• Journal of The Korean Association of Information Education
• /
• v.7 no.2
• /
• pp.219-226
• /
• 2003

It takes a lot of time to classify official documents in schools and educational institutions. In order to reduce the overhead, we propose an automatic document classification method using word information of the titles of documents in this paper. At first, meaningful words are extracted from titles of existing documents and Inverse Document Frequency(IDF) weights of words are calculated against each category. Then we build a word weight dictionary. Documents are automatically classified into the appropriate category of which the sum of weights of words of the title is the highest by using the word weight dictionary. We also evaluate the performance of the proposed method using a real dataset of a middle school.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 1998.05a
• /
• pp.307-312
• /
• 1998

In forklift operations, awkward postures due to backward driving may put drivers to the risk of CTD or low back pain. In this research, 6 forklift drivers were surveyed with OWAS for objective posture evaluation and bodymaps for self-report evaluation. The backward driving happened more frequently than forward driving as expected, and, as work hours passed by, the drivers naturally tended to assume the easier work postures in inverse proportion to the frequency of the backward operations. According to the results of OWAS, 60 % of the work postures in the forklift operations belonged to the category II, III, and IV classified serious. Especially, in the backward driving, the postures with the neck twisted over $45^{\circ}$ occupied 82.4 %. In addition, discomfort on the neck, left shoulder, and low back was frequently reported in the self-reports.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.359-366
• /
• 2021

A number of construction companies in Korea invest considerable human and financial resources to construct a system for managing apartment defect data and for categorizing repair tasks. Thus, this study proposes machine learning models to automatically classify defect complaint text-data into one of the sub categories of 'finishing work' (i.e., one of the defect repair tasks). In the proposed models, we employed two word representation methods (Bag-of-words, Term Frequency-Inverse Document Frequency (TF-IDF)) and two machine learning classifiers (Support Vector Machine, Random Forest). In particular, we conducted both binary- and multi- classification tasks to classify 9 sub categories of finishing work: home appliance installation work, paperwork, painting work, plastering work, interior masonry work, plaster finishing work, indoor furniture installation work, kitchen facility installation work, and tiling work. The machine learning classifiers using the TF-IDF representation method and Random Forest classification achieved more than 90% accuracy, precision, recall, and F1 score. We shed light on the possibility of constructing automated defect classification systems based on the proposed machine learning models.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.9
• /
• pp.918-922
• /
• 2015

As international environmental regulations for pollutant and greenhouse gas emissions discharged from ships are being reinforced, it is drawing attention to use LNG as ship fuel. This paper compares the explosion risk potential in the LNG fuel gas supply systems of two types used in marine LNG fuelled vessels. By selecting 8500 TEU class container ships as target, LNG storage tank was designed and pressure conditions were assumed for the use of each fuel supply type. The leak hole sizes were divided into three categories, and the leak frequencies for each category were estimated. The sizes of the representative leak holes and release rates were estimated. The release rate and the leak frequency showed an inverse relationship. The pump type fuel gas supply system showed high leak frequency, and the pressure type fuel gas supply system showed high release rate. Computational fluid dynamics simulation was applied to perform a comparative analysis of the explosion risk potential of each fuel supply system.

• The Journal of Information Systems
• /
• v.27 no.2
• /
• pp.1-28
• /
• 2018

Purpose More than 7.6 million mobile apps could be approved on both Apple iTunes Store and Google Play. For managing those existed Apps, Apple Inc. established twenty-four primary categories, as well as Google Play had thirty-three primary categories. However, all of their categorizations have appeared more and more problems in managing and classifying numerous apps, such as app miscategorized, cross-attribution problems, lack of categorization keywords index, etc. The purpose of this study focused on introducing individual information cognitive processing as the classification criteria to update the current categorization on Apple iTunes Store. Meanwhile, we tried to observe the effectiveness of the new criteria from a classification process on Apple iTunes Store. Design/Methodology/Approach A research approach with four research stages were performed and a series of mixed methods was developed to identify the feasibility of adopting individual information cognitive processing as categorization criteria. By using machine-learning techniques with Term Frequency-Inverse Document Frequency and Singular Value Decomposition, keyword lists were extracted. By using the prior research results related to car app's categorization, we developed individual information cognitive processing. Further keywords extracting process from the extracted keyword lists was performed. Findings By TF-IDF and SVD, keyword lists from more than five thousand apps were extracted. Furthermore, we developed individual information cognitive processing that included a categorization teaching process and learning process. Three top three keywords for each category were extracted. By comparing the extracted results with prior studies, the inter-rater reliability for two different methods shows significant reliable, which proved the individual information cognitive processing to be reliable as criteria of categorization on Apple iTunes Store. The updating suggestions for Apple iTunes Store were discussed in this paper and the results of this paper may be useful for app store hosts to improve the current categorizations on app stores as well as increasing the efficiency of app discovering and locating process for both app developers and users.

• Korean Journal of Community Nutrition
• /
• v.23 no.5
• /
• pp.397-410
• /
• 2018

Objectives: An association between dietary patterns and mental health in children has been suggested in a series of studies, yet detailed analyses of dietary patterns and their effects on ADHD (attention deficit hyperactivity disorder) are limited. Methods: We included 4569 children who had dietary intake data as part of the CHEER (Children's Health and Environmental Research) study conducted nationwide from 2005 to 2010. We assessed ADHD (Attention Deficit Hyperactivity Disorder) by the DuPaul's ADHD Rating Scales and dietary intake by a semi-quantitative food frequency questionnaire. Using intake data, we constructed five dietary patterns: "Plant foods & fish," "Sweets," "Meat & fish," "Fruits & dairy products," and "Wheat based." Results: The overall proportion of ADHD was 12.3%. Boys (17.8%) showed a higher rate of ADHD than girls (6.5%). The total intake of calories (85 kcal) and plant fat (2g) in the ADHD group was significantly higher than that of the normal group. ADHD was significantly negatively associated with dietary habits such as having breakfast and meal frequency, and positively associated with eating speed, unbalanced diet, overeating, and rice consumption. Regarding dietary patterns, the "Sweets" category was relevant to high ADHD risk (OR 1.59, 95% CI: 1.18, 2.15 for Q5 vs. Q1) in a linear relationship. An inverse, non-linear association was found between "Fruits & dairy products" and ADHD (OR 0.55, 95% CI: 0.39, 0.76 for Q4 vs. Q1). Conclusions: Our study confirms both positive and negative associations between diet and ADHD in elementary school age children. Moreover, linear or nonlinear associations between diet and ADHD draw attention to the possible threshold role of nutrients. Further studies may consider characteristics of diet in more detail to develop better intervention or management in terms of diet and health.

• Korean Journal of Biological Psychiatry
• /
• v.27 no.1
• /
• pp.18-26
• /
• 2020

Objectives The aim was to find effective vectorization and classification models to predict a psychiatric diagnosis from text-based medical records. Methods Electronic medical records (n = 494) of present illness were collected retrospectively in inpatient admission notes with three diagnoses of major depressive disorder, type 1 bipolar disorder, and schizophrenia. Data were split into 400 training data and 94 independent validation data. Data were vectorized by two different models such as term frequency-inverse document frequency (TF-IDF) and Doc2vec. Machine learning models for classification including stochastic gradient descent, logistic regression, support vector classification, and deep learning (DL) were applied to predict three psychiatric diagnoses. Five-fold cross-validation was used to find an effective model. Metrics such as accuracy, precision, recall, and F1-score were measured for comparison between the models. Results Five-fold cross-validation in training data showed DL model with Doc2vec was the most effective model to predict the diagnosis (accuracy = 0.87, F1-score = 0.87). However, these metrics have been reduced in independent test data set with final working DL models (accuracy = 0.79, F1-score = 0.79), while the model of logistic regression and support vector machine with Doc2vec showed slightly better performance (accuracy = 0.80, F1-score = 0.80) than the DL models with Doc2vec and others with TF-IDF. Conclusions The current results suggest that the vectorization may have more impact on the performance of classification than the machine learning model. However, data set had a number of limitations including small sample size, imbalance among the category, and its generalizability. With this regard, the need for research with multi-sites and large samples is suggested to improve the machine learning models.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.6
• /
• pp.103-108
• /
• 2016

The size of urban areas is currently growing and the functions of cities are becoming increasingly complicated. Furthermore, more people are living in cities. The life of urban is getting closer and linked with neighboring people in many parts. In particular, people are making artificial noise, even though it might not consciously be noticed, in their daily live. Seoul is the most crowded place in Korea and the noise levels are 73dB or higher. People living in cities are exposed to noise pollution. In particular, loudspeakers used during demonstrations or to generate publicity, cause considerable noise, which in turn can be related to stress. Moreover, the noise restrictions defined by law are not adhered to. If enhanced noise regulations, no matter how residents are not forced to be a great stress field close to the noise and reduces the loudness -5dB do not feel well if the difference. Limiting the duration of noise rather than reducing the volume thus is a much more plausible way of reducing the damage caused by noise pollution. If the stress caused by the noise, you will see people or vehicles holding a megaphone at the roadside is not good for health if it may be a wise way to live that is getting rid of the noise pollution so quickly out of the area.

• Journal of Preventive Medicine and Public Health
• /
• v.9 no.1
• /
• pp.11-24
• /
• 1976

This study was a part of large scale of a prospective study on attitudes of professional students in medicine, nursing and teaching toward population related issues in Korea. The study was first conducted in May 1974 and then in May 1975 for the 1974 class cohot using a questionaire consisted of attitude scales and other items developed by Lee. The purpose of stuay was twohold, namely, to determine the difference in students among specializations on one hand and between the first and second years in the 1974 class cohot regarding tile subject matter. A one-way analysis of variance was used for attitude scale, and absolute and relative frequency were computed for the analysis of non-attitude scale items by employing Fishers' Ratio and Duncan's multiple range test at 5% level and chi square test at 5% level as significance tests. The hypothesis 'students in health profession are more likely to have positive attitudes toward population related issues progressively as class year advances than students in teaching profession' was tested and the following results were obtained: 1) Nursing students were more likely to display favarable attitudes toward family planning than medical or teaching students although the class cohot showed slightly negative improvement in the second year. Medical and teaching students apperaed to have slightly improved attitudes in the second year. 2) Respondents in general perceived national family planning program as a means of population control and this tendency was more true among nursing students as the class year advances than two other professional groups of students. Students in teaching profession appeared to perceive it more as a means to improve individual family welfare while health students were likely to see as to improve maternal and child health. This tendency was progressively improved as the class year advanced. 3) The majority of students regardless of their respective specializations believed that family planning program should be directed toward the improvement of individual family welfare. No progressive changes in the class cohot were observed. 4) About the plan to use contraceptives in future, no singnificant differences were observes among different specializations nor in different class years. However, the majority was confirmed to have a plan to use contracepives in future. An increasing proportion of the undecided category was observed, as class year advanced among health students. 5) Students in health profession were found to be more favorable about 'more leisure opportunities' as motive for limiting number of children whereas education students indicated the reasons as 'facilitate ambitions' and 'economic base' The progressive changes toward positive direction in both groups were observed as the class years advanced. 6) Attitudes toward induced abortions of the health students were observed to be positively related to class years while an inverse relationship was found in teaching students who showed much less favor in the subject matter than health students. This phenomenon may be due to the different exposure to learning environments unique to respective specializations. 7) Health students were found to have more favorable attitudes toward population education in general than the teaching students. The teaching students appeared to have changed more to the negative direction when they became the second year while no such development was observed in health students. The teaching students seemed to hold a very conservative position with regard to sex education in schools. 8) About the equality of sexes, the nursing group was found to be most favorable while the reverse was true in the teaching group. A change in the negative direction as the class year advanced was found in the teaching group. 9) About questions related to fertility values-the 10 percent of respondents regardless of specialization indicated that they would maintain their single status in future, however no change was observed in the second year. The desired number of children was found to be two by the majority of students in nursing, medicine and teaching in order of high proportion. No changes in a different class year were observed. The childless marriage was seen by nursing students as a problem more than other students, but a slight change in positive direction was found when the nursing students became the second year. In summing, as data supported in the above, students in health profession demonstrated more favorable attitudes toward population related issues than the teaching students and this tendency became more apparent in the second year. It was noticed that health students were more conscious about the health aspect of population and family planning program while the teaching students gave more attention to the socioeconomic aspect. The sex variable seemed to have operated in the item related to the equality of sexes. In conclusion, as data presented in the above, the hypothesis of this study was accepted except in the few items. It should be noted that the limitation of this study is the short duration of the observation in measuring the possible attitude changes. It should include curriculum analysis for the respective specializations in order to indentify the area of curriculum impact on students in future study.