• Journal of the Korean Chemical Society
• /
• v.36 no.1
• /
• pp.113-124
• /
• 1992

The pattern recognition methods of chemometrics have been applied to multivariate data, for which ninety four Korean ancient glass pieces have been determined for 12 elements by neutron activation analysis. For the purpose, principal component analysis and non-linear mapping have been used as the unsupervised learning methods. As the result, the glass samples have been classified into 6 classes. The SIMCA (statistical isolinear multiple component analysis), adopted as a supervised learning method, has been applied to the 6 training set and the test set. The results of the 6 training set were in accord with the results by principal component analysis and non-linear mapping. For test set, 17 of 33 samples were each allocated to one of the 6 training set.

• Korean Journal of Human Ecology
• /
• v.7 no.2
• /
• pp.63-73
• /
• 1998

To get well-fitted ready-made clothings with beautiful silhouettes, it's better to classify body forms into several forms and to assign sizing within each form than to grade just based on body size regardless of body styles. This study illucidated the importance of drop value in the results of surveying the current values of sizing and grading. Therefore, it's meaningful to get the classification of body form with appropriate distribution of drop values of the body, and the distribution of drop value and the frequency of each form is very helpful to name the combined sizing or coverage of ready-made clothes. This study aimed at classifying body forms with various drop values using multivariate analysis for sizing and grading. Factor analysis and cluster analysis were done using measured values from 346 unmarried women. The results are as follows: 1. The factor which explains body forms was obtained by factor analysis, and the representative major 18 items which have important roles in classifying body forms were selected among the measured values with high factor loading and communality. 2. The body forms were classified into 8 groups based on the charateristics, frequencies and distributions of them obtained from cluster analysis. 3. Each classified body form showed conspicuous difference in drop value and the difference of body form mainly resulted from the difference between waist and hip rather than the difference between bust circumference and waist in Korean unmarried women.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.12 no.3
• /
• pp.395-403
• /
• 2005

Purpose: Methicillin-resistant Staphylococcus aureus (MRSA) is a major nosocomial pathogen in the intensive care units (ICUS). The purpose of this case-control study is to identify risk factors for acquisition of MRSA during ICU stays in patients with and without MRSA. Method: The study was conducted in a 16 beds-neurosurgical intensive care unit of a 2200-bed tertiary care university hospital in Seoul, Korea. Medical record and Critical Classification Scoring System were reviewed retrospectively in patients who were admitted more than 3 days from August 1, 2003 to May 30, 2004. Cases and controls were matched for age and gender. The obtained specimens were nasal swab and sputum. Result: There were 950 patients' admissions during the period. Among them, MRSA was isolated from twenty-three patients who were considered as hospital acquired. Artificial airway (p=.045), frequency of suction (p=.002), nasogastric tube (p=.004), wound drain (p=.045), and vancomycin (p=.019) were risk factors for MRSA acquisition in univariate analysis. Frequency of suction (p=.012, OR 3.5) was revealed as the only risk factor in multivariate conditional logistic regression. Conclusion: Our findings give support to recent studies that suggest that frequent physical contact maγ increase the nosocomial acquisition of MRSA in a neurosurgical ICU.

• Journal of the Ergonomics Society of Korea
• /
• v.18 no.1
• /
• pp.13-24
• /
• 1999

The objective of the study is to discriminate EEG(electroencephalogram) due to emotional changes. Emotion was evoked by the series of auditory stimuli which were selected from the natural sounds in the sound effect collection of compact disc. Seventeen university students participated and experienced positive or negative emotions by six auditory stimuli with intermission between stimuli. Temporal EEG ($T_3$, $T_4$, $T_5$, and $T_6$) was recorded at the same time and a subjective test was performed on the eleven point scales after the experiment. The maximum and minimum scores of the EEG among six stimuli EEG were analyzed for discrimination of emotion. The EEG signals were transformed into feature objects based on scalar intervention model coefficients. Auditory stimulus was considered as intervention variable. They were classified by Discriminant Analysis for each channel. The features showed results with the best classification accuracy of 91.2 % in $T_4$ for auditory stimuli. This study could be extended to establish an algorithm which quantifies and classifies emotions evoked by auditory stimulus using time-series models.

• Journal of the Korean Home Economics Association
• /
• v.34 no.3
• /
• pp.219-232
• /
• 1996

This study is intended to find changing of upper body shape according to the increase of age of elderly women, to extract the factors which form the upper body shapes and to classify the upper body shapes and grasp the characteristics of each body type. The subject were 225 elderly women aged 55-79 years old. Data were analyzed by the multivariate method, especially factor and cluster analysis. The results are as follows: 1. The items of stature, weight and width and circumference of upper body decreased according to the increase of age. And, in the length items except the side neck point - the nipple point length decreased significantly. There were significant difference of upper body shape between age groups according to each group. 2. The shape of elderly women's upper body is determined the main 6 factors(the obesity of upper body, the shape of shoulder, the length of back side of upper body, the length of front side of upper body and the size of vertical direction between stature and arm and front neck width). 3. Elderly women have 4 types of upper body shapes, which are distributed evenly. The body type of Elderly woman changes from long and fat type to small and slim, type according to the increase of age.

• Industrial Engineering and Management Systems
• /
• v.15 no.1
• /
• pp.110-121
• /
• 2016

With the growing interest in skincare and maintenance, there are increasing numbers of studies on the classification of skin type and the factors influencing each type. This study presents a novel methodology by using data mining, for the determination of the relationships between skin type, lifestyle, and patterns of cosmetic utilization. Eight skin-specific factors, which are moisture, sebum in U-zone (both cheeks), sebum in T-zone (forehead, nose, and chin), pore, melanin, wrinkle, acne, hemoglobin, were measured in 1,246 subjects living in South Korea, in conjunction with a questionnaire survey analyzing their lifestyles and pattern of cosmetic utilization. Using various multivariate statistical methods and data mining techniques, we classified the skin types based on the skin-specific values, determined the relationship between skin type and lifestyle, and accordingly sorted the subjects into clusters. Logistic regression analysis revealed gender-related differences in the skin; therefore, separate analyses were performed for males and females. Using the Gaussian Mixture Modeling (GMM) technique, we classified the subjects based on skin type (two male and four female). Using the ANOVA and decision tree techniques, we attempted to characterize the relationship between each skin type and the lifestyles of the subjects. Menstruation, eating habits, stress, and smoking were identified as the major factors affecting the skin.

• Korean Journal of Remote Sensing
• /
• v.5 no.2
• /
• pp.109-122
• /
• 1989

The ISODATA method, which is one of the most famous of the square-error clustering methos, has been applied to two Chungju multivariate data sets in order to evaluate the effectiveness of the regional lithological mapping. One is an airborne radiometric data set and the other is a mixed data set of the airborne radiometric and Landsat TM data. In both cases, the classification of the Bulguksa granite and the Kyemyongsan biotite-quartz gneiss are the most successful. Hyangsanni dolomitic limestone and neighboring Daehyangsan quartzite are also classified by their typical lowness of the radioactive intensities, though it is still confused with some others such as water-covered areas and nearby alluvials, and unaltered limestone areas. Topographically rugged valleys are also classified as the same cluster as above. This could be due to unavoidable variations of flight height and the attitude of the airborne system in such rugged terrains. The regional geological mapping of sedimentary rock units of the Ockchun System is in general confused. This might be due to similarities between different sediments. Considarable discrepancies occurred in mapping some lithological boundaries might also be due to secondary effects such as contamination or smoothing in digitizing process. Further study should be continued in the variable selection scheme as no absolutely superior method claims to exist yet since it seems somewhat to be rather data dependent. Study could also be made on the data preprocessing in order to reduce the erratic effects as mentioned above, and thus hoprfully draw much better result in regional geological mapping.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.5
• /
• pp.749-759
• /
• 2021

We investigate the relationship between ownership control disparity and future firm value in high-technology industries, and whether the effect of ownership control disparity on future firm value is differentiated when high-tech industry firms belong to chaebol groups. Using 11,848 firm-year observations of Korean firms listed on the stock market from 2006 to 2019, we employ univariate analysis and Heckman 2 stage analysis to test our hypotheses. We define high-technology industries as ICT industries based on the Korean Standard Industrial Classification. We measure future firm value using average Tobin's q for the next three years and ownership control disparity using the shareholding ratio of affiliated companies. Our univariate test results show that mean of Tobin's q is higher in ICT firms than non-ICT firms and firms largely owned by affiliates. In multivariate test, we find that the ICT firms with higher ownership control disparity are positively associated with future firm value. However, this association is lessened when firms belong to a chaebol group. Based on our findings, we suggest ownership control disparity has an additional positive effect on future firm in high-technology industries. The negative impact of chaebol groups on the association suggests the possibility of diversification discount in business group.

• Journal of Biomedical Engineering Research
• /
• v.42 no.5
• /
• pp.232-240
• /
• 2021

Heterogeneity in cancer is the major obstacle for precision medicine and has become a critical issue in the field of a cancer diagnosis. Many attempts were made to disentangle the complexity by molecular classification. However, multi-dimensional information from dynamic responses of cancer poses fundamental limitations on biomolecular marker-based conventional approaches. Cell morphology, which reflects the physiological state of the cell, can be used to track the temporal behavior of cancer cells conveniently. Here, we first present a hybrid learning-based platform that extracts cell morphology in a time-dependent manner using a deep convolutional neural network to incorporate multivariate data. Feature selection from more than 200 morphological features is conducted, which filters out less significant variables to enhance interpretation. Our platform then performs unsupervised clustering to unveil dynamic behavior patterns hidden from a high-dimensional dataset. As a result, we visualize morphology state-space by two-dimensional embedding as well as representative morphology clusters and trajectories. This cell morphology profiling strategy by hybrid learning enables simplification of the heterogeneous population of cancer.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.3
• /
• pp.2091-2095
• /
• 2013

Background: The $7^{th}$ TNM staging is the first authoritative standard for evaluation of effectiveness of treatment of gastric cancer worldwide. However, revision of pN classification within TNM needs to be discussed. In particular, the N3 sub-stage is becoming more conspicuous. Methods: Clinical data of 302 pN3M0 stage gastric cancer patients who received radical gastrectomy in Tianjin Medical University Cancer Institute and Hospital from January 2001 to May 2006 were retrospectively analyzed. Results: Location of tumor, depth of invasion, extranodal metastasis, gastric resection, combined organs resection, lymph node metastasis, rate of lymph node metastasis, negative lymph nodes count were important prognostic factors of pN3M0 stage gastric cancers. TNM stage was also associated with prognosis. Patients at T2N3M0 stage had a better prognosis than other sub-classification. T3N3M0 and T4aN3aM0 patients had equal prognosis which followed the T2N3M0. T4aN3bM0 and T4bN3aM0 had lower survival rate than the formers. T4bN3bM0 had worst prognosis. In multivariate analysis, TNM stage group and rate of lymph node metastasis were independent prognostic factors. Conclusions: The sub-stage of N3 may be useful for more accurate prediction of prognosis; it should therefore be applied in the TNM stage system.