• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.646-650
• /
• 2014

In this paper, in order to avoid the deterioration of the pattern classification performance which results from the curse of dimensionality, we propose a new feature selection method. The newly proposed feature selection method is based on Fuzzy C-Means clustering algorithm which analyzes the data points to divide them into several clusters and the concept of a function with fuzzy numbers. When it comes to the concept of a function where independent variables are fuzzy numbers and a dependent variable is a label of class, a fuzzy number should be related to the only one class label. Therefore, a good feature is a independent variable of a function with fuzzy numbers. Under this assumption, we calculate the goodness of each feature to pattern classification problem. Finally, in order to evaluate the classification ability of the proposed pattern classifier, the machine learning data sets are used.

• Bulletin of the Korean Chemical Society
• /
• v.28 no.3
• /
• pp.379-385
• /
• 2007

Receptor-oriented pharmacophore-based in silico screening is a powerful tool for rapidly screening large number of compounds for interactions with a given protein. Inhibition of the enzyme catechol-Omethyltransferase (COMT) offers a novel possibility for treating Parkinson's disease. Bisubstrate inhibitors of COMT containing the adenine of S-adenosylmethionine (SAM) and a catechol moiety are a new class of potent and selective inhibitor. In the present study, we used receptor-oriented pharmacophore-based in silico screening to examine the interactions between the active site of human COMT and bisubstrate inhibitors. We generated 20 pharmacophore maps, of which 4 maps reproduced the docking model of hCOMT and a bisubstrate inhibitor. Only one of these four, pharmacophore map I, effectively described the common features of a series of bisubstrate inhibitors. Pharmacophore map I consisted of one hydrogen bond acceptor (to Mg2+), three hydrogen bond donors (to Glu199, Glu90, and Gln120), and one hydrophobic feature (an active site region surrounded by several aromatic and hydrophobic residues). This map represented the most essential pharmacophore for explaining interactions between hCOMT and a bisubstrate inhibitor. These results revealed a pharmacophore that should help in the development of new drugs for treating Parkinson's disease.

• Korean Journal of Agricultural Science
• /
• v.4 no.1
• /
• pp.112-117
• /
• 1977

This survey was conducted to secure a basic data for the effective training programs that might be an essential part of any successful mechanization of agriculture in Korea. Chung Nam provincial training center and 17 guidance offices with farm machinery training centers which were thought to be a medium level on their scale in whole country were selected in the survey on its training accomplishments, stafts, facilities, schedule and number of trainees at one time or in a class. The results and recommendations from this survey were as follows; To enhance the effect of farm machinery training, it was absolutely necessary for city or county training center to complement its facilities and equipments. It might be desirable that instructors of each training center should be the one educated or highly trained in the institution of farm machinery, and that the number of technical assistants should be increased and their present part time working condition should be changed to full-time status. It was recommended that training for farmers should be scheduled during off-season so that farmers could participate in the training couses, and that the number of trainees in a class should be reduced to about 10 trainees, which was approximately a fourth of the present situation.

• Journal of Korean Academy of Nursing
• /
• v.3 no.2
• /
• pp.81-90
• /
• 1973

Since there is nothing in the literature regarding how Koreans value their children, this is an exploratory study attempting to (1) generate ideas as to why women of child- bearing age want children and (2) discover aspects of the interaction between the value of children and the fertility behavior according to socio-economic class and level of education. Fifty women from the Yonhee A Citizen′s Apartment and 50 women from the slum area surrounding the Yonhee Apartment were interviewed by the investigator during the period of October 10 to October 25, 1972. All of the women interviewed were under 35 years of age and had more than one child. The questionnaire consisted of questions regarding the general characteristics of the respondents, the status of current family planning practice, the number of induced abortions and the reasons for wanting children. An open ended question followed by a forced choice question was the method used to determine the reasons for wanting children. The results of the study were as follows: 1. Half of all the respondents were between 30 and 34 years of age. 2. Four percent of the respondents had no schooling, 51 percent had graduated from primary school, and 45 percent were educated beyond middle school. 3. The most important reasons tot wanting children given by the respondents were categorized as follows: (1) carrying on the family name, (2) old age security, (3) value of life, (4) fun of rearing children, (5) avoidance of loneliness, (6) responsibility of women. 4. The number of consistent answers between the open ended and forced choice questions regarding reasons for wanting children was significantly different. Only 30 women among the total respondents gave consistent answers. Carrying on the family name was the category in which there was the highest rate of consistency. 5. The reasons for wanting children were not significantly different for age, educational level, and number of living children for all of the respondents. 6. In response to the question "If you want to have only one child, which sex , would you prefer\ulcorner" 96 percent of the respondents said they would select a son. 7. Major suggestions for further study were to differentiate. (1) between reasons women want children and reasons women have children and (2) between reasons men want children and reasons women want children.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.3 no.1
• /
• pp.25-31
• /
• 2011

These days, almost all of the embedded systems have microprocessors or micro-controllers in them as their brains. So microprocessor related subjects become very important and most engineering departments have those kinds of subjects in their curriculums with practice hours. However, in most universities in Korea, the number of students in a class is more than 40 and only one teaching assistant is assigned to the class. So it is very hard job to find out an appropriate method to evaluate the students' achievements in their practice hours fairly. In this study, the author introduces some suggestions for the evaluation of the students' achievements in microprocessor practice courses. In addition to it, the author also introduces some guidelines for contents of microprocessor related subjects.

• Bulletin of the Korean Chemical Society
• /
• v.35 no.7
• /
• pp.2057-2064
• /
• 2014

Thermochemical sulfate reduction (TSR) was conducted in autoclave on the system of crude oil and $MgSO_4$ at different temperatures. Gas chromatography pulsed flame photometric detector (GC-PFPD) was used to detected the composition of organic sulfur compounds in oil phase products. The results of the analysis indicate that with increased temperature, the contents of organic sulfur compounds with high molecular weight and thermal stability, such as benzothiophenes and dibenzothiophenes, gradually became dominated. In order to gain greater insight into the formation and distribution of organic sulphur compounds from TSR, positive ion electrospray Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) was used in detecting the detailed elemental composition and distribution of them. The mass spectra showed that the mass range of sulfur compounds was 200-550 Da. Four sulfur class species, $S_1$, $N_1S_1$, $O_1S_1$ and $O_2S_1$, were assigned in the positive-ion spectrum. Among the identified sulfur compounds, the $S_1$ class species was dominant. The most abundant $S_1$ class species increase associated with the DBE value and carbon number increasing which also indicates the evolution of organic sulfur compounds in TSR is from the labile series to the stable one. In pure blank pyrolysis experiments with crude oil cracking without TSR, different composition and distribution of organic sulfur compounds in oil phase products were seen from mass spectra in order to evaluate their pyrolysis behaviors without $MgSO_4$. FT-IR and XRD were used in analyzing the products of solid phases. Two distinct crystallographic phases MgO and $MgSO_4$ are found to coexist in the products which demonstrated the transformation of inorganic sulfur compounds into organosulfur compounds exist in TSR.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.1
• /
• pp.59-64
• /
• 2015

In this paper, we found the usefulness of the deep belief network (DBN) in the fields of brain-computer interface (BCI), especially in relation to imagined speech. In recent years, the growth of interest in the BCI field has led to the development of a number of useful applications, such as robot control, game interfaces, exoskeleton limbs, and so on. However, while imagined speech, which could be used for communication or military purpose devices, is one of the most exciting BCI applications, there are some problems in implementing the system. In the previous paper, we already handled some of the issues of imagined speech when using the International Phonetic Alphabet (IPA), although it required complementation for multi class classification problems. In view of this point, this paper could provide a suitable solution for vowel classification for imagined speech. We used the DBN algorithm, which is known as a deep learning algorithm for multi-class vowel classification, and selected four vowel pronunciations:, /a/, /i/, /o/, /u/ from IPA. For the experiment, we obtained the required 32 channel raw electroencephalogram (EEG) data from three male subjects, and electrodes were placed on the scalp of the frontal lobe and both temporal lobes which are related to thinking and verbal function. Eigenvalues of the covariance matrix of the EEG data were used as the feature vector of each vowel. In the analysis, we provided the classification results of the back propagation artificial neural network (BP-ANN) for making a comparison with DBN. As a result, the classification results from the BP-ANN were 52.04%, and the DBN was 87.96%. This means the DBN showed 35.92% better classification results in multi class imagined speech classification. In addition, the DBN spent much less time in whole computation time. In conclusion, the DBN algorithm is efficient in BCI system implementation.

• School Mathematics
• /
• v.12 no.4
• /
• pp.507-530
• /
• 2010

The purpose of this study was to help teachers for their teaching practice by analyzing the excellent lesson videos. To analyze the lesson videos between teacher and students, the researchers classified excellent lesson classes into four types as 'Discourse type', 'Representation type', 'Operation type' and 'Complex type' by mathematical communication pattern and kept close watch each lesson videos. Mathematical communication of the best discourse type classroom was analyzed in terms of questioning, explaining, and the sources of mathematical ideas. As a result, the number of Discourse type classes was 6. Operation type classes were 16 owing to characteristic of elementary class. Representation type class was 1 and Complex type class was 1. The Classes excluding Operation type was more planned by teachers. Teachers need to know about mathematical communication accurately because they designed just 5 lesson plan considering mathematical communication of students and only one of the lessons has the intellectual purpose of communication. Furthermore teachers should reflect questioning for student-to-student in their lesson plan.

• Journal of Biomedical Engineering Research
• /
• v.32 no.2
• /
• pp.134-143
• /
• 2011

The selection of meaningful clinical tests and its reference values from a high-dimensional clinical data with imbalanced class distribution, one class is represented by a large number of examples while the other is represented by only a few, is an important issue for differential diagnosis between similar diseases, but difficult. For this purpose, this study introduces methods based on the concepts of both discernibility matrix and function in rough set theory (RST) with two discretization approaches, equal width and frequency discretization. Here these discretization approaches are used to define the reference values for clinical tests, and the discernibility matrix and function are used to extract a subset of significant clinical tests from the translated nominal attribute values. To show its applicability in the differential diagnosis problem, we have applied it to extract the significant clinical tests and its reference values between normal (N = 351) and abnormal group (N = 101) with either cholecystitis or cholelithiasis disease. In addition, we investigated not only the selected significant clinical tests and the variations of its reference values, but also the average predictive accuracies on four evaluation criteria, i.e., accuracy, sensitivity, specificity, and geometric mean, during l0-fold cross validation. From the experimental results, we confirmed that two discretization approaches based rough set approximation methods with relative frequency give better results than those with absolute frequency, in the evaluation criteria (i.e., average geometric mean). Thus it shows that the prediction model using relative frequency can be used effectively in classification and prediction problems of the clinical data with imbalanced class distribution.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.11
• /
• pp.159-165
• /
• 2013

This paper proposes a O(E) polynomial-time algorithm that has been devised to simultaneously solve edge-coloring problem and graph classification problem both of which remain NP-complete. The proposed algorithm selects an edge connecting maximum and minimum degree vertices so as to determine the number of edge coloring ${\chi}^{\prime}(G)$. Determined ${\chi}^{\prime}(G)$ is in turn either ${\Delta}(G)$ or ${\Delta}(G)+1$. Eventually, the result could be classified as class 1 if ${\chi}^{\prime}(G)={\Delta}(G)$ and as category 2 if ${\chi}^{\prime}(G)={\Delta}(G)+1$. This paper also proves Vizing's planar graph conjecture, which states that 'all simple, planar graphs with maximum degree six or seven are of class one, closing the remaining possible case', which has known to be NP-complete.