웨이블렛 필터뱅크를 이용한 자동차 소음에 강인한 고립단어 음성인식

이대종,곽근창,유정웅,전명근,Lee, Dae-Jong,Kwak, Keun-Chang,Ryu, Jeong-Woong,Chun, Myung-Geun 한국지능시스템학회 2002 한국지능시스템학회논문지 Vol.15 No.4

본 논문에서는 웨이블렛 서브밴드 필터링기법을 이용하여 다중의사 결정기법에 기반을 둔 외부 잡음에 강인한 고립단어 음성인식 알고리즘을 제안하고자 한다. 음성인식에 있어서 외부잡음은 음성인식 알고리듬의 인식률을 저하시키는 주요 원인으로 지적되므로 음성인식기의 성능을 향상시키기 위해서 무엇보다도 잡음에 강인한 음성인식 알고리즘의 개발이 절실히 요구되고 있다. 제안된 알고리즘의 타당성을 검증하기 위하여 다양한 자동차 소음하에서 한국어 단독 숫자음 10단어의 인식률 변동을 알아 보았다. 그 결과 현재 음성인식 기법으로 널리 쓰이고 있는 벡터양자화 알고리즘만을 적용한 경우에 비해 9~25%의 향상된 인식률을 보였다. This paper proposes a robust speech recognition algorithm based on the wavelet filter banks. Since the proposed algorithm adopts a multiple band decision-making scheme, it performs robustness for noise as the presence of noisy severely degrades the performance of speech recognition system. For evaluating the performance of the proposed scheme, we compared it with the conventional speech recognizer based on the VQ for the 10-isolated korean digits with car noise. Here, the proposed method showed more 9~27% improvement of the recognition rate than the conventional VQ algorithm for the various car noisy environments.

마그네틱 베어링의 가변구조제어

이대종,박장환,유정웅 제어로봇시스템학회 1996 제어로봇시스템학회 국내학술대회 논문집 Vol.1 No.10

노광설비용 다채널 레이저 다이오드 제어 보드 개발

이대종,최환용,임재윤,지평식 대한전기학회 2019 전기학회논문지 P Vol.68 No.4

Currently, mercury lamps are used as light sources in semiconductor and display photo processes. Mercury lamp light sources contain heavy metals, which are environmentally destructive and are entirely imported from Japan. In addition, mercury lamps need to be replaced 12 times a year for one month of service life, resulting in continuous replacement costs. In addition, due to the deterioration of the exposure machine, periodic maintenance is also required, and the environmental burden for waste disposal of the light source is high, and thus, the retrofit to other light sources needs improvement. Therefore, in this paper, we develop a multi-channel control board for photo lithography equipment using laser diode as a method to replace the existing mercury lamp.

PlSrl반 c-퍼지 모델트리를 이용한 클로로필-a 농도 예측

이대종,전명근,박상영,정남정,이혜근,박진일 한국지능시스템학회 2006 한국지능시스템학회논문지 Vol.16 No.6

This paper proposes a c-fuzzy model tree using partial least square method to predict the Chlorophyll-a concentration in each zone. First, cluster centers are calculated by fuzzy clustering method using all input and output attributes. And then, each internal node is produced according to fuzzy membership values between centers and input attributes. Linear models are constructed by partial least square method considering input-output pairs remained in each internal node. The expansion of internal node is determined by comparing errors calculated in parent node with ones in child node, respectively. On the other hands, prediction is performed with a linear model having the highest fuzzy membership value between input attributes and cluster centers in leaf nodes. To show the effectiveness of the proposed method, we have applied our method to water quality data set measured at several stations. Under various experiments, our proposed method shows better performance than conventional least square based model tree method. 본 논문에서는 부분최소법 (PLS: Partial least square)과 c-퍼지 모델트리를 적용하여 클로로필-a 농도의 예측 모델을 제안한다. 제안된 방법은 모든 입력속성을 고려하여 퍼지 클러스터에 의해 계산된 중심벡터를 설정한 후, 각각의 중심벡터들과 입력속성간의 소속도를 이용하여 내부 노드를 형성하고, 형성된 내부노드에서 PLS를 적용하여 지역모델(Local model)을 구축한다. 노드의 분리기준으로서 부모노드(parent node)에서 구축된 모델에서 계산된 에러값이 자식노드(child node)에서 계산된 에러값보다 클 경우에 분기가 이루어진다. 최종 단계에서는 임의의 입력데이터와 잎노드에서 계산된 클러스터 중심값과 비교하여 소속도가 높은 클러스터에 속한 지역모델을 선택하여 출력값을 예측한다. 제안된 방법의 우수성을 보이기 위해 수질 데이터를 대상으로 실험한 결과 기존의 모델트리 방식에 비하여 향상된 성능을 보임을 알 수 있었다.

슬라이딩모드기법을 이용한 자기부상시스템의 강인한 관측기 설계

이대종,김주식,유정웅 한국조명전기설비학회 2002 조명·전기설비학회논문지 Vol.16 No.3

본 논문에서는 자기부상시스템의 상태추정을 위한 슬라이딩모드 관측기와 동적 안정화를 위한 슬라이딩모드 제어기를 제안한다. 제안된 슬라이딩모드 관측기는 관측오차를 감소시키기 위해서 Lyapunov 안정도이론에 의하여 구성되고, 추정된 상태에 대해서 등가 제어입력과 비선형 제어입력의 일차결합으로 슬라이딩모드 제어기가 설계된다. 제안된 설계방법의 유용성은 모의실험결과로부터 검증한다. This paper presents a sliding mode observer and Controller far the state estimation and the dynamic stabilization of the magnetic levitation systems. The proposed striding mode observer is constructed by means of Lyapunov stability theorem to decrease the observer error, and the sliding rode controller is designed by a linear combination of the equivalent and nonlinear control input for the estimated states. The feasibilities of the suggested design method are illustrated with the simulation results.

LTE Cat M1 무선모듈을 이용한 태양광 발전 설비 원격 모니터링 시스템 개발

이대종,전명근 대한전기학회 2023 전기학회논문지 P Vol.72 No.3

Most solar monitoring systems are operated by computers in places where solar power generation facilities are installed. However, if there is no operator managing solar facilities or there is no monitoring program due to a small scale, immediate maintenance is not performed even if the solar power generation facility fails. Therefore, in this paper, a remote monitoring system for solar power generation facilities using LTE Cat M1 wireless modules was developed. In order to build a remote monitoring system for solar power facilities, we developed a device that collects power generation information and environmental data from places where solar power facilities are installed, transmits data wirelessly, and implements a server program that can remotely monitor transmitted data. To evaluate the usefulness of the developed system, it was confirmed that data was accurately transmitted and received every minute as a result of evaluating data wireless transmission performance at a location 5km away from the solar installation site.

RN-ECC Based Fuzzy Vault for Protecting Fingerprint Templates

이대종,신용녀,박선홍,전명근 한국지능시스템학회 2011 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.11 No.4

Biometrics systems are used in a wide range of areas, including the area of crime prevention, due to their unique characteristics. However, serious problems can occur if biometric information is disclosed to an unauthorized user. To address these issues, this paper proposes a real valued fuzzy vault method, which adopts a real number error correction code to implement a fuzzy vault scheme for protecting fingerprint temples. The proposed method provides the benefit of allowing the private key value to be changed at any time, unlike biometric template such as a fingerprint, which is not easily renewable even if its security has been breached. The validity of the proposed method is verified for fingerprint verification.

적응적 뉴로-퍼지 추론 시스템을 이용한 UV LED 광 출력 보상 알고리즘 개발

이대종,윤재웅,전명근 한국지능시스템학회 2022 한국지능시스템학회논문지 Vol.32 No.4

산업용에 사용되는 고 출력 UV LED는 온도에 따라 광 출력이 저하되므로 온도에 따른 보정 알고리즘이 적용되지 않을 경우 광 출력 변화로 인한 불량 제품을 생산할 우려가 높다. 따라서 본 논문에서는 온도가 상승함에 따라 광 출력이 감소하는 문제점을 해결하기 위해뉴로-퍼지모델을 이용한 UV LED 광 출력 보상 알고리즘 개발을 개발하여 적용하였다. 제안된 알고리즘은 뉴로-퍼지모델을 이용하여 온도와 ADC 레벨에 따른 광 출력 추정 알고리즘을 개발한 후, 최종적으로 추정된 광 출력과 환산계수를 이용하여 광 출력의 보상이 이루어진다. 다양한 조건에서 취득한 데이터를 이용하여 제안된 방법의 타당성을 평가하였으며,평가 결과 제안된 방법을 적용한 결과 온도 상승에 관계없이 일정한 광 출력이 발생함을 알수 있었다

홍채와 음성을 이용한 고도의 개인확인시스템

이대종,고현주,곽근창,전명근,Lee, Dae-Jong,Go, Hyoun-Joo,Kwak, Keun-Chang,Chun, Myung-Geun 한국지능시스템학회 2003 한국지능시스템학회논문지 Vol.15 No.2

본 논문에서는 홍채인식과 화자식별 방법을 결합한 고도의 개인확인 시스템을 제안한다. 제안된 방법은 홍채인식과 화자식별의 장점만을 부각시켜 최종적으로 결정법칙에 의해 화자를 인식하는 구조로 되어 있으며, 특히 음성에 노이즈가 첨가된 환경하에서도 우수한 성능을 보일 수 있도록 시스템을 구성하였다. 제안된 알고리즘의 성능을 검증하기 위하여 실험한 결과, 보안의 정도가 높은 상급(High)에 해당하는 인식률은 홍채만을 이용한 경우보다 56.7%, 음성을 이용한 화자식별 방법만을 사용한 경우보다 10% 정도 인식률이 향상되었다. 또한 음성에 노이즈를 첨가한 경우에도 보안의 정도가 높은 상급(High)에 해당하는 인식률은 홍채만 이용한 경우보다 인식률이 30%, 노이즈가 첨가된 음성만 이용한 경우보다 60% 정도 향상된 인식률을 보였다. This proposes a new algorithm for advanced personal identification system using iris pattern and speech signal. Since the proposed algorithm adopts a fusion scheme to take advantage of iris recognition and speaker identification, it shows robustness for noisy environments. For evaluating the performance of the proposed scheme, we compare it with the iris pattern recognition and speaker identification respectively. In the experiments, the proposed method showed more 56.7% improvements than the iris recognition method and more 10% improvements than the speaker identification method for high quality security level. Also, in noisy environments, the proposed method showed more 30% improvements than the iris recognition method and more 60% improvements than the speaker identification method for high quality security level.

우리나라 대도시의 도시성장관리 평가 연구

이대종 한국도시재생학회 2015 도시재생 Vol.1 No.2

The purpose of this study is to evaluate and understand Seoul and 6 other metropolitan cities by developing a proper index of evaluation for the urban growth management and to propose improvements and implications. A precise frame of super ordinate concept has been defined through consideration on previous studies of foreign and domestic urban growth management, in order to develop the index of evaluation. The final index of evaluation was established by integrating foreign and domestic index with the frequency of quotation and the potential for subscription in regards to the subordinate concept. Population, housing, land use, infrastructure, economic, finance and environment had been considered as the primary evaluation criteria of urban growth management and the ones for quantification had been selected to be the detailed index of evaluation. The importance level of the developed index of evaluation had been analyzed through network analytic decision making method analysis(ANP) after the survey on experts. The result of ANP analysis presents each importance level as land use and infrastructure(0.383), population and housing(0.328), economy and finance (0.168), environment(0.119). the overall importance on detailed index of evaluation is listed as land use density(0.2099), population increase(0.1327), population density(0.0890), price stabilization(0.0824), prevention on expansion of urban area(0.0753). Urban growth management had been evaluated on Seoul and 6 other metropolitan cities in order to apply the developed index of evaluation. As a result, it showed that the urban growth management was well-conducted in the following sequence: Ulsan(81.93), Incheon(81.80), Seoul (80.20), Busan(76.66), Daegu (74.99), Gwangju(73.45) and Daejeon(71.36) The result of this study shows that it is required to perform maintenance on urban growth management while emphasizing the importance it to a greater level with the standard of the index of evaluation for each city. The result shows that it would provide a great help to the urban growth management if Seoul puts more emphasis on managing and procuring low cost housing, protecting environmental resources, open spaces, Busan self- sufficiency, protecting environmental resources, Daegu on self-sufficiency, protecting environmental resources, Incheon on self-sufficiency, protecting environmental resources, open spaces, Gwangju on protecting historical cultural resources, Daejeon on self-sufficiency, procuring low cost housing, Ulsan on selfsufficiency, procuring low cost housing. Moreover, there should be urban growth management for all local metropolitan cities as well as the capital area including Seoul and Gyeonggi-do. This would require the researches and studies on the policy and system for the urban growth management system of local metropolitan cities. Keywords: Urban growth management, index of evaluation, network analytic decision making method(ANP), importance.