• /
• 2017

In this abstract, the FPGA system using solar tracking is introduced. Solar tracking system combined with sensor tracking and solar altitude programming is utilized. The sensor tracking system consists of image sensor, light sensor, and the programs for sun altitude received by the computer. The sun altitude is received from the national weather database by wireless communication. The goal is to have maximum energy generation efficiency using bi-directional tracking and mixed tracking with FPGAs that are relatively inexpensive in terms of developing and programming the system.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.1
• /
• pp.81-88
• /
• 2014

The researcher of this study applied PCA on aerial hyper-spectral sensor and selectively combined bands which contain high amount of information, creating five types of PCA images. By applying Spectral Angle Mapping-supervised classification technique on each type of image, classification process was carried out and accuracy was evaluated. The test result showed that the amount of information contained in the first band of PCA-transformation image was 76.74% and the second accumulated band contained 98.40%, suggesting that most of information were contained in the first and the second PCA components. Quantitative classification accuracy evaluation of each type of image showed that total accuracy, producer's accuracy and user's accuracy had similar patterns. What drew the researcher's attention was the fact that the first and the second bands of the PCA-transformation image had the highest accuracy according to the classification accuracy although it was believed that more than four bands of PCA-transformation image should be contained in order to secure accuracy when doing the qualitative classification accuracy.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.785-796
• /
• 2023

In this study, a methodology for real-time classification and prediction of defects that may appear in PVDF(Polyvinylidene fluoride) sensors, which are widely used for structural integrity monitoring, is proposed. The types of sensor defects appearing according to the sensor attachment environment were classified, and an impact test using an impact hammer was performed to obtain an output signal according to the defect type. In order to cleary identify the difference between the output signal according to the defect types, the time domain statistical features were extracted and a data set was constructed. Among the machine learning based classification algorithms, the learning of the acquired data set and the result were analyzed to select the most suitable algorithm for detecting sensor defect types, and among them, it was confirmed that the highest optimization was performed to show SVM(Support Vector Machine). As a result, sensor defect types were classified with an accuracy of 92.5%, which was up to 13.95% higher than other classification algorithms. It is believed that the sensor defect prediction technique proposed in this study can be used as a base technology to secure the reliability of not only PVDF sensors but also various sensors for real time structural health monitoring.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.8
• /
• pp.1654-1660
• /
• 2004

In this paper, we describes the design and implementation of LonWorks communication module for distributed intelligent control using LonWorks technology of Echelon. LonWorks communication module can be divided hardware and firmware. First, hardwares is divided into microcontroller attaching sensors and LonWorks components for working together control network and data network. Hardwares are consisted of neuron chip, microcontroller, transceiver, LONCard. Second, operating firmware is realized with neuron C using NodeBulider 3.0 development tool. Produced and implemented LonWorks communication module is pretested using LTM-10A, Gizmo 4 I/O board, parallel I/O Interface. For field test, microcontroller module part is tested by HyperTerminal, communication procedure in data network is certified by transmitting and receiving short message using LonMaker for Windows tool. Herewith, LON technology is based on network communication technique using LonWorks.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1353-1362
• /
• 2023

Various methods are being attempted to resolve the inconvenience of blood glucose meters used to check blood sugar levels. In this paper, we attempted to estimate blood sugar levels non-invasively using machine learning technology from spectral data acquired using a near-infrared sensor. The non-invasive blood glucose meter used in the study has a total of six near-infrared ray emitters, including visible rays, and a light receiver that receives them. It is a device created to collect spectral data on specific parts of the human body, such as the fingers. To verify whether there was a significant difference depending on blood sugar level, we attempted to estimate blood sugar level through machine learning algorithms. As a result of applying five machine learning algorithm techniques to the collected data and adjusting various hyper parameters, it was confirmed that the support vector regression algorithm showed the best performance.