• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.8
• /
• pp.766-770
• /
• 2010

In this paper, we present an effective covariance tracking algorithm based on adaptive size changing of tracking window. Recent researches have advocated the use of a covariance matrix of object image features for tracking objects instead of the conventional histogram object models used in popular algorithms. But, according to the general covariance tracking algorithm, it can not deal with the scale changes of the moving objects. The scale of the moving object often changes in various tracking environment and the tracking window(or object kernel) has to be adapted accordingly. In addition, the covariance matrix of moving objects should be adaptively updated considering of the tracking window size. We provide a solution to this problem by segmenting the moving object from the background pixels of the tracking window. Therefore, we can improve the tracking performance of the covariance tracking method. Our several simulations prove the effectiveness of the proposed method.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.959-971
• /
• 2019

CNN (Convolutional Neural Network) is one representative deep learning algorithm, which can extract high-level spatial and spectral features, and has been applied for hyperspectral image classification. However, one significant drawback behind the application of CNNs in hyperspectral images is the high dimensionality of the data, which increases the training time and processing complexity. To address this problem, several CNN based hyperspectral image classification studies have exploited PCA (Principal Component Analysis) for dimensionality reduction. One limitation to this is that the spectral information of the original image can be lost through PCA. Although it is clear that the use of PCA affects the accuracy and the CNN training time, the impact of PCA for CNN based hyperspectral image classification has been understudied. The purpose of this study is to analyze the quantitative effect of PCA in CNN for hyperspectral image classification. The hyperspectral images were first transformed through PCA and applied into the CNN model by varying the size of the reduced dimensionality. In addition, 2D-CNN and 3D-CNN frameworks were applied to analyze the sensitivity of the PCA with respect to the convolution kernel in the model. Experimental results were evaluated based on classification accuracy, learning time, variance ratio, and training process. The size of the reduced dimensionality was the most efficient when the explained variance ratio recorded 99.7%~99.8%. Since the 3D kernel had higher classification accuracy in the original-CNN than the PCA-CNN in comparison to the 2D-CNN, the results revealed that the dimensionality reduction was relatively less effective in 3D kernel.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.53 no.4
• /
• pp.427-433
• /
• 2008

Barley Yellow Mosaic Virus (BaYMV) caused significant reduction in barley yield and is difficult to control due to alive parasitic soil-borne fungus, Palmyra gamines that transmits the, virus. Previous studies have indicated that a virus-free soil could be infested by using virus-contaminated farming machineneries and implements. For the further confirmation of this finding, different proportions of BaYMV-infested soil were mixed into virus free soil. Three barley varieties (Hordum vulgarae, cv "Olbori", "Baegdong" and "Sacheon 6") were sown in pots treated with different rate of P. graminis-infested soil ranging from 0% to 100% in October 20, 2001. Results showed that BaYMV infection increased as the rate of infested soil increased. Initial symptoms were observed in a pots treated with 10% infested soil in all the 3 varieties of barley. "Olbori" had about 5% infection in 20% infested soil and about 10% infection in 40% or 50% infested soil and about 20% infection in 60% infested soil. In "Baegdong", the trend of BYMV occurrence was similar with "Olbori" but the time of severe infection was earlier than "Olbori". BaYMV infection in "Sacheon 6" was even earlier than "Baegdong" with much more severe symptoms than "Baegdong". The growth rate of barley was affected by about 19-22% when grown in 20% infested soil. As the rate of BaYMV infested soil increased the heading date was delayed but the maturing date was early in "Olbori" and "Sacheon 6". Also, reduction rate of culm length in 3 varieties increased with increase of infested soil content. However, "Olbori" showed the highest reduction. "Sacheon 6", have been characterized with long spike length, however was significantly reduced as the infested soil increased. On the other hand, spike length of "Olbori" was not significantly affected despite of increased of infested soil. The reduction rate of 1000 kernel weight was higher in large kernel size cultivar "Sacheon 6" and "Olbori" than small kernel size "Baegdong" as increase of BaYMV-infested soil content.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.1
• /
• pp.1-9
• /
• 2009

Let us consider that the variance function in regression model has a discontinuity/change point at unknown location. Yu and Jones (2004) proposed the local polynomial fit to estimate the log-variance function which break the positivity of the variance. Using the local polynomial fit, Huh (2008) estimate the discontinuity point of the log-variance function. We propose a test for the existence of a discontinuity point in the log-variance function with the estimated jump size in Huh (2008). The proposed method is based on the asymptotic distribution of the estimated jump size. Numerical works demonstrate the performance of the method.

• Journal of the Korean Society of Costume
• /
• v.25
• /
• pp.105-118
• /
• 1995

Chinese shroud through literature are as follows. 1. Taetae, SimeI, P'oo, Hansam, Ko, Mal, Nukpaek , Kwatu, Ch'ungi, Pokkn, Myokmok, Ri, Aksu, Mo and m were used the most in China. 2. The cloths of Chinese shroud were p'o, Paek , Kyon and Kum. The colors of the Chinese shroud were Hyon, Hun and white. 3. The size of the Chinese shroud is as follows . The size of the Ch'ungi was similar to the size of jujube kernel, the length of Myokmok was one Chk two Chn or one Chk two Chn or one Chk five Chn, the length of Aksu was one Chjk two Chn and it's width was five Chn. The chil of Mo reached the hands and the length of Swae was three Chk and the length of m was five Chn. 4. In Chinese shroud, , cotton was put in P'oo. Aksu was tide by the strings at two corners. Myokmok was tied by the strings of four corners. The tip of the m was divided and Mo warpped the whole body. 5. The clothes of Soryom was nineteen Ch'ing. The clothes of Taeryom in Kum were one hundred Ch'ing in the Chinese. The impliment of Soryon were Kum, kyo, SangeI, SaneI, Ch'im , Yok and Kyon in the Chinese shroud. In the case of the implement of TAeryom, the chinese shroud had Kum , Kyo, SangeI, Sane, Ch'im and Yok.

• Journal of the Korean Society of Costume
• /
• v.25
• /
• pp.117-118
• /
• 1995

Chinese shroud through literatures are as follows. 1. Taetae, Sime i, P'oo, Hansam, Ko, Mal, Nukpaek, Kwatu, Cu'ungi, Pokk n, Myokmok, Ri, Aksu, Mo and m were used the most in China. 2. The cloths of Chinese shroud were p'o, Paek, Kyon and Kum. The colors of the Chinese shroud were Hyon, Hun and white. 3. The size of the Chinese shroud is as follows. The size of the Ch'ungi was similar to the size of jujube kernel, the length of Myokmok was one Ch' k two Ch'on or one Ch' k five Ch'on, the length of Aksu was one Ch' k two Ch'on and it's width was five Ch'on. The chil of Mo reached the hands and the length of Swae was three Ch' k and the length of m was five Ch'on. 4. In Chinese shroud, cotton was put in P'oo, Aksu was tide by the strings at two corners. Myokmok was tied by the strings of four corners. The tip of the m was divided and Mo wrapped the whole body. 5. The clothes of Soryom was nineteen Ch'ing. The clothes of Taeryom in Kun were one hundred Ch'ing in the Chinese. The impliment of Soryom were Kum, Kyo, Sange i, Sane i, Ch'im, Yok and Kyon in the Chinese shroud. In the case of the implement of Taeryom, the chinese shroud had Kum, Kyo, Sange i, Sane i, Ch'im and Yok.

• Journal of the Korean Society of Visualization
• /
• v.21 no.1
• /
• pp.94-102
• /
• 2023

Three design parameters were considered in this study: outlet nozzle angle (30°, 60°, 80°), neck length (1 mm, 3 mm), and flow rate (0.5, 0.6, 0.7, 0.8 lpm). A neck diameter of 0.5 mm induced cavitation flow at a venture nozzle. A secondary transparent chamber was connected after ejection to increase bubble duration and shape visibility. The bubble size was estimated using a Gaussian kernel function to identify bubbles in the acquired images. Data on bubble size were used to obtain Sauter's mean diameter and probability density function to obtain specific bubble state conditions. The degree of bubble generation according to the bubble size was compared for each design variable. The bubble diameter increased as the flow rate increased. The frequency of bubble generation was highest around 20 ㎛. With the same neck length, the smaller the CV number, the larger the average bubble diameter. It is possible to increase the generation frequency of smaller bubbles by the cavitation method by changing the magnification angle and length of the neck. However, if the flow rate is too large, the average bubble diameter tends to increase, so an appropriate flow rate should be selected.

• Journal of the Korean Society of Costume
• /
• v.34
• /
• pp.79-89
• /
• 1997

Comparison of Korean shroud with Chinese shroud are as follows. 1. Taetae Simeui P'oo Hansam Ko, Mal, Nukpaek, Kwatu, Ch'ungi Po-kkon Myokmok Ri Aksu Mo and Om were used the most inchina. However Mangkon Tapho Tanko Sotae Ri and Kop'o were used more widely in Korea. 2. The cloths of Chinese shroud were p'o, Paek and Kyun but those of the orean were paek Chu Chung and P'o The colors of the chinese and Koean shroud was Hyun Hun and white. 3. The size of the Cinese shroud is as follows. The size of the Ch ungi ws si-milar tothe size of jujube kernel the len-gth of Myokmok was one Ch'ok two Ch'on or one Ch'ok five Ch'on the length of Aksu was one Ch'ok two Ch'on and its width was five Ch'on. The chil of Mo reached the hands and the length of Sw-ae was three Ch'ok and the length of Om ws five Ch'on. the size of the Korean shroud was the same as Chinese shroud except that the size fo Myokmok and the lenth of Chil and Swae was seven Ch'ok respectively,. 4. In Korean and Chinese shroud Aksu was tied by the strings at two corners Myokmok was teid by the strings of four corners. The tip of the Om was divided and Mo wrapped the shole body. 5. The clothes of Soryom was nineteen Ch'ing in Korean and chinese shroud. The clothes of Taeryom in Kun were one hundred Ch'ing in the chinese and ninety Ch'ing in the Korean shroud. The imple-ment of Soryom were Kum Kyo Sangeui Saneui Ch'im Yok and Kyon in the Chinese shroud and were Kum Kyo Sangeui Saneui Ch'im Yok Kyonand Sinmyon in the Korean shroud. In the case of the implement of Taeryom the Chinese shroud had Kum Kyo Sangeui Saneui Ch'im and Yok the same as Korean shroud.

• Journal of Ecology and Environment
• /
• v.34 no.4
• /
• pp.365-370
• /
• 2011

The water deer (Hydropotes inermis) is one of the most primitive extant deer of the family Cervidae. Unlike Chinese water deer, Korean water deer have rarely been studied, even though they have relatively well remained in Korea. In particular, the home range of the Korean water deer has not yet been studied. Here we estimated the home range of the Korean water deer using two different methods (GPS and radio tracking) and analyzed the home range according to sex, time, and season. The mean home range size of four individuals was 2.77 $km^2$ and 0.34 $km^2$ under the 95% minimum convex polygon (MCP) and the 50% kernel (K) method, respectively. There seemed to be a difference in home range size between males (3.30 $km^2$) and females (2.25 $km^2$) under the 95% MCP method. We also found a difference in home range size between day (1.90 $km^2$) and night (2.43 $km^2$) by 95% MCP method. In addition, a home range size difference was observed between summer (4.65 $km^2$) and spring (0.48 $km^2$) or fall (0.85 $km^2$) using the 95% MCP method. Water deer seemed to have a larger home range in night than in day, and males also have a larger home range. We presumed that the GPS tracking method of the code division multiple access system could be a very useful tool for understanding the ecology of the water deer using the radio tracking method. Using these tracking methods and through future research, we can better understand the habitat use pattern of these water deer.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.16 no.4
• /
• pp.436-442
• /
• 2016

An electroencephalogram (EEG)-connectome processor to monitor and diagnose mental health is proposed. From 19-channel EEG signals, the proposed processor determines whether the mental state is healthy or unhealthy by extracting significant features from EEG signals and classifying them. Connectome approach is adopted for the best diagnosis accuracy, and synchronization likelihood (SL) is chosen as the connectome feature. Before computing SL, reconstruction optimizer (ReOpt) block compensates some parameters, resulting in improved accuracy. During SL calculation, a sparse matrix inscription (SMI) scheme is proposed to reduce the memory size to 1/24. From the calculated SL information, a small world feature extractor (SWFE) reduces the memory size to 1/29. Finally, using SLs or small word features, radial basis function (RBF) kernel-based support vector machine (SVM) diagnoses user's mental health condition. For RBF kernels, look-up-tables (LUTs) are used to replace the floating-point operations, decreasing the required operation by 54%. Consequently, The EEG-connectome processor improves the diagnosis accuracy from 89% to 95% in Alzheimer's disease case. The proposed processor occupies $3.8mm^2$ and consumes 1.71 mW with $0.18{\mu}m$ CMOS technology.