• ETRI Journal
• /
• 제38권6호
• /
• pp.1190-1196
• /
• 2016

We propose a new bandpass filter (BPF)-based online channel normalization method to dynamically suppress channel distortion when the speech and channel noise components are unknown. In this method, an adaptive modulation frequency filter is used to perform channel normalization, whereas conventional modulation filtering methods apply the same filter form to each utterance. In this paper, we only normalize the two mel frequency cepstral coefficients (C0 and C1) with large dynamic ranges; the computational complexity is thus decreased, and channel normalization accuracy is improved. Additionally, to update the filter weights dynamically, we normalize the learning rates using the dimensional power of each frame. Our speech recognition experiments using the proposed BPF-based blind channel normalization method show that this approach effectively removes channel distortion and results in only a minor decline in accuracy when online channel normalization processing is used instead of batch processing

• 한국인쇄학회지
• /
• 제5권1호
• /
• pp.33-45
• /
• 1987

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1993년도 학술논문발표회 논문집 제12권 1호
• /
• pp.238-241
• /
• 1993

We present a new method to normalize spectral variations of different speakers based on physiological studies of hearing. The proposed method uses the cochlear frequency map to warp the input speech spectra by interpolation or decimation. Using this normalization method, we can obtain much improved recognition results for speaker independent speech recognition.

• 호남수학학술지
• /
• 제35권4호
• /
• pp.739-746
• /
• 2013

There are several ways to normalize a Haar measure on the orders in a quaternion algebra. In order to understand the arithmetic properties of orders, we study the volumes of orders and compute them for some cases.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 추계학술대회 논문집 전력기술부문
• /
• pp.30-34
• /
• 2005

Due to old Toshiba EMS's database size limit and hardware old aging, KPX(Korea Power Exchange) had introduced New EMS from AREVA(old ALSTOM) in July 2002. After then KPX had committed many man power and time to normalize EMS NA(Network Analysis) functions for using real power system. At initial stage, to normalize State Estimator which is the backbone of all other NA functions and DTS(Dispatcher Training Simulator}, KPX had corrected numerous topology errors, network model errors, non-scanned and wrongly scanned SCADA measured errors. After SE function study, running test and tuning, State Estimator could finally have been run properly and stably from June 2003. Based on SE running, KPX had normalized real time Contingency Analysis, and study mode Power Flow, STNET and DTS. From early 2004, dispatchers have been trained to use NA and DTS for the purpose of stable SE running, NA operation & results reading and urgent equipment outage reviewing. EMS NA have been greatly contributed to operate real time power system stably. Above NA normal operation by KPX own efforts under the no experience of NA running, KPX made a good precedent. This paper is intended to introduce EMS NA normalization process, operation status, and etc in Korea power system operation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.976-990
• /
• 2020

The k-means algorithm is widely used in academia and industry due to easy and simple implementation, enabling fast learning for complex datasets. However, k-means struggles to classify datasets without prior knowledge of specific domains. We proposed the repulsive k-means (RK-means) algorithm in a previous study to improve the k-means algorithm, using the repulsive force concept, which allows deleting unnecessary cluster centroids. Accordingly, the RK-means enables to classifying of a dataset without domain knowledge. However, three main problems remain. The RK-means algorithm includes a cluster repulsive force offset, for clusters confined in other clusters, which can cause cluster locking; we were unable to prove RK-means provided optimal convergence in the previous study; and RK-means shown better performance only normalize term and weight. Therefore, this paper proposes the advanced RK-means (ARK-means) algorithm to resolve the RK-means problems. We establish an initialization strategy for deploying cluster centroids and define a metric for the ARK-means algorithm. Finally, we redefine the mass and normalize terms to close to the general dataset. We show ARK-means feasibility experimentally using blob and iris datasets. Experiment results verify the proposed ARK-means algorithm provides better performance than k-means, k'-means, and RK-means.

• 정보보호학회논문지
• /
• 제29권6호
• /
• pp.1375-1382
• /
• 2019

최근 상용 프로텍터인 Themida의 최신 버전이 업데이트되면서, 추적할 초기 데이터를 제공하는 가상 메모리 할당을 사용하지 않도록 변경해 기존 연구의 정규화된 대응방안을 적용할 수 없게 되었다. 또한, 실행 중에 결정되는 값이 많아 동적으로 추적하기 수월했던 기존의 버전에 비해, 프로텍터를 적용하는 시점에 결정된 고정값이 많아 동적으로 추적하는데 어려움이 생겼다. API 난독화 과정을 정규화하기 어려워지도록 최신 버전의 Themida가 어떤 방식을 채용했는지 알아보고, 이를 해제하는 자동화된 시스템을 추후 개발하기 위해 어떠한 기술을 적용할 수 있을지 가능성을 검토해 본다.

• 한국자원식물학회:학술대회논문집
• /
• 한국자원식물학회 2022년도 추계학술대회
• /
• pp.114-114
• /
• 2022

Excessive endogenous endotoxin, especially lipopolysaccharide (LPS) reflux from gastrointestinal (GI) tract to the liver tissue is one of the most serious reasons of severe and acute liver injury which is mainly mediated by Kupffer cell activations. However, there is no clear molecular clues to explain the exact pathophysiological mechanism and effective drugs available till nowadays. We aimed to comprehend the pathophysiological features of LPS-induced liver injury and evaluate the efficacies of potential therapeutic drug, Ga-mi-Yuk-Mi-Jihwang-Tang (GYM), which is composed of herbal plants. GYM remarkably caused to normalize hepatic inflammation and oxidations against LPS-induced liver injury by evidence of serum liver enzymes, histopathological analysis, both hepatic protein and gene expression levels of pro-inflammatory cytokines, nitric oxide levels, and hepatic tissue levels of reactive oxygen species (ROS) levels, malondialdehyde (MDA), and 4-hydroxyneoneal, respectively. To assess molecular events in the hepatic tissue, we further found hepatic Sirtuin6 (Sirt6) levels were considerably depleted by LPS injection with aberrant alterations of Nrf2/HO-1 signaling pathways, whereas administration with GYM notably exerted to normalize these abnormalities. Our results exhibited that GYM would be one of target drug to diminish hepatic inflammation as well as oxidative stress by regulation of hepatic Sirt6 levels.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 제11회 음성통신 및 신호처리 워크샵 논문집 (SCAS 11권 1호)
• /
• pp.403-406
• /
• 1994

음성은 화자의 상태 및 주변 환경에 따라 그 특징이 다양하게 변화한다. 본 논문에서는 음성신호의 특징 파라미터로 널리 쓰이고 있는 mel-cepstrum에 대해, 단어내에서의 변화를 정규화함으로써 인식성능을 향상시키고자 하였다. mel-cepstrum이란 단어 전체에 대한 mel-cepstrum의 평균 값으로 normalize 시킨 것이다. 한국어 숫자음에 대한 인식 실험결과, 본 논문에서 제안한 정규화된 mel-cepstrum이 정규화되지 않은 mel-cepstrum에 비해 우수한 인식 성능을 나타내었다. 또한 잡음 환경하에서 비교 실험한 결과에서도 상대적으로 우수한 인식률을 보였다.

• 음성과학
• /
• 제11권1호
• /
• pp.21-29
• /
• 2004

In this paper we examined the effect of normalization on discriminating the pathological voice into normal and abnormal classes using artificial neural network. Average values per each parameter were used to normalize each set of parameter values. Artificial neural networks were used as classifiers. And the effect of normalization was evaluated by comparing the discrimination results between original and normalized parameter sets.