• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.11
• /
• pp.1035-1045
• /
• 2017

Classification of age and gender has been carried out through different approaches such as facial-based and audio-based classifications. One of the limitations of facial-based methods is the reduced recognition rate over large distances, while another is the prerequisite of the faces to be located in front of the camera. Similarly, in audio-based methods, the recognition rate is reduced in a noisy environment. In contrast, gait-based methods are only required that a target person is in the camera. In previous works, the view point of a camera is only available as a side view and gait data sets consist of a standard gait, which is different from an ordinary gait in a real environment. We propose a feature extraction method using skeleton models from an RGB-D sensor by considering characteristics of age and gender using ordinary gait. Experimental results show that the proposed method could efficiently classify age and gender within a target group of individuals in real-life environments.

• Journal of Digital Convergence
• /
• v.19 no.12
• /
• pp.477-486
• /
• 2021

This study was conducted to detect metabolic syndrome risk factors and gender difference in adults. 18,616 cases of adults are collected by Korea Health and Nutrition Examination Study from 2016 to 2019. Using 4 types of machine Learning(Logistic Regression, Decision Tree, Naïve Bayes, Random Forest) to predict Metabolic Syndrome. The results showed that the Random Forest was superior to other methods in men and women. In both of participants, BMI, diet(fat, vitamin C, vitamin A, protein, energy intake), number of underlying chronic disease and age were the upper importance. In women, education level, menarche age, menopause was additional upper importance and age, number of underlying chronic disease were more powerful importance than men. Future study have to verify various strategy to prevent metabolic syndrome.

• Journal of Practical Engineering Education
• /
• v.11 no.1
• /
• pp.105-115
• /
• 2019

This study focused on the importance of job position as a role model for female career adaptation. To do this, we used the KWMP data to conduct a Multinomial logit analysis to examine the influence factors of the tenure women managers. As a result, first, section chief position showed a low level of life satisfaction and showed difficulty of beginner's manager. Second, it is predicted that the position of the Deputy Head of Department will establish the identity of work as an intermediate manager. Third, head of department Director showed a high age, target status, possibility of achieving the target, and duration of the next job. Fourth, executive level has the least average experience of discrimination on monthly average wage. It was suggested that it is important to develop individual career by recognizing that the organizational atmosphere and personnel management are lower than those of the other positions. It was found that age, organizational atmosphere and personnel management, goal status, possibility of achieving goals, next job tenure period, monthly average wage, welfare, and life satisfaction factors were the most influential factors in women career adjustment. Finally, implications and limitations were discussed based on the results of this study.

• 한국벤처창업학회:학술대회논문집
• /
• 2021.11a
• /
• pp.161-165
• /
• 2021

스타트업 제품 모델링에 있어 기존 제품에 대한 분석은 매우 중요한 역할을 한다. 그리고 이러한 분석은 다양한 방식과 프로그램 들을 통해 측정이 가능하다. 하지만, 다수의 스타트업들은 이러한 프로그램 운영이나 통계적 산출을 할 수 있는 인력 공급이 원활하지 않아 실제 사용에 많은 어려움을 겪고 있다. 이에 본 연구는 특별히 뛰어난 수리적 지식이 없더라도 중, 소 스타트업의 입장에서 직원 누구나 활용 가능한 제품 분석 방법에 대해 찾게 되었으며 그 결과 Kano 모형이 가장 적합할 것이라는 예측을 하였다. Kano 모형을 적용할 제품군으로는 많은 소비자가 존재하지만 시장이 크지 않아 진출 기회가 열려있는 스마트워치를 대상으로 하였다. 본 연구에서는 일반적으로 많은 회사에서 활용하고 있는 기본 오피스 프로그램인 EXCEL만을 활용해 제품의 Kano 모델 측정을 진행하였으며 그 결과 매력적요소 4가지(배터리 유효기간, 워치페이스의 종류와 수, 외형의 손상방지, 브랜드이미지), 일원적요소 13가지(단말기의 무게, 단말기의 외형, 구매가격, 오류발생, 스마트페이 기능, A/S용이성, 사용 가능한 앱의 수, 충전의 용이성, 방수 등 부가기능, 단말기 색상의 다양성, 헬스케어, 통화기능, 알림기능), 당연적요소 1가지(자사 기기와의 연동), 무관심요소 2가지(워치밴드의 디자인, 타사 기기와의 연동) 항목들을 측정하는 것이 가능하였으며 향후 본 Kano 모델을 활용하거나 해석함에 있어 최종학력, 전공, 연령 등이 어떠한 영향을 미치며 모델 사용에 필요한 최소 지식 수준에 따른 추가적인 연구를 진행할 것이다.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.37-44
• /
• 2020

AI technology has developed in the form of decision support technology in law, patent, finance and national defense and is applied to disease diagnosis and legal judgment. To search real-time information with Deep Learning, Big data Analysis and Deep Learning Algorithm are required. In this paper, we try to predict the entrance rate to high-ranking universities using a Deep Learning model, RNN(Recurrent Neural Network). First, we analyzed the current status of private academies in administrative districts and the number of students by age in administrative districts, and established a socially accepted hypothesis that students residing in areas with a high educational fever have a high rate of enrollment in high-ranking universities. This is to verify based on the data analyzed using the predicted hypothesis and the government's public data. The predictive model uses data from 2015 to 2017 to learn to predict the top enrollment rate, and the trained model predicts the top enrollment rate in 2018. A prediction experiment was performed using RNN, a Deep Learning model, for the high-ranking enrollment rate in the special education zone. In this paper, we define the correlation between the high-ranking enrollment rate by analyzing the household income and the participation rate of private education about the current status of private institutes in regions with high education fever and the effect on the number of students by age.

• Environmental and Resource Economics Review
• /
• v.25 no.2
• /
• pp.199-228
• /
• 2016

This study investigates the effects of economic factors and forest environments on rural residential area development in seven north central states of the U.S. by focusing on the relative importance of not only economic factors but also forest environments by forest type as core drivers of residential development. An empirical model of locations and magnitudes of population changes since 1950 in the north central region is first constructed, and then a panel model with fixed effects for counties is used to explain population growth by age group over time at the county level. Then a set of three equations is estimated for three major age groups, and a cross-sectional model is estimated for the last time period that regresses county-level environmental amenity variables on fixed effects coefficients for counties. Finally, an equation explaining changes in rural housing density is estimated. The results imply that immigrant age is a key factor influencing the choice of the place of residence and that the effects of environmental amenity factors on population growth and subsequent housing development in a county vary according to the age group.

• Journal of Digital Convergence
• /
• v.18 no.8
• /
• pp.201-215
• /
• 2020

We conducted the analysis using the data of the '2019 Korean Middle and Elderly Technology Acceptance Survey' to verify the comprehensive senior technology acceptance model. In this study, we examined the significant effect the relationship between behavioral intention to use the diital health devices and perceived usefulness, perceived ease of use, gerontechnology self-efficacy, gerontechnology anxiety, facilitating conditions, attitude to life and satisfaction through the structural equation. The results of the research model are as follows. First, the usefulness and ease of use had significant effects on intention to use. Second, the self-efficacy had significant effects on the intention to use. But they had negative effect. Third, perceived usefulness, self-efficacy and anxiety had significant effects on ease of use. Lastly, self-efficacy, facilitating conditions, attitude to life and satisfaction had significant effects on perceived usefulness. These findings highlight that verified the comprehensive senior technology acceptance model in Korea.

• Journal of the Korean earth science society
• /
• v.29 no.7
• /
• pp.539-550
• /
• 2008

In this paper, we investigate the geochemical and isotope properties of the Jeongeup foliated granite (hereafter, the JFG) in the Jeongeup area, aiming at establishing the movement age of the Honam shear zone by U-Pb sphene geochronology. In the AMF diagram, the JFG corresponds to the calc alkalic rock series, and belongs to the magnesia region in the diagram of silica versus $FeO^{total}/(FeO^{total}+MgO)$. Additionally, in the Rb-Ba-Sr diagram, it is classified as granodiorite and anomalous granite with distinctive negative Eu-anomaly in the REE patterns. According to the silica and trace element contents, the JFG falls on the type VAG+syn-COLG, which implies that this was formed under the circumstance of compressional continental margin or volcanic arc. $^{143}Nd/^{144}Nd$ isotope ratios range from 0.511495 to 0.511783 and $T_{DM}$ are calculated to be about $1.68{\sim}2.36Ga$. U-Pb sphene ages of the JFG are $172.9{\pm}1.7Ma$ and $170.7{\pm}2.8Ma$, based on $^{238}U-^{206}Pb$ and $^{235}U-^{207}Pb$ ages, respectively. Presumably, the dextral ductile shearing in the Jeongeup area has occurred after 173 Ma.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.62-71
• /
• 2016

Food insecurity is associated with poor health outcomes. In particular, previous studies marked the adverse outcomes on mental health. This study examined the association of food insecurity and mental health in Korean adults using the data from the 2013 Korean National Health and Nutrition Examination Survey (KNHANES). The study population was 5,685 adults in Korea. Food insecurity was examined using 18-items. A diagnosis of depression was considered to be depression. Depressive symptoms were defined as more than 2 weeks of depression feelings. Multivariate logistic regression models examined the associations between food insecurity and depression and depressive symptom. The overall prevalence of depression was 3.8% in the participants. Food insecurity was associated significantly with depression and depressive symptom in the unadjusted and age and sex adjusted model. Food insecurity was associated with depression, depressive symptoms in the multivariate logistic regression model (OR:3.49, OR:3.70). Marginal food insecurity was not associated with depression in the multivariate logistic regression model. The results showed that food insecurity is associated with depression and depressive symptoms in adults. Multi-disciplinary interventions are needed including nutrition, health, health policy, and a healthy environment for the food insecurity group to achieve a better health outcome, especially mental health.

• The Journal of the Petrological Society of Korea
• /
• v.26 no.1
• /
• pp.13-43
• /
• 2017

In the Hapcheon area, hypersthene-bearing monzonite (mangerite) and syenite are recognized. The main minerals of syenite are alkali feldspar, plagioclase, amphibole, biotite, and quartz. Anhedral hornblende and biotite are interstitial between feldspar and quartz, indicating that the hydrous minerals were crystallized later on. Based on petrochemical studies of major elements, syenite is alkaline series, metaluminous, and I-type. The variation patterns in the trace and rare earth elements of mangerite and syenite show the features of subduction-related igneous rock such as depletion of HFSE, relative enrichment in LILE to LREE, and negative Nb-P-Ti anomalies. Based on the experimental data and petrographic characteristics of the syenite, Hapcheon syenitic magma is considered to be formed by partial melting in a dry system. SHRIMP U-Pb zircon data yield the Triassic age as $227.4{\pm}1.4Ma$ in mangerite, $215.3{\pm}1.2Ma$ in syenite, and $217.9{\pm}2.6Ma$ in coarse-grained syenite, respectively. The mangerite age is similar to those of post-collisional plutonic rocks in Hongseong (226~233 Ma), Yangpyeong (227~231 Ma), and Odaesan (231~234 Ma) areas in the Gyeonggi Massif. Syenites were intruded after about 10 Ma. The features seen in the mangereite and syenite rocks can be explained by models such as the continental collision and slab break-off and the lithosphere thinning and asthenosphere upwelling model.