• Journal of Korea Entertainment Industry Association
• /
• v.13 no.2
• /
• pp.145-154
• /
• 2019

The purpose of this study is to investigate the performance, learning motivation and satisfaction of the students who take the university 's Lifelong Education Program. The research method was interviewed. The results are as follows. In terms of operations; First, the awareness of the kindness of employees of the college lifelong education institute needs to be strengthened at the beginning of the school year. Second, in the operation of the College Lifelong Education Center, the support such as the parking fee should be extended to the students. Third, lifelong education facilities should be supplemented. In terms of participation motivation; First, it can be seen that there are the most learners who want to do complementary learning. Most of them are people who look back on their lives and prepare for their future directions. Second, as the life span of human beings became longer, the economic preparation for life became necessary. Thus, all learning tends to be perceived as a preparation for economic income. Third, most people who participate in lifelong education are very interested in health. Therefore, it is necessary to increase the motivation for participation by expanding health related programs. In terms of satisfaction; First, it depends on the purpose of the individual. Satisfaction was high for those who aimed at hobbies and relationships, and satisfaction for those who aimed for economic activities was low. Second, it is also necessary to consider the instructor 's instructional process. In other words, lifelong learners tend to be adults, so little complaints are not revealed. Therefore, I would like to ask the lecturers to advance the education for the class. The implications for the improvement direction of the lifelong education center are as follows; First, we need to drastically reduce the number of programs overlapping with other universities and conduct research to develop new programs. In order to do this, it is necessary to continuously carry out a survey of demanders' needs. Second, it is necessary to find the appropriate place for program operation considering the movement distance of learners. It should be avoided that the program should be operated with the existing university facilities. Third, universities' lifelong education should go to education that includes college students.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.3
• /
• pp.181-192
• /
• 2019

The purpose of this study is to look at the fun that high school students from blind schools feel in sports programs. A questionnaire was used to collect data from 10 out of 12 blind schools nationwide, including 122 male and 102 female students. Research tools are open questionnaires and questions are as follows. - Questionnaire: "Write down three of the most interesting things about sports programs." The data analysis was done with frequency analysis and the following conclusions were drawn. First, male high school students at blind schools are able to build up their physical strength in the area of competent factors (control-self) (23, 21.5%), in the area of competent factors (7, 77.8%) and in the area of motion-related factors (competition) (24, 15.1%), and in the area of non-execution factors (26, 37.7%), Second, high school girls with visual impairments did not respond in the areas of proficiency (control-self) because of stress release (25, 26.6%), in the areas of control-tain), in the areas of movement (competition) because they were able to do various exercises (22, 15.7%), and in the areas of non-watering (environmental) (18, 37.5%). Third, in the sports program comparative analysis of high school students between genders of blind schools, boys are interested in health and physical fitness in the field of competent factors (control-self) and girls are considered to be a means of relieving stress. In the field of competent factors (control-others), boys and girls can react to a variety of sports opportunities. In the future, by studying the fun of students in the physical education program through research to find out more fun in the school physical education program, we will explore practical ways to maximize student participation and increase motivation level The educational aspect of the process, that is, the educational value provided by the physical education, should be composed of content that can change the thinking and behavior of the teacher and the student so that the program contents and operation method.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.589-597
• /
• 2023

Floating debris in large quantities from land during heavy rainfall has adverse social, economic, and environmental impacts, but the monitoring system for the concentration area and amount is insufficient. In this study, we proposed an efficient monitoring method for floating debris entering the river during heavy rainfall in Daecheong Lake, the largest water supply source in the central region, and applied remote sensing techniques to estimate the standing-stock of floating debris. To investigate the status of floating debris in the upper of Daecheong Lake, we used a tracking buoy equipped with a low-orbit satellite communication terminal to identify the movement route and behavior characteristics, and used a drone to estimate the potential concentration area and standing-stock of floating debris. The location tracking buoys moved rapidly during the period when the cumulative rainfall for 3 days increased by more than 200 to 300 mm. In the case of Hotan Bridge, which showed the longest distance, it moved about 72.8 km for one day, and the maximum moving speed at this time was 5.71 km/h. As a result of calculating the standing-stock of floating debris using a drone after heavy rainfall, it was found to be 658.8 to 9,165.4 tons, with the largest amount occurring in the Seokhori area. In this study, we were able to identify the main concentrations of floating debris by using location-tracking buoys and drones. It is believed that remote sensing-based monitoring methods, which are more mobile and quicker than traditional monitoring methods, can contribute to reducing the cost of collecting and processing large amounts of floating debris that flows in during heavy rain periods in the future.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.13 no.1
• /
• pp.42-55
• /
• 2008

To evaluate the accuracy of currents measured by HF radar in the coastal sea off Keum River estuary, we compared the facing radial vectors of two HF radars, and HF radar-derived currents with in-situ measurement currents. Principal component analysis was used to extract regression line and RMS deviation in the comparison. When two facing radar's radial vectors at the mid-point of baseline are compared, RMS deviation is 4.4 cm/s in winter and 5.4 cm/s in summer. When GDOP(Geometric Dilution of Precision) effect is corrected from the RMS deviations that is analyzed from the comparison between HF radar-derived and current-metermeasured currents, the error of velocity combined by HF radar-derived current is less than 5.1 cm/s in the stations having moderate GDOP values. These two results obtained from different method suggest that the lower limit of HF radar-derived current's accuracy is 5.4 cm/s in our study area. As mentioned in previous researches, RMS deviations become large in the stations located near the islands and increase as a function of mean distance from the radar site due to decrease of signal-to-noise level and the intersect angle of radial vectors. We found that an uncertain error bound of HF radar-derived current can be produced from the separation process of RMS deviations using GDOP value if GDOP value for each component is very close and RMS deviations obtained from current component comparison are also close. When the current measured in the stations having moderate GDOP values is separated into tidal and subtidal current, characteristics of tidal current ellipses analyzed from HF radar-derived current show a good agreement with those from current-meter-measured current, and time variation of subtidal current showed a response reflecting physical process driven by wind and density field.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.47-67
• /
• 2017

Steel plate faults is one of important factors to affect the quality and price of the steel plates. So far many steelmakers generally have used visual inspection method that could be based on an inspector's intuition or experience. Specifically, the inspector checks the steel plate faults by looking the surface of the steel plates. However, the accuracy of this method is critically low that it can cause errors above 30% in judgment. Therefore, accurate steel plate faults diagnosis system has been continuously required in the industry. In order to meet the needs, this study proposed a new steel plate faults diagnosis system using Simultaneous MTS (S-MTS), which is an advanced Mahalanobis Taguchi System (MTS) algorithm, to classify various surface defects of the steel plates. MTS has generally been used to solve binary classification problems in various fields, but MTS was not used for multiclass classification due to its low accuracy. The reason is that only one mahalanobis space is established in the MTS. In contrast, S-MTS is suitable for multi-class classification. That is, S-MTS establishes individual mahalanobis space for each class. 'Simultaneous' implies comparing mahalanobis distances at the same time. The proposed steel plate faults diagnosis system was developed in four main stages. In the first stage, after various reference groups and related variables are defined, data of the steel plate faults is collected and used to establish the individual mahalanobis space per the reference groups and construct the full measurement scale. In the second stage, the mahalanobis distances of test groups is calculated based on the established mahalanobis spaces of the reference groups. Then, appropriateness of the spaces is verified by examining the separability of the mahalanobis diatances. In the third stage, orthogonal arrays and Signal-to-Noise (SN) ratio of dynamic type are applied for variable optimization. Also, Overall SN ratio gain is derived from the SN ratio and SN ratio gain. If the derived overall SN ratio gain is negative, it means that the variable should be removed. However, the variable with the positive gain may be considered as worth keeping. Finally, in the fourth stage, the measurement scale that is composed of selected useful variables is reconstructed. Next, an experimental test should be implemented to verify the ability of multi-class classification and thus the accuracy of the classification is acquired. If the accuracy is acceptable, this diagnosis system can be used for future applications. Also, this study compared the accuracy of the proposed steel plate faults diagnosis system with that of other popular classification algorithms including Decision Tree, Multi Perception Neural Network (MLPNN), Logistic Regression (LR), Support Vector Machine (SVM), Tree Bagger Random Forest, Grid Search (GS), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The steel plates faults dataset used in the study is taken from the University of California at Irvine (UCI) machine learning repository. As a result, the proposed steel plate faults diagnosis system based on S-MTS shows 90.79% of classification accuracy. The accuracy of the proposed diagnosis system is 6-27% higher than MLPNN, LR, GS, GA and PSO. Based on the fact that the accuracy of commercial systems is only about 75-80%, it means that the proposed system has enough classification performance to be applied in the industry. In addition, the proposed system can reduce the number of measurement sensors that are installed in the fields because of variable optimization process. These results show that the proposed system not only can have a good ability on the steel plate faults diagnosis but also reduce operation and maintenance cost. For our future work, it will be applied in the fields to validate actual effectiveness of the proposed system and plan to improve the accuracy based on the results.

• Tuberculosis and Respiratory Diseases
• /
• v.64 no.6
• /
• pp.433-438
• /
• 2008

Background: Measurement of the maximum oxygen uptake in patients with chronic obstructive pulmonary disease (COPD) has been used to determine the intensity of exercise and to estimate the patient's response to treatment during pulmonary rehabilitation. However, cardiopulmonary exercise testing is not widely available in Korea. The 6-minute walk test (6MWT) is a simple method of measuring the exercise capacity of a patient. It also provides high reliability data and it reflects the fluctuation in one' s exercise capacity relatively well with using the standardized protocol. The prime objective of the present study is to develop a regression equation for estimating the peak oxygen uptake ($VO_2$) for men with moderate to very severe COPD from the results of a 6MWT. Methods: A total of 33 male patients with moderate to very severe COPD agreed to participate in this study. Pulmonary function testing, cardiopulmonary exercise testing and a 6MWT were performed on their first visits. The index of work ($6M_{work}$, 6-minute walk distance [6MWD]${\times}$body weight) was calculated for each patient. Those variables that were closely related to the peak $VO_2$ were identified through correlation analysis. With including such variables, the equation to predict the peak $VO_2$ was generated by the multiple linear regression method. Results: The peak $VO_2$ averaged $1,015{\pm}392ml/min$, and the mean 6MWD was $516{\pm}195$ meters. The $6M_{work}$ (r=.597) was better correlated to the peak $VO_2$ than the 6MWD (r=.415). The other variables highly correlated with the peak $VO_2$ were the $FEV_1$ (r=.742), DLco (r=.734) and FVC (r=.679). The derived prediction equation was $VO_2$ (ml/min)=($274.306{\times}FEV_1$)+($36.242{\times}DLco$)+($0.007{\times}6M_{work}$)-84.867. Conclusion: Under the circumstances when measurement of the peak $VO_2$ is not possible, we consider the 6MWT to be a simple alternative to measuring the peak $VO_2$. Of course, it is necessary to perform a trial on much larger scale to validate our prediction equation.

• Journal of Korean Society of Forest Science
• /
• v.66 no.1
• /
• pp.16-36
• /
• 1984

It is very important in forestry to study the shear strength of weathered granitic soil, because the soil covers 66% of our country, and because the majority of land slides have been occured in the soil. In general, the causes of land slide can be classified both the external and internal factors. The external factors are known as vegetations, geography and climate, but internal factors are known as engineering properties originated from parent rocks and weathering. Soil engineering properties are controlled by the skeleton structure, texture, consistency, cohesion, permeability, water content, mineral components, porosity and density etc. of soils. And the effects of these internal factors on sliding down summarize as resistance, shear strength, against silding of soil mass. Shear strength basically depends upon effective stress, kinds of soils, density (void ratio), water content, the structure and arrangement of soil particles, among the properties. But these elements of shear strength work not all alone, but together. The purpose of this thesis is to clarify the characteristics of shear strength and the related elements, such as water content ($w_o$), void ratio($e_o$), dry density (${\gamma}_d$) and specific gravity ($G_s$), and the interrelationship among related elements in order to decide the dominant element chiefly influencing on shear strength in natural/undisturbed state of weathered granitic soil, in addition to the characteristics of soil hardness of weathered granitic soil and root distribution of Pinus rigida Mill and Pinus rigida ${\times}$ taeda planted in erosion-controlled lands. For the characteristics of shear strength of weathered granitic soil and the related elements of shear strength, three sites were selected from Kwangju district. The outlines of sampling sites in the district were: average specific gravity, 2.63 ~ 2.79; average natural water content, 24.3 ~ 28.3%; average dry density, $1.31{\sim}1.43g/cm^3$, average void ratio, 0.93 ~ 1.001 ; cohesion, $ 0.2{\sim}0.75kg/cm^2$ ; angle of internal friction, $29^{\circ}{\sim}45^{\circ}$ ; soil texture, SL. The shear strength of the soil in different sites was measured by a direct shear apparatus (type B; shear box size, $62.5{\times}20mm$; ${\sigma}$, $1.434kg/cm^2$; speed, 1/100mm/min.). For the related element analyses, water content was moderated through a series of drainage experiments with 4 levels of drainage period, specific gravity was measured by KS F 308, analysis of particle size distribution, by KS F 2302 and soil samples were dried at $110{\pm}5^{\circ}C$ for more than 12 hours in dry oven. Soil hardness represents physical properties, such as particle size distribution, porosity, bulk density and water content of soil, and test of the hardness by soil hardness tester is the simplest approach and totally indicative method to grasp the mechanical properties of soil. It is important to understand the mechanical properties of soil as well as the chemical in order to realize the fundamental phenomena in the growth and the distribution of tree roots. The writer intended to study the correlation between the soil hardness and the distribution of tree roots of Pinus rigida Mill. planted in 1966 and Pinus rigida ${\times}$ taeda in 199 to 1960 in the denuded forest lands with and after several erosion control works. The soil texture of the sites investigated was SL originated from weathered granitic soil. The former is situated at Py$\ddot{o}$ngchangri, Ky$\ddot{o}$m-my$\ddot{o}$n, Kogs$\ddot{o}$ng-gun, Ch$\ddot{o}$llanam-do (3.63 ha; slope, $17^{\circ}{\sim}41^{\circ}$ soil depth, thin or medium; humidity, dry or optimum; height, 5.66/3.73 ~ 7.63 m; D.B.H., 9.7/8.00 ~ 12.00 cm) and the Latter at changun-long Kwangju-shi (3.50 ha; slope, $12^{\circ}{\sim}23^{\circ}$; soil depth, thin; humidity, dry; height, 10.47/7.3 ~ 12.79 m; D.B.H., 16.94/14.3 ~ 19.4 cm).The sampling areas were 24quadrats ($10m{\times}10m$) in the former area and 12 in the latter expanding from summit to foot. Each sampling trees for hardness test and investigation of root distribution were selected by purposive selection and soil profiles of these trees were made at the downward distance of 50 cm from the trees, at each quadrat. Soil layers of the profile were separated by the distance of 10 cm from the surface (layer I, II, ... ...). Soil hardness was measured with Yamanaka soil hardness tester and indicated as indicated soil hardness at the different soil layers. The distribution of tree root number per unit area in different soil depth was investigated, and the relationship between the soil hardness and the number of tree roots was discussed. The results obtained from the experiments are summarized as follows. 1. Analyses of simple relationship between shear strength and elements of shear strength, water content ($w_o$), void ratio ($e_o$), dry density (${\gamma}_d$) and specific gravity ($G_s$). 1) Negative correlation coefficients were recognized between shear strength and water content. and shear strength and void ratio. 2) Positive correlation coefficients were recognized between shear strength and dry density. 3) The correlation coefficients between shear strength and specific gravity were not significant. 2. Analyses of partial and multiple correlation coefficients between shear strength and the related elements: 1) From the analyses of the partial correlation coefficients among water content ($x_1$), void ratio ($x_2$), and dry density ($x_3$), the direct effect of the water content on shear strength was the highest, and effect on shear strength was in order of void ratio and dry density. Similar trend was recognized from the results of multiple correlation coefficient analyses. 2) Multiple linear regression equations derived from two independent variables, water content ($x_1$ and dry density ($x_2$) were found to be ineffective in estimating shear strength ($\hat{Y}$). However, the simple linear regression equations with an independent variable, water content (x) were highly efficient to estimate shear strength ($\hat{Y}$) with relatively high fitness. 3. A relationship between soil hardness and the distribution of root number: 1) The soil hardness increased proportionally to the soil depth. Negative correlation coefficients were recognized between indicated soil hardness and the number of tree roots in both plantations. 2) The majority of tree roots of Pinus rigida Mill and Pinus rigida ${\times}$ taeda planted in erosion-controlled lands distributed at 20 cm deep from the surface. 3) Simple linear regression equations were derived from indicated hardness (x) and the number of tree roots (Y) to estimate root numbers in both plantations.

• Journal of Korean Academy of Nursing
• /
• v.8 no.1
• /
• pp.16-42
• /
• 1978

This survey was made for a month starting from November 15 to December 15, 1977 covering 711 students taking the junior. (3rd-yea.) and the senior. (4th-year) at nine college of nursing in Seoul concerning their perception and Attitude toward the profession of nursing, motive for the necessity of learning, environment of study, attitude of study and particulars relevant with study performance, particulars of library, references and reading, assignments and particulars of the degree of confidence for the learning achievement. Through the survey of the above Particulars, the following results were obtained by classifying all subject matters and by analysing motive of the selection of their course, awarding or not awarding of scholarships. 1. General characteristics: it was revealed that 406 students (57.1%) were attending at the junior. while 305 students (42.9%) were taking the senior. Thus, the total number was 711 and their average age was 21.4 years. Their dwelling category was; 73.9 percent of them resided at their parent's home, 214 students (30.1%) were awarded with scholarships. The reason to be attracted by nursing science was the possibility of continuing social life after graduation (43.5%). 2. Their perception and attitude toward the profession of nursing: According to the perception of profession by the students of each grade, students of the 4th grade showed comparatively strong conception. Also, students of the 4th grade showed more positive attitude in the purchase and reading of magazines relative with the science of nursing, in the reading of Code for Nurses and in their interest in the activity of nursing field. For the necessity of mission of nurse, 97.7 percent of the entire number of students covered responded to necessity. For the necessity of the particular humanity and particularity in the character of nurses, 95.8 percent of those students responded to necessity. By the each grade, students of the 4th grade showed more response. 3. As to professional field desired after completing the professional course: 57 percent of those students desired for clinician nurse while 55 percents desired for community health-nurse. 4. As to the environment of study: they were mostly satisfied with their present residential environment. However, they complained of inconvenience at their lecture-halls. Students of the 3rd grade showed more complain. As to their attitude toward the adjustment of environment of study, they showed a affirmative response. As to the opinion of factors which interfere with their study, comparatively strong response was showed in their scepticism in the science of nursing, insufficient comprehension in general learning, relation with professors n4 discrepancy in the method of study. According to opinions of students at each grade, students of the 4th grade showed more scepticism. 5. Particulars relative with their attitude and performance of study : As to their knowledge of the objectives of their study of subject, the majority was to study with a partial knowledge of the objectives of their study. As to the plan of study, a low percentage indicated management of routine life under regular scheduling. Students of the 4th grade responded to rather planned life. As to time spent in independent study, response to concentrated study when necessary was stronger than that to regular daily study. Students of the 4th grade showed stronger response to regular study than that of the 3rd grade. As to the contents of their note-taking, 67.4 percents of those students responded to such regulatory procedure performing in the lecture-hall as they listen to lectures. 17.3 percents of those students showed response to adding supplementary informations from references to what was entered in choir note-taking at their lecture-halls. 6. Particulars of library, references and reading books: As to receiving of instruction for the utilization of library and time of receiving such instruction 64.7 percents of those students had received such instruction. 66.7 percents of the those responded received such instruction at orientation conducted for freshmen. As to the convenience of the utilization of library, 49.9 percents of those students responded to convenience. However, students of the 3rd grade showed a much stronger response to inconvenience. As to the time of the utilization of library,92.5 percents of those students showed a response to occasional utilization for particular purpose than regular utilization. 53.2 percents of those students responded to ordinary in quantity that library have references. 34.2 percents of those students responded to insufficient. As to the particular relative with the method and field of reading: 53.5 percents of those students responded to intensive reading and was the majority. As to the reading field, fiction u as the majority. When read any books for their major, they usually rend Korean text-b, oks. 7. Particular relative with giving assignment: All respondents were well aware of the objectives of giving home tasks. As to the attitude toward assignments and performing home tasks, 54.8 percents of those students to making ostentatious study because of an excessive quantity of assignments imposed. For performing assignment, they showed comparatively positive response. Also, 52.2 percents of those students responded that they usually submitted complected assignment with references. 8. As to motive to realize the necessity of study : 55.6 percents of those students responded that they realized such necessity in communication with patients when they were engaged in clinical practice. Also, 8.6, the lowest percents of those students responded that they realized such necessity in the course of conversation with nurses when they were engaged in clinical practice. 9. As to the determination of their confidence in the performance of study relative with clinical experience: They showed a general inclination of having in nursing. The major response was that they came to well comprehend the patients families. the lowest response was that they could apply what was learned at lecture-hall to practice. This response incidentally showed the distance the lecture-hall and practical study. In general items, students of the 4th grade showed more favorable response than students of the 3rd grade and there was a significant difference. 10. As to the perception and attitude toward profession according to the motive of selecting the nursing science : Those who selected the nursing voluntarily showed stronger conception than those who selected the nursing through indirect influence. However, there was no significant difference on this point. Only there was a remarkable difference in the reading of Code for Nurses. 11. Those who showed a stronger conception in the profession of nursing according to the motives of attractive nursing science indicated a strong will and ability to manage stable life and comparatively strong response was shown in the management of good home life because of the good adaptability of the science to their character. This group showed a strong conception of the profession than those who responded that they prefer this profession out of a longing for the work of a hospital and for the easy obtaining of opportunity to immigrate to over seas and for economic cause and for high school grade. There was significant difference between these two groups, 12. As to the conception and attitude toward the profession of nursing according to benefits by scholarships, those who were benefitted by scholarship showed stronger conception of profession than those who did not receive scholarship and there was a remarkable difference between these two categories. However, there was no remarkable difference between these two categories in the extent of interest of the activities of nursing fields and in the reading of Code for Nurses. 13. As activation for study according to the benefits of scholarships, those who were benefitted by scholarships showed stronger response to the motive for study comparing with those who receive. 14. As to tile field of reading according to the benefits by scholarships, those who received scholarships tended to read autobiographies and essayers to a considerable extent. Those who did not receive scholarships tended to read novels. Those who received scholarships more read nursing boots than those who did not receive scholarships. 15. As to the attitude of study and doing of assignment according to benefits of scholarships, those who received scholarships managed a favorable life with schedules for study, More students of receiving scholarship showed a regular study for more than one hour per day. Also, in the method of doing home tasks, more students of receiving scholarship showed reference to relative books frequently for the submission of completed assignments.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.