• 전자공학회논문지CI
• /
• 제42권3호
• /
• pp.9-16
• /
• 2005

정규화(normalization)는 데이터의 불필요한 중복의 정도를 최소화찰 뿐만 아니라 데이터의 무결성을 높이는데 기여하기 때문에 데이터베이스를 효율적으로 설계하기 위해 수행하고 있다. 그러나 정규화를 깊숙이 수행한 데이터베이스인 경우 자료 검색 시 필요에 따라 테이블 간의 조인을 해야 하기 때문에 자료 처리 속도의 저하 현상이 발생될 수도 있다. 이러한 정규화의 부작용을 다소나마 해소하기 위한 수단으로 기업에서는 궁여지책으로 역정규화를 함으로써 어느 정도 완화시킬 수 있다고 보는 견해가 있다. 본 논문에서는 정규화와 역정규화와의 성능 평가를 위해 고객관련업무 시스템에 대해 두 가지 방법을 적용하여 데이터베이스 시스템을 구축하고 분석하여 비교하였다. 실험 결과 데이터베이스 크기에 따른 응답 시간은 전체적으로 역정규화 모델이 정규화 모델보다 더 길게 나왔다. 역정규화가 데이터의 중복을 발생시키기 때문에 시스템 성능 향상에 기여하는 바가 거의 없는 것으로 나타났다.

• 항공우주시스템공학회지
• /
• 제8권4호
• /
• pp.39-43
• /
• 2014

This paper examines the statistical process that should be performed with caution in the composite material qualification and equivalency process, and describes statistically significant considerations on outlier finding and handling process, data pooling through normalization process, review for data distributions and design allowables determination process for structural analysis. Based on these considerations, the need for guidance on statistical process for aircraft manufacturers who use the composite material properties database are proposed.

• 음성과학
• /
• 제11권1호
• /
• pp.31-42
• /
• 2004

This paper presents methods using Gaussian normalization for converting pitch contours based on prosodic phrases along with experimental tests on the Korean database of 16 declarative sentences and the first sentences of the story of 'The Three Little Pigs'. We propose a new conversion method using Gaussian normalization to the pitch deviation of pitch contour subtracted by partial declination lines: by using partial declination lines for each accentual phrase of pitch contour, we avoid the problem that a Gaussian normalization using average values and standard deviations of intonational phrase tends to lose individual local variability and thus cannot modify individual characteristics of pitch contour from a source speaker to a target speaker. From the results of the experiments, we show that this slanted Gaussian normalization using these declination lines subtracted from pitch contour of accentual phrases can modify pitch contour more accurately than other methods using Gaussian normalization.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.65-70
• /
• 2020

CNN's technologies that represent emotional detection include primitive CNN algorithms, deployment normalization, and drop-off. We present the methods and data of the three experiments in this paper. The training database and the test database are set up differently. The first experiment is to extract emotions using Batch Normalization, which complemented the shortcomings of distribution. The second experiment is to extract emotions using Dropout, which is used for rapid computation. The third experiment uses CNN using convolution and maxpooling. All three results show a low detection rate, To supplement these problems, We will develop a deep learning algorithm using feature extraction method specialized in image processing field.

• 한국음향학회지
• /
• 제34권4호
• /
• pp.316-320
• /
• 2015

본 논문에서는 Cepstral Mean Normalization(CMN)과 Cepstral Mean and Variance Normalization(CMVN) 프레임워크에서 극점 필터링(pole filtering) 개념을 Mel-Frequency Cepstral Coefficient(MFCC) 특징 벡터에 적용한다. 또한 분산 정규화를 대신하여 스케일 정규화를 사용하는 Cepstral Mean and Scale Normalization(CMSN)의 성능을 잡음 환경 음성인식 실험을 통해 평가한다. CMN과 CMVN은 보통 발화 단위로 수행되기 때문에 짧은 발화의 경우 특징에 대한 평균과 분산의 추정 신뢰도가 보장되지 않는 문제점을 가지는데, 극점 필터링과 스케일 정규화 방식을 적용함으로 이러한 문제점을 보완할 수 있다. Aurora 2 데이터베이스를 이용한 실험 결과, 극점 필터링과 스케일 정규화를 결합한 특징 정규화 방식의 성능이 가장 높은 성능 향상을 보인다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권1호
• /
• pp.43-50
• /
• 2016

본 논문에서는 ASM(Active Shape Model) 특징점(Landmark)을 이용하여 정밀한 얼굴영역을 획득하고, 외형기반 접근법으로 표정을 인식하는 방법에 대하여 제안한다. 외형기반 표정인식은 EHMM(Embedded Hidden Markov Model) 및 이진패턴 히스토그램 특징과 SVM(Support Vector Machine)을 사용하는 알고리즘으로 구성되며, 제안 방법의 성능평가는 공인 CK 데이터베이스와 JAFFE 데이터베이스를 이용하여 수행되었다. 더불어, 성능비교는 기존의 눈 거리 기반의 얼굴 정규화 방법과 비교를 통하여 수행되었고, 또한 ASM 전체 특징점 및 변형된 특징을 SVM으로 인식하는 기하학적 표정인식 방법론과 성능비교를 수행하였다. 실험 결과, 제안 방법은 거리기반 얼굴정규화 영상을 사용한 방법보다 CK 데이터베이스 및 JAFFE 데이터베이스 경우, 최대 6.39%와 7.98%의 성능향상을 보였다. 또한, 제안 방법은 기하학적 특징점을 사용한 방법보다 높은 인식 성능을 보였으며, 이로부터 제안하는 표정인식 방법의 효용성을 확인하였다.

• 산업경영시스템학회지
• /
• 제26권3호
• /
• pp.1-9
• /
• 2003

Databases are central to business information systems and RDBMS is most widely used for the database system. Normalization was designed to control various anomalies (insert, update, delete anomalies). However, normalized database design does not account for the tradeoffs necessary for performance. In this research, I model a database design method considering denormalization of duplicating attributes in order to reduce frequent join processes. This model considers response time for processing each select, insert, update, delete transaction, and for treating anomalies. A branch and bound method is proposed for this model.

• 음성과학
• /
• 제13권1호
• /
• pp.129-139
• /
• 2006

In this paper, we propose two effective energy feature normalization methods for robust speech recognition in noisy environments. In the first method, we estimate the noise energy and remove it from the noisy speech energy. In the second method, we propose a modified algorithm for the Log-energy Dynamic Range Normalization (ERN) method. In the ERN method, the log energy of the training data in a clean environment is transformed into the log energy in noisy environments. If the minimum log energy of the test data is outside of a pre-defined range, the log energy of the test data is also transformed. Since the ERN method has several weaknesses, we propose a modified transform scheme designed to reduce the residual mismatch that it produces. In the evaluation conducted on the Aurora2.0 database, we obtained a significant performance improvement.

• 한국환경보건학회지
• /
• 제43권4호
• /
• pp.298-306
• /
• 2017

Objectives: Since 1998, the Korea National Health and Nutrition Examination Survey (KNHANES) has been conducted in order to investigate the health and nutritional status of Koreans. The food intake data of individuals in the KNHANES has also been utilized as source dataset for risk assessment of chemicals via food. To improve the reliability of intake estimation and prevent missing data for less-responded foods, the structure of integrated long-standing datasets is significant. However, it is difficult to merge multi-year survey datasets due to ineffective cleaning processes for handling extensive numbers of codes for each food item along with changes in dietary habits over time. Therefore, this study aims at 1) cleaning the process of abnormal data 2) generation of integrated long-standing raw data, and 3) contributing to the production of consistent dietary exposure factors. Methods: Codebooks, the guideline book, and raw intake data from KNHANES V and VI were used for analysis. The violation of the primary key constraint and the $1^{st}-3rd$ normal form in relational database theory were tested for the codebook and the structure of the raw data, respectively. Afterwards, the cleaning process was executed for the raw data by using these integrated codes. Results: Duplication of key records and abnormality in table structures were observed. However, after adjusting according to the suggested method above, the codes were corrected and integrated codes were newly created. Finally, we were able to clean the raw data provided by respondents to the KNHANES survey. Conclusion: The results of this study will contribute to the integration of the multi-year datasets and help improve the data production system by clarifying, testing, and verifying the primary key, integrity of the code, and primitive data structure according to the database normalization theory in the national health data.

• 음성과학
• /
• 제12권2호
• /
• pp.183-191
• /
• 2005

This paper describes the automated call routing for call center system based on speech recognition. We focus on the task of automatically routing telephone calls based on a users fluently spoken response instead of touch tone menus in an interactive voice response system. Vector based call routing algorithm is investigated and normalization method suggested. Call center database which was collected by KT is used for call routing experiment. Experimental results evaluating call-classification from transcribed speech are reported for that database. In case of small training data, an average call routing error reduction rate of 9% is observed when normalization method is used.