• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1037-1052
• /
• 2019

We had developed in preceding study a classification model for the Korean pine and Larch with an accuracy of 98 percent using Hyperion and Sentinel-2 satellite images, texture information, and geometric information as the first step for tree species mapping in the inaccessible North Korea. Considering a share of major tree species in North Korea, the classification model needs to be expanded as it has a large share of Oak(29.5%), Pine (12.7%), Fir (8.2%), and as well as Larch (17.5%) and Korean pine (5.8%). In order to classify 5 major tree species, national forest type map of South Korea was used to build 11,039 training and 2,330 validation data. Sentinel-2 data was used to derive spectral information, and PlanetScope data was used to generate texture information. Geometric information was built from SRTM DEM data. As a machine learning algorithm, Random forest was used. As a result, the overall accuracy of classification was 80% with 0.80 kappa statistics. Based on the training data and the classification model constructed through this study, we will extend the application to Mt. Baekdu and North and South Goseong areas to confirm the applicability of tree species classification on the Korean Peninsula.

• Korean Journal of Social Welfare Studies
• /
• v.49 no.1
• /
• pp.221-262
• /
• 2018

This study aims to explore life experiences associated with poverty and discrimination in processes of growth, career exploration, entry into the labor market, and career accumulation of the working high school graduate youths. With this exploration, we also intent to grasp their difficulties and needs, thus look for policy tasks for them. The analysis is based on qualitative case study. The results are following. Typical working high school graduate youths choose not to go on to university under the influence of unfavorable economic situation of the original families. They enter the labor market without enough career exploration and try to continue working mainly in low-income and unskilled jobs. They usually work long hours to increase incomes, thus, do not have enough time to invest on their own human resources. They locate in a vicious circle of income poverty, time poverty, and skill poverty, but rarely protected by existing employment and income support programs. It is necessary to improve or introduces policy packages including labor market transition support for the high school graduate, education, training, and career exploration support, income support for the working poor, social network support, and support for reducing the dead zone of social insurances.

• Korean Journal of Comparative Education
• /
• v.24 no.5
• /
• pp.27-51
• /
• 2014

The objective of this study is to analyze problems and needs regarding recent education informatization in China and to seek implications for prospective international education cooperation between Korea and China. Toward this end, 76 individual and team reports submitted by Chinese trainees participated in APEC e-Learning Training Program from 2006 to 2013 were analyzed. The results are as follows. First, the most critical problem related to Chinese education informatization was identified as a lack of educational resources. The next three problems identified were, in order of importance, a lack of motivation to use ICT in education, the absence of a system for management and evaluation, and labor shortages in the supply of teachers and professional personnel. Second, with regard to the changing annual trends in China's education informatization needs, the issues of education/training and organizational environment to activate ICT use in education have been ranked high for the last eight years. In contrast, the matter of infrastructure has not been cited as a problem since 2008. However, more recently, the lack of relevant policy and the management and evaluation system have been raised, emphasizing the need for more systematic and professional policies and administrative systems.

• Journal of the Korean Society of Radiology
• /
• v.15 no.2
• /
• pp.153-158
• /
• 2021

X-ray image analysis is a very important field to improve the early diagnosis rate and prediction accuracy of periodontal disease. Research on the development and application of artificial intelligence-based algorithms to improve the quality of such dental X-ray images is being widely conducted worldwide. Thus, the aim of this study was to design a super-resolution algorithm for predicting periodontal disease and to evaluate its applicability in dental X-ray images. The super-resolution algorithm was constructed based on the convolution layer and ReLU, and an image obtained by up-sampling a low-resolution image by 2 times was used as an input data. Also, 1,500 dental X-ray data used for deep learning training were used. Quantitative evaluation of images used root mean square error and structural similarity, which are factors that can measure similarity through comparison of two images. In addition, the recently developed no-reference based natural image quality evaluator and blind/referenceless image spatial quality evaluator were additionally analyzed. According to the results, we confirmed that the average similarity and no-reference-based evaluation values were improved by 1.86 and 2.14 times, respectively, compared to the existing bicubic-based upsampling method when the proposed method was used. In conclusion, the super-resolution algorithm for predicting periodontal disease proved useful in dental X-ray images, and it is expected to be highly applicable in various fields in the future.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.4
• /
• pp.433-440
• /
• 2019

Offshore working environments such as ships, offshore oil and gas plants, and offshore wind turbines are isolated and directly exposed to rough seas, which pose high risks of safety accidents. Therefore, all workers in offshore plants should be able to cope with emergency situations and must be qualified according to relevant laws and regulations such as the International Convention on Standards of Training, Certification and Watchkeeping for Seafarers (STCW Convention) and Offshore Petroleum Industry Training Organization (OPITO) standards. In particular, marine workers should be able to perform cardiopulmonary resuscitation (CPR) in isolated locations or enclosed and confined spaces such as those in life-boats, life-rafts, rescue-boats, etc. Because the floor material is made of rubber, it may be difficult to perform chest compressions in life-rafts used to escape from emergency situations in ships or offshore plants. Chest compressions performed on life-rafts may reduce the accuracy of CPR and increase fatigue for those providing aid. To measure the accuracy and fatigue of those performing CPR in life-rafts, 15 experimenters with more than five years of experience as first aid instructors were exposed to different CPR environments in a marine safety training center equipped with an artificial wave generator. The results showed that the accuracy of CPR in the classroom was 99.6 %, but that in various life-raft environments was only 84 %. T-verification of the two sites confirmed the reduced accuracy of CPR performed on life-rafts. CPR on life-rafts should be performed in groups of two and with the use of automated chest compression devices.

• 재활복지
• /
• v.22 no.3
• /
• pp.189-208
• /
• 2018

This case study investigated the changes in speech intelligibility of patients with head and neck cancers who participated in a therapeutic singing-based intervention. Three patients received a total of twelve 30-minute individual sessions. The intervention consisted of three steps: movements for relaxing breathing muscles, vocalization for increasing the range of articulatory movements, and therapeutic singing. In order to examine the changes in speech intelligibility, the voice quality parameters, diadochokinesis (DDK) and the quadrangle vowel space area (VSA) were measured at pre- and posttest. The recording of what each patient read a written paragraph, which were transcribed by blinded assessors, were also analyzed. The results demonstrated that all of the patients showed positive changes in the voice quality, the rate of repetitive syllable production measured by DDK, and the articulatory working space measured by VSA. Along with these measured changes, increases in positive mood and rehabilitation motivation reported by the patients support that the therapeutic singing-based intervention could induce meaningful changes in terms of speech intelligibility from patients with head and neck cancers. Given that this study was conducted with a small sample size, suggestions for further investigation on the effects of the intervention were also presented.

• 재활복지
• /
• v.21 no.3
• /
• pp.65-84
• /
• 2017

This study identified predictors of intention to work among people with disabilities who maintain economic inactivity for two successive years by analyzing a total of 2,255 Participants in the 2014 data of the Panel Survey of Employment for the Disabled (PSED) with through $X^2$, t test, logistic regression. To explore factors affecting intention to work among people with disabilities who maintain economic inactivity, this study hypothesized the effectiveness of variables of demographic, disability, human resources, psycho-social factors based on previous studies. The analysis showed that male, spouse-being, low income status out of demographic variables were related to high probability of having intention to work among people with disabilities who maintain economic inactivity. In case of disability variables, experiencing disability-related discrimination significantly predicted the probability of having intention to work. However, the relationship between disability-related discrimination experiences and high intention to work needs to be viewed as correlated rather than cause-and-effect.In addition, literacy related to computer use/English proficiency/interpersonal and adaptation skills(human resources), experiences of vocational rehabilitation services (human resources), self-esteem (psycho-social) significantly predicted the probability of having intention to work among people with disabilities who maintained economic inactivity. Based on these results, support services for females with disabilities, effective rehabilitation programs of improving literacy related to computer use/English proficiency/interpersonal and adaptation skills and self-esteem, general expansion of vocational rehabilitation services for people with disabilities are suggested.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.1
• /
• pp.1-8
• /
• 2019

In December 2017, many collision accidents of small vessels, such as those between oil refineries and fishing boats, occurred near Yeonghung-do in Incheon. In order to prevent marine casualties from small vessels, the government is striving to improve the safety capabilities of ship operators by strengthening education and improving the working environment. They are providing education and refining training regulations for fishermen operating vessels under 5 tons. However, the situation includes certain vulnerabilities. In this study, we propose a collision prevention algorithm for small vessels using the Wireless Access in Vehicular Environments (WAVE) communication system, which is a new communication technique to prevent collisions with small ships. The collision avoidance algorithm used is based on DCPA/TCPA. Research analyses, simulation experiments and questionnaires have been conducted to define the criteria of DCPA/TCPA. As a result, the standard for DCPA was $8(L_a+L_b)$ and for TCPA was 2.5 min. Three different accident cases were selected, and this algorithm was applied to confirm alarm responses at certain times. This algorithm can provide information to the operators of small ships in advance to help them recognize potential collision situations.

• The Korean Journal of Applied Statistics
• /
• v.32 no.2
• /
• pp.213-227
• /
• 2019

In this paper, we propose an end-to-end deep learning model combining Bayesian neural network with Korean speech recognition. In the past, Korean speech recognition was a complicated task due to the excessive parameters of many intermediate steps and needs for Korean expertise knowledge. Fortunately, Korean speech recognition becomes manageable with the aid of recent breakthroughs in "End-to-end" model. The end-to-end model decodes mel-frequency cepstral coefficients directly as text without any intermediate processes. Especially, Connectionist Temporal Classification loss and Attention based model are a kind of the end-to-end. In addition, we combine Bayesian neural network to implement the end-to-end model and obtain Monte Carlo estimates. Finally, we carry out our experiments on the "WorimalSam" online dictionary dataset. We obtain 4.58% Word Error Rate showing improved results compared to Google and Naver API.

• Journal of Industrial Convergence
• /
• v.16 no.3
• /
• pp.9-15
• /
• 2018

The purpose of this study was to investigate the relationship between empathy ability and attitude toward mental illness in nursing college students. The subjects of this study were collected in June, 2017 for the 4th grade students attending the nursing department in D city. The data were collected using the SPSS.19 program. The results showed that empathy ability of nursing college students had a significant effect on the attitude toward mentally ill patients. The explanatory power of empathy ability on each subscale was 18% for benevolence, 16% for authoritarianism, 9 % for social restrictiveness, and 4% for community mental health ideology. In conclusion, the empathy ability of nursing college students was found to affect the attitude toward the mentally ill. As the empathy increased, the authoritarianism of the mentally ill was lowered, the benevolence was increased, the social life support and community mental health ideology was positive, so the positive attitude toward mental illness was increased overall. Therefore, it is necessary to systematically train and education nursing college students to develop empathy needed for the therapeutic relationship. These efforts will contribute to the improvement of the awareness of the mentally ill.