• Journal of KIISE
• /
• v.45 no.1
• /
• pp.15-21
• /
• 2018

Low-Rank Representation (LRR) based methods are widely used in many practical applications, such as face clustering and object detection, because they can guarantee high prediction accuracy when used to constructing graphs in graph - based semi-supervised learning. However, in order to solve the LRR problem, it is necessary to perform singular value decomposition on the square matrix of the number of data points for each iteration of the algorithm; hence the calculation is inefficient. To solve this problem, we propose an improved and faster LRR method based on the recently published Fast LRR (FaLRR) and suggests ways to introduce and optimize additional constraints on the underlying optimization goals in order to address the fact that the FaLRR is fast but actually poor in classification problems. Our experiments confirm that the proposed method finds a better solution than LRR does. We also propose Fast MLRR (FaMLRR), which shows better results when the goal of minimizing is added.

• Analytical Science and Technology
• /
• v.9 no.4
• /
• pp.392-398
• /
• 1996

Eleven organic chemical substances, tetrachloroethylene, ethyl benzene, p-xylene, o-xylene, isopropyl benzene, n-propyl benzene. 1,2,4-trimethyl benzene, 1,3,5-trimethyl benzene, p-isopropyl toluene. see-butyl benzene, and naphthalene, which have hazardously influenced to human, were extracted from untreated wastewater collected at 26 companies of 8 types industry in the basin of Kwangju stream. Their structures were elucidated by Gas Chromatography/Mass Spectrometry(GC/MS) and in comparison with each standard reagents.

• Journal of Oriental Neuropsychiatry
• /
• v.23 no.4
• /
• pp.107-122
• /
• 2012

Objectives : The purpose of this study is to examine the general personality profiles of patients who visited an oriental neuropsychiatric clinic and to investigate the specific profiles of patients diagnosed with Hwa-byung. Methods : We analyzed the profiles of 122 patients who completed TCI-RS questionnaire for the purpose of counseling. Patients were divided by sex, age and diagnosis related groups. Scales and subscales of each group were compared by an independent t-test and ANCOVA with SPSS windows 16.0. Types of temperament and character were classified by percentile ranks of the total patients and diagnosis related groups. Results : 1. Total patients were classified as the high harm avoidance type of temperament and of low self-directedness type of character. 2. Male patients showed significantly higher scores on NS, all subscales of NS, P2 and P3 than female patients. HA4 and C5 scores were significantly higher in the female group. Younger patients showed significantly higher scores on NS, all subscales of NS, HA1 and P3. However, older patients had significantly higher scores on SD4, SD5, ST2 and ST3. 3. Between diagnosis related groups, Hwa-byung group had significantly higher scores on RD, ST, SD3 and ST2. However P3 score of non-hwa-byung patients was higher than hwa-byung patients. In typical classification, both hwa-byung and non-hwa-byung groups were classified as the same types as total patients. Conclusions : This study showed that the patients visited an oriental neuropsychiatric clinic and had similar personality with that of general psychiatric disorders. Hwa-byung patients exhibited higher RD and ST scores than other disorders, but they had no typical differences.

• Journal of Preventive Medicine and Public Health
• /
• v.30 no.4 s.59
• /
• pp.884-892
• /
• 1997

Currently, there are 100 community emergency centers which expect to provide professional emergency care like Level 1 trauma centers in U.S.A. To evaluate perforance of emergency centers, most studies have been widely adopted death rate based methods such as Trauma and Injury Severity Score(TRISS) and A Severity Characterization of Trauma(ASCOT). However, these methods are only applicable in situation where registration process of trauma patients is well established. Therefore, an alternative method should be applied to evaluate performance of emergency centers in Korea which does not have well-developed registration scheme. This study aims to develop new performance measures which are applicable to Korea and evaluate performance of 35 community emergency centers through new measures. The new measures are included that 'W-statistic' ; death rate calculated on the basis of International Classification based Injury Severity Score(ICISS), and 'the degree of severity' ; rate of severe trauma patients of each emergency medical centers. The study results can be summarized as follows. First, about 34% of sample emergency centers show they provide proper care in terms of their function. Second, tertiary hospitals, university hospitals, and hospitals located in Seoul show higher severity degree of patients and lower severity-adjusted death rate.

• Fashion & Textile Research Journal
• /
• v.12 no.1
• /
• pp.80-85
• /
• 2010

The purpose of this study was to examine the characteristics of armscye circumference which will be used to develop total contents for the apparel industry. The subjects of this study were 16- to 49-year-old women whose 3D body shape data were analyzed. 72 length and length-ratio measurements were taken to each subject' armscye circumference. The used analysis methods are descriptive statistics, principal component analysis, and cluster analysis. The results are follows; 1. Considering the Length of armscye circumference, the result of principal component analysis were extracted 3 factors and those factors comprised 95% of total variance. As the result of the cluster analysis of factor scores, subjects were classified into 4 cluster by their size characteristic. 2. Considering the length-ratio of armscye circumference, the result of principal component analysis were extracted 5 factors and those factors comprised 96.45% of total variance. As the result of the cluster analysis of factor scores, subjects were classified into 5 cluster by their shape characteristic. So that, this research could be useful to manufacture garment which reflected 3D body figure and improved fitting.

• Journal of Fashion Business
• /
• v.16 no.1
• /
• pp.83-102
• /
• 2012

The instant trend of mobile functionality in the digital age is performing a mediating role of promoting the hybrid tendency in fashion and cosmetics industry. Consumers' needs, which are getting complex and diversified along with development in scientific technology, are requiring product of technology equipped with multi-tasking function in the whole industry. The social and cultural factors, which are shown in cosmetics due to the instant trend of mobile functionality, came to be known on the basis of a ground for classification caused by a change in nomadic lifestyle and by the advance in scientific technology. The irst, The mobile functionality, which is being developed in fashion in the digital age, was indicated to be types such as mobility, one-off, and unity. Second, Even the types of mobile functionality, which are also being developed in make-up and cosmetics in digital age, were indicated to be mobility, one-off, and unity. Third, The trend caused by mobile functionality in fashion was consistent with a type in mobile functionality, which is being developed in cosmetics, thereby having been indicated to be the same type. This implies that there is the same type through independent trend in each sphere even while fashion and cosmetics organically function in the middle of the whole frame, which expresses a human being's external beauty, and implies that even the cosmetics are influenced by fashion. Swift-type beauty product, which is thrown away within one week lengthily and after being used once, are being launched diversely. This quick product can be said to be product that best reflected the characteristic of digital age. However, at this point of time that fast fashion and instant cosmetics, which are thrown away in the wake of being worn easily, are overflowing, the clothing and product with perfection, which has philosophy and thinking of being put more devotion, exert more value and are felt to be necessary.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.3093-3115
• /
• 2020

Network anomaly detection system plays an essential role in detecting network anomaly and ensuring network security. Anomaly detection system based machine learning has become an increasingly popular solution. However, due to the unbalance and high-dimension characteristics of network traffic, the existing methods unable to achieve the excellent performance of high accuracy and low false alarm rate. To address this problem, a new network anomaly detection method based on data balancing and recursive feature addition is proposed. Firstly, data balancing algorithm based on improved KNN outlier detection is designed to select part respective data on each category. Combination optimization about parameters of improved KNN outlier detection is implemented by genetic algorithm. Next, recursive feature addition algorithm based on correlation analysis is proposed to select effective features, in which a cross contingency test is utilized to analyze correlation and obtain a features subset with a strong correlation. Then, random forests model is as the classification model to detection anomaly. Finally, the proposed algorithm is evaluated on benchmark datasets KDD Cup 1999 and UNSW_NB15. The result illustrates the proposed strategies enhance accuracy and recall, and decrease the false alarm rate. Compared with other algorithms, this algorithm still achieves significant effects, especially recall in the small category.

• Journal of Korean Society for Geospatial Information Science
• /
• v.19 no.3
• /
• pp.49-56
• /
• 2011

Because urban areas change rapidly, it is necessary to reflect urban changes in a digital map database in a timely manner. To address these issues, LiDAR data was used to detect changes in urban area buildings. The purpose of this study is to detect object-based building change using LiDAR data and existing digital maps, and classify change types. In the study, we classified change type using overlay and shape comparison with building layer of the digital maps and point-based extracted building outline from the LiDAR data. When applying the overlay method, we were able to increase the accuracy and objectivity of the change detection process throughout an adaptive threshold applied to each object. In the experiments, it was demonstrated that classifying and detecting changes in urban areas using the proposed method can provide superior classification accuracy compared with the existing methodology.

• Korean Journal of Ecology and Environment
• /
• v.47 no.3
• /
• pp.146-159
• /
• 2014

In this study, we evaluated the temporal changes of water quality in the 90 reservoirs in Korea and the relationships between water quality and their environmental factors in the reservoirs for effective management of reservoirs. The majority of study reservoirs were categorized as the eutrophic state based on Carlson's trophic index. Among 90 reservoirs, more than 55.0% were nutrient-rich based on $TSI_{TP}$ in each month, where more than 50.0% were nutrient-rich based on $TSI_{Chl-a}$ from June to November. Seasonal Mann-Kendall test was used to analyze temporal variation of water quality in the selected 60 reservoirs using monthly data from 2004 to 2008. The results showed that 27 (45.0%) reservoirs showed the improvement of water quality based on TP and Chl-a concentrations, while 14 (23.3%) and 11 (18.3%) reservoirs displayed the degradation of water quality based on TP and Chl-a concentrations, respectively. Meanwhile, a self-organizing map classified the study reservoirs into five groups based on differences of hydrogeomorphology (altitude, catchment area, bank height, lake age, etc.). Physicochemical factors and land use/cover types showed clear differences among groups. Finally, hydrogeomorphology of reservoirs were related to water quality, indicating that the hydrogeomorphological characters strongly affect water quality of reservoirs.

• Journal of Korea Game Society
• /
• v.17 no.2
• /
• pp.17-26
• /
• 2017

Excessive use of the internet and smart phones have become a social issue. The level of engagement has both positive and negative effects such as good performance or indulgence phenomenon, respectively. This study was to develop an algorithm to determine the engagement state based on cardiovascular response. The participants were asked to play a pattern matching game and the experimental design was divided into cooperation and competition task to provide the level of engagement. The correlation between heart rate and amplitude was analyzed according to each task. The regression equation and accuracy were verified by polynomial regression analysis. The results showed that heart rate and amplitude were positively correlated when the task was a game, and negatively correlated when there was a reference task. The accuracy of classifying between game and reference task was 89%. The accuracy between tasks was confirmed to be 76.5%. This study is expected to be used to quantitatively evaluate the level of engagement in real time.