• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.5
• /
• pp.423-432
• /
• 2018

Surface water mapping has been widely used in various remote sensing applications. Water indices have been commonly used to distinguish water bodies from land; however, determining the optimal threshold and discriminating water bodies from similar objects such as shadows and snow is difficult. Deep learning algorithms have greatly advanced image segmentation and classification. In particular, FCN (Fully Convolutional Network) is state-of-the-art in per-pixel image segmentation and are used in most benchmarks such as PASCAL VOC2012 and Microsoft COCO (Common Objects in Context). However, these data sets are designed for daily scenarios and a few studies have conducted on applications of FCN using large scale remotely sensed data set. This paper aims to fine-tune the pre-trained FCN network using the CRMS (Coastwide Reference Monitoring System) data set for surface water mapping. The CRMS provides color infrared aerial photos and ground truth maps for the monitoring and restoration of wetlands in Louisiana, USA. To effectively learn the characteristics of surface water, we used pre-trained the DeepWaterMap network, which classifies water, land, snow, ice, clouds, and shadows using Landsat satellite images. Furthermore, the DeepWaterMap network was fine-tuned for the CRMS data set using two classes: water and land. The fine-tuned network finally classifies surface water without any additional learning process. The experimental results show that the proposed method enables high-quality surface mapping from CRMS data set and show the suitability of pre-trained FCN networks using remote sensing data for surface water mapping.

• Journal of radiological science and technology
• /
• v.43 no.5
• /
• pp.397-404
• /
• 2020

Coronavirus disease(COVID-19) is highly infectious disease that directly affects the lungs. To observe the clinical findings from these lungs, the Chest Radiography(CXR) can be used in a fast manner. However, the diagnostic performance via CXR needs to be improved, since the identifying these findings are highly time-consuming and prone to human error. Therefore, Artificial Intelligence(AI) based tool may be useful to aid the diagnosis of COVID-19 via CXR. In this study, we explored various Deep learning(DL) approach to classify COVID-19, other viral pneumonia and normal. For the original dataset and lung-segmented dataset, the pre-trained AlexNet, SqueezeNet, ResNet18, DenseNet201 were transfer-trained and validated for 3 class - COVID-19, viral pneumonia, normal. In the results, AlexNet showed the highest mean accuracy of 99.15±2.69% and fastest training time of 1.61±0.56 min among 4 pre-trained neural networks. In this study, we demonstrated the performance of 4 pre-trained neural networks in COVID-19 diagnosis with CXR images. Further, we plotted the class activation map(CAM) of each network and demonstrated that the lung-segmentation pre-processing improve the performance of COVID-19 classifier with CXR images by excluding background features.

• The Journal of the Korea Contents Association
• /
• v.19 no.3
• /
• pp.466-474
• /
• 2019

The purpose of this study was to investigate the enhancing creative competency and changes in academic challenge for the pre-service teachers. For this purpose, 94 pre-service teachers participated in project learning through the preparation of the convergence instruction and the class demonstration during one semester. The pre and post questionnaire survey was conducted the measurement of creative leader competence and K-NSSE for academic challenge. Analysis of data was performed using the IBM SPSS 18.0 program for the corresponding sample t test. The creative competency included 'higher mental thinking', 'problem solving', 'curiosity', 'sensitivity' 'task commitment', 'the pursuit of social value', and 'co-operations and considerations'. This results was significant(p< .05). Academic challenge, high-order learning domain and learning strategies domain were significant(p< .05). Based on this, in order to generalize the convergence education and convergence lesson, it is necessary to design various convergence lessons and practice study to make a plan and practice it. In addition, the implications for the necessity of correcting and supplementing the effects after repeated convergence lessons were discussed.

• Korean Journal of Exercise Nutrition
• /
• v.13 no.2
• /
• pp.115-122
• /
• 2009

Intracerebral hemorrhage (ICH) is a common cause of stroke, and it occurs mainly in the striatum, thalamus, cerebellum, and pons. Physical exercise is known to ameliorate neurologic impairment induced by various brain insults. In the present study, the influence of pre-and post-conditioning of treadmill exercise on spatial learning ability, the lesion volume, and apoptotic neuronal cell death in the striatum following ICH in rats was investigated. ICH in the striatum was induced by injection of collagenase using strereotaxic instrument. The rats in the pre-exercise group were scheduled to run on a treadmill before ICH induction for 2 consecutive weeks. The rats in the post-exercise group were scheduled to run on a treadmill after ICH induction for 2 weeks. The rats in the pre-exercise and post-exercise group were scheduled to run on a preconditioning treadmill exercise 2 weeks before ICH induction until postconditioning treadmill exercise 2 weeks after ICH induction, except the day of surgery. For this study, radial arm maze task, Nissl staining, terminal deoxynucleotidyl transferase-mediated dUTP nick end labeling (TUNEL) assay, and immunohistochemistry for caspase-3 were performed. Our date showed that treadmill exercise suppressed the ICH-induced apoptotic neuronal cell death and decreased lesion volume in the stratum. Treadmill exercise also alleviated the ICH-induced impairment of spatial learning ability. Preconditioning treadmill exercise before the ICH insult and postconditioning treadmill exercise after the ICH insult showed similar effectiveness on the recovery of ICH. In this study, however, preconditioning exercise before the ICH insult and postconditioning exercise after the ICH insult showed the most potent effectiveness on the recovery of ICH.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.4
• /
• pp.27-39
• /
• 2024

Soil texture is determined by the proportions of sand, silt, and clay within the soil, which influence characteristics such as porosity, water retention capacity, electrical conductivity (EC), and pH. Traditional classification of soil texture requires significant sample preparation including oven drying to remove organic matter and moisture, a process that is both time-consuming and costly. This study aims to explore an alternative method by developing an AI model capable of predicting soil texture from images of pre-sorted soil samples using computer vision and deep learning technologies. Soil samples collected from agricultural fields were pre-processed using sieve analysis and the images of each sample were acquired in a controlled studio environment using a smartphone camera. Color distribution ratios based on RGB values of the images were analyzed using the OpenCV library in Python. A convolutional neural network (CNN) model, built on PyTorch, was enhanced using Digital Image Processing (DIP) techniques and then trained across nine distinct conditions to evaluate its robustness and accuracy. The model has achieved an accuracy of over 80% in classifying the images of pre-sorted soil samples, as validated by the components of the confusion matrix and measurements of the F1 score, demonstrating its potential to replace traditional experimental methods for soil texture classification. By utilizing an easily accessible tool, significant time and cost savings can be expected compared to traditional methods.

• Journal of Educational Research in Mathematics
• /
• v.12 no.1
• /
• pp.29-48
• /
• 2002

The purpose of this paper is to investigate the transfer in mathematics learning, especially focussing on arithmetic and algebra. There are many obstacles at the stage of transfer in learning. In the case of mathematics, each learning contents are definitely categorized by the learning level, therefore these obstacles are more happened than other subjects. First of all, this paper investigates the historical transfer from arithmetic to algebra by Sfard's perspectives. And we define prealgebra as the stage between arithmetic and algebra, which may be revised obstacles or misconceptions happened in the early algebra learning. Also, this paper discusses various obstacles and concrete examples happened in the transfer from arithmetic to algebra. To advance the understanding in the learning of algebra, we consider the core contents of the algebra learning which should be stressed at the prealgebra stage. Finally we present the teaching units of (pre)algebra which are sequenced from the variable concepts to equations.

• Journal of the Korean Chemical Society
• /
• v.62 no.2
• /
• pp.159-165
• /
• 2018

For the first time, the spot the differences (STD) game was employed in the teaching of basic organic chemistry course. Three sets of paired pictures associated with selected topics in organic chemistry were presented to the students and they were required to spot the differences between the two pictures. Based on the students' pre and post self-assessment, the STD game resulted in several positive learning outcomes as indicated in the students' reflective writing, including knowledge recall, deeper understanding of a subject, enhanced analytical skill, motivation and fun-filled learning, learning from peers and self-empowerment in learning. The STD game is a desirable teaching and learning tool, as learning in an entertaining and interactive way is highly sought after in today's classroom, especially to novice students. In the future, the STD game can be modified and implemented to cater the needs of different courses and topics.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.25 no.4
• /
• pp.508-516
• /
• 2019

Purpose: This study was conducted to examine the effects of jigsaw cooperative learning on the communication ability, problem solving ability, critical thinking disposition, self-directed learning ability and cooperation of nursing students. Methods: A one-group, pre-post design was utilized with 92 nursing students as subjects. The data were analyzed using descriptive statistics and paired t-tests using SPSS/WIN 24.0. Results: The scores on problem solving ability, self-directed learning ability and cooperation were significantly increased after the education intervention. Conclusion: These findings indicate that cooperation learning is an effective intervention for improving problem-solving, self-directed learning ability, and cooperation in nursing education.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.24 no.2 s.201
• /
• pp.45-50
• /
• 2006

• Journal of Korean Academy of Nursing Administration
• /
• v.13 no.1
• /
• pp.53-64
• /
• 2007

Purpose: This study was aimed to develop and evaluate of a Problem-based Learning (PBL) in the course of Nursing Management and Ethics. Method: The design of the study was both methodological and one group only pre-post design. The sample included 61 senior students who are currently enrolled in Nursing management and Ethics course in college of nursing. Data regarding PBL evaluation were collected on the critical thinking and clinical reasoning using structured questionnaires during March to June, 2005. Data were analyzed using descriptives and paired t-test. Results: A total of three PBL packages was developed by the two faculty members and two teaching assistants who are majoring in nursing management. PBL packages that had been developed was applied to 61 senior students for three months. Critical thinking and clinical reasoning were measured twice pre and post the application of PBL packages. There were statistically significant differences in the critical thinking and clinical reasoning between the pre and post PBL application. Conclusion: PBL was considered to be effective in understanding the learning concepts in the Nursing Management and Ethics. Further research on the facilitative strategies and development model considering the characteristics of Nursing Management and Ethics course is needed.