• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.1
• /
• pp.31-35
• /
• 2010

This paper presents the development of automatic defect detection program using 3D computed tomography image of small solid rocker motor. We applied the neighbor pixel comparison algorithm with beam hardening correction for the recognition of defect. We made the artificial defect specimen in order to decide a standard CT value of defect. The program was tested with 150 small solid rocket motors and it could detect the disbond, crack, foreign material and void. The program showed more reliable and faster results than human inspector's interpretation.

• Journal of KIISE
• /
• v.42 no.1
• /
• pp.68-75
• /
• 2015

This paper proposes a method for the automatic word spacing of unsegmented Korean sentences. In our method, eojeol monograms are used for word spacing as opposed to the syllable n-grams that have been used in previous studies. The use of a Korean morphological analyzer is limited to the correction of typical word spacing errors. Our method gives a 98.06% syllable accuracy and a 94.15% eojeol recall, when 10-fold cross-validated with the Sejong corpus, after filtering out non-hangul eojeols. The processing rate is 250K eojeols or 1.8 MB per second on a typical personal computer. Syllable accuracy and eojeol recall are related to the size of the eojeol dictionary, better performance is expected with a bigger corpus.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3981-4004
• /
• 2019

This paper proposes a novel method for locating objects in real space from a single remote image and measuring actual distances between them by automatic detection and perspective transformation. The dimensions of the real space are known in advance. First, the corner points of the interested region are detected from an image using deep learning. Then, based on the corner points, the region of interest (ROI) is extracted and made proportional to real space by applying warp-perspective transformation. Finally, the objects are detected and mapped to the real-world location. Removing distortion from the image using camera calibration improves the accuracy in most of the cases. The deep learning framework Darknet is used for detection, and necessary modifications are made to integrate perspective transformation, camera calibration, un-distortion, etc. Experiments are performed with two types of cameras, one with barrel and the other with pincushion distortions. The results show that the difference between calculated distances and measured on real space with measurement tapes are very small; approximately 1 cm on an average. Furthermore, automatic corner detection allows the system to be used with any type of camera that has a fixed pose or in motion; using more points significantly enhances the accuracy of real-world mapping even without camera calibration. Perspective transformation also increases the object detection efficiency by making unified sizes of all objects.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06a
• /
• pp.59-60
• /
• 2007

휴대폰과 메신저 등 통신 환경에서 사용되는 표준어가 아닌 SMS의 변형된 어휘 및 띄어쓰기 오류를 자동으로 교정하여 형태소 분석 및 품사 태깅의 성능 저하 문제를 방지하는 문자열 오류의 교정 방법을 제안하였다. 통신 어휘들의 문자열 사전 구축 방법으로 통신어휘집을 기반으로 수동으로 구축하는 방법과 수작업으로 구축된 말뭉치로부터 자동으로 변형된 문자열을 추출하는 방법, 그리고 문맥을 고려하는 방법을 비교-분석하고 실험 및 성능 평가 결과를 제시하였다.

• Proceedings of the IEEK Conference
• /
• 2002.06e
• /
• pp.67-70
• /
• 2002

In this paper, we have researched a Automatic Power Factor Correction and THD reduction System for the multiple connection of CFL. Also in this paper, the power factor has been researched for the design of CFL, found the reason why the power factor is low and THD is too high. This paper has designed the PFC System for the multiple connection of CFL, and then we have increased the power factor and reduced the total harmonic distortion, by implementing them.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1527-1543
• /
• 2021

In this paper, we explore the applicability and utility of a technology that generating clustered solid building models based on point cloud automatically by applying it to various data. In order to improve the quality of the model of insufficient quality due to the limitations of the automatic building modeling technology, we develop the building shape modification and texture correction technology and confirmed the resultsthrough experiments. In order to explore the applicability of automatic building model generation technology, we experimented using point cloud and LiDAR (Light Detection and Ranging) data generated based on UAV, and applied building shape modification and texture correction technology to the automatically generated building model. Then, experiments were performed to improve the quality of the model. Through this, the applicability of the point cloud data-based automatic clustered solid building model generation technology and the effectiveness of the model quality improvement technology were confirmed. Compared to the existing building modeling technology, our technology greatly reduces costs such as manpower and time and is expected to have strengths in the management of modeling results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9A
• /
• pp.1372-1382
• /
• 1999

The major source of errors in high-speed networks such as Broadband ISDN(B-lSDN) is buffer overflow during congested conditions. These congestion errors are the dominant sources of errors in 1high-speed networks and result in cell losses. Conventional communication protocols use error detection and retransmission to deal with lost packets and transmission errors. However, these conventional ARQ(Automatic Repeat Request) methods are not suitable for the high-speed networks since the transmission delay due to retransmissions becomes significantly large. As an alternative, we have presented a method to recover consecutive cell losses using forward error correction(FEC) in ATM(Asynchronous Transfer Mode)networks to reduce the problem. The performance estimation based on the cell discard process model has showed our method can reduce the cell loss rate substantially. Also, the performance estimations in ATM networks by interleaving and IP multicast service are discussed.

• Journal of IKEEE
• /
• v.4 no.2 s.7
• /
• pp.274-280
• /
• 2000

The fact that error probability is higher in wireless communication environment than the one in a fixed network makes it inappropriate to apply the same DLC (Data Link Control) protocol used in a wireline network to a wireless network. And since the existing DLC protocol for wireless network was optimized for low-rate data service, it is not suitable for a wireless network environment which should support high-speed and multimedia traffic. Therefore it is desperate to have a new DLC protocol for todays wireless mobile communication environment. In this paper, we propose an error control scheme in WATM (Wireless Asynchronous Transfer Mode) environment. which supportsmultiple traffic attributes, high-speed, multimedia data service. In this paper we modified the existing ASR ARQ (Adaptive Selective Repeat Automatic Repeat Request) protocol where cells exceeding maximum allowable delay range are discarded. And adding FEC (Forward Error Correction) for delay-sensitive traffic resulted in smaller increase of transmission delay.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.3
• /
• pp.310-315
• /
• 2014

The domestic maritime environment shows higher frequency of maritime accidents amidst greater traffic volume arising from increasing international seaborne trade and maritime leisure activities. To reduce such maritime accidents, there exist various kinds of safety navigation devices in the ship bridge aimed to mitigate burdens of navigators and support their accurate decision making. Amongst is the AIS considered very important, which is an automatic tracking system to assist understanding of the circumstances in the vicinity by receiving information of other ships and also sending its own; where the information contains errors initially, however, such wrong information is periodically transmitted, accordingly giving rise to hindrance sometimes in decision making by shore operators or ship navigators at sea. This study is to propose the error data and field management algorithm using fuzzy theory toward improving reliability and accuracy in ship related information received from AIS.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.181-184
• /
• 2016

This study is to compensate for inaccuracies in accordance with the change in the deviation correction value due to the movement and location of the ship cargo, equipment of the vessel, and eliminating the inconvenience of hand. By modifying the deviation through the simplification and automation was planned for accuracy and ease of modification of the modified value. The main method used is charted by measuring 24 direction and inputting the value of magnetic compass direction in automatic deviation-correcting apparatus manually or automaticallyThe measured values are exhibited in Table data and made it possible to calculate accurate correction value deviation. From this it can make deviation table having the margin of error within ${\pm}3^{\circ}$in all regions of the world And this table will help to navigational safety and economy under the unavailable or limited gyro contion.