• MALSORI
• /
• no.60
• /
• pp.181-190
• /
• 2006

This paper describes a speech enhancement scheme that leads to significant improvements in recognition performance when used in the ASR front-end. The proposed approach is based on adaptive comb filtering and an MMSE-related parameter estimator. While adaptive comb filtering reduces noise components remarkably, it is rarely effective in reducing non-stationary noises. Furthermore, due to the uniformly distributed frequency response of the comb-filter, it can cause serious distortion to clean speech signals. This paper proposes an improved comb-filter that adjusts its spectral magnitude to the original speech, based on the speech absence probability and the gain modification function. In addition, we introduce the modified comb filtering-based speech enhancement scheme for ASR in mobile environments. Evaluation experiments carried out using the Aurora 2 database demonstrate that the proposed method outperforms conventional adaptive comb filtering techniques in both clean and noisy environments.

• Journal of Korea Multimedia Society
• /
• v.18 no.6
• /
• pp.691-700
• /
• 2015

Here, we present a new framework for histogram equalization in which both local and global contrasts are enhanced using neighborhood metrics. When checking neighborhood information, filters can simultaneously improve image quality. Filters are chosen depending on image properties, such as noise removal and smoothing. Our experimental results confirmed that this does not increase the computational cost because the filtering process is done by our proposed arrangement of making the histogram while checking neighborhood metrics simultaneously. If the two methods, i.e., histogram equalization and filtering, are performed sequentially, the first method uses the original image data and next method uses the data altered by the first. With combined histogram equalization and filtering, the original data can be used for both methods. The proposed method is fully automated and any spatial neighborhood filter type and size can be used. Our experiments confirmed that the proposed method is more effective than other similar techniques reported previously.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1260-1272
• /
• 2024

This paper tackles the prevalent challenges faced by existing tourism route recommendation methods, including data sparsity, cold start, and low accuracy. To address these issues, a novel intelligent tourism route recommendation method based on collaborative filtering is introduced. The proposed method incorporates a series of key steps. Firstly, it calculates the interest level of users by analyzing the item attribute rating values. By leveraging this information, the method can effectively capture the preferences and interests of users. Additionally, a user attribute rating matrix is constructed by extracting implicit user behavior preferences, providing a comprehensive understanding of user preferences. Recognizing that user interests can evolve over time, a weight function is introduced to account for the possibility of interest shifting during product use. This weight function enhances the accuracy of recommendations by adapting to the changing preferences of users, improving the overall quality of the suggested tourism routes. The results demonstrate the significant advantages of the approach. Specifically, the proposed method successfully alleviates the problem of data sparsity, enhances neighbor selection, and generates tourism route recommendations that exhibit higher accuracy compared to existing methods.

• Journal of the Korean Statistical Society
• /
• v.27 no.2
• /
• pp.221-235
• /
• 1998

Suppose that an observed process can be written as the additive model of the signal process and the noise process with unknown parameters. In practice the signal process is not directly observed. We consider the problem of estimating parameter from the observation process using the quasi-likelihood method.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1157-1165
• /
• 2017

2-D complex Gabor filtering has found numerous applications in the fields of computer vision and image processing. Especially, in some applications, it is often needed to compute 2-D complex Gabor filter bank consisting of the 2-D complex Gabor filtering outputs at multiple orientations and frequencies. Although several approaches for fast 2-D complex Gabor filtering have been proposed, they primarily focus on reducing the runtime of performing the 2-D complex Gabor filtering once at specific orientation and frequency. To obtain the 2-D complex Gabor filter bank output, existing methods are repeatedly applied with respect to multiple orientations and frequencies. In this paper, we propose a novel approach that efficiently computes the 2-D complex Gabor filter bank by reducing the computational redundancy that arises when performing the Gabor filtering at multiple orientations and frequencies. The proposed method first decomposes the Gabor basis kernels to allow a fast convolution with the Gaussian kernel in a separable manner. This enables reducing the runtime of the 2-D complex Gabor filter bank by reusing intermediate results of the 2-D complex Gabor filtering computed at a specific orientation. Experimental results demonstrate that our method runs faster than state-of-the-arts methods for fast 2-D complex Gabor filtering, while maintaining similar filtering quality.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.489-498
• /
• 2006

Clustering results differ according to the datasets and the performance worsens even while using web documents which are manually processed by an indexer, because although representative clusters for a feature can be obtained by statistical feature selection methods, irrelevant features(i.e., non-obvious features and those appearing in general documents) are not eliminated. Those irrelevant features should be eliminated for improving clustering performance. Therefore, this paper proposes three feature-filtering algorithms which consider feature values per document set, together with distribution, frequency, and weights of features per document set: (l) features filtering algorithm in a document (FFID), (2) features filtering algorithm in a document matrix (FFIM), and (3) a hybrid method combining both FFID and FFIM (HFF). We have tested the clustering performance by feature selection using term frequency and expand co link information, and by feature filtering using the above methods FFID, FFIM, HFF methods. According to the results of our experiments, HFF had the best performance, whereas FFIM performed better than FFID.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.2
• /
• pp.149-156
• /
• 2017

Nuclear fuel requires high reliability and safety and therefore contains debris filtering devices to prevent failure-inducing debris from entering it. The debris filtering performance of nuclear fuel is one of the most important factors for fuel integrity. Therefore, the performance must be evaluated and the measurement must be reasonable. In this study, a calculation method of the comprehensive filtering efficiency using the weighted mean was proposed to establish a standard filtering efficiency index. To confirm the suitability of the proposed method, representative debris specimens were selected and the filtering efficiency with the weighted mean was compared with the efficiency of the arithmetic mean. The weighting factor of the weighted mean was introduced to produce a fair evaluation. In addition, the analysis of the debris filtering mechanism was performed according to the size of debris specimens, and the main dimensions of the filtering feature for commercial nuclear fuel.

• The Journal of the Korea Contents Association
• /
• v.11 no.7
• /
• pp.1-8
• /
• 2011

In modern society, the amount of information has been significantly increased according to the development of Internet and IT convergence technology and that leads to develop information obtaining and searching technologies from lots of data. Although the system integration for medicare has been largely established and that accumulates large amounts of information, there is a lack of providing and supporting information for nursing activities using such established database. In particular, the judgement for the intervention of pains depends on the experience of individual nurses and that leads to make subjective decisions in usual. In this paper, a pain nursing supporting method that uses the existing medical data and performs collaborative filtering is proposed. The proposed collaborative filtering is a method that extracts some items, which represent a high relativeness level, based on similar preferences. A preference estimation method using a user based collaborative filtering method calculates user similarities through Pearson correlation coefficients in which a neighbor selection method is used based on the user preference.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.3
• /
• pp.659-666
• /
• 2015

In this paper, we propose a novel reconstruction method of spatially filtered 3D images in integral imaging based on parallel lens array. The parallel lens array is composed of two lens arrays, which are positioned side by side through longitudinal direction. Conventional spatial filtering method by using convolution property between periodic functions has drawback that is the limitation of the position of target object. this caused the result that the target object should be located on the low depth resolution region. The available spatial filtering region of the spatial filtering method is depending on the focal length and the number of elemental lens in the integral imaging pickup system. In this regard, we propose the parallel lens array system to enhance the available spatial filtering region and depth resolution. The experiment result indicate that the proposed method outperforms the conventional method.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.6
• /
• pp.736-747
• /
• 2006

Simultaneous Localization and Map Building(SLAM) is one of the fundamental problems in robot navigation. The Extended Kalman Filter(EKF), which is widely adopted in SLAM approaches, requires extensive computation. The conventional particle filter also needs intense computation to cover a high dimensional state space with particles. This paper proposes an efficient SLAM method based on the recursive unscented Kalman filtering in an environment including a large number of landmarks. The posterior probability distributions of the robot pose and the landmark locations are represented by their marginal Gaussian probability distributions. In particular, the posterior probability distribution of the robot pose is calculated recursively. Each landmark location is updated with the recursively updated robot pose. The proposed method reduces filtering dimensions and computational complexity significantly, and has produced very encouraging results for navigation experiments with noisy multiple simultaneous observations.