• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11a
• /
• pp.637-640
• /
• 2005

We propose a sound source localization method using the Head-Related-Transfer-Function (HRTF) to be implemented in a given platform. HRTFs contain not only the information regarding proper time delays but also phase and magnitude distortions due to diffraction and scattering by the shading object. Therefore, a set of HRTFs for any given platform provides a substantial amount of information as to the whereabouts of the source. In this study, we introduce new phase criterion in order to find the sound source location in accordance with the HRTF database empirically obtained in an anechoic chamber with the given platform. Using this criterion, we analyze the estimation performance of the proposed method in a household environment.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.3
• /
• pp.200-206
• /
• 2010

In ultrasound-excited thermography, the injected ultrasound to an object is transformed to heat and the appearance of defects can be visualized by thermography camera. The advantage of this technology is selectively sensitive to thermally active defects. Despite the apparent simplicity of the scheme, there are a number of experimental considerations that can complicate the implementation of ultrasound excitation thermography inspection. Factors including acoustic horn location, horn-crack proximity, horn-sample coupling, and effective detection range all significantly affect the detect ability of this technology. As conclusions, the influence of coupling pressures between ultrasound exciter and specimen was analyzed, which was dominant factor in frictional heating model.

• Proceedings of the KAIS Fall Conference
• /
• 2008.05a
• /
• pp.98-100
• /
• 2008

최근 무선통신 기술의 발달과 편리성으로 무선 랜의 활용 증가하고 있다. 이와 더불어 무선 랜의 보안 위협과 취약성에 대하여 이슈화 되고 있다. 따라서 IEEE에서는 802.11 표준안을 제정하고 무선 랜의 보안 취약점을 보완하기 위해 802.11i등 새로운 표준들을 제정하고 있지만, 아직까지 해결되지 않은 보안 위협들이 존재한다. 본 논문에서는 액세스 포인트의 비콘 프레임을 이용하여 건물 내 액세스 포인트의 보안 상태 와 비인가 액세스 포인트를 탐지하는 시스템과 RSSI, 삼각측량범 및 칼만필터 알고리즘을 사용한 위치탐지 알고리즘을 제안하고, 기존 탐지 알고리즘과 제안 알고리즘의 결과 비교로 성능을 평가하였다.

• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.398-400
• /
• 2019

Faced with the increasing demand for image recognition on mobile devices, how to run convolutional neural network (CNN) models on mobile devices with limited computing power and limited storage resources encourages people to study efficient model design. In recent years, many effective architectures have been proposed, such as mobilenet_v1, mobilenet_v2 and PeleeNet. However, in the process of feature selection, all these models neglect some information of shallow features, which reduces the capture of shallow feature location and semantics. In this study, we propose an effective framework based on Feature Pyramid Networks to improve the recognition accuracy of deep and shallow images while guaranteeing the recognition speed of PeleeNet structured images. Compared with PeleeNet, the accuracy of structure recognition on CIFA-10 data set increased by 4.0%.

• Annual Conference of KIPS
• /
• 2000.04a
• /
• pp.324-327
• /
• 2000

본 논문에서는 LAN 상에서의 장애 검출과 장애를 유발시킨 호스트에 대한 위치 확인을 통하여 보다 효율적인 네트워크 장애 관리가 이루어질 수 있도록 하기 위한 알고리즘을 제시하고 있다. LAN 상에서의 주된 장애로 충돌율에 의한 네트워크 지연 장애를 들 수 있다. 따라서 패킷 충돌 감지를 통하여 네트워크 지연을 감지하고 이를 통하여 브로드캐스트, 멀티캐스트, 에러 발생 패킷 등을 분석하여 충돌율을 많이 발생시킨 호스트를 찾는다. 패킷을 많이 발생시킨 호스트에 대하여 RMON2를 이용하여 응용 프로토콜의 종류를 파악하고 이에 대한 내용을 관리자에게 통보함으로써 네트워크 장애 관리를 효율적으로 수행할 수 있다.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2003.03a
• /
• pp.38-44
• /
• 2003

Artificial blasts, defined as seismo-acoustic events, were discriminated from natural earthquakes in the Korean Peninsula by the seismo-acoustic analysis. Total 197 seismo-acoustic events corresponding to 9 percent of seismic events in 2002 were analyzed and classified as artificial surface blasts. Events distribution pattern of the seismo-acoustic events in 2002 was similar to the previous result in 1999-2001, except for two regions. Newly determined seismo-acoustic events were added to the previous artificial blast database. To extend infrasound detection capability, new small-scale infrasound array(TJIAR) was installed in KIGAM. Preliminary analysis for the small array was conducted to discriminate artificial blasts in the southwestern part of the Korean Peninsula. The small array discriminated S seismo-acoustic events during short period analysis. And two infrasound arrays(TJIAR and CHNAR) were used to determine approximate sound source location by cross bearing method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.196-197
• /
• 2009

In Video, key frame generated from the scene change detection is to perform character recognition through the projections. The separation between the text are separated by a vertical projection. Phoneme is separated Cho-sung, Jung-sung, and Jong-sung and is divided 6 types. Phoneme pattern is separated to suitable 6 types through the horizontal projection. Phoneme are separated horizontal, vertical, diagonal, reverse-diagonal direction. Phoneme is recognized using the 4-direction projection and location information.

• Journal of the Korean Society for Railway
• /
• v.6 no.2
• /
• pp.81-86
• /
• 2003

This study proposes the neural network simulator for the integrity evaluation of weld zone in railway rails. For these purposes, the ultrasonic signals for defects(crack) of weld zone in frames are acquired in the type of time series data and echo strength. The detection of the natural defects in railway truck is performed using the characteristics of echodynamic pattern in ultrasonic signal. And then their applications evaluated feature extraction based on the time-frequency-attractor domain(peak to peak, rise time, rise slope, fall time, fall slope, pulse duration, power spectrum, and bandwidth) and attractor characteristics (fractal dimension and attractor quadrant) etc. The constructed neural network simulator agrees fairly well with the measured results of test block(defect location, beam propagation distance, echo strength, etc). The Proposed neural network simulator in this study can be used for the integrity evaluation of weld zone in railway rails.

• Journal of the Semiconductor & Display Technology
• /
• v.9 no.3
• /
• pp.59-63
• /
• 2010

This paper proposes computer visual inspection algorithms for various LCD defects which are found in a manufacturing process. Modular vision processing steps are required in order to detect different types of LCD defects. Those key modules include RGB filtering for pixel defects, gray-scale morphological processing and Hough transform for line defects, and adaptive threshold for spot defects. The proposed algorithms can give users detailed information on the type of defects in the LCD panel, the size of defect, and its location. The machine vision inspection system is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithms are quite successful.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.3
• /
• pp.19-27
• /
• 2019

This paper proposes a new method using multi-layer overlapped windows to improve the performance of YOLO network which is vulnerable to detect small dense objects. In particular, the proposed method uses the YOLO Network based on the multi-layer overlapped windows to track small dense vehicles that approach from long distances. The method improves the detection performance for location and size of small vehicles. It allows crossing area of two multi-layer overlapped windows to track moving vehicles from a long distance to a short distance. And the YOLO network is optimized so that GPU computation time due to multi-layer overlapped windows should be reduced. The superiority of the proposed algorithm has been proved through various experiments using captured images from road surveillance cameras.