• 전자공학회논문지SC
• /
• 제46권5호
• /
• pp.15-21
• /
• 2009

LED와 같은 소형 제품의 불량검색은 제품의 질을 향상 시키는 것만 아니라 생산성 향상에서 중요한 역할을 한다. 본 연구에서는 LED에 발생하는 여러 가지 불량을 자동으로 검사하는 시스템을 구성하였다. LABVIEW Builder를 사용하여 그래픽 인터페이스 상에서 LED의 불량을 검출을 자동판단하며, 사용자가 쉽게 사용 가능하도록 설계하였다. 1394 카메라를 통해 영상을 획득하고 Vision Builder의 각 영상처리 요소를 적용하였다. 에지탐색, 기하학 위치 설정, 거리측정 등의 영상처리 알고리즘을 조합하여 색과 크기가 다른 다양한 LED의 불량을 검출하는 알고리즘을 설계하였다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2008년도 춘계 학술발표회 초청강연 및 논문집
• /
• pp.199-210
• /
• 2008

Acoustic emission(AE)/Microseimsic(MS) activities are low-energy seismic events associated with a sudden inelastic deformation such as the sudden movement of existing fractures, the generation of new fractures or the propagation of fractures. These events rapidly increase before major failure and happen within a given rock volume and radiate detectable seismic waves. The main difference between AE and MS signals is that the seismic motion frequencies of AE signals are higher than those of MS signals. As the failure of geotechnical structures usually happens as a high velocity and small displacement, it is not easy to determine the precursor and initiation stress level of failure in displacement detection method. To overcome this problem, AE/MS techniques for detection of structure failure and damage have recently adopt in civil engineering. In this study, AE/MS monitoring system, which consist of sensor, data acquisition and operation program, is constructed with domestic technology. To verify and optimize the developed system, we are now carrying out the field application at an underground research laboratory and the developed AE/MS monitoring will be used in detecting of seismic events with various scales.

• Spatial Information Research
• /
• 제13권4호
• /
• pp.393-400
• /
• 2005

네트워크와 인터넷의 발달로 인해, 디지털 데이터의 보급과 확산이 쉽게 이루어지고 있다. 디지털 데이터는 손실없이 복제되고 보급될 수 있다는 장점이 있지만, 저작권 문제와 더불어 데이터의 무분별한 복제 문제가 발생하고 있다. 이러한 문제는 GIS에서도 발생하고 있다. GIS에서 데이터 획득을 위해 큰 비용을 지불하고 있는 반면에 데이터 소유권에 대한 보호 노력은 미흡한 실정이다. 현재 워터마킹은 데이터의 소유권을 보장해 줄 수 있는 좋은 방안으로 대두되고 있다. 이 논문에서는 워터마킹의 기본적인 정의를 설명하고 GIS에서 사용되는 raster 형식의 데이터와 vector 데이터에 대한 워터마킹 연구동향을 분석하여 보고자 한다.

• 수산해양교육연구
• /
• 제28권1호
• /
• pp.172-179
• /
• 2016

The study of Mobile MGIS (Marine Geographic Information System) based on the Android Mobile Platform is mainly performed on effective methodologies which transform real world data to computing world data. Mobile GUI system has its own target on reliable data service by acquisition of geometric information using EFDC (Environmental Fluid Dynamics Code) Model, accurate measurement and graphical visualization. Even simple visualizations can aid in the interpretation of complex hydrodynamic relationships that are frequently encountered in the marine environment. The Mobile MGIS provides an easy way for hydrodynamics geoscientists to construct complex visualizations that can be viewed with free software. This study proposes a Mobile GUI MGIS using EFDC Model result of Seomjin River estuary. Finally, we design a Seomjin River estuarine Coastal Waters Mobile MGIS integrating above data models. It must adds more ecological information and the various service item for approach more easily in order to user.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.386-389
• /
• 2008

It is important that the training stage of a supervised classification is designed to provide the spectral information. On the design of the training stage of a classification typically calls for the use of a large sample of randomly selected pure pixels in order to characterize the classes. Such guidance is generally made without regard to the specific nature of the application in-hand, including the classifier to be used. An approach to the training of a support vector machine (SVM) classifier that is the opposite of that generally promoted for training set design is suggested. This approach uses a small sample of mixed spectral responses drawn from purposefully selected locations (geographical boundaries) in training. A sample of such data should, however, be easier and cheaper to acquire than that suggested by traditional approaches. In this research, we evaluated them against traditional approaches with high-resolution satellite data. The results proved that it can be used small mixed pixels to derive a classification with similar accuracy using a large number of pure pixels. The approach can also reduce substantial costs in training data acquisition because the sampling locations used are commonly easy to observe.

• 제어로봇시스템학회논문지
• /
• 제14권1호
• /
• pp.36-41
• /
• 2008

Cooling tower is an important equipment of the cooling systems for large buildings like factory and department store. Water used for cooling in cooling tower is reused continuously. If the water is polluted, corrosion and scale can happen at equipments and pipes. In order to prevent this problem, it is necessary to control the water quality using chemicals. To control the water quality, an automatic control system is designed, fabricated, and experimented. The control system is based on an imbedded microcontroller. Relays are used for power driving, an LCD and LED for display, and RS485 for remote data acquisition. Monitoring program is also developed for easy man-machine interface and extraction of data stored in the imbedded processor and EEPROM. The control system calculates amounts of chemicals necessary using sensor data and injects the chemicals into the cooling tower on proper time. The developed water quality control system is expected to reduce cost of maintenance and extend the lifetime of the cooling systems with low cost.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권2호
• /
• pp.194-199
• /
• 2003

Data are an expression of the language or numerical values that show some features. And the information is extracted from data for the specific purposes. The knowledge is utilized as information to construct rules that recognize patterns or make a decision. Today, knowledge extraction and application of that are broadly accomplished for the easy comprehension and the performance improvement of systems in the several industrial fields. The knowledge extraction can be achieved by some steps that include the knowledge acquisition, expression, and implementation. Such extracted knowledge is drawn by rules with data mining techniques. Clustering (CL), input space partition (ISP), neuro-fuzzy (NF), neural network (NN), extension matrix (EM), etc. are employed for the knowledge expression based upon rules. In this paper, the various approaches of the knowledge extraction are surveyed and categorized by methodologies and applied industrial fields. Also, the trend and examples of each approaches are shown in the tables and graphes using the categories such as CL, ISP, NF, NN, EM, and so on.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.6-10
• /
• 2007

Classification of hyperspectral images is challenging. A very high dimensional input space requires an exponentially large amount of data to adequately and reliably represent the classes in that space. In other words in order to obtain statistically reliable classification results, the number of necessary training samples increases exponentially as the number of spectral bands increases. However, in many situations, acquisition of the large number of training samples for these high-dimensional datasets may not be so easy. This problem can be overcome by using multiple classifiers. In this paper we compared the effectiveness of two approaches for creating multiple classifiers, feature selection and feature extraction. The methods are based on generating multiple feature subsets by running feature selection or feature extraction algorithm several times, each time for discrimination of one of the classes from the rest. A maximum likelihood classifier is applied on each of the obtained feature subsets and finally a combination scheme was used to combine the outputs of individual classifiers. Experimental results show the effectiveness of feature extraction algorithm for generating multiple classifiers.

• 한국측량학회지
• /
• 제21권3호
• /
• pp.261-267
• /
• 2003

두 시기의 분류영상으로부터 추출된 각각의 정보를 지리정보의 속성정보로 입력하여 지리정보시스템의 한 매개변수로 이용함으로써 두 시기의 지표변화정보를 동시에 추출할 수 있다. 따라서 본 연구에서는 지표피복 정보를 획득할 수 있는 원격탐사기법과 지리정보시스템의 장점을 활용하여 토지이용 변화양상과 더불어 지표의 효율적인 관리 및 개발을 위한 기초자료를 제시하고자 하였다 지표변화정보 추출에 관한 연구를 수행한 결과 기존의 영상분류방법보다 영상정보처리를 쉽게 할 수 있어 각 화소에 대한 지표의 변화과정을 쉽게 알 수 있었다.

• 한국통신학회논문지
• /
• 제14권2호
• /
• pp.137-145
• /
• 1989

本文에서는 變形된 bent函數를 利用하여 bent 器를 構成하였으며 實驗과 시뮬레이숀을 通하여 發生된 bent 系列은 週期 $2^n$-1, 最大相關函數 $2n/2$+1과 最大符號群을 $2n/2$個를 갖으며 要求하는 系列로 쉽게 初期化될 수 있어 한 符號에서 다른 符號로의 變換이 빠르게 이루어질 수 있음을 보였다. 그리고 DS-CDMA를 위한 同期시스템을 bent 符號發生器를 국부 符號發生器로 利用하고 sliding相關器와 DLL 方式을 각각 初期同期 시스템과 追跡同期 시스템으로 構成하였으며 符號同期에 對한 動作特性을 확인하였다.