• Speech Sciences
• /
• v.10 no.2
• /
• pp.77-84
• /
• 2003

In this research, we seek the beginning of the speech and detect the stationary speech region using lip information. Performing running average of the estimated speech signal in the stationary region, we reduce the effect of musical noise which is inherent to the conventional MlMSE (Minimum Mean Square Error) speech enhancement algorithm. In addition to it, SFM (Spectral Flatness Measure) is incorporated to reduce the speech signal estimation error due to speaking habit and some lacking lip information. The proposed algorithm with Wiener filtering shows the superior performance to the conventional methods according to MOS (Mean Opinion Score) test.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.23 no.6
• /
• pp.840-845
• /
• 1986

In this Part II of the paper, we evaluated the fabrication error and dividing characteristics for the opticalfilters proposed in the Part I. Furthermore, we propose an integrated optical filter with a new function that can eliminate the fabdrication error. The fabrication method and filtering characteristics have been tested by experiments, thereby confirming the validity of the design theory.

• Journal of information and communication convergence engineering
• /
• v.1 no.1
• /
• pp.1-5
• /
• 2003

This paper discusses the spectral efficiency and performance of asynchronous direct sequency spread spectrum multiple access systems strict bandwidth limitation by Nyquist filtering. The signal to noise plus interference ratio(SNIR) at the output from the correlation receiver is derived analytically taking the cross correlation characteristics of spreading sequences into account, and also an approximated SNIR of a simple form is presented for the systems employing Gold sequences. Based on the analyzed result of SNIR, bit error rate performance and spectral efficiency are also estimated. and at last, we analyzed improvement rate using RS, convolution as a method for improving functions.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.17-20
• /
• 2000

In a digital communication system, the transmission channel may introduce error into the digital signal being transmitted. It would be useful if a process could be devised so that the error could be removed in order to recover the transmitted digital signal. We design a corrective filter that is inverse filter, which will generate an output signal identical to the input signal. in order for two systems connected in cascade to produce an output which is identical to the input signal, the over-all unit sample response of the cascade connection must be a unit sample function.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.449-451
• /
• 2003

The estimation of time-series data is fundamental process in many data analysis cases. However, the unwanted measurement error is usually added to true data, so that the exact estimation depends on efficient method to eliminate the error components. The wavelet transform method nowadays is expected to improve the accuracy of estimation, because it is able to decompose and analyze the data in various resolutions. Therefore, the wavelet based Kalman filter method for the estimation of time-series data is proposed in this paper. The wavelet transform separates the data in accordance with frequency bandwidth, and the detail wavelet coefficient reflects the stochastic process of error components. This property makes it possible to obtain the covariance of measurement error. We attempt the estimation of true data through recursive Kalman filtering algorithm with the obtained covariance value. The procedure is verified with the fundamental example of Brownian walk process.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.6
• /
• pp.2107-2113
• /
• 2014

Particle filtering (PF) has shown its outperforming results compared to that of classical Kalman filtering (KF), particularly for highly nonlinear problems. However, PF may not be universally superior to the extended KF (EKF) although the case (i.e. an example that the EKF outperforms PF) is seldom reported in the literature. Particularly, PF approaches show degraded performance for problems where the state noise is very small or zero. This is because particles become identical within a few iterations, which is so called particle impoverishment (PI) phenomenon; consequently, no matter how many particles are employed, we do not have particle diversity regardless of if the impoverished particle is close to the true state value or not. In this paper, we investigate this PI phenomenon, and show an example problem where a classical KF approach outperforms PF approaches in terms of mean squared error (MSE) criterion. Furthermore, we compare the processing speed of the EKF and PF approaches, and show the better speed performance of classical EKF approaches. Therefore, PF approaches may not be always better option than the classical EKF for nonlinear problems. Specifically, we show the outperforming result of unscented Kalman filter compared to that of PF approaches (which are shown in Fig. 7(c) for processing speed performance, and Fig. 6 for MSE performance in the paper).

• The Journal of Korean Association of Computer Education
• /
• v.14 no.5
• /
• pp.97-104
• /
• 2011

Collaborative filtering is a methodology to recommend websites by obtaining data and opinions from the other users with similar tastes. During the past few years, this method has been used in various fields such as books, food, and movies in e-commerce systems. This study addresses the computation of similarity between users to determine items to be recommended in collaborative filtering systems. Previous studies measured similarity between users by treating each user's ratings independently without considering the distribution of the user's ratings. In contrast, this study measures similarity by utilizing position and rank information of each rating in the range of the user's ratings. The result of the experiments on the real datasets demonstrated that the proposed method improves the mean absolute error significantly, compared to the previous methods, especially when the predetermined range of ratings is large.

• The KIPS Transactions:PartD
• /
• v.16D no.3
• /
• pp.451-462
• /
• 2009

Collaborative Filtering (CF), one of the most successful technologies among recommender systems, is a system assisting users in easily finding the useful information. However, despite its success and popularity, CF encounters a serious limitation with quality evaluation, called cold start problems. To alleviate this limitation, in this paper, we propose a unique method of building models derived from explicit ratings and applying the models to CF recommender systems. The proposed method is divided into two phases, an offline phase and an online phase. First, the offline phase is a building pre-computed model phase in which most of tasks can be conducted. Second, the online phase is either a prediction or recommendation phase in which the models are used. In a model building phase, we first determine a priori predicted rating and subsequently identify prediction errors for each user. From this error information, an error-reflected model is constructed. The error-reflected model, which is reflected average prior prediction errors of user neighbors and item neighbors, can make accurate predictions in the situation where users or items have few opinions; this is known as the cold start problems. In addition, in order to reduce the re-building tasks, the error-reflected model is designed such that the model is updated effectively and users'new opinions are reflected incrementally, even when users present a new rating feedback.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.5
• /
• pp.521-529
• /
• 2003

In this paper we present an improved method by using demographic information for overcoming the similarity miss-calculation from the sparsity problem in collaborative filtering recommendation systems. The similarity between a pair of users is only determined by the ratings given to co-rated items, so items that have not been rated by both users are ignored. To solve this problem, we add virtual neighbor's rating using demographic information of neighbors for improving prediction accuracy. It is one kind of extentions of traditional collaborative filtering methods using the peason correlation coefficient. We used the Grouplens movie rating data in experiment and we have compared the proposed method with the collaborative filtering methods by the mean absolute error and receive operating characteristic values. The results show that the proposed method is more efficient than the collaborative filtering methods using the pearson correlation coefficient about 9% in MAE and 13% in sensitivity of ROC.

• Journal of KIISE
• /
• v.43 no.8
• /
• pp.835-840
• /
• 2016

Monte Carlo ray tracing has been widely used for simulating a diverse set of photo-realistic effects. However, this technique typically produces noise when insufficient numbers of samples are used. As the number of samples allocated per pixel is increased, the rendered images converge. However, this approach of generating sufficient numbers of samples, requires prohibitive rendering time. To solve this problem, image filtering can be applied to rendered images, by filtering the noisy image rendered using low sample counts and acquiring smoothed images, instead of naively generating additional rays. In this paper, we proposed a Stein's Unbiased Risk Estimator (SURE) based $\grave{A}$-Trous wavelet to filter the noise in rendered images in a near-interactive rate. Based on SURE, we can estimate filtering errors associated with $\grave{A}$-Trous wavelet, and identify wavelet coefficients reducing filtering errors. Our approach showed improvement, up to 6:1, over the original $\grave{A}$-Trous filter on various regions in the image, while maintaining a minor computational overhead. We have integrated our propsed filtering method with the recent interactive ray tracing system, Embree, and demonstrated its benefits.