• ETRI Journal
• /
• 제29권3호
• /
• pp.300-304
• /
• 2007

This paper proposes a new data-driven method for high-pass approaches, which suppresses slow-varying noise components. Conventional high-pass approaches are based on the idea of decorrelating the feature vector sequence, and are trying for adaptability to various conditions. The proposed method is based on temporal local decorrelation using the information-maximization theory for each utterance. This is performed on an utterance-by-utterance basis, which provides an adaptive channel normalization filter for each condition. The performance of the proposed method is evaluated by isolated-word recognition experiments with channel distortion. Experimental results show that the proposed method yields outstanding improvement for channel-distorted speech recognition.

• 한국음향학회지
• /
• 제6권4호
• /
• pp.21-30
• /
• 1987

단어음성인식에서 발성속도의 차이에 따른 단어음성 길이의 비선형적 변화는 정확한 인식을 어렵게 하는 주요한 원인이 되어 왔다. DP매칭은 시간축의 비선형 신축에 의해 시간정규화를 행함으로써 인식결과에 대한 신뢰성을 상당히 높였으나 시간정규화 파정에 요구되는 과도한 계산부담이 문제로 되어 있다. 본 논문에서는 시간정규화가 필요없는 방법으로 멀티섹션벡터양자화에 새로운 길이정규화법을 적용하는 방법을 제안한다. 이 방법은 종래의 고정프레임 길이정규화에 의해 멀티섹션코드북을 작성할 때보다. 정규화길이의 실정에 훨씬 융통성을 가질 수 있으므로 분석 및 거리계산의 양면에서 시간 단축을 가능케 하여 좀더 신속히 인식결과를 얻을 수 있는 장점이 있다

• 약학회지
• /
• 제38권4호
• /
• pp.366-371
• /
• 1994

To improve the identification power of TLC/HPTLC the in situ reflectance spectra obtained directly from plates with commercial scanner are used. The spectrum normalization should be carried out prior to comparing and searching the spectra from library for the identification of compounds. Because the reflectance does not obey the Lambert-Beer's law, there arise some problems in normalization. These problems could be solved to some extent by normalizing the spectra with regression methods. The spectra are manipulated with the regression function of a curve obtained from the correlation plot. When the parabola was used as the manipulating function, the spectra were identified with the accuracy of 97% and this result was better than that of conventionally used the point and area normalization method.

• 한국통신학회논문지
• /
• 제41권1호
• /
• pp.77-79
• /
• 2016

본 논문에서는 디지털 방송시스템의 전송방식에서 널리 사용 되고 있는 계층 변조 (Hierarchical Modulation)를 고려한다. 계층 변조기법은 다수의 독립적인 데이터 스트림의 송신 신호 전력을 조절하여 변조 심볼로 매핑하기 때문에 종래의 M-QAM에서 사용하는 정규화 인수 (Normalization Factor)를 사용할 수 없다. 본 논문에서는 3-level 계층 64QAM 기법의 정확한 정규화 인수를 구하기 위한 방법과 과정을 유도하여 제시한다.

• 대한전자공학회논문지SP
• /
• 제41권4호
• /
• pp.103-111
• /
• 2004

화자 정규화 방법은 화자 독립 음성인식 시스템에서 음성 인식의 정확성을 높이기 위한 성공적인 방법으로 알려져 왔다. 널리 사용되는 화자 정규화 방법은 maximum likelihood 반의 주파수 warping 방법이다. 본 논문은 주파수 warping 보다 더 좋은 화자 정규화의 성능 개선을 위해 새로운 파워 스펙트럼 warping 방법을 제안한다. 파워 스펙트럼 warping은 멜 주파수 켑스트럼 분석(MFCC) 방법을 이용하며, MFCC 처리 단계에서 필터 뱅크의 파워 스펙트럼을 조절함으로써 화자 정규화를 수행하는 간단한 메커니즘으로 갖는다. 또한 본 논문은 파워 스펙트럼 warping과 주파수 warping 방법을 서로 결합한 hybrid VTN 방법을 제안한다. 본 논문의 실험은 baseline 시스템에 각 화자 정규화 방법을 적용하여 SKKU PBW DB에서 인식 성능을 비교 분석하였다. 실험 결과를 보면 baseline 시스템의 단어 인식 성능을 기준으로 주파수 warping은 2.06%, 파워 스펙트럼 warping은 3.05%, 그리고 hybrid VTN은 4.07%의 단어 에러 율의 감소를 보였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.193-195
• /
• 2009

In this paper, we propose an effective compression method for electrocardiogram(ECG) signals. 1-D ECG signals are reconstructed to 2-D ECG data by period and complexity sorting schemes with image compression techniques to Increase inter and intra-beat correlation. The proposed method added block division and mean-period normalization techniques on top of conventional 2-D data ECG compression methods. JPEG 2000 is chosen for compression of 2-D ECG data. Standard MIT-BIH arrhythmia database is used for evaluation and experiment. The results show that the proposed method outperforms compared to the most recent literature especially in case of high compression rate.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 추계학술대회
• /
• pp.262-267
• /
• 2004

The unloading compliance method is the most commonly used method to evaluate the fracture resistance characteristics of a material. In dynamic loading condition, the direct current potential drop(DCPD) method has been used because the unloading compliance method can not be applied due to the discontinuity of loading. However, even in the dynamic test using DCPD method, there is a problem that the voltage drops sharply on the initiation of crack. For the reason metioned above, the normalization method was suggested on ASTM E 1820 which is revised recently, as a new method to evaluate the dynamic fracture resistance characteristic. The nomalization method can be used to obtain a fracture resistance curve directly from a load-load line displacement. In this study, we obtained two fracture resistance curves from static test of welding part of nuclear piping both by unloading compliance and nomalization method. The two curves were almost same each other, so the adaptability of the nomalization method has been proved. We conducted a dynamic fracture resistance test for the same material. The fracture resistance curve from the dynamic test was obtained by normalization method and compared to that of the static test result.

• 한국통신학회논문지
• /
• 제31권8C호
• /
• pp.801-805
• /
• 2006

A normalization approach to coefficient adaptation in the escalator(ESC) filter structure that conventionally employs least mean square(LMS) algorithm is introduced. Using Taylor's expansion of the local error signal, a normalized form of the ESC-LMS algorithm is derived. Compared with the computational complexity of the conventional ESC-LMS algorithm employs input power estimation for time-varying convergence coefficient using a single-pole low-pass filter, the computational complexity of the proposed method can be reduced by 50% without performance degradation.

• Nuclear Engineering and Technology
• /
• 제38권7호
• /
• pp.639-656
• /
• 2006

In order to apply the leak before break (LBB) concept to nuclear piping systems, the dynamic strain aging effect of low carbon steel materials has to be taken into account, in compliance with the requirements of the Korean Standard Review Guide (KSRG) 3.6.3-1. For this goal, J-R tests are needed for a range of various temperatures and loading rates, including dynamic loading conditions. In the dynamic loading J-R test, the unloading compliance method can not be applied to measure the crack growth and direct current potential drop (DCPD) method; this method also has a problem defining the crack initiation point. The normalization method is known as a very useful method to determine the J-R curve under dynamic loading because it does not need additional equipment or complicated loading sequences such as electric current or unloading. This method was accepted by the American Society for Testing and Materials (ASTM) as a standard test method E1820 A15 in 2001. However, it has not yet been clearly verified yet if the normalization method is sufficiently reliable to be applied to LBB. In this study, the basic background of the J-integral, LBB and dynamic loading J-R test are explained, and the current status for dynamic loading J-R test methods are reviewed from the view point of LBB for nuclear piping. In particular, the theoretical and historical background of the normalization method which has received attention recently, is summarized. Recent studies for this method are introduced and future works are suggested that may improve the reliability of LBB for nuclear piping.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4028-4042
• /
• 2021

Aiming at the problem of software defect prediction difficulty caused by insufficient software defect marker samples and unbalanced classification, a semi-supervised software defect prediction model based on a tri-training algorithm was proposed by combining feature normalization, over-sampling technology, and a Tri-training algorithm. First, the feature normalization method is used to smooth the feature data to eliminate the influence of too large or too small feature values on the model's classification performance. Secondly, the oversampling method is used to expand and sample the data, which solves the unbalanced classification of labelled samples. Finally, the Tri-training algorithm performs machine learning on the training samples and establishes a defect prediction model. The novelty of this model is that it can effectively combine feature normalization, oversampling techniques, and the Tri-training algorithm to solve both the under-labelled sample and class imbalance problems. Simulation experiments using the NASA software defect prediction dataset show that the proposed method outperforms four existing supervised and semi-supervised learning in terms of Precision, Recall, and F-Measure values.