• Journal of Digital Convergence
• /
• v.16 no.10
• /
• pp.59-67
• /
• 2018

There are not that many m-health related services limited to the elderly. Many of the elderly who are at risk of dementia are unfamiliar to smart devices, so it is required to design an user-customized App. Therefore, I design and embody a mobile voice alert integrated app, which enables voice input to increase the accessibility of the elderly, so as to prevent diseases caused by declined cognitive function such as dementia. I conducted interviews and questionnaire after having the students use the app in Lifelong Education Center in H region of Gyeongbuk, and the analysis result has showed the high satisfaction. It is expected that it will be able to play a key role for M-Health service for the elderly since it is possible to prevent dementia through the voice health care alert app. I would like to learn deep learning in the future to predict the life patterns and the possibility of dementia of the elderly.

• Journal of Digital Convergence
• /
• v.13 no.5
• /
• pp.269-276
• /
• 2015

In order to examine the relationship between cholesterol level on serum and depression in Korean adults, this study used data of the fourth Korea National Health and Nutrition Examination Survey (KNHANES). 834 persons with depressive symptoms were selected as an index group and 3,317 persons without depressive symptoms as a control group, and odds ratios were calculated by multivariate logistic regression. As a result, odds ratio of depressive symptoms was higher in low LDL group (OR=6.435, 95% CI; 2,358-17.557) than in high LDL group adjusted after monthly income, marital status, period of education, occupation, smoking status, and physical activity. Etiopathogenic mechanism must be found by convergent study in the future.

• Journal of Digital Convergence
• /
• v.19 no.9
• /
• pp.463-468
• /
• 2021

Although the IoT is showing explosive growth due to the development of technology and the spread of IoT devices and activation of services, serious security risks and financial damage are occurring due to the activities of various botnets. Therefore, it is important to accurately and quickly detect the activities of these botnets. As security in the IoT environment has characteristics that require operation with minimum processing performance and memory, in this paper, the minimum characteristics for detection are selected, and KNN (K-Nearest Neighbor), Naïve Bayes, Decision Tree, Random A comparative study was conducted on the performance of machine learning algorithms such as Forest to detect botnet activity. Experimental results using the Bot-IoT dataset showed that KNN can detect DDoS, DoS, and Reconnaissance attacks most effectively and efficiently among the applied machine learning algorithms.

• Journal of Digital Convergence
• /
• v.14 no.12
• /
• pp.561-569
• /
• 2016

Purpose : We will clarify the situation of using a smartphone and what kind of factors are currently related when people use a smartphone while doing something else in order to obtain basic information to educate people to prevent the use of smartphone while doing something else. Methods : We conducted an anonymous self-administered questionnaire survey with 885 people who commuted by train to six companies located in Tokyo, Chiba, and Osaka and 550 university students who commuted by train to five universities located in the same areas. The research period was from April to May of 2014. Results : 33% of the subjects used a feature phone and 73% of the subjects used a smartphone. 38% of them listened to music, using their smartphones or feature phones while walking. Binominal logistic regression analysis was done with dependent variables of using a smartphone while walking and independent variables of age, sex, and educational advertisement. The results showed that people in their 20s used a smartphone while walking 4.93 times more than people in their 30s(p <0.00). No significant difference was found in the relationship between sex and educational advertisement(poster, TV, or magazine) and using a smatphone while doing something else.

• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.215-223
• /
• 2017

This research conducted a survey targeting 238 dental employees in Daegu Gyeongbuk region in order to improve awareness on danger risk of dental materials henceforth by analyzing the awareness on material safety health data (MSDSs) and working environment characteristics that influence thereon. Accordingly, the average score of importance per item based on material safety health data(MSDSs) appeared $3.98{\pm}0.59$, and the highest item appeared 'danger risk', and the average score of necessity in improvement appeared $4.34{\pm}0.57$. Average score of necessity in improvement appeared higher as the career increased, and difference in importance per item showed higher score in the target who worked in the dentist (p<0.01). This research expects that the employees of dentist hospital secure safety on chemical substances of dental materials and pay more attention on chemical substance material of dental material and the material safety health data (MSDSs) that explains this, in order to improve quality of working environment, also, the researcher wishes that concrete policy and institution would be prepared for the safety of dentist hospital employees' working environment safety.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.455-460
• /
• 2023

Text augmentation is a methodology that creates new augmented texts by transforming or generating original texts for the purpose of improving the performance of NLP models. However existing text augmentation techniques have limitations such as lack of expressive diversity semantic distortion and limited number of augmented texts. Recently text augmentation using large language models and few-shot learning can overcome these limitations but there is also a risk of noise generation due to incorrect generation. In this paper, we propose a text augmentation method called TAGS that generates multiple candidate texts and selects the appropriate text as the augmented text. TAGS generates various expressions using few-shot learning while effectively selecting suitable data even with a small amount of original text by using contrastive learning and similarity comparison. We applied this method to task-oriented chatbot data and achieved more than sixty times quantitative improvement. We also analyzed the generated texts to confirm that they produced semantically and expressively diverse texts compared to the original texts. Moreover, we trained and evaluated a classification model using the augmented texts and showed that it improved the performance by more than 0.1915, confirming that it helps to improve the actual model performance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.4
• /
• pp.1541-1550
• /
• 2012

The study examines entrepreneurial motivation and maintenance factors of independent publication, a rising business in the current digital era. Focusing on a case of independent publication which has been successful, this research discloses that personal attributes and backgrounds of individuals are the main factors to motivate them to establish businesses. Personal attributes include desire for achievement, self-control, risk-taking inclination, and etc., and personal backgrounds contain educational background, work experiences in the same line of business, social network, and etc. Moreover, this research also discovers that both intrinsic reward indicating the belief that the individuals will be able to publish the books which they want, and extrinsic reward as market profits are the main maintenance factors. This case study will contribute to developing the education and consulting programs for independent publication entrepreneurship and the related policies.

• Journal of Digital Convergence
• /
• v.14 no.5
• /
• pp.21-37
• /
• 2016

The purpose of study was to examine the entrepreneurial supporting policy and the entrepreneurship which can affect the entrepreneurial intention, and to prove the moderating effect of the business failure burden and the self-efficacy on the relationship of the entrepreneurial supporting policy, entrepreneurship and the entrepreneurial intention through the empirical study in the fusion of industries. We used data from 321 survey participants by using structured questionnaires, excluding dishonest respondents, and statistical analysis was conducted using SPSS 18.0 statistic package. We used hierarchical regression technique to prove our hypothesis. The results showed that education and marketing support which are part of the entrepreneurial supporting policy in the fusion of industries will have positive influence on innovativeness, pro-activeness and risk acceptability which are part of entrepreneurship. It has been reported that only funding support has positive influence on entrepreneurship pro-activeness. The results also indicated that the entrepreneurial supporting policy will have positive influence on the entrepreneurial intention, but business failure burden and self-efficacy will have no moderating effect in the relation between the entrepreneurial supporting policy and the entrepreneurship. The theoretical and practical implications of the findings were discussed and the directions for future research were presented.

• Journal of Digital Convergence
• /
• v.11 no.1
• /
• pp.289-297
• /
• 2013

The destination of this study is a convenience sample of 301 people age 65 and older to use each one elderly welfare center D, M received a structured questionnaire for one-on-one interviews with the subjects to read all the questions and questionnaire was written. The depressed group and the normal group, identify the general characteristics, the ADL, and sleep, and the difference between the two groups, and relative risk were analyzed. The results of the study are as follows: Showed depressed group compared to normal group was the low level of ability to perform daily living, sleep well, not more than the ability to perform daily living, dressing, bowel and bladder management, and complained of the difficulty to perform instrumental activities of daily living ability of grooming, more difficult to appeal to public transportation, shopping. In conclusion, elderly health promotion strategy when you want to take into account whether or not the depression of the elderly will require the development of a variety of education and physical activity programs, and suggest the need for expanded research to determine the effectiveness.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.641-646
• /
• 2018

Purpose : The aim of this research was to clarify the difference in awareness of food safety and what they feel as dangerous among parents in Japan, China, and Korea and how they are different among the nations. Methods : Research subjects were 250 parents in Japan, 181 parents in China, 166 parents in Korea whose children attend a child institution or a day care center. We conducted a questionnaire survey that was self-written and anonymous. Results : Parents in Japan feel safer than Korea and China, and parents in Korea feel safer than China about food that are sold generally. Especially, in China, the average of 5 level scale was lower than the median so it shows that people do not trust food that are sold in the market. All 3 countries tend to have the awareness that "pesticide that is over the standard amount is detected from vegetables in China" and "vegetable grown without pesticides and organic produce are safe" and showed no significant difference. Also, there was a significant difference statistically for the awareness that "it makes it easier to get cancer if you eat food that contain radiation" and "there is a possibility that seafood caught near Japan contain radiation". Parents in Japan emphasize that "the price is low" the most and it was significantly higher than in China and Korea. Also, similar to parents in Japan, parents in Korea tend to emphasize that it is "domestic". On the other hand, it verified that parents in China emphasized "the meat or fish is grown without antibiotics" and "it uses vegetable grown without pesticides".