• Journal of Cadastre & Land InformatiX
• /
• v.48 no.2
• /
• pp.171-183
• /
• 2018

Despite the rapid expansion of satellite images supply, the application of imagery is often restricted due to unautomated image processing. This paper presents the automated process for the selection of training areas which are essential to conducting supervised image classification. The training areas were selected based on the prior and cover information. After the selection, the training data were used to classify land cover in an urban area with the latest image and the classification accuracy was valuated. The automatic selection of training area was processed with following steps, 1) to redraw inner areas of prior land cover polygon with negative buffer (-15m) 2) to select the polygons with proper size of area ($2,000{\sim}200,000m^2$) 3) to calculate the mean and standard deviation of reflectance and NDVI of the polygons 4) to select the polygons having characteristic mean value of each land cover type with minimum standard deviation. The supervised image classification was conducted using the automatically selected training data with Sentinel-2 images in 2017. The accuracy of land cover classification was 86.9% ($\hat{K}=0.81$). The result shows that the process of automatic selection is effective in image processing and able to contribute to solving the bottleneck in the application of imagery.

• Korean Journal of Radiology
• /
• v.24 no.6
• /
• pp.541-552
• /
• 2023

Objective: Detection of pneumoperitoneum using abdominal radiography, particularly in the supine position, is often challenging. This study aimed to develop and externally validate a deep learning model for the detection of pneumoperitoneum using supine and erect abdominal radiography. Materials and Methods: A model that can utilize "pneumoperitoneum" and "non-pneumoperitoneum" classes was developed through knowledge distillation. To train the proposed model with limited training data and weak labels, it was trained using a recently proposed semi-supervised learning method called distillation for self-supervised and self-train learning (DISTL), which leverages the Vision Transformer. The proposed model was first pre-trained with chest radiographs to utilize common knowledge between modalities, fine-tuned, and self-trained on labeled and unlabeled abdominal radiographs. The proposed model was trained using data from supine and erect abdominal radiographs. In total, 191212 chest radiographs (CheXpert data) were used for pre-training, and 5518 labeled and 16671 unlabeled abdominal radiographs were used for fine-tuning and self-supervised learning, respectively. The proposed model was internally validated on 389 abdominal radiographs and externally validated on 475 and 798 abdominal radiographs from the two institutions. We evaluated the performance in diagnosing pneumoperitoneum using the area under the receiver operating characteristic curve (AUC) and compared it with that of radiologists. Results: In the internal validation, the proposed model had an AUC, sensitivity, and specificity of 0.881, 85.4%, and 73.3% and 0.968, 91.1, and 95.0 for supine and erect positions, respectively. In the external validation at the two institutions, the AUCs were 0.835 and 0.852 for the supine position and 0.909 and 0.944 for the erect position. In the reader study, the readers' performances improved with the assistance of the proposed model. Conclusion: The proposed model trained with the DISTL method can accurately detect pneumoperitoneum on abdominal radiography in both the supine and erect positions.

• Journal of Korean Public Health Nursing
• /
• v.25 no.1
• /
• pp.38-47
• /
• 2011

Purpose: The study investigated the effects of 9 weeks of group music rope-jumping training on health-related physical fitness and blood lipid in obese elementary school boys and girls. Method: Subjects were randomly assigned to either a training group (37 boys and 18 girls) or control group (36 boys and 19 girls). The training group exercised for 1 hour, 2 days per week during the 9-week supervised music rope-jumping training program. The control group was asked to maintain their normal daily physical activities. The effects of the interventions on physical fitness and blood lipids were analyzed by two-way repeated measures ANOVA (group ${\times}$ time). Results: There were significant group ${\times}$ time interaction effects on body weight (p<.023), %body fat (p=.09), body mass index (p=.018), and body fat mass (p=.019) in school girls. However, there was not an interaction effect on serum lipids in both genders. Conclusion: The 9-week music rope-jumping training program used was effective for improving body composition in obese elementary school girls.

• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1298-1311
• /
• 2022

Purpose To develop and validate a deep learning-based screening tool for the early diagnosis of scoliosis using chest radiographs with a semi-supervised generative adversarial network (GAN). Materials and Methods Using a semi-supervised learning framework with a GAN, a screening tool for diagnosing scoliosis was developed and validated through the chest PA radiographs of patients at two different tertiary hospitals. Our proposed method used training GAN with mild to severe scoliosis only in a semi-supervised manner, as an upstream task to learn scoliosis representations and a downstream task to perform simple classification for differentiating between normal and scoliosis states sensitively. Results The area under the receiver operating characteristic curve, negative predictive value (NPV), positive predictive value, sensitivity, and specificity were 0.856, 0.950, 0.579, 0.985, and 0.285, respectively. Conclusion Our deep learning-based artificial intelligence software in a semi-supervised manner achieved excellent performance in diagnosing scoliosis using the chest PA radiographs of young individuals; thus, it could be used as a screening tool with high NPV and sensitivity and reduce the burden on radiologists for diagnosing scoliosis through health screening chest radiographs.

• Journal of Ginseng Research
• /
• v.42 no.2
• /
• pp.192-198
• /
• 2018

Background: Ginseng has been used as an ergogenic agent, although evidence for its effectiveness is weak. A randomized, double-blind, placebo-controlled clinical trial was conducted to evaluate the effect of a ginsenoside complex (UG0712) on changes in exercise performance. Methods: Sedentary individuals (n = 117) were randomly assigned into one of three groups: low-dose ginsenoside supplementation (100 mg/d, n = 39), high-dose ginsenoside supplementation (500 mg/d, n = 39), or a placebo group (500 mg/d, n = 39). All participants underwent a supervised 12-wk aerobic and resistance exercise training course. To assess the effects of supplementation on physical performance, maximal oxygen consumption ($VO_2max$), anaerobic threshold (AT), lactic acid, and muscle strength of the dominant knee were measured at baseline, every visit, and after the training program. Results: Both ginsenoside groups showed significant increases in $VO_2max$ and muscular strength during exercise training. There were no definite changes in AT and lactic acid levels over time. After exercise training, there were definite differences in the $VO_2max$ (28.64.9 to $33.7{\pm}4.9ml/kg/min$ in high-dose group vs. $30.4{\pm}6.7$ to $32.8{\pm}6.6ml/kg/min$ in placebo, p = 0.029) and AT ($19.3{\pm}4.2$ to $20.9{\pm}3.5ml/kg/min$ in high-dose group vs. $20.0{\pm}5.1$ to $20.0{\pm}4.9ml/kg/min$ in placebo, p = 0.038) between the high-dose ginsenoside and placebo groups. However, there was no difference in $VO_2max$ between the low-dose ginsenoside and placebo groups (p = 0.254). There were no differences in muscular strength during exercise training among the three groups. Conclusion: High-dose ginsenoside supplementation (UG0712) augmented the improvement of aerobic capacity by exercise training.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.791-801
• /
• 2021

In this paper, an educational case that can be applied as artificial intelligence literacy education for preservice teachers and incumbent teachers was studied. To this end, a case of educating the operating principle of an artificial neural network that recognizes images is proposed. This training case focuses on the basic principles of artificial neural network operation and implementation, and applies the method of finding parameter optimization solutions required for artificial neural network implementation in a spreadsheet. In this paper, we focused on the artificial neural network of supervised learning method. First, as an artificial neural network principle education case, an artificial neural network education case for recognizing two types of images was proposed. Second, as an artificial neural network extension education case, an artificial neural network education case for recognizing three types of images was proposed. Finally, the results of analyzing artificial neural network training cases and training satisfaction analysis results are presented. Through the proposed training case, it is possible to learn about the operation principle of artificial neural networks, the method of writing training data, the number of parameter calculations executed according to the amount of training data, and parameter optimization. The results of the education satisfaction survey for preservice teachers and incumbent teachers showed a positive response result of over 70% for each survey item, indicating high class application suitability.

• Journal of KIISE:Software and Applications
• /
• v.31 no.8
• /
• pp.991-998
• /
• 2004

In many practical teaming problems including bioinformatics area, there is a small amount of labeled data along with a large pool of unlabeled data. Labeled examples are fairly expensive to obtain because they require human efforts. In contrast, unlabeled examples can be inexpensively gathered without an expert. A common method with unlabeled data for data classification and analysis is co-training. This method uses a small set of labeled examples to learn a classifier in two views. Then each classifier is applied to all unlabeled examples, and co-training detects the examples on which each classifier makes the most confident predictions. After some iterations, new classifiers are learned in training data and the number of labeled examples is increased. In this paper, we propose a new co-training strategy using unlabeled data. And we evaluate our method with two classifiers and two experimental data: WebKB and BIND XML data. Our experimentation shows that the proposed co-training technique effectively improves the classification accuracy when the number of labeled examples are very small.

• The Journal of Information Technology
• /
• v.8 no.1
• /
• pp.51-56
• /
• 2005

The Back propagation algorithm is a very effective supervised training method for multi-layer feed forward neural networks. This paper studies the decision boundary formation based on the Back propagation algorithm. The discriminating powers of several neural network topology are also investigated against five manually created data sets. It is found that neural networks with multiple hidden layer perform better than single hidden layer.

• Proceedings of the KAIS Fall Conference
• /
• 2007.05a
• /
• pp.147-149
• /
• 2007

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.4
• /
• pp.1065-1071
• /
• 2007

A partial amendment of probability and statistics education in Korea has carried out from January, 2007. We have compared between the patial amendment and 7th national mathematics curriculum. Some ideas are proposed to achieve goals of the revision; textbooks of mathematics are well supervised by well-trained statisticians and teachers are periodically trained for the statistical knowledge.