LPC 스팩트럼 정규화 기법에 의한 한국어 모음의 포만트 분석 ( An analysis of korean vowel using LPC spectrum normalization method )

위진우,고형화 한국통신학회 1991 한국통신학회 학술대회논문집 Vol.10 No.1

잡음이 혼입된 음성신호에 있어서 피치추출의 성능평가 ( Evalution of Pitch Estimation for Speech Signal Processing in Noisy Environment )

위진우,강철호 대한전자공학회 1992 대한전자공학회 학술대회 Vol.1992 No.1

사단 공병정찰 전담부대 편성에 관한 연구

위진우,김익현,백병호 한국군사과학기술학회 2019 한국군사과학기술학회지 Vol.22 No.5

The purpose of this study is to analyze the necessity of organizing an exclusive unit to perform the divisionEngineering Reconnaissance, and how to organize exclusive unit. To this end, first, it was analyzed whetherexclusive unit organization was necessary by using organization-conditions and AHP. Next, through ARENA modelsimulation and task-analysis, it was determined how many people would be organized, and how the class structurewould be appropriate. As a result, first, it is reasonable to organize the Engineering Reconnaissance unit as anexclusive unit, and the best way is to organize all-time(war/peace time). Second, the exclusive unit should beorganized into a total of 10 persons(2~3 cadres, 7~8 soldiers). We hope that the research will contribute to therational procedure of our military unit structure organization and set the standards for applying the quantitativemethodology.

가중된 예측 오차 파라미터를 사용한 화자 확인 성능 개선

위진우,강철호 한국음향학회 2001 韓國音響學會誌 Vol.20 No.5

LPC분석 기반 화자 확인에서 잔여성분(residue) 예측은 보통 무시되고, LPCC(LPC-cepstrum)만이 특징 파라미터로 사용된다. 본 연구에서는 잔여성분으로부터 추출된 예측파라미터인 잔여 켑스트럼(residual cepstrum)을 LPCC와 함께 여러 환경에서 구축된 데이터 베이스에서 화자특징 파라미터로 사용하였다. 또한, 잔여 켑스트럼에 포함되어있는 화자 고유성분인 피치(pitch)성분에 큰 가중치(weighting)를 줌으로써 화자간 변이(inter-speaker variation)가 커지도록 하는 가중치 함수를 제안한다. 실험 결과, LPCC만을 특징 파라미터로 사용하였을 경우보다 잔여 켑스트럼 (RCEP)과 LPCC를 동시에 사용했을 경우 약 6%가량의 인식 오류율이 향상 되었으며, 제안한 가중치 함수를 적용한 잔여 켑스트럼 (RCEP)과 LPCC를 동시에 사용했을 경우 인식 오류율이 가중치를 주지 않은 경우보다 약 2.45%가량 개선되었다. In speaker verification based on LPC analysis the prediction residues are ignored and LPCC(LPC cepstrum) are only used to compose feature vectors. In this study, LPCC and RCEP (residual cepstrum) extracted from residues are used as feature parameters in the various environmental speaker verification. We propose the weighting function which can enlarge inter-speaker variation by weighting pitch, speaker inherent vector, included in residual cepstrum. Simulation results show that the average speaker verification rate is improved in the rate of 6% with RCEP and LPCC at the same time and is improved in the rate of 2.45% with the proposed weighted RCEP and LPCC at the same time compared with no weighting.

잡음환경에 강인한 HMM기반 화자 확인 시스템에 관한 연구

위진우,강철호 한국음향학회 2001 韓國音響學會誌 Vol.20 No.7

화자확인에서 화자내 변이, 잡음환경, 그리고 학습환경과 인식 환경의 불일치는 화자확인 시스템이 실용화될 수 없는 가장 큰 원인이다. 본 연구에서는, 실제 환경에 강인한 화자 확인 시스템의 구현에 초점을 맞추어 음성 전처리 과정인 잡음환경에 강인한 끝점추출 알고리즘, 잡음제거 및 마이크특성 보상기법, LPG(Linear Predictive Coefficient)켑스트럼 가중치에 의한 화자간 변별력 향상 기법을 제안한다. 실험 결과, LPC잔차신호(residue)를 이용한 끝점추출 알고리즘을 사용한 경우 약 17.65% 가량의 끝점 추출 에러율을 향상시켰으며, 제안한 잡음제거 및 마이크특성 보상기법을 사용한 경우 다른 마이크 환경에서 화자 오인식율이 약 36.93% 가량 개선되었다. 또한, 제안한 LPC켑스트럼 가중치에 의한 화자간 변별력 향상 기법은 평균 화자 오인식율을 약 6.515% 향상시켰다. Intra-speaker variation, noise environments, and mismatch between training and test conditions are the major reasons for the speaker verification system unable to use it practically. In this study, we propose robust end-point detection algorithm, noise cancelling with the microphone property compensation technique, and inter-speaker discriminate technique by weighting cepstrum for robust speaker verification system. Simulation results show that the average speaker verification rate is improved in the rate of 17.65% with proposed end-point detection algorithm using LPC residue and is improved in the rate of 36.93% with proposed noise cancelling and microphone property compensation algorithm. The proposed weighting function for discriminating inter-speaker variations also improves the average speaker verification rate in the rate of 6.515%.

한국의 고령 화농성 간농양 환자들의 임상적 특성과 예후

위진우 ( Jin Woo Wi ),조은애 ( Eun Ae Cho ),전충환 ( Chung Hwan Jun ),박선영 ( Seon Young Park ),박창환 ( Chang Hwan Park ),주영은 ( Young Eun Joo ),김현수 ( Hyun Soo Kim ),최성규 ( Sung Kyu Choi ),류종선 ( Jong Sun Rew ),정숙인 ( 대한소화기학회 2015 대한소화기학회지 Vol.66 No.1

Background/Aims: Incidence of pyogenic liver abscess (PLA) has been increasing worldwide, especially in the elderly population. Therefore, the aim of this study is to elucidate the clinical features and outcomes of PLA in elderly patients. Methods: A total of 602 patients diagnosed with PLA from January 2003 to January 2013 were analyzed retrospectively. The patients were divided according to two age groups; ≥65 years (n=296) and <65 years (n=306). Results: The mean age was 73.59±5.98 (range, 65-93) years in the elderly group. Significantly higher incidence of females (52.4% vs. 29.1%, p<0.001), hepatobiliary disease (41.2% vs. 24.8%, p<0.001), hepatobiliary procedure (29.4% vs. 13.7%, p<0.001), underlying malignancy (18.2% vs. 4.6%, p<0.001), culture positivity of resistant organism (20.6% vs. 14.4%, p=0.047), occurrence of complication (19.6% vs. 12.8%, p=0.026), and higher white blood cell (13.44±6.56 vs. 12.26±5.89, p=0.021), but lower rates of right lobe abscess (67.2% vs. 80.4%, p<0.001), fever (68.6% vs. 79.3%, p=0.003), and lower CRP (16.79±9.67 vs. 18.80±9.86, p=0.012) was observed in elderly PLA patients, compared to younger patients. Regarding complications, elderly patients had higher incidence of septic shock (8.1% vs. 2.3%, p=0.001) and cardiovascular disease (2% vs. 0%, p=0.014). Conclusions: More atypical presentations and complications tend to occur in elderly PLA patients compared with younger patients. Clinicians should be aware of these age-related differences in PLA and devise management strategies accordingly. (Korean J Gastroenterol 2015;66:27-32)

군 교육과정 설계 방법에 관한 연구 - 육군 대위 지휘참모과정 제병협동작전 교육체계를 중심으로 -

위진우 ( Jinwoo We ),전기석 ( Kiseok Jeon ) 미래군사학회 2023 한국군사학논총 Vol.12 No.1

본 연구의 목적은 교육과정 계획단계에서의 의사결정 방법, 과목 조정 기준·절차를 개선함으로써, 「제병협동작전 교육체계」최선안을 도출하는 것이다. 먼저「제병협동작전 교육체계」의 교육효과 제고를 위해 제안된 3개의 개선방안을 AHP를 적용하여 비교해 봄으로써 최선안을 선정하였고, 다음은 델파이 기법을 적용하여 과목 조정기준을 정립하고 정립된 조정기준에 따라 현 편성과목의 적절성을 분석함으로써 조정안을 제시하였다. 연구결과는 다음과 같다. 첫째, 선행훈련 2주 및 종합훈련 4주의 방안이 최선안으로 도출되었다. 둘째, 최선안 시행을 위해서는 96시간의 추가시간이 필요한데, 대위 지휘참모과정 편성과목을 과목 조정기준에 따라 삭제·전환·축소·통합을 검토한 결과, 보병학교는 166시간, 포병학교는 174시간, 기갑학교는 119시간의 추가시간 확보가 가능하다. 본 연구에서 제시한 연구방법과 개선방안은 군에서 교육과정을 설계 및 조정하고, 「제병협동작전 교육체계」를 개선하는데 유용하게 활용될 수 있을 것이다. The purpose of this study is to suggest the best plan for the 「Combined Forces Education System」 and the curriculum design plan by improving the decision-making method and subject adjustment criteria and procedures at the curriculum planning stage. First, the three improvement plans were compared by applying AHP, and the best was selected. Next, the subject adjustment criteria were established by applying the Delphi technique. In addition, the curriculum design plan was presented by analyzing the appropriateness of the current curriculum according to the established adjustment criteria. The results of this study are as follows. First, 2 weeks of prior training and 4 weeks of comprehensive training were deduced as the best plan. Second, 96 hours of additional time are needed to implement the best plan. According to the results of reviewing the subjects provided in Army OAC based on subject adjustment criteria, additional hours of 166 hours for infantry schools, 174 hours for artillery schools, and 119 hours for armoured schools can be secured. The research methods and improvement measures proposed in this study can be useful for designing and coordinating the curriculum in the military and improving the 「Combined Forces Education System」.

CAN/LIN 통신제어기의 통합 모듈 개발에 관한 연구

위진우(Jinwoo Wee) 한국산업기술융합학회(구. 산업기술교육훈련학회) 2021 산업기술연구논문지 (JITR) Vol.26 No.4

As the number of electronic control devices mounted in the vehicle increases, communication standards between electronic control devices are evolving. In particular, the recently released new car is equipped with various types of advanced driver assistance systems that receive and process information from camera sensors and radar, so more data must be exchanged quickly and safely. LIN and CAN are currently the most widely used in-vehicle communication standards, but their maximum communication speed is slow at 40 Kbit/s and 1 Mbit/s, respectively. CAN communication controllers and LIN communication controllers are essential when testing functions and performance after manufacturing in-vehicle devices. Since the CAN communication controller and the LIN communication controller are produced and sold as separate products, manufacturing costs of inspection equipment increase, and data processing speed decreases due to repeated data generation and transmission in the control PC. That is, there is a problem of incorrectly recognizing data loss due to data bottleneck as a defect in the device to be inspected. An integrated module was developed to solve this problem and software was developed in data transmission.

잡음환경에 강인한 화자확인에 관한 연구

위진우(Jinwoo Wee) 산업기술교육훈련학회 2019 산업기술연구논문지 (JITR) Vol.24 No.4

The first proposed speaker verification method for the preprocessing part is the linear predictive coding (LPC) cepstrum weighting function that modifies the existing one. Simulation results show that the average speaker verification rate is improved by 17.7% using the proposed end-point detection algorithm using LPC residue, and it is improved by 37% using the proposed noise cancelling and microphone property compensation algorithm. The proposed weighting function for discriminating inter-speaker variations also improves the average speaker verification rate by 6.6% (FR). The second proposed speaker verification method for the speaker verification part is a modified clustering algorithm. In this study, a nonlinear clustering algorithm is used. The proposed method increased the speaker verification rate by 1.0% (FR). The following are proposed in the study: a method for reducing the training utterance number, a method using the personal vector quantization code book for improving the imposter acceptance rate, the observation symbol probability smoothing method by probability weights for improving the DHMM performance, and the speaker model adaptation method for adapting the voice variance. The two verification methods mentioned above are applied to the general DHMM. The results showed a performance enhancement of about 1.1% in FA and 41.7% in FR.

ISO-14443 타입 A와 B 호환 모듈개발에 관한 연구

위진우(Jinwoo Wee) 산업기술교육훈련학회 2011 산업기술연구논문지 (JITR) Vol.16 No.4

Operating on 13.56 MHz frequency, these contactless smart credential readers provide one of the most advanced identification reader technologies available today. In this study, the new proposed readers will help organizations support diversified smart credential applications ranging from biometrics to cashless vending and transit passes. The new proposed contactless smart credential readers provide advanced compatability by supporting all applicable both ISO-14443 Type A and B standards transfering module. This modules that are developed have a good compatibility, then result in the performance of about 99% in recognition rate and average 8.8cm in recognition distance. As a result, it is shown that the proposed ISO-14443 standards Type A and B compatibility system module is very efficient in real life.