• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.183-190
• /
• 2016

This paper proposes algorithm to reduce the computing time in a neural network that reduces transmission of data for tracking mobile objects in surveillance networks in terms of detection and communication load. Object Detection can be defined as follows : Given image sequence, which can forom a digitalized image, the goal of object detection is to determine whether or not there is any object in the image, and if present, returns its location, direction, size, and so on. But object in an given image is considerably difficult because location, size, light conditions, obstacle and so on change the overall appearance of objects, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact object detection which overcomes some restrictions by using neural network. Proposed system can be object detection irrelevant to obstacle, background and pose rapidly. And neural network calculation time is decreased by reducing input vector size of neural network. Principle Component Analysis can reduce the dimension of data. In the video input in real time from a CCTV was experimented and in case of color segment, the result shows different success rate depending on camera settings. Experimental results show proposed method attains 30% higher recognition performance than the conventional method.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.2
• /
• pp.47-53
• /
• 2018

This paper proposes a method to express an MP3 audio file by a series of color QR codes which can be printed on the paper. Moreover, the method can compress the data considerably. Firstly, an MP3 file is divided into many small files which have maximum capacity of binary file of a QR code. Secondly, the multiple files are converted to multiple black-and-white QR codes. Lastly, every three QR codes are combined into color QR codes. When combining, each of three black-and-white QR codes are regarded as red, green, blue components respectively. In this method, the areas of a color QR code where two QR codes are overlapped are expressed by the colors Cyan, Magenta and Yellow. And the areas where three components are overlapped are expressed by white color. Contrarily, the areas that no components are overlapped are expressed by white color. Experimentation result shows that an MP3 file with 8.5MB the original MP3 files are compressed with the compression rate around 15.7. This method has the advantage that can be used in the environments that the internet access is impossible.

• Journal of dental hygiene science
• /
• v.9 no.5
• /
• pp.485-490
• /
• 2009

The purpose of this study was to obtain basic data for improvement about oral health education, contents and method for college and university students. A question was used 10 questionnaire by 332 college and university students in the Tae gu-city and Gu mi-city. In conclusion, 1. They answered that dental caries cause is 'No-brushing'(88.3%). The man respondents answered that the cause of periodontal disease is 'weak disease'(39.2%). 2. The reason about visit to dental clinic is 'for treatment'(72.0%) and they answered that the tooth is 'very important in their life'(82.5%). 3. They answered that the frequency of tooth-brushing is 'two times in a day'(44.8%) and using auxiliary oral hygiene material is 'dental floss' by male(15.2%) and female(16.6%). 4. In the case of high oral health knowledge level showed high response rate about level of oral health attitude and oral health recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.2
• /
• pp.30-36
• /
• 2000

The hidden node plays a role of the functional units that classifies the features of input pattern in the given question. Therefore, a neural network that consists of the number of a suitable optimum hidden node has be on the rise as a factor that has an important effect upon a result. However there is a problem that decides the number of hidden nodes based on back-propagation learning algorithm. If the number of hidden nodes is designated very small perfect learning is not done because the input pattern given cannot be classified enough. On the other hand, if designated a lot, overfitting occurs due to the unnecessary execution of operation and extravagance of memory point. So, the recognition rate is been law and the generality is fallen. Therefore, this paper suggests a method that decides the number of neural network node with feature information consisted of the parameter of learning algorithm. It excludes a node in the Pruning target, that has a maximum value among the feature value obtained and compares the average of the rest of hidden node feature value with the feature value of each hidden node, and then would like to improve the learning speed of neural network deciding the optimum structure of the multi-layer neural network as pruning the hidden node that has the feature value smaller than the average.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.4
• /
• pp.138-147
• /
• 2007

Metabolic pathway is a series of chemical reactions occuning within a cell and can be used for drug development and understanding of life phenomenon. Many biologists are trying to extract metabolic pathway information from huge literatures for their metabolic-circuit regulation study. We propose a text-mining technique based on the keyword and pattern. Proposed technique utilizes a web robot to collect huge papers and stores them into a local database. We use gene ontology to increase compound recognition rate and NCBI Tokenizer library to recognize useful information without compound destruction. Furthermore, we obtain useful sentence patterns representing metabolic pathway from papers and KEGG database. We have extracted 66 patterns in 20,000 documents for Glycosphingolipid species from KEGG, a representative metabolic database. We verify our system for nineteen compounds in Glycosphingolipid species. The result shows that the recall is 95.1%, the precision 96.3%, and the processing time 15 seconds. Proposed text mining system is expected to be used for metabolic pathway reconstruction.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.970-976
• /
• 2007

In this study, Polynomial Network Pattern Classifier(PNC) based on Fuzzy Inference Mechanism is designed and its parameters such as learning rate, momentum coefficient and fuzzification coefficient are optimized by means of Particle Swarm Optimization. The proposed PNC employes a partition function created by Fuzzy C-means(FCM) clustering as an activation function in hidden layer and polynomials weights between hidden layer and output layer. Using polynomials weights can help to improve the characteristic of the linear classification of basic neural networks classifier. In the viewpoint of linguistic analysis, the proposed classifier is expressed as a collection of "If-then" fuzzy rules. Namely, architecture of networks is constructed by three functional modules that are condition part, conclusion part and inference part. The condition part relates to the partition function of input space using FCM clustering. In the conclusion part, a polynomial function caries out the presentation of a partitioned local space. Lastly, the output of networks is gotten by fuzzy inference in the inference part. The proposed PNC generates a nonlinear discernment function in the output space and has the better performance of pattern classification as a classifier, because of the characteristic of polynomial based fuzzy inference of PNC.

• Journal of agricultural medicine and community health
• /
• v.23 no.2
• /
• pp.175-192
• /
• 1998

This study was performed investigate the opinion of civil servants in Health center about Rural Health Service Improvement Project The survey by mail was carried out for 447 servants of 25 health centers in Kyungsangbuk-do and the data were collected through self-administered questionnaires to servants about need, participation, concern, and comprehension for the project and satisfied with current facility and equipment of health center. The results were as follows. Generally considered, 48.2% of the improved health center servants was satisfied with health center building and 14.0% or 24.1% of the improving or unimproved center was. About the location of health center, 37.7% of the improved health center servants was satisfied, 25.9% of the unimproved center was. Of the improved health center servants, 43% was satisfied with the medical equipment but in unimproved place, the dissatisfaction was appeared higher than any other place. 49.7% of respondents was participated in making out the Rural Health Service Improvement Project. 50.6% was interested in this project. In the improved area. 65.5% of health center servants replied that the mayor's or county executive's concern about this project was high and 46.5% in councilors but in the unimproved area. their concern was low. About the contents of the project. 24,6% of the servants in the improved center, only 15.2% in unimproved center replied that they had known well. After making out the plan, 13.6% of respondents was unsatisfied with this plan and 17.1% replied that the estimating method of selecting the project area was not good. After the improvement of institution and equipment, 86.1% of health center servants answered that the medical service provided by health center would increase but 59.2% replied that the residents' utilization rate of private medical facility would decrease. The servants of the improved health center replied that the recognition about the developing will of health service(91.2%), the efficiency(91.2%), the quality of health and medical service(93.0%), the amount of health project(91.2%) were improved. In health center which had already improved the institution and equipment, 88.5% of servants replied that the residents' utilization for health center was increased. So, this project should be continuously carried out for health center and health center must develope new project to fit region condition.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.40-47
• /
• 2009

This paper proposes a method for vehicle license plate detection using mathematical morphology and symmetry. In general, the shape, color, size, and position of license plate are regulated by authorities for a better recognition by human. Among them, the relatively big intensity difference between the letter and the background region of the license plate and the symmetry about the plate are major discriminating factors for the detection. For the first, the opened image is subtracted from the closed image to intensify the region of plate using the rectangular structuring element which has the width of the distance between two characters. Second the subtraction image is average filtered with the mask size of the plate. Third, the column maximum graph of the average filtered image is acquired and the symmetry of the graph is measured at every position. Fourth, the peaks of the average filtered image are searched. Finally, the plate is assumed to be positioned around the one of local maxima nearest to the point of the highest symmetry. About 1,000 images taken by speed regulation camera are used for the experiment. The experimental result shows that the plate detection rate is about 93%.

• Korean Journal of Community Nutrition
• /
• v.11 no.5
• /
• pp.608-617
• /
• 2006

This study compared the food habits and attitudes towards dietary life culture in types of feeding management, gender and grade. The subjects were 352 elementary school students who lived in Seocheon, Chungnam. The independently managed school students were better than jointly managed school students in food habits (p<0.05). In skipping school meals, upper grade students were skipped more than lower grade students (p<0.05). In rate of eating school meals, boys were faster than girls (p<0.001). The independently managed school students and the jointly managed school students were different on distasteful food. Boys disliked vegetables and girls disliked cereals and beans (p<0.05). Upper grade students ate more well-balanced meals than lower grade students (p<0.05). As for the question 'what you will do if the distasteful foods are provided through school meals', they responded. the highest percent of students, 'I will try once or twice'. And the response 'I have them for health' was higher independently in managed school students than the jointly managed school students (p<0.05), girls than boy (p<0.05), and the lower grades than the upper grades (p<0.05). As for the question 'what you will do if the distasteful foods are provided, after the guide for school meals was performed', the response, 'I will make an effort to have it' accounted for the highest percents, and there were differences in lower grade students who were high percents than upper grade students (p<0.01). As for the recognition for unbalanced diets, most of the students recognized that it is a 'bad habit'; the girl students accounted for more percentage than boys (p<0.05). The criterion of food choice were different in gender and grade (p<0.01). As for the factor of influences for the food habits formation, lower grade students were 'school education' and upper grade students were 'parents' (p<0.05). Thus, the systematic guide for proper intakes of nutrition should be performed. Also, the time when students can be educated by an expert of nutritional education, which is connected with school meals and students can grow healthily.

• Journal of the Korean Home Economics Association
• /
• v.30 no.1
• /
• pp.179-198
• /
• 1992

The purspoe of this study is to identify the socialization level of household work of the employed and unemployed housewives and it's related variables in order to provide some fundamental information for the rational and effective performation of the household task. For the purpose of this study, 700 questionnaire were distributed to the employed and unemployed wives who lived in Seoul. The data were analyed by the Frequency distribution, Percentile, t-test, F-test, Duncan's Multiple Range Test, and Multiple Regression Analysis. The main results were as follows : (1) Socialization level of household work of the employed wives was a little below medium point. When the household work was devided into three subdomains, in the domain of food and shelter, the socialization level was far below medium point. In the domain of clothes, the socialization level was a little higher than medium point. Socialization level of household work of the unemployed wives far below average. When the household work was devided into three sudbomains, in the domain of food, clothes and shelter, the socialization level was far below average, too. Socialization level of household work was significantly different according to the employment. (2) Among the background veriables, family income, household work helper, and frequency of leisure activities have a significant influence on the socialization level of the employed wives. Duration of marriage, housewife's education level and house income have a important effect on the socialization level of the unemployed wives background. (3) Among the background variabels of household work, performing competence of household work is powerful effect on the socialization level of the employed wives. And as for the unemployed wives, performing competence of household task and recognition of the velue of household work are significant variables. (4) The psychological variable such as sex-role attitude gave no noticeable influence on the socialization level of employed and unemployed wives. (5) In conclusion, classifing the variances influencing on the socialization level of household work in a measure of respcetive effect, it appears to be performing competence of household task, frequency of leisure activities, house income, sex-role attitued and educational level in the order of their influences for the employed wives. And as for the unemployed wives, it seems to be house income, educational level, performing competence of household work and frequency of leisure activities. To the two sides, the rate of explanation is shown at 35%.