• Journal of the Korean Statistical Society
• /
• v.36 no.3
• /
• pp.435-445
• /
• 2007

This paper addresses for the first time the use of complete data information criteria in unsupervised learning of the Naive-Bayes model. A Monte Carlo study sets a large experimental design to assess these criteria, unusual in the Bayesian network literature. The simulation results show that complete data information criteria underperforms the Bayesian information criterion (BIC) for these Bayesian networks.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.2
• /
• pp.817-821
• /
• 2012

In this paper we applied the optimal mixture number estimation technique in GMM(Gaussian mixture model) using BIC(Bayesian information criterion) and MDL(minimum description length) as a model selection criterion for environmental sounds recognition. In the experiment, we extracted 12 MFCC(mel-frequency cepstral coefficients) features from 9 kinds of environmental sounds which amounts to 27747 data and classified them with GMM. As mentioned above, BIC and MDL is applied to estimate the optimal number of mixtures in each environmental sounds class. According to the experimental results, while the recognition performances are maintained, the computational complexity decreases by 17.8% with BIC and 31.7% with MDL. It shows that the computational complexity reduction by BIC and MDL is effective for environmental sounds recognition using GMM.

• Communications for Statistical Applications and Methods
• /
• v.27 no.3
• /
• pp.301-311
• /
• 2020

Schwarz's Bayesian information criterion (BIC) is one of the most popular criteria for model selection, that was derived under the assumption of independent and identical distribution. For correlated data in longitudinal studies, Jones (Statistics in Medicine, 30, 3050-3056, 2011) modified the BIC to select the best linear mixed effects model based on the effective sample size where the number of parameters in covariance structure was not considered. In this paper, we propose an extended Jones' modified BIC by considering covariance parameters. We conducted simulation studies under a variety of parameter configurations for linear mixed effects models. Our simulation study indicates that our proposed BIC performs better in model selection than Schwarz's BIC and Jones' modified BIC do in most scenarios. We also illustrate an example of smoking data using a longitudinal cohort of cancer patients.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.687-695
• /
• 2009

The Bayesian multiple change-point estimation has been applied to the daily means of ozone and PM10 data in Seoul for the period 1999. We focus on the detection of multiple change-points in the ozone and PM10 bivariate vectors by evaluating the posterior probabilities and Bayesian information criterion(BIC) using the stochastic approximation Monte Carlo(SAMC) algorithm. The result gives 5 change-points of mean vectors of ozone and PM10, which are related with the seasonal characteristics.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.325-327
• /
• 2001

본 논문은 온라인 문자 인식을 연속 밀도 HMM의 구조의 최적화 문제를 다룬다. 최적이란 최소한의 모델 파라미터를 사용하여 최소한의 오류를 허용하는 것이라고 정의할 수 있다. 본 연구에서는 HMM 구조의 최적화를 위해 Bayesian 모델 선택 방법론을 사용한다. 먼저 잘 알려진 BIC(Bayesian Information Criterion)을 적용해보고, 그것을 HMM의 복잡한 구조에 적합하도록 본 논문에서 제안한 HBIC(HMM-Oriented BIC)와 비교해본다. BIC는 모델의 사전 확률 분포를 추정하지 않고 다변량 정규분포라고 가정하는데 비해 HBIC는 모델의 각 파라미터로부터 사전 확률을 추정한 후 그것들을 사용함으로써 더 좋은 결과를 얻도록 한다. 실험 결과 BIC와 HBIC 둘 다 기존 방법보다 모델의 파라미터 수를 현저히 감소시킴을 확인했고, HBIC가 BIC에 비해 더 적은 수의 파라미터를 사용해도 비슷한 인식률을 얻을 수 있었다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.1
• /
• pp.84-90
• /
• 2011

In this paper, a VoIP-based voice secure telecommunication technology using the text-independent speaker authentication in the telematics environments is proposed. For the secure telecommunication, the sender's voice packets are encrypted by the public-key generated from the speaker's voice information and submitted to the receiver. It is constructed to resist against the man-in-the middle attack. At the receiver side, voice features extracted from the received voice packets are compared with the reference voice-key received from the sender side for the speaker authentication. To improve the accuracy of text-independent speaker authentication, Gaussian Mixture Model(GMM)-supervectors are applied to Support Vector Machine (SVM) kernel using Bayesian information criterion (BIC) and Mahalanobis distance (MD).

• Journal of KIISE:Software and Applications
• /
• v.30 no.9
• /
• pp.867-875
• /
• 2003

This paper concerns continuous density HMM topology optimization. There have been several researches for HMM topology optimization. BIC (Bayesian Information Criterion) is one of the well known optimization criteria, which assumes statistically well behaved homogeneous model parameters. HMMs, however, are composed of several different kind of parameters to accommodate complex topology, thus BIC's assumption does not hold true for HMMs. Even though BIC reduced the total number of parameters of HMMs, it could not improve the recognition rates. In this paper, we proposed two new model selection criteria, HBIC (HMM-oriented BIC) and BIC_Anti. The former is proposed to improve BIC by estimating model priors separately. The latter is to combine BIC and anti-likelihood to accelerate discrimination power of HMMs. We performed some comparative research on couple of model selection criteria for online handwriting data recognition. We got better recognition results with fewer number of parameters.

• The Journal of the Korea Contents Association
• /
• v.6 no.1
• /
• pp.23-30
• /
• 2006

A clustering method for temporal data takes a model-based approach. This uses automata based model for each cluster. It is necessary to construct global models for a set of data in order to elicit individual models for the cluster. The preparation for building individual models is completed by determining the number of clusters inherent in the data set. In this paper, BIC(Bayesian Information Criterion) approximation is used to determine the number clusters and confirmed its applicability. A search technique to improve efficiency is also suggested by analyzing the relationship between data size and BIC values. A number of experiments have been performed to check its validity using artificially generated data sets. BIC approximation measure has been confirmed that it suggests best number of clusters through experiments provided that the number of data is relatively large.

• The Korean Journal of Applied Statistics
• /
• v.22 no.1
• /
• pp.197-204
• /
• 2009

In the model selection problem, the main objective is to choose the true model from a manageable set of candidate models. An information criterion gauges the validity of a statistical model and judges the balance between goodness-of-fit and parsimony; "how well observed values ran approximate to the true values" and "how much information can be explained by the lower dimensional model" In this study, we introduce some information criteria modified from the Akaike Information Criterion (AIC) and the Bayesian Information Criterion(BIC). The information criteria considered in this study are compared via simulation studies and real application.

• The Journal of the Korea Contents Association
• /
• v.6 no.6
• /
• pp.26-32
• /
• 2006

Predictions on stock prices have been a hot issue in stock market as people get more interested in stock investments. Assuming that the stock price is moving by a trend in a specific pattern, we believe that a model can be derived from past data to describe the change of the price. The best model can help predict the future stock price. In this paper, our model derivation is based on automata over temporal data to which the model is explicable. We use Bayesian Information Criterion(BIC) to determine the best number of states of the model. We confirm the validity of Bayesian Information Criterion and apply it to building models over stock price indices. The model derived for predicting daily stock price are compared with real price. The comparisons show the predictions have been found to be successful over the data sets we chose.