• 대한음성학회지:말소리
• /
• 제50호
• /
• pp.139-150
• /
• 2004

A Phonetic Tied-Mixture (PTM) model has been proposed as a way of efficient decoding in large vocabulary continuous speech recognition systems (LVCSR). It has been reported that PTM model shows better performance in decoding than triphones by sharing a set of mixture components among states of the same topological location[5]. In this paper we propose a Phonetic Tied-Mixture Syllable (PTMS) model which extends PTM technique up to syllables. The proposed PTMS model shows 13% enhancement in decoding speed than PTM. In spite of difference in context dependent modeling (PTM : cross-word context dependent modeling, PTMS : word-internal left-phone dependent modeling), the proposed model shows just less than 1% degradation in word accuracy than PTM with the same beam width. With a different beam width, it shows better word accuracy than in PTM at the same or higher speed.

• Smart Structures and Systems
• /
• 제21권5호
• /
• pp.591-600
• /
• 2018

The probabilistic characterization of wind field characteristics is a significant task for fatigue reliability assessment of long-span railway bridges in wind-prone regions. In consideration of the effect of wind direction, the stochastic properties of wind field should be represented by a bivariate statistical model of wind speed and direction. This paper presents the construction of the bivariate model of wind speed and direction at the site of a railway arch bridge by use of the long-term structural health monitoring (SHM) data. The wind characteristics are derived by analyzing the real-time wind monitoring data, such as the mean wind speed and direction, turbulence intensity, turbulence integral scale, and power spectral density. A sequential quadratic programming (SQP) algorithm-based finite mixture modeling method is proposed to formulate the joint distribution model of wind speed and direction. For the probability density function (PDF) of wind speed, a double-parameter Weibull distribution function is utilized, and a von Mises distribution function is applied to represent the PDF of wind direction. The SQP algorithm with multi-start points is used to estimate the parameters in the bivariate model, namely Weibull-von Mises mixture model. One-year wind monitoring data are selected to validate the effectiveness of the proposed modeling method. The optimal model is jointly evaluated by the Bayesian information criterion (BIC) and coefficient of determination, $R^2$. The obtained results indicate that the proposed SQP algorithm-based finite mixture modeling method can effectively establish the bivariate model of wind speed and direction. The established bivariate model of wind speed and direction will facilitate the wind-induced fatigue reliability assessment of long-span bridges.

• Smart Structures and Systems
• /
• 제17권6호
• /
• pp.1087-1105
• /
• 2016

Traffic load and volume is one of the most important physical quantities for bridge safety evaluation and maintenance strategies formulation. This paper aims to conduct the statistical analysis of traffic volume information and the multimodal modeling of gross vehicle weight (GVW) based on the monitoring data obtained from the weigh-in-motion (WIM) system instrumented on the arch Jiubao Bridge located in Hangzhou, China. A genetic algorithm (GA)-based mixture parameter estimation approach is developed for derivation of the unknown mixture parameters in mixed distribution models. The statistical analysis of one-year WIM data is firstly performed according to the vehicle type, single axle weight, and GVW. The probability density function (PDF) and cumulative distribution function (CDF) of the GVW data of selected vehicle types are then formulated by use of three kinds of finite mixed distributions (normal, lognormal and Weibull). The mixture parameters are determined by use of the proposed GA-based method. The results indicate that the stochastic properties of the GVW data acquired from the field-instrumented WIM sensors are effectively characterized by the method of finite mixture distributions in conjunction with the proposed GA-based mixture parameter identification algorithm. Moreover, it is revealed that the Weibull mixture distribution is relatively superior in modeling of the WIM data on the basis of the calculated Akaike's information criterion (AIC) values.

• 아동학회지
• /
• 제31권3호
• /
• pp.83-97
• /
• 2010

Growth mixture modeling was used to identify types of changes in overt aggression from Grades 4 to 7 among a sample from the Korean Youth Panel Survey. Three discrete patterns were found to adequately explain changes of overt aggression in both boys and girls : Persistent intermediate aggression; Increasing aggression; and Decreasing aggression. Most boys (93%) fell into the Persistent intermediate aggression group and 49% of girls were found to fall into the Increasing aggression group. This suggests that prevention programs should recognize that girls are at risk of increasing aggression in their early adolescence. Multinomial logistic regression analysis shows that self-control, child abuse, peer support, and involvement with deviant peers at Grades 4 were all strongly associated with trajectory class membership. These associations did not differ by gender. These findings suggest that prevention programs should focus on the multiple risk factors of both boys and girls.

• ETRI Journal
• /
• 제33권6호
• /
• pp.914-923
• /
• 2011

This paper concerns robust and reliable speaker model training for text-independent speaker verification. The baseline speaker modeling approach is the Gaussian mixture model (GMM). In text-independent speaker verification, the amount of speech data may be different for speakers. However, we still wish the modeling approach to perform equally well for all speakers. Besides, the modeling technique must be least vulnerable against unseen data. A traditional approach for GMM training is expectation maximization (EM) method, which is known for its overfitting problem and its weakness in handling insufficient training data. To tackle these problems, variational approximation is proposed. Variational approaches are known to be robust against overtraining and data insufficiency. We evaluated the proposed approach on two different databases, namely KING and TFarsdat. The experiments show that the proposed approach improves the performance on TFarsdat and KING databases by 0.56% and 4.81%, respectively. Also, the experiments show that the variationally optimized GMM is more robust against noise and the verification error rate in noisy environments for TFarsdat dataset decreases by 1.52%.

• 한국지능시스템학회논문지
• /
• 제13권5호
• /
• pp.512-519
• /
• 2003

본 논문에서는 계층적 클러스터링과 GMM을 순차적으로 이용하여 최적의 파라미터를 추정하고 이를 뉴로-퍼지 모델의 초기 파리미터로 사용하여 모델의 성능 개선을 제안한다. 반복적인 시도 중 가장 좋은 파라미터를 선택하는 기존의 알고리즘 과 달리 계층적 클러스터링은 데이터들 간의 유클리디언 거리를 이용하여 클러스터를 생성하므로 반복적인 시도가 불필요하다. 또한 클러스터링 방법에 의해 퍼지 모델링을 행하므로 클러스터와 동일한 갯수의 적은 규칙을 갖는다. 제안된 방법의 유용함을 비선형 데이터인 Box-Jenkins의 가스로 예측 문제와 Sugeno의 비선형 시스템에 적용하여 이전의 연구보다 적은 규칙으로도 성능이 개선되는 것을 보였다.

• Geomechanics and Engineering
• /
• 제35권4호
• /
• pp.425-436
• /
• 2023

An effective tool for researching actual problems in geotechnical and mining engineering is to conduct physical modeling tests using similar materials. A reliable geometric scaled model test requires selecting similar materials and conducting tests to determine physical properties such as the mixing ratio of the mixed materials. In this paper, a method is proposed to determine similar materials that can reproduce target properties using a polynomial model based on experimental results on modeling materials using a gypsum-sand mixture (GSM) to simulate rocks. To that end, a database is prepared using the unconfined compressive strength, elastic modulus, and density of 459 GSM samples as output parameters and the weight ratio of the mixing materials as input parameters. Further, a model that can predict the physical properties of the GSM using this database and a polynomial approach is proposed. The performance of the developed method is evaluated by comparing the predicted and observed values; the results demonstrate that the proposed polynomial model can predict the physical properties of the GSM with high accuracy. Sensitivity analysis results indicated that the gypsum-water ratio significantly affects the prediction of the physical properties of the GSM. The proposed polynomial model is used as a powerful tool to simplify the process of determining similar materials for rocks and conduct highly reliable experiments in a physical modeling test.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2005년도 춘계학술대회
• /
• pp.705-707
• /
• 2005

For the development of geothermal energy, many different kind of geoscientific data including both surface geological data and underground geomechanical data, are acquired. Integration of such data itself for better understanding of underground condition is not a simple process due to complexity of the data, i.e. mixture of 20 and 3D data, mixture of geological data, geochemical data, geomechanical data and hydrogeological data. This paper reports a preliminary suggestion of GIS modeling for such specific purpose. Data used for GIS modeling mainly came from British case studies. The modeling is much more focused on the design of database for 3D underground geotechnical data in this study.

• Communications for Statistical Applications and Methods
• /
• 제22권6호
• /
• pp.589-598
• /
• 2015

In longitudinal studies missing data are common and require a complicated analysis. There are two popular modeling frameworks, pattern mixture model (PMM) and selection models (SM) to analyze the missing data. We focus on the PMM and we also propose Bayesian pattern mixture models using generalized linear mixed models (GLMMs) for longitudinal binary data. Sensitivity analysis is used under the missing not at random assumption.

• Korean Chemical Engineering Research
• /
• 제53권1호
• /
• pp.22-30
• /
• 2015

지금까지의 분리막 공정 모델링에 대한 연구는 주로 2성분계 원료의 분리공정에 집중되어 왔다. 실제 운전에 있어서는 2성분계 혼합물은 매우 드물며 다성분계 혼합물이 대부분이므로 막분리 공정의 설계를 위해서는 다성분계 막분리 공정에 대한 모델개발이 필수적이다. 본 연구에서는 중공사막을 이용하는 분리막 공정에서 다성분 혼합물 원료에 대한 분리공정 모델링을 수행하였다. 다양한 형태의 다성분 공정모델을 구현하였으며 실험결과를 이용하여 모델의 정확도 및 신뢰도를 조사하였다. 개발된 모델들은 원료 흐름의 유입조건과 다양한 운전조건에 대하여 안정적이고 실험 데이터에 근접한 모사결과를 보여 주었다.