• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.2
• /
• pp.359-366
• /
• 2016

The normal tissue in radiation therapy, to minimize radiation, it is most important to maximize local tumor control rates in intensive research the exact dose to the tumor sites. Therefore, the initial, therapist accuracy of detecting movement of the patient fatigue therapist has been a problem that is weighted down directly. Also, by using a web camera, a difference value between the image to be updated to the reference image is calculated, if the result exceeds the reference value, using the system for determining the motion has occurred. However, this system, it is not possible to quantitatively analyze the movement of the patient, the background is changed when moving the treatment bed in the co-therapeutic device was not able to sift the patient. In this paper, using a alpah(${\alpha}$) filter index is an attempt to solve these limitations points, quantifies the movement of the patient, by separating a background image of the patient and treatment environment, and movement of the patient during treatment It senses only, it was possible to reduce the problems due to patient movement.

• Structural Engineering and Mechanics
• /
• v.74 no.1
• /
• pp.55-67
• /
• 2020

The common practice to predict the characteristic structural load effects (LEs) in long reference periods is to employ the extreme value theory (EVT) for building limit distributions. However, most applications ignore that LEs are driven by multiple loading events and thus do not have the identical distribution, a prerequisite for EVT. In this study, we propose the composite extreme value modeling approach using clustering to (a) cluster initial blended samples into finite identical distributed subsamples using the finite mixture model, expectation-maximization algorithm, and the Akaike information criterion; (b) combine limit distributions of subsamples into a composite prediction equation using the generalized Pareto distribution based on a joint threshold. The proposed approach was validated both through numerical examples with known solutions and engineering applications of bridge traffic LEs on a long-span bridge. The results indicate that a joint threshold largely benefits the composite extreme value modeling, many appropriate tail approaching models can be used, and the equation form is simply the sum of the weighted models. In numerical examples, the proposed approach using clustering generated accurate extrema prediction of any reference period compared with the known solutions, whereas the common practice of employing EVT without clustering on the mixture data showed large deviations. Real-world bridge traffic LEs are driven by multi-events and present multipeak distributions, and the proposed approach is more capable of capturing the tendency of tailed LEs than the conventional approach. The proposed approach is expected to have wide applications to general problems such as samples that are driven by multiple events and that do not have the identical distribution.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.2
• /
• pp.107-116
• /
• 2013

In this paper, we propose a hybrid music recommendation system combining users' listening habits and tag information in a social music site. Most of commercial music recommendation systems recommend music items based on the number of plays and explicit ratings of a song. However, the approach has some difficulties in recommending new items with only a few ratings or recommending items to new users with little information. To resolve the problem, we use tag information which is generated by collaborative tagging. According to the meaning of tags, a weighted value is assigned as the score of a tag of an music item. By combining the score of tags and the number of plays, user profiles are created and collaborative filtering algorithm is executed. For performance evaluation, precision, recall, and F-measure are calculated using the listening habit-based recommendation, the tag score-based recommendation, and the hybrid recommendation, respectively. Our experiments show that the hybrid recommendation system outperforms the other two approaches.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.385-396
• /
• 2005

In this paper, a new structural approach to on-line signature verification is presented. A primitive pattern is defined as a part segmented by a local minimal position of speed. And a structural description of signature is composed of subpatterns which are defined as such forms as rotation shape, cusp shape and bell shape, acquired by composition of the primitives regarding the directional changes. As the matching method to find identical parts between two signatures, a modified DP(dynamic programming) matching algorithm is presented. And also, variation and complexity of local parts are computed from the training samples, and reference model and decision boundary are derived from these. Error rate, execution time and memory usage are compared among the functional approach, the parametric approach and the proposed structural approach. It is found that the average error rate can be reduced from 14.2% to 4.05% when the local parts of a signature are weighted and the complexity is used as a factor of decision threshold. Though the error rate is similar to that of functional approaches. time consumption and memory usage of the proposed structural approach are shown to be very effective.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.7
• /
• pp.540-547
• /
• 2004

Since speech enhancement algorithms based on Kalman/Wiener filter require a priori knowledge of the noise and have focused on the minimization of the variance of the estimation error between clean and estimated speech signal, small estimation error on the noise statistics may lead to large estimation error. However, H/sub ∞/ filter does not require any assumptions and a priori knowledge of the noise statistics, but searches the best estimated signal among the entire estimated signal by applying least upper bound, consequently it is more robust to the variation of noise statistics than Kalman/Wiener filter. In this paper, we Propose a speech enhancement method using HMM and multi H/sub ∞/ filters. First, HMM parameters are estimated with the training data. Secondly, speech is filtered with multiple number of H/sub ∞/ filters. Finally, the estimation of clean speech is obtained from the sum of the weighted filtered outputs. Experimental results shows about 1dB∼2dB SNR improvement with a slight increment of computation compared with the Kalman filter method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.727-734
• /
• 2014

Digital processing technologies are being studied in various areas of image compression, recognition and recovery. However, image deterioration still occurs due to the noises in the process of image acquisition, storage and transmission. Generally in the typical noises which are included in the images, there are Gaussian noise and the mixed noise where the Gaussian noise and impulse noise are overlapped and in order to remove these noises, various researches are being executed. In order to preserve the edge and effectively remove mixed noises, image recovery filter algorithm was suggested in this study which sets and processes the adaptive weight using the median values and average values after noise judgment. Additionally, existing methods were compared through simulations and PSNR(peak signal to noise ratio) was used as a judgment standard.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.1C
• /
• pp.67-77
• /
• 2007

Virus throttling technique, one of many early worm detection techniques, detects Internet worm propagation by limiting connect requests within a certain ratio. The typical virus throttling controls the period of rate limiter autonomically by utilizing weighted average delay queue length to reduce connection delay time without hanving a large effect on worm detection time. In the existing virus throttling research, a minimum period of variable rate limiter is fired and a turning point which is a point that the period of rate limiter has been being decreased and starts to be increased is also fixed. However, these two performance factors have different effects on worm detection time and connection delay. In this paper, we analyze the effect of minimum period and turning point of variable rate limiter, and then propose an algorithm which determines values of performance factors by referencing current traffic pattern. Through deep experiments, it is verified that the proposed technique is more efficient in respect of reducing worm detection time and connection delay than the existing virus throttling which fixed the performance factors.

• Journal of Biosystems Engineering
• /
• v.20 no.1
• /
• pp.95-103
• /
• 1995

A series of study has been conducted to develop a multi-purpose fruit grader using a black ＆ white image processing system equipped with a 550 nm interference filter. A device and high performance algorithms were developed for sizing and color grading of Fuji apple in the previous study. In this study an emphasis was put on finding correlations between weights of several kinds of fruits and their area fractions(AF), and on compensating the blurring effect upon sizing and color grading by conveying speed of fruit. Also, the effect of orientation and direction of fruit on conveyor during image forming was analyzed to identify any difficulty (or utilizing an automatic fruit feeder. The results are summarized as follows. 1. The correlation coefficients(r) between the weights of fruits and their image sizes were 0.984~0.996 for apples, 0.983~0.990 for peachs, 0.995 for tomato, 0.986 for sweet persimmon and 0.970~0.993 for pears. 2. It was possible to grade fruits by color with the area weighted mean gray values(AWMGV) based on the mean gray valves of direct image and the compensated values of reflected image of a fruit, and also possible to sort fruits by size with AF. Accuracies in sizing and color grading ranged over 81.0% ~95.0% and 82.0% ~89.7% respectively as compared with results from sizing by electronic weight scale and grading by expert. 3. The blurring effect on the sizing and color grading depending on conveying speed was identified and regression equations were derived. 4. It was found that errors in sizing and coloring grading due to the change in direction and orientation of Fuji apple on the conveyor were not significant as far as the stem end of apple keeping upward.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.1-14
• /
• 2010

The back-propagation neural network (BPN) has long been successfully applied in bankruptcy prediction problems. Despite its wide application, some major issues must be considered before its use, such as the network topology, learning parameters and normalization methods for the input and output vectors. Previous studies on bankruptcy prediction with BPN have shown that many researchers are interested in how to optimize the network topology and learning parameters to improve the prediction performance. In many cases, however, the benefits of data normalization are often overlooked. In this study, a genetic algorithm (GA)-based normalization transform, which is defined as a linearly weighted combination of several different normalization transforms, will be proposed. GA is used to extract the optimal weight for the generalization. From the results of an experiment, the proposed method was evaluated and compared with other methods to demonstrate the advantage of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3984-4005
• /
• 2017

Image recognition has become an increasingly important topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The recognition systems rely on a key component, i.e. the low-level feature or the learned mid-level feature. The recognition performance can be potentially improved if the data distribution information is exploited using a more sophisticated way, which usually a function over hidden variable, model parameter and observed data. These methods are called generative score space. In this paper, we propose a discriminative extension for the existing generative score space methods, which exploits class label when deriving score functions for image recognition task. Specifically, we first extend the regular generative models to class conditional models over both observed variable and class label. Then, we derive the mid-level feature mapping from the extended models. At last, the derived feature mapping is embedded into a discriminative classifier for image recognition. The advantages of our proposed approach are two folds. First, the resulted methods take simple and intuitive forms which are weighted versions of existing methods, benefitting from the Bayesian inference of class label. Second, the probabilistic generative modeling allows us to exploit hidden information and is well adapt to data distribution. To validate the effectiveness of the proposed method, we cooperate our discriminative extension with three generative models for image recognition task. The experimental results validate the effectiveness of our proposed approach.