• 대한음성학회지:말소리
• /
• 제58호
• /
• pp.83-99
• /
• 2006

One key factor that hinders the widespread deployment of speaker identification technologies is the requirement of long enrollment utterances to guarantee low error rate during identification. To gain user acceptance of speaker identification technologies, adaptation algorithms that can enroll speakers with short utterances are highly essential. To this end, this paper applies MLLR speaker adaptation for speaker enrollment and compares its performance against other speaker modeling techniques: GMMs and HMM. Also, to speed up the computational procedure of identification, we apply speaker clustering method which uses principal component analysis (PCA) and weighted Euclidean distance as distance measurement. Experimental results show that MLLR adapted modeling method is most effective for short enrollment utterances and that the GMMs performs better when long utterances are available.

• 국제초고층학회논문집
• /
• 제11권3호
• /
• pp.221-226
• /
• 2022

Installation of Structural Health Monitoring (SHM) system is a legal obligation for high-rise buildings over 200 m or 50-floor high in South Korea. CNP Dongyang has developed key technologies for SHM system design, installation, and data analyzing. Also, CNP Dongyang has applied SHM technology to a plenty of South Korea's representative high-rise buildings. The SHM technology, also, could be used in safety management of construction phase, evaluation of structural performance, etc. In this paper, state of the art SHM technologies and their application examples are introduced to give insight for future research and practical use of SHM.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2010년도 추계학술대회 논문집
• /
• pp.537-537
• /
• 2010

High precision sensing is very important in various technologies. Especially, it is more important when it were applied to nano/micro meter level's sensing like AFM, storage, etc. And capacitive sensing is widely used method. To improve the measurement efficiency, many signal conditioners were studied and one of them was surface acoustic wave (SAW) device. SAW device is very widely used as a high frequency bandwidth filter. Due to the reflective characteristic of high frequency, the response of SAW device contains both propagative and reflective signal at the external impedance. In this paper, we used SAW device as signal conditioner of capacitive sensor. And high precision gap measurement was executed using capacitive load. Reference signal was reflective SAW response and the magnitude at the center frequency of SAW device by the change of impedance was checked. Finally, the attainable gap resolution was determined.

• 한국소음진동공학회논문집
• /
• 제21권1호
• /
• pp.47-55
• /
• 2011

Reactor vessel internals comprehensive vibration assessment program(RVI CVAP) is one of the necessary tests to ensure the safety of nuclear power plants. RVI CVAP of U.S. nuclear regulatory commission regulatory guide 1.20(U.S. NRC R.G. 1.20) consists of the analysis, measurement and inspection. One of the core technologies of the measurement program for RVI CVAP is to select suitable sensors because the measurement is conducted during the critical path of the construction period of nuclear power plants. Therefore, we analyzed RVI thermal-hydraulic and structure design data of Palo Verde nuclear power plant(U.S.), Yonggwang nuclear power plant(Korea) and APR1400 and researched measuring sensors used in them; moreover, we investigated sensors used for measurement of RVI CVAP for the last 20 years throughout the world. Based on these results, we selected suitable measuring sensors for RVI CVAP in advanced power reactor 1400(APR1400).

• Smart Structures and Systems
• /
• 제8권1호
• /
• pp.53-67
• /
• 2011

Human state in human-machine systems highly affects the overall system performance, and should be detected and monitored. Physiological cues are essential indicators of human state and useful for the purpose of monitoring. The study presented in this paper was focused on developing a bio-inspired sensing system, i.e., Nano-Skin, to non-intrusively measure physiological cues on human-machine contact surfaces to detect human state. The paper is presented in three parts. The first part is to analyze the relationship between human state and physiological cues, and to introduce the conceptual design of Nano-Skin. Generally, heart rate, skin conductance, skin temperature, operating force, blood alcohol concentration, sweat rate, and electromyography are closely related with human state. They can be measured through human-machine contact surfaces using Nano-Skin. The second part is to discuss the technologies for skin temperature measurement. The third part is to introduce the design and manufacture of the Nano-Skin for skin temperature measurement. Experiments were performed to verify the performance of the Nano-Skin in temperature measurement. Overall, the study concludes that Nano-Skin is a promising product for measuring physiological cues on human-machine contact surfaces to detect human state.

• 전자공학회논문지SC
• /
• 제45권1호
• /
• pp.25-30
• /
• 2008

본 논문에서는 상용 고휘도 백색광 LED 및 CCD 어레이 검파기를 이용하여 Fourier-domain 방식의 광 계측기를 구현하였다. 제안된 기술의 축 방향 측정 거리 범위는 $125{\mu}m$이고, 축 방향 분해능은 $1.24{\mu}m$이다. 기존 시스템이 고가의 광대역 광원을 사용하면서도 분해능이 수 ${\mu}m$ 이상인 것에 비추어 볼 때, 본 시스템은 저가의 상용 LED와 CCD 어레이 검파기를 사용하여 구현되므로 소형이며 가격적인 면에서 유리하면서도 높은 분해능을 얻을 수 있다.

• 한국IT서비스학회지
• /
• 제11권sup호
• /
• pp.103-111
• /
• 2012

In epigraph field to study ancient scripts, alternative readability improvement technologies have been developed to replace existing rubbing method which has low resolution and causes surface pollution of heritages from the viewpoints of extraction process and used materials. Recently many methods which are based on analysis of pixel data for extracting outlines of the specific image have been developed with advancement of image processing techniques. But these methods are not applicable and the results are not satisfied in the damaged inscriptions which are weathered by wind and rain for a long time and in the narrowed one. In this paper laser scanning techniques which uses optical triangulation measurement principle are developed to minimize scanning error. The proposed techniques are consisted of 3 parts：(1) the understanding of optical triangulation measurement principle to find scanning guideline (2) determinations of points interval, scanning distance and scanning angle to guarantee scanning data quality (3) identification of valid point data area which will be used in registration process. The proposed character identification method contributed in decoding an ancient inscription on SeukBingGo in Kyungju.

• 제어로봇시스템학회논문지
• /
• 제14권6호
• /
• pp.519-522
• /
• 2008

As industry of a semiconductor and LCD industry have been rapidly growing, precision technologies of machining such as etching and 3D measurement are required. Stylus has been important measuring method in traditional manufacturing process. However, its disadvantages are low measuring speed and damage possibility at contacting point. To overcome mentioned disadvantage, non-contacting measurement method is needed such as PMP(Phase Measuring Profilometry), WSI(white scanning interferometer) and Confocal Profilometry. Among above 3 well-known methods, WSI started to be applied to FPD(flat panel display) manufacturing process. Even though it overcomes 21t ambiguity of PMP method and can measure objects which has specular surface, the measuring speed and vibration coming from manufacturing machine are one of main issue to apply full automatic total inspection. In this study, We develop high speed WSI system and algorithm to reduce unknown noise. The developing WSI and algorithm are implemented to measure 3D surface of wafer. Experimental results revealed that the proposed system and algorithm are able to measure 3D surface profile of wafer with a good precision and high speed.

• 반도체디스플레이기술학회지
• /
• 제16권3호
• /
• pp.8-13
• /
• 2017

In this paper, the measurement of the inner diameter dimension of the circular hole by using a machine vision system was studied. This paper was focused on the theory and key technologies of machine vision inspection technology for the improvement of measurement accuracy and speed of the micro circular holes. A new method was proposed and was verified through the experiments on Gray conversion, binarization, edge extraction and Hough transform in machine vision system processes. Firstly, the Hough transform was proposed in order to improve the speed increase and implementation ease, it demonstrated the superiority of Hough transform and improvement through a comparative experiment. Secondly, we propose a calibration method of the system in order to obtain exactly the inner diameter of the circular hole. Finally, we demonstrate the reliability of the entire system as a MATLAB-based implementation of the GUI program, measuring the inner diameter of the circular hole through the circular holes of different dimensions measuring experiment.

• 한국IT서비스학회지
• /
• 제19권4호
• /
• pp.49-61
• /
• 2020

Prior studies on technology predictions attempted to predict the emergence and spread of emerging technologies through the analysis of correlations and changes between data using objective data such as patents and research papers. Most of the previous studies predicted future technologies only from the viewpoint of technology development. Therefore, this study intends to conduct technical forecasting from the perspective of the consumer by using keyword search frequency of search portals such as NAVER before and after the introduction of emerging technologies. In this study, we analyzed healthcare technologies into three types : measurement technology, platform technology, and remote service technology. And for the keyword analysis on the healthcare, we converted the classification of technology perspective into the keyword classification of consumer perspective. (Blood pressure and blood sugar, healthcare diagnosis, appointment and prescription, and remote diagnosis and prescription) Naver Trend is used to analyze keyword trends from a consumer perspective. We also used the ARIMA model as a technology prediction model. Analyzing the search frequency (Naver trend) over 44 months, the final ARIMA models that can predict three types of healthcare technology keyword trends were estimated as "ARIMA (1,2,1) (1,0,0)", "ARIMA (0,1,0) (1,0,0)", "ARIMA (1,1,0) (0,0,0)". In addition, it was confirmed that the values predicted by the time series prediction model and the actual values for 44 months were moving in almost similar patterns in all intervals. Therefore, we can confirm that this time series prediction model for healthcare technology is very suitable.