• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.548-550
• /
• 1999

무인 주행 차량에 있어서, 포장 또는 비포장 도로의 시각적 추적은 매우 중요한 문제중의 하나이다. 따라서, 비디오 이미지로부터 비포장 도로를 추적할 수 있는 신속한 비젼 알고리즘의 개발이 필요하다. 이 논문에서는 칼만 필터와 EM(Expectation Maximization) 이론을 이용해 도로를 예측하고 시스템 파라미터를 갱신하는 방법을 제시한다. 시스템 파라미터, 도로 state, 도로 경계선, 그리고 모든 과거 데이터들을 각각 EM 파라미터, hidden data, incomplete data와 complete data로 정의함으로서 도로 state를 예측하고 시스템 파라미터를 추정할 수 있는 시간 회귀적 수식을 유도해 낼 수 있다. 이러한 방법을 이용하여 도로 state는 칼만 필터에 의해 매 프레임마다 예측되며, 시스템 파라미터들은 주기적으로 갱신되는 것이다. 결과적으로 이 방법은 주변환경과 날씨에 많은 영향을 받는 도로의 모양과 특징을 잘 찾아낼 수 있다. 또한 도로의 다음 state를 예측할 수 있는 점을 이용하면 계산량을 줄일 수 있으므로 실시간 구현에 용이하다. 이와 같은 방법으로 우리는 0.1 sec/frame 처리속도를 보장하는 도로추적 시스템을 구현하였다.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.382-384
• /
• 2004

In this parer, we propose a clustering that perform algorithm using new convergence properties. For detection and optimization of cluster, we use to similarity measure with cumulative probability and to inference the its parameters with MLE. A merits of using the cumulative probability in our method is very effectiveness that robust to noise or unnecessary data for inference the parameters. And we adopt similarity threshold to converge the number of cluster that is enable to past convergence and delete the other influence for this learning algorithm. In the simulation, we show effectiveness of our algorithm for convergence and optimization of cluster in riven data set.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.2
• /
• pp.167-174
• /
• 2002

In the case of "nonignorable missing data", it is necessary to assume a model dealing with the missing on each situations. In this article, for example, we sometimes meet situations where data set are income amounts in a survey of individuals and assume a model as the values are the larger, a missing data probability is the higher. The method is to maximize using the EM(Expectation and Maximization) algorithm based on the (missing data) mechanism that creates missing data of the case of exponential distribution. The method started from any initial values, and converged in a few iterations. We changed the missing data probability and the artificial data size to show the estimated accuracy. Then we discuss the properties of estimates.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.9-11
• /
• 2014

본 논문에서는 오디오 신호의 특성 표현에 유용한 nonnegative matrix factorization(NMF)에 대해 설명하였으며, expectation maximization (EM)을 이용한 NMF 파라미터 추출 및 EM-NMF 기반한 오디오 소스 분리 기술에 대해서 설명했다. 또한, 다중 단계 NMF-EM 구조의 객체 분리를 통해서 객체 분리 성능을 향상시키기 위한 알고리즘을 제안하며, 제안된 알고리즘은 K-pop 음원과 SDR(source distortion ratio)를 통해서 객체 분리 성능을 평가한다. 성능 평가 결과 제안된 알고리즘은 다중 단계를 통해 약 3dB 의 보컬 분리 성능이 향상되며, 상업적 음원 제작에서 사용되는 가상 오디오 효과가 많이 적용된 음원에서 약 5dB 의 분리 성능을 향상시켰다. 그러므로 제안된 방식은 오디오 객체 분리에 유용한 방법이 될 것으로 생각된다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.3
• /
• pp.9-14
• /
• 2002

In this paper we propose a method for performance enhancement of speech recognizer under noisy conditions. The parallel combination model which is presented at the PMC method using multiple Gaussian-distributed mixtures have been adapted to the variation of each mixture. The CDHMM(continuous observation density HMM) which has multiple Gaussian distributed mixtures are combined by the proposed PMC method. Also, the EM(expectation maximization) algorithm is used for adapting the model mean parameter in order to reduce the variation of the mixture density. The result of simulation, the proposed PMC adaptation method show better performance than the conventional PMC method.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.193-198
• /
• 2006

Among 242 Hyperion bands, there are 46 bands that contain completely no information and some other bands with various kinds of noise. It is mainly due to the atmosphenc absorption and the low signal-to-noise ratio. The visual inspection for selecting clean and stable bands is a simple practice, but is a manual, inefficient, and subjective Process. Though uncalibrated, overlapping, and all deep water absorption bands are removed, there still exist noisy bands. In this paper, we propose that the extrema ratio be measured for noise estimation and the unsupervised band selection be performed using the Expectation-Maximization algorithm. The Hyperion data were classified into 5 categories according to the image quality by visual inspection, and used as the reference data. The accuracy of the proposed method was compared with signal-to-noise ranking and entropy ranking. As a result, the proposed mettled was effective as preprocessing step for band selection.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.243-248
• /
• 2006

In this paper, we propose the unsupervised change detection algorithm that apply the similarity measure techniques to the hyperspectral image. The general similarity measures including euclidean distance and spectral angle were compared. The spectral similarity scale algorithm for reducing the problems of those techniques was studied and tested with Hyperion data. The thresholds for detecting the change area were estimated through EM(Expectation-Maximization) algorithm. The experimental result shows that the similarity measure techniques and EM algorithm can be applied effectively for the unsupervised change detection of the hyperspectral data.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.678-685
• /
• 2005

Estimating parameters of the lifetime distribution is investigated when field failure data are not completely reported. To take into account the reality and the accuracy of the estimates in such a case, the failure reporting probability is incorporated in estimating parameters. Firstly, method of maximum likelihood estimate(MLE) is used to estimate parameters of the lifetime distribution when failure reporting probability is known. Secondly, Expectation and Maximization(EM) algorithm is used to estimate the failure reporting probability and parameters of the lifetime distribution simultaneously when failure reporting probability is unknown. For both case, procedures of estimation are illustrated for single Weibull distribution and mixed Weibull distribution. Simulation results show that MLE obtained by the proposed method is more accurate than the conventional MLE.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.263-266
• /
• 2007

This paper discusses the Bayesian statistical inference. This paper discusses the Bayesian inference, MCMC (Markov Chain Monte Carlo) integration, MCMC method, Metropolis-Hastings algorithm, Gibbs sampling, Maximum likelihood estimation, Expectation Maximization algorithm, missing data processing, and BMA (Bayesian Model Averaging). The Bayesian statistical inference is used to process a large amount of data in the areas of biology, medicine, bioengineering, science and engineering, and general data analysis and processing, and provides the important method to draw the optimal inference result. Lastly, this paper discusses the method of principal component analysis. The PCA method is also used for data analysis and inference.

• International Journal of Contents
• /
• v.9 no.1
• /
• pp.1-5
• /
• 2013

Standard Gaussian Mixture Model (GMM) is a well-known method for image segmentation. However, one of its problems is that we consider the pixel as independent to each other, which can cause the segmentation results sensitive to noise. It explains why some of existing algorithms still cannot segment texts from the background clearly. Therefore, we present a new method in which we incorporate the spatial relationship between a pixel and its neighbors inside $3{\times}3$ windows to segment the text. Our approach works well with images containing texts, which has different sizes, shapes or colors in case of light changes or complex background. Experimental results demonstrate the robustness, accuracy and effectiveness of the proposed model in image segmentation compared to other methods.