• Proceedings of the KAIS Fall Conference
• /
• 2004.11a
• /
• pp.157-159
• /
• 2004

오늘날 자동화 산업 부분에서 원격 제어 및 모니터링은 유지 보수가 쉽고 시간적 공간적으로 많은 효율성을 기대할 수 있기 때문에 중요한 부분을 차지하고 있다. 그러나 네트워크 환경이 미처 구비되지 못한 산업 현장에서 전용 장비나 전용 라인을 사용하여 네트워크 환경을 추가로 구축하려 한다면 큰 경제적 부담이 될 수 있다. 하지만 나날이 성능이 향상되고 있는 일반 PC를 사용한다면 상대적인 비용의 절감 효과를 기대 할 수 있다. 본 논문에서는 3축의 Motion Control System을 구성하여 현재 산업 현장에서 주로 쓰이는 Manipulator의 기본적인 환경을 구현하고 LabVIEW를 이용하여 별도의 네트워크 전용 장비 없이 일반 PC에서 무선 인터넷을 통하여 실시간으로 모니터링 및 제어를 할 수 있게 하였고, 나아가 인터넷상에서 원격제어의 가능성을 활용하여 산업체에서의 활용범위를 넓히고, 가상 교육환경의 가능성을 열었다.

• Proceedings of the KIEE Conference
• /
• 2005.07b
• /
• pp.1120-1122
• /
• 2005

인터넷의 급속한 보급으로 인해 데이터 전송 시 발생하는 공간상의 제약을 쉽게 극복 할 수 있게 되어 전 세계 어디서든지 데이터를 주고받을 수 있게 되었다. 이러한 인터넷 웹기반의 장점을 살려서 그동안 실험 연구용으로 사용하던 서보시스템의 PID 제어방법을 인터넷을 기반으로 한 원격제어 시스템으로 구현하였다. 본 논문에서는 DC 서보 모터와 모터 제어 보드, NI사의 DAQ, PC로 시스템을 구현 하였다. UI(User Interface)는 LabVIEW 프로그램을 이용하여 GUI(Graphical User Interface)로 DC 서보 모터의 제어와 작동상태의 모니터링이 용이하도록 하였고, 최적의 PID 이득값을 설정하여 원하는 속도 응답 특성이 양호한 제어를 할 수 있게 하였다. 더 나아가 PID 제어 방법을 원격 실시간의 가상 실습이 가능한 e-Learning에 적용 할 수 있음을 확인하였다.

• Proceedings of the KAIS Fall Conference
• /
• 2003.06a
• /
• pp.165-167
• /
• 2003

인터넷의 비약적인 발달은 제어시스템의 설계 및 운영에도 많은 영향을 미치게 되어 지금까지와는 전혀 다른 시스템 구현이 가능한 환경으로 만들어 가고 있다. 이와 같은 배경에서 본 연구에서는 그동안 실험연구용으로 사용하던 서보시스템의 PID 제어방법을 인터넷을 기반으로 한 새로운 방법의 원격제어 시스템으로 구현하였다. 본 논문에서는 NI사의 DAQ보드와 TY36A모터 보드를 사용하여 서보모터의 속도 위치를 web상에서 원격 제어하는 시스템 구현 방법을 제안하였다. LabVIEW 프로그래밍에서 인터페이스 부분은 Graphical한 프로그래밍 기법을 사용하여 모터의 제어와 작동상태의 모니터링이 용이하도록 하였으며, 최적한 PID 이득값을 설정하여 원하는 속도 및 위치응답 특성이 양호한 제어를 할 수 있게 하였다. 나아가 인터넷상에서 원격제어의 가능성을 활용하여 산업체에서의 활용범위를 넓히고, 가상 교육환경의 가능성을 열었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.1010-1013
• /
• 2009

The youths of the farming village have moved to the metropolis, thus the most of the manpower which engages to a production remained in the village reaches layer old age and all thing sprouts long the whole and it is one. So to remove the waste of barn rather than to give feed to the livestock is hard that what step all automation of this part is necessary. Consequently we have developed the automation system in order to reduce the massive death of the livestock at the time of intense cold and hot. The system will be able to clean the waste of the barn and confront quickly in the change of temperature which is sudden it came. And we proposed also the system that will be able to watch at real-time and monitor the operational environment from a remote using CCD camera. In this paper, we proposed the remote control system which uses PDA in order to control the automation system of a stall while moving. The proposed system was embodied in order for the control and the monitor while the user is mobile using PDA screens. We also added a protection system in that system. The system sends the case warning and SMS while will have the fire and the intrusion from the outside and prevents a robbery.

• Korean Journal of Remote Sensing
• /
• v.28 no.2
• /
• pp.181-189
• /
• 2012

Recently, interest in potential for estimating water quality using high resolution satellite images is increasing. However, low SNR(Signal to Noise Ratio) over inland water and radiometric errors such as non-linearity of brightness value of high resolution satellite images often lead to accuracy degradation in water quality estimation. Therefore radiometric correction should be carried out to estimate water quality for high resolution satellite images. For KOMPSAT-2 images parameters for brightness value-radiance conversion are not available and precise radiometric correction is difficult. To exploit KOMPSAT-2 images for water quality monitoring, it is necessary to investigate non-linearity of brightness value and noise over inland water. In this paper, we performed brightness value comparison between KOMPSAT-2 images and IKONOS/GeoEye-1, which are known to show the linearity. We used the images obtained over the same area and on the same date for comparison. As a result, we showed that although KOMPSAT-2 images are more noisy;the trend of brightness value and pattern of noise are almost similar to reference images. The results showed that appropriate target area to minimize the impact of noise was $5{\times}5$. Non-linearity of brightness value between KOMPSAT-2 and reference images was not observed. Therefore we could conclude that KOMPSAT-2 may be used for estimation of water quality parameters such as concentration of chlorophyll.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1149-1161
• /
• 2021

With a trend of the utilization of computer vision for satellite images, cloud detection using deep learning also attracts attention recently. In this study, we conducted a U-Net cloud detection modeling using SPARCS (Spatial Procedures for Automated Removal of Cloud and Shadow) Cloud Dataset with the image data augmentation and carried out 10-fold cross-validation for an objective assessment of the model. Asthe result of the blind test for 1800 datasets with 512 by 512 pixels, relatively high performance with the accuracy of 0.821, the precision of 0.847, the recall of 0.821, the F1-score of 0.831, and the IoU (Intersection over Union) of 0.723. Although 14.5% of actual cloud shadows were misclassified as land, and 19.7% of actual clouds were misidentified as land, this can be overcome by increasing the quality and quantity of label datasets. Moreover, a state-of-the-art DeepLab V3+ model and the NAS (Neural Architecture Search) optimization technique can help the cloud detection for CAS500 (Compact Advanced Satellite 500) in South Korea.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.71-80
• /
• 2024

In this study, a proposed ensemble learning technique aims to enhance the semantic segmentation performance of images captured by Unmanned Aerial Vehicles (UAVs). With the increasing use of UAVs in fields such as urban planning, there has been active development of techniques utilizing deep learning segmentation methods for land cover segmentation. The study suggests a method that utilizes prominent segmentation models, namely U-Net, DeepLabV3, and Fully Convolutional Network (FCN), to improve segmentation prediction performance. The proposed approach integrates training loss, validation accuracy, and class score of the three segmentation models to enhance overall prediction performance. The method was applied and evaluated on a land cover segmentation problem involving seven classes: buildings,roads, parking lots, fields, trees, empty spaces, and areas with unspecified labels, using images captured by UAVs. The performance of the ensemble model was evaluated by mean Intersection over Union (mIoU), and the results of comparing the proposed ensemble model with the three existing segmentation methods showed that mIoU performance was improved. Consequently, the study confirms that the proposed technique can enhance the performance of semantic segmentation models.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.9
• /
• pp.1808-1818
• /
• 2015

Recently, the wind power has experienced great attentions and growths among many renewable energy sources. To increase the power generation performance and economic feasibility, the size of wind turbine (WT) is getting bigger and most of wind power plants are being constructed on offshore. Therefore, the maintenance cost is relatively high because boats or helicopters are needed operators to reach the WT. In order to combat this kind of problem, remote monitoring and control system for the WT is needed. In this paper, the small-scale WT monitoring and control system is implemented using wireless sensor network technologies. To do this, sensor devices are installed to measure and send the WT status and control device is installed to receive control message for specific operation. The WT is managed by control center through graphic user interface (GUI) based monitoring and control software. Also, smart device based web-program is implemented to make the remote monitoring of the WT possible even though operators are not in control room.

• Archives of design research
• /
• v.17 no.2
• /
• pp.221-230
• /
• 2004

Existing usability testing method, particularly lab-based usability testing, has been widely implemented for development of user interface. However, the method has critical disadvantages such as high cost, time and effort, unnatural testing environment, and lack of user's direct participation in information architecture. With these backgrounds, this paper aims to develop the web-based participatory tool with particular focus on card sorting. Our tool was developed for allowing user to participate in card sorting with his own computer through web. All the data generated while user is participating in the test are automatically sent to the server, which makes it very easy to collect card sorting data. Users can drag cards of interface elements directly and build the interface structure in their own from their computer-screen so that they can represent their mental models on interface structure of testing website. These functions of our tool can help designers to implement card sorting without tedious and time consuming procedures and improve the method of usability testing by reinforcing user's active participation in building an information architecture.

• Korean Journal of Remote Sensing
• /
• v.17 no.2
• /
• pp.183-188
• /
• 2001

The NOAA AVHRR remotely sensed SST data, collected by the National Fisheries Research and Development Institute (NFRDI), are analyzed in order to understand the spatial and temporal distributions of SST in the sea near korea. Our study is based on 10-day SST images during last 7 years (1991-1997). For a time series analysis of multiple SST images, all of images must be consistent exactly at the same position by adjusting the scales and positions of each SST image. We devised an algorithm which automatically detects cloud pixels from multiple SST images. The cloud detection algorithm is based on a physical constraint that SST anomalies in the ocean do not exceed certain limits (we used $\pm$3$^{\circ}C$ as a criterion of SST anomalies). The remotely sensed SST data are tuned by comparing remotely sensed data with observed SST at coastal stations. Seasonal variations of SST are studied by harmonic fit of SST normals at each pixel and the SST anomalies are studied by statistical method. It was found that the SST anomalies are rather persistent for one or two months. Utilizing the persistency of SST anomalies, we devised an algorithm for a prediction of future SST. In the Markov lprocess model of SST anomalies, autoregression coefficients of SST anomalies during a time elapse of 10 days are between 0.5 and 0.7. The developed algorithm with automatic cloud pixel detection and rediction of future SST is expected to be incorporated to the operational real time service of SST around Korea.