• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.661-666
• /
• 2013

The aim of this study was to evaluate the property of heterophoria and fusional reserve in Adults in Jeon-buk Area. We examined the corrected visual acuity, corrected refractive error, heterophoria and fusional reserve of 116 healthy myopes aged from 20 to 44 old who had no strabismus no ocular and phyisical diseases. Using Von Graefe test of horizontal heterophoria Measurement, we measured orthophoria(26.7%), exophoria(52.5%) and esophoria(20.7%) for at near distance. The subjects who had exophoria of 0-6${\Delta}$ in the range of normal state was 38.8%, while the subjects who had exophoria in the range of abnormal state was 61.2%. Reducing fusional reserve was associated with increasing phoria. We found a relationship between asthenopia and fusional reserve of heterophoria and considered that fusional reserve must be examined when we preserve for a patient with heterophoria. Furthermore, Gradient method AC/A ratio was found 4.03 and its relationship to refractive error could not be determined.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1329-1341
• /
• 2022

Destroying the marine environment and marine ecosystem and causing marine accidents, marine debris is generated every year, and among them, submerged marine debris is difficult to identify and collect because it is on the seabed. Therefore, deep-learning-based semantic segmentation was experimented on waste fish nets and waste ropes using underwater images to identify efficient collection and distribution. For segmentation, a high-resolution network (HRNet), a state-of-the-art deep learning technique, was used, and the performance of each optimizer was compared. In the segmentation result fish net, F1 score=(86.46%, 86.20%, 85.29%), IoU=(76.15%, 75.74%, 74.36%), For the rope F1 score=(80.49%, 80.48%, 77.86%), IoU=(67.35%, 67.33%, 63.75%) in the order of adaptive moment estimation (Adam), Momentum, and stochastic gradient descent (SGD). Adam's results were the highest in both fish net and rope. Through the research results, the evaluation of segmentation performance for each optimizer and the possibility of segmentation of marine debris in the latest deep learning technique were confirmed. Accordingly, it is judged that by applying the latest deep learning technique to the identification of submerged marine debris through underwater images, it will be helpful in estimating the distribution of marine sedimentation debris through more accurate and efficient identification than identification through the naked eye.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.1
• /
• pp.241-249
• /
• 2013

Since the enactment of "Mobility Promotion Law for Transportation Vulnerable", each municipality has been various efforts to improve the transportation vulnerable's the right of movement. However, the effectiveness of mobility promotion policy for the transportation vulnerable is awfully inadequate because circumstances which associated with operation of transportation of the handicapped such as local conditions and transport characteristics have not been considered. Thus, in this study investigated traffic characteristics of the transportation vulnerable through the data of regional slope, non-step buses and handicap vehicles operating conditions and so on in Busan Metropolitan. Also, we proposed to introduction of the 'mobility index' which is based on local condition analysis of Busan. And we suggested that how to improve the convenience of transportation vulnerable's movement.

• The Korean Journal of Applied Statistics
• /
• v.28 no.6
• /
• pp.1063-1073
• /
• 2015

In the long-term care insurance (LTCI) system, National Health Insurance Service (NHIS) provide counseling services for beneficiaries and their family caregivers, which help them use LTC services appropriately. The purpose of this study was to develop a Target Selection Model for the Counseling Services based on needs of beneficiaries and their family caregivers. To develope models, we used data set of total 2,000 beneficiaries and family caregivers who have used the long-term care services in their home in March 2013 and completed questionnaires. The Target Selection Model was established through various data-mining models such as logistic regression, gradient boosting, Lasso, decision-tree model, Ensemble, and Neural network. Lasso model was selected as the final model because of the stability, high performance and availability. Our results might improve the satisfaction and the efficiency for the NHIS counseling services.

• Journal of Ecology and Environment
• /
• v.39 no.1
• /
• pp.17-29
• /
• 2016

We conducted the study on the relationship between the distribution of coastal sand dune plants and edaphic factors from the shoreline to inland in sand dune ecosystem. The application of TWINSPAN classification based on 10 species, led to the recognition of three vegetative groups (A-C), which associated with their habitats (foredune, hummuck in semistable zone and stable zone). The associations were separated along soil gradient far from the seashore. The relationships between species composition and environmental gradients were explained by canonical correspondence analysis (CCA). Distance from the shoreline was an important indicator to determine soil properties (pH, total ion contents, sand particle sizes, organic matters and nitrogen contents) from the seaward area to inland area and distribution pattern of coastal sand dune plants. Group A is foredune zone, characterized by Calystegia soldanella; group included typical foredune species such as Elymus mollis, Carex kobomugi, Ixeris repens, C. soldanella and Glehnia littoralis. Group B on semi-stabilized zone was characterized by Vitex rotundifolia, a perennial woody shrub. This group was associated the proportion of fine sand size (100 to 250 μm). The results on the proportion of soil particle size showed a transition in sand composition, particularly with respect to the proportion of fine sand size that occurred from the foredune ridge at 32.5 m to the Vitex rotundifolia community at 57.5 m from the shoreline. Group C on stabilized zone was characterized by Zoysia macrostachya, Lathyrus japonicus and Cynodon dactylon and were associated soil organic matter and nitrogen contents. The spatial distribution of plants in the Goraebul coastal sand dune system may result from the interactions between the plant species and environmental heterogeneity.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.253-263
• /
• 2021

Machine learning is the process of constructing a cost function using learning data used for learning and an artificial neural network to predict the data, and finding parameters that minimize the cost function. Parameters are changed by using the gradient-based method of the cost function. The more complex the digital signal and the more complex the problem to be learned, the more complex and deeper the structure of the artificial neural network. Such a complex and deep neural network structure can cause over-fitting problems. In order to avoid over-fitting, a weight decay regularization method of parameters is used. We additionally use the value of the cost function in this method. In this way, the accuracy of machine learning is improved, and the superiority is confirmed through numerical experiments. These results derive accurate values for a wide range of artificial intelligence data through machine learning.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.44-50
• /
• 2021

Recently, enterprise storage systems that require large-capacity storage devices to accommodate big data have used large-capacity flash memory-based storage devices with high density compared to cost and size. This paper proposes a high-efficiency life prediction method with slope descent to maximize the life of flash memory media that directly affects the reliability and usability of large enterprise storage devices. To this end, this paper proposes the structure of a matrix for storing metadata for learning the frequency of defects and proposes a cost model using metadata. It also proposes a life expectancy prediction policy in exceptional situations when defects outside the learned range occur. Lastly, it was verified through simulation that a method proposed by this paper can maximize its life compared to a life prediction method based on the fixed number of times and the life prediction method based on the remaining ratio of spare blocks, which has been used to predict the life of flash memory.

• Journal of Digital Convergence
• /
• v.17 no.8
• /
• pp.337-346
• /
• 2019

This study aimed to assess trends in the prevalence, treatment, and control of diabetes according to the socio-economic level in Korean adults aged ${\geq}30$ years, using the 2007-2017 Korea National Health and Nutrition Examination Survey data. Socio-economic status was assessed based on the household income. Multivariable logistic regression and predictive margins were used to evaluate the adjusted proportion of diabetes prevalence, awareness, treatment, and adequate glycemic control. During 2007-2017, the socio-economic inequalities on diabetes prevalence were observed in both men and women. However, the gradient of inequality increased only in men (p for interaction=0.034). Diabetes awareness, treatment, and control did not show socio-economic inequalities or increasing gradients in both sexes. Monitoring of these trends should be continued, and further research on effective interventions is needed.

• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.251-258
• /
• 2021

In this paper, we proposed an encoder-decoder model utilizing residual learning to improve the accuracy of the U-Net-based semantic segmentation method. U-Net is a deep learning-based semantic segmentation method and is mainly used in applications such as autonomous vehicles and medical image analysis. The conventional U-Net occurs loss in feature compression process due to the shallow structure of the encoder. The loss of features causes a lack of context information necessary for classifying objects and has a problem of reducing segmentation accuracy. To improve this, The proposed method efficiently extracted context information through an encoder using residual learning, which is effective in preventing feature loss and gradient vanishing problems in the conventional U-Net. Furthermore, we reduced down-sampling operations in the encoder to reduce the loss of spatial information included in the feature maps. The proposed method showed an improved segmentation result of about 12% compared to the conventional U-Net in the Cityscapes dataset experiment.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.