• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.3
• /
• pp.328-334
• /
• 2020

At the recent practice test of the Remote Controlled Munition system (for practice), nine out of 125 samples were generated. Although 7.2 % misfires occurred, the acceptance test met the defense standards. Minimizing the probability of broken fuses is essential to reducing the number of samples and improving the AQL according to the process quality. In addition, it is necessary to increase military training and ensure user safety. In the case of practical grenades, hit-type detonators are applied. Unlike the normal design, which takes a hit by strikers, a different design of a hit by pressure from a pressure generator was used. This study analyzed the detonator surface through computational fluid dynamics. The results showed that the probability of functional weakness and retraction increased with increasing slope of the detonator surface. To overcome this, design changes were made to improve the fuse crimping process and increase the detonator holder seat. A performance test with the same number of samples from the whole quantity was operated. The probability of broken fuses was 0 %. Therefore, the reliability and performance of the ammunition can be improved and is expected to contribute to the drawing and process design when developing similar ammunition.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.999-1009
• /
• 2019

The importance of high-resolution sea ice maps of the Arctic Ocean is increasing due to the possibility of pioneering North Pole Routes and the necessity of precise climate prediction models. In this study,sea ice classification algorithms for two deep learning models were examined using Sentinel-1 A/B SAR data to generate high-resolution sea ice classification maps. Based on current ice charts, three classes (Open Water, First Year Ice, Multi Year Ice) of training data sets were generated by Arctic sea ice and remote sensing experts. Ten sea ice classification algorithms were generated by combing two deep learning models (i.e. Simple CNN and Resnet50) and five cases of input bands including incident angles and thermal noise corrected HV bands. For the ten algorithms, analyses were performed by comparing classification results with ground truth points. A confusion matrix and Cohen's kappa coefficient were produced for the case that showed best result. Furthermore, the classification result with the Maximum Likelihood Classifier that has been traditionally employed to classify sea ice. In conclusion, the Convolutional Neural Network case, which has two convolution layers and two max pooling layers, with HV and incident angle input bands shows classification accuracy of 96.66%, and Cohen's kappa coefficient of 0.9499. All deep learning cases shows better classification accuracy than the classification result of the Maximum Likelihood Classifier.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.597-608
• /
• 2022

Remotely sensed data have been used in various fields, such as disasters, agriculture, urban planning, and the military. Recently, the demand for the multitemporal dataset with the high-spatial-resolution has increased. This manuscript proposed an automatic image matching algorithm using a deep learning technique to utilize a multitemporal remotely sensed dataset. The proposed deep learning model was based on High Resolution Net (HRNet), widely used in image segmentation. In this manuscript, denseblock was added to calculate the correlation map between images effectively and to increase learning efficiency. The training of the proposed model was performed using the multitemporal orthophotos of the National Geographic Information Institute (NGII). In order to evaluate the performance of image matching using a deep learning model, a comparative evaluation was performed. As a result of the experiment, the average horizontal error of the proposed algorithm based on 80% of the image matching rate was 3 pixels. At the same time, that of the Zero Normalized Cross-Correlation (ZNCC) was 25 pixels. In particular, it was confirmed that the proposed method is effective even in mountainous and farmland areas where the image changes according to vegetation growth. Therefore, it is expected that the proposed deep learning algorithm can perform relative image registration and image matching of a multitemporal remote sensed dataset.

• Journal of Industrial Convergence
• /
• v.22 no.1
• /
• pp.137-148
• /
• 2024

This study aims to analyse the research trends and identify issues in elementary physical education in the new normal era. For this purpose, the taxonomic analysis method proposed by Spradley (2016) was applied, and 43 Korean academic articles were finally categorised and analysed. The findings are as follows. First, due to the changes in the educational environment caused by COVID-19, most of the remote and online physical education classes were conducted as content-oriented classes. It was found that there was a lack of communication between teachers and students in online physical education classes. Second, the difficulties of remote and online physical education classes and online and offline combined physical education classes, as well as research on how to overcome and improve them, were concentrated. Third, the need for evolution of physical education teachers and training of future professionals in line with the methodological transformation of primary physical education and the current situation was raised. In addition, the number of studies utilising blended learning, flipped learning, and new technologies, which have gained attention in primary physical education due to COVID-19, has increased. Based on the findings, we proposed the direction and future tasks of elementary physical education in the new normal era.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.6_2
• /
• pp.585-592
• /
• 2013

CBIR is an effective tool to search and extract image contents in a large remote sensing image database queried by an operator or end user. However, as imaging principles are different by sensors, their visual representation thus varies among image modality type. Considering images of various modalities archived in the database, image modality difference has to be tackled for the successful CBIR implementation. However, this topic has been seldom dealt with and thus still poses a practical challenge. This study suggests a cross modality CBIR (termed as the CM-CBIR) method that transforms given query feature vector by a supervised procedure in order to link between modalities. This procedure leverages the skill of analyst in training steps after which the transformed query vector is created for the use of searching in target images with different modalities. Current initial results show the potential of the proposed CM-CBIR method by delivering the image content of interest from different modality images. Despite its retrieval capability is outperformed by that of same modality CBIR (abbreviated as the SM-CBIR), the lack of retrieval performance can be compensated by employing the user's relevancy feedback, a conventional technique for retrieval enhancement.

• International journal of advanced smart convergence
• /
• v.8 no.4
• /
• pp.147-153
• /
• 2019

Recently, the perception of software education, which had been considered as a field of education for programmers in this field, is changing in response to recent changes with the trend of 4th industrial revolution. Major counties competitively invest in software education and the target age group for software education is also on the decline. However, the traditional text-based programing languages such as JAVA and Python, have a high entry barrier. To address the shortcoming, a variety of methods have been recently proposed for the effective software education for kindergarten and elementary school student. In this paper, we propose a robot-based coding education system with steps for coding education for effective software education. The proposed method is divided into three stages, depending on the level of the student being trained in the software coding education to interact with robots. The proposed stages consists of unplugged coding using a remote control, coding using a graphic-based programming language and text- based coding. We conducted an experiment with performing separate missions while providing propoer tutorials for each stage to verify the effectiveness of the proposed software education system.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.144-147
• /
• 1999

The objective of this study is to quantitatively evaluate the effects of various SAR speckle reduction methods for multisource land-cover classification by backpropagation neural network, especially over the coastal region. The land-cover classification using neural network has an advantage over conventional statistical approaches in that it is distribution-free and no prior knowledge of the statistical distributions of the classes is needed. The goal of multisource land-cover classification acquired by different sensors is to reduce the classification error, and consequently SAR can be utilized an complementary tool to optical sensors. SAR speckle is, however, an serious limiting factor when it is exploited for land-cover classification. In order to reduce this problem. we test various speckle methods including Frost, Median, Kuan and EPOS. Interpreting the weights about training pixel samples, the “Importance Value” of each SAR images that reduced speckle can be estimated based on its contribution to the classification. In this study, the “Importance Value” is used as a criterion of the effectiveness.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.7
• /
• pp.987-993
• /
• 2014

Pitching machines have been around for many years for casual amusement purpose or professional athletes' training usage, and so forth. The current pitching machines are usually built on the firm ground and do not have any mobility function. In this paper, we develop a pitching machine that has both ball-shooting and mobility functions. Our developed pitching machine consists of two parts. The upper body part has a function of shooting a ball using two DC motors and the lower body part has a function of mobility like mobile robots by using two wheels governed by DC motors. All these functions are operated wirelessly by Android smartphones via bluetooth. The control of each DC motor is done by ${\epsilon}$-PID control method in which the gain tuning is simplied by using a single parameter ${\epsilon}$. Simulation and actual experiment show that our developed pitching machine has both nontrivial shooting and mobility features.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.635-638
• /
• 2006

Regression of conventional prediction techniques in data mining uses the model which is generated from the training step. This model is applied to new input data without any change. If this model is applied directly to time series, the rate of prediction accuracy will be decreased. This paper proposes an incremental regression for time series prediction like typhoon track prediction. This technique considers the characteristic of time series which may be changed over time. It is composed of two steps. The first step executes a fractional process for applying input data to the regression model. The second step updates the model by using its information as new data. Additionally, the model is maintained by only recent data in a queue. This approach has the following two advantages. It maintains the minimum information of the model by using a matrix, so space complexity is reduced. Moreover, it prevents the increment of error rate by updating the model over time. Accuracy rate of the proposed method is measured by RME(Relative Mean Error) and RMSE(Root Mean Square Error). The results of typhoon track prediction experiment are performed by the proposed technique IMLR(Incremental Multiple Linear Regression) is more efficient than those of MLR(Multiple Linear Regression) and SVR(Support Vector Regression).