• 한국정보전자통신기술학회논문지
• /
• 제17권1호
• /
• pp.31-37
• /
• 2024

본 연구에서는 컴퓨팅 자원이 제한된 환경에서도 효율적으로 동작 가능한 머신비전 기반의 보행자 신호 검출 알고리즘을 제안하였다. 이 알고리즘은 제한된 자원에서도 높은 효율성을 발휘하며, 주변 조명 등의 영향을 최소화하기 위해 HSV 색공간 기반의 영상처리, 이진화, 모폴로지 연산, 라벨링 등의 단계를 순차적으로 적용하여 빛 번짐과 같은 현상에 대응할 수 있도록 설계되었다. 특히, 이 알고리즘은 비교적 단순한 형태로 구성되어 임베디드 시스템 환경에서 부담 없이 동작할 수 있도록 고려되었다. 이를 통해 낮은 컴퓨팅 자원을 보유한 환경에서도 안정적으로 작동할 수 있는 구조를 갖췄다. 또한, 제안된 보행등은 보행신호 검출 기능뿐만 아니라 IoT 기능을 탑재하여 무선으로 웹서버와 연동되는 기능을 갖췄다. 이에 따라 보행등 설치자 및 제어권자들은 웹 서버를 통해 신호등의 상태를 모니터링하고 제어할 수 있는 편의성을 제공받을 수 있다. 더불어, 50W급 LED 보행등을 효과적으로 제어할 수 있는 구현이 완료되었다. 이러한 제안된 시스템은 자원 제한 환경에서의 신속하고 효율적인 보행자 신호 검출 및 제어 시스템으로, 실제 도로 환경에서의 적용 가능성을 고려하고 있다. 이를 통해 보다 안전하고 지능적인 도로 교통 시스템의 구축에 기여할 것으로 기대된다.

• 한국항공우주학회지
• /
• 제35권6호
• /
• pp.539-547
• /
• 2007

본 논문은 영상정보를 이용하여 사용자의 눈의 움직임을 통해 응시점을 추적하는 실시간 아이트랙커 시스템 개발에 대한 연구이다. 개발된 시스템은 광학기반의 동공추적 기법을 이용하여 사용자의 눈의 움직임을 추적한다. 광학기반의 방법은 사용자의 눈에 아무런 장애도 일으키지 않고 눈의 위치를 매우 정확하게 측정 할 수 있다는 장점을 가진다. 동공영상을 획득하기 위해 적외선 카메라를 사용하며, 획득한 영상으로부터 정확한 동공영역을 추출하기 위해 적외선 LED를 사용한다. 실시간 영상처리가 가능하게 하기위해 칼만필터를 적용한 동공추적 알고리즘을 개발하고 DSP(Digital Signal Processing) 시스템을 사용하여 동공영상을 획득한다. 실시간 아이트랙커 시스템을 통하여 실시간으로 사용자의 동공움직임을 추적하고 사용자가 바라보는 배경영상에 사용자의 응시점을 나타낸다.

• Journal of Microbiology and Biotechnology
• /
• 제21권12호
• /
• pp.1306-1311
• /
• 2011

Recombinant Rhodopseudomonas palustris, harboring the carotenoid-metabolizing gene crtI (CrtIBS), and whose color changes from greenish yellow to red in response to inorganic As(III), was cultured in transparent microplate wells illuminated with a light emitting diode (LED) array. The cells were seen to grow better under near-infrared light, when compared with cells illuminated with blue or green LEDs. The absorbance ratio of 525 to 425 nm after cultivation for 24 h, which reflects red carotenoid accumulation, increased with an increase in As(III) concentrations. The detection limit of cultures illuminated with near-infrared LED was 5 ${\mu}g$/l, which was equivalent to that of cultures in test tubes illuminated with an incandescent lamp. A near-infrared LED array, in combination with a microplate, enabled the simultaneous handling of multiple cultures, including CrtIBS and a control strain, for normalization by the illumination of those with equal photon flux densities. Thus, the introduction of a near-infrared LED array to the assay is advantageous for the monitoring of arsenic in natural water samples that may contain a number of unknown factors and, therefore, need normalization of the reporter event.

• 한국위성정보통신학회논문지
• /
• 제7권3호
• /
• pp.63-68
• /
• 2012

가시광 통신 시스템은 LED를 통해 방사되는 가시광을 이용한 차세대 통신 시스템으로, 유비쿼터스 네트워크 서비스 구축 시 에너지 절감 효과를 가져 올 수 있다. 또한 기존 인프라를 활용하여 고출력 전송이 가능하며 유지 보수 비용을 절감할 수 있다. 하지만 가시광 통신 시스템에서는 인접 송신기 간섭 신호의 영향으로 네트워크 경계에 위치한 수신기의 신호 검출 성능은 급격히 열화되고 전송 효율은 감소하게 된다. 본 논문에서는 가시광 통신 시스템에서 다수의 Tx가 인접해 있을 때 발생하는 송신기간 간섭 문제를 광 릴레이와 광 빔포밍 기법 적용을 통하여 효율적으로 간섭을 완화하고 그 성능을 평가한다. 제안하는 시스템의 결과로 사용하지 않는 기존 가시광 통신 시스템 대비 BER 측면과 채널 용량에서 모의실험을 통하여 향상된 성능을 보인다.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.617-625
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• 한국수의병리학회:학술대회논문집
• /
• 한국수의병리학회 2003년도 추계학술대회초록집
• /
• pp.28-28
• /
• 2003

Hepatitis E virus (HEV), previously referred to as enterically transmitted non-A, non-B hepatitis, is responsible for sporadic infections as well as large epidemics of acute viral hepatitis in developing countries. The disease generally affects young adults and reportedly has a mortality rate of up to 20％ in infected pregnant women. HEV was once considered to be a member of the family Caliciviridae, but the unique genomic organization of HEV has led to the removal of HEV from the family and it was provisionally classified in an unassigned family of HEV-like viruses. In situ hybridization provides any cellular detail and histological architecture.[1] However, use of in situ hybridization is largely restricted to the laboratories because this technique is the greater technical complexity and expense compared with immunohistochemistry. Therefore, the objective of this study is to develop the immunohistochemistry for the detection of swine HEV from formalin-fixed, paraffin-embedded hepatic tissues. (omitted)

• 제어로봇시스템학회논문지
• /
• 제22권8호
• /
• pp.627-632
• /
• 2016

In this paper, we propose a new vision-based defect inspection system for the surface of hot slabs. To minimize the influence of self-emission from slab surfaces with high temperature, an optic method based on blue LED light and a blue pass filter is proposed. Because the slab surface is partially covered with scales, which are unavoidable oxidized substances caused during manufacturing, it is difficult to distinguish between vertical cracks and scale. In order to resolve this problem and to improve the detection performance, the use of a Gabor filter and dynamic programming are proposed. Finally, the effectiveness of the proposed method is shown by means of experiments conducted on images of hot slabs that were obtained from an actual slab production line.

• 반도체디스플레이기술학회지
• /
• 제16권1호
• /
• pp.29-33
• /
• 2017

This paper presents a development of vision aligner with three channels for the wafer and plate bonding machine in manufacturing of LED. The developed vision aligner consists of three cameras and performs wafer alignment of rotation and translation, flipped wafer detection, and UV Tape detection on the target wafer and plate. Normally the process step of wafer bonding is not defined by standards in semiconductor's manufacturing which steps are used depends on the wafer types so, a lot of processing steps has many unexpected problems by the workers and environment of manufacturing such as the above mentioned. For the mass production, the machine operation related to production time and worker's safety so the operation process should be operated at one time with considering of unexpected problem. The developed system solved the 4 kinds of unexpected problems and it will apply on the massproduction environment.

• Journal of electromagnetic engineering and science
• /
• 제14권2호
• /
• pp.79-81
• /
• 2014

In B-scan data measured by a pulse-type monostatic borehole radar, target signatures are seriously obscured by two clutters that differ in orientation and intensity. The primary clutter appears as a nearly constant time delay, which is caused by internal ringing between antenna and transceiver in the radar system. The secondary clutter occurs as an oblique time delay due to the guided borehole wave along the logging cable of the radar antenna. This issue led us to perform adaptive filtering processing for orientation-based clutter removal. This letter describes adaptive filtering processing consisting of a combination of edge detection, data rotation, and eigenimage filtering. We show that the hyperbolic signatures of a dormant air-filled tunnel target can be more distinctly enhanced by applying the proposed approach to the B-scan data, which are measured in a well-suited test site for underground tunnel detection.

• Journal of Multimedia Information System
• /
• 제5권2호
• /
• pp.99-104
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.