• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.8
• /
• pp.1619-1625
• /
• 2017

Civil global navigation satellite system (GNSS) does not meet user performance requirements for specific PNT (Positioning, Navigation, and Time) applications. Therefore, various differential systems are used to augment GNSS for improving positioning accuracy and integrity. The MTSAT satellite augmentation system (MSAS) is the Japanese satellite based augmentation system. This paper is for analyzing the characteristics of Japanese MSAS in Korean peninsula. First of all, it was done for analyzing not only DGNSS navigation signal but also the navigation parameter through simulation and experimental tests. As a result of data analyses, the sufficient navigation satellites to determine 3-D position based on DGNSS are simultaneously available at MSAS monitering station and the southern region of Korean peninsula. It was verified that the carrier to noise signals are stable to maintain the reliable 3-D position and that the level of 2m (2drms) accuracy is very similar to the ordinary worldwide DGNSS as well.

• Annals of Rehabilitation Medicine
• /
• v.42 no.6
• /
• pp.777-787
• /
• 2018

Objective To examine the long-term effects of the low-frequency repetitive transcranial magnetic stimulation (LF-rTMS) combined with task-specific training on paretic hand function following subacute stroke. Methods Sixteen participants were randomly selected and grouped into two: the experimental group (real LF-rTMS) and the control group (sham LF-rTMS). All the 16 participants were then taken through a 1-hour task-specific training of the paretic hand. The corticospinal excitability (motor evoke potential [MEP] amplitude) of the non-lesioned hemisphere, and the paretic hand performance (Wolf Motor Function Test total movement time [WMFT-TMT]) were evaluated at baseline, after the LF-rTMS, immediately after task-specific training, 1 and 2 weeks after the training. Results Groups comparisons showed a significant difference in the MEP after LF-rTMS and after the training. Compared to the baseline, the MEP of the experimental group significantly decreased after LF-rTMS and after the training and that effect was maintained for 2 weeks. Group comparisons showed significant difference in WMFT-TMT after the training. Only in the experimental group, the WMFT-TMT of the can lifting item significantly reduced compared to the baseline and the effect was sustained for 2 weeks. Conclusion The results of this study established that the improvement in paretic hand after task-specific training was enhanced by LF-rTMS and it persisted for at least 2 weeks.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.123-131
• /
• 2019

In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.346-347
• /
• 2021

For pattern recognition for machine learning, the larger the amount of learning data, the better its performance. However, it is not always possible to secure a large amount of learning data with the types and information of patterns that must be detected in daily life. Therefore, it is necessary to significantly inflate a small data set for general machine learning. In this study, we study techniques to augment data so that machine learning can be performed. A representative method of performing machine learning using a small data set is the transfer learning technique. Transfer learning is a method of obtaining a result by performing basic learning with a general-purpose data set and then substituting the target data set into the final stage. In this study, a learning model trained with a general-purpose data set such as ImageNet is used as a feature extraction set using augmented data to detect a desired pattern.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1451-1466
• /
• 2023

In the context of maritime emergencies, the utilization of drones has rapidly increased, with a particular focus on their application in search and rescue operations. Deep learning models utilizing drone images for the rapid detection of distressed vessels and other maritime drift objects are gaining attention. However, effective training of such models necessitates a substantial amount of diverse training data that considers various weather conditions and vessel states. The lack of such data can lead to a degradation in the performance of trained models. This study aims to enhance the performance of deep learning models for distress ship detection by developing a maritime environment simulator to augment the dataset. The simulator allows for the configuration of various weather conditions, vessel states such as sinking or capsizing, and specifications and characteristics of drones and sensors. Training the deep learning model with the dataset generated through simulation resulted in improved detection performance, including accuracy and recall, when compared to models trained solely on actual drone image datasets. In particular, the accuracy of distress ship detection in adverse weather conditions, such as rain or fog, increased by approximately 2-5%, with a significant reduction in the rate of undetected instances. These results demonstrate the practical and effective contribution of the developed simulator in simulating diverse scenarios for model training. Furthermore, the distress ship detection deep learning model based on this approach is expected to be efficiently applied in maritime search and rescue operations.

• Journal of the Korea Convergence Society
• /
• v.8 no.12
• /
• pp.55-62
• /
• 2017

The Named Entity Recognition system is a system that recognizes words or phrases with object names such as personal name (PS), place name (LC), and group name (OG) in the document as corresponding object names. Traditional approaches to named entity recognition include statistical-based models that learn models based on hand-crafted features. Recently, it has been proposed to construct the qualities expressing the sentence using models such as deep-learning based Recurrent Neural Networks (RNN) and long-short term memory (LSTM) to solve the problem of sequence labeling. In this research, to improve the performance of the Korean named entity recognition system, we used a hand-crafted feature, part-of-speech tagging information, and pre-built lexicon information to augment features for representing sentence. Experimental results show that the proposed method improves the performance of Korean named entity recognition system. The results of this study are presented through github for future collaborative research with researchers studying Korean Natural Language Processing (NLP) and named entity recognition system.

• Journal of Korean Society of Transportation
• /
• v.20 no.1
• /
• pp.77-90
• /
• 2002

Network expansion has been an inevitable method for most traffic equilibrium assignments to consider intersection movements such as intersection delays. The drawback of network expansion is that because it dramatically increases network sizes to emulate possible directional movements as corresponding links, not only is complexities for building network amplified, but computational performance is shrunk. This paper Proposes a new variational inequality formulation for a user-optimal traffic equilibrium assignment model to explicitly consider directional delays without building expanded network structures. In the formulation, directional delay functions are directly embedded into the objective function, thus any modification of networks is not required. By applying a vine-based shortest Path algorithm into the diagonalization algorithm to solve the problem, it is additionally demonstrated that various loop-related movements such as U-Turn, P-Turn, etc., which are frequently witnessed near urban intersections, can also be imitated by blocking some turning movements of intersections. The proposed formulation expects to augment computational performance through reduction of network-building complexities.

• Applied Biological Chemistry
• /
• v.50 no.4
• /
• pp.362-366
• /
• 2007

This study was conducted to examine the effects of Asterias amurensis prethanol extract on growth performance, serum traits, and superoxide production of phagocytes in Sebastes schlegeli. The effects of Asterias amurensis extract on growth performance, specific growth rate (SGR), feed concentration ratio (FCR), coefficient of fatness (CF), and survival rate (SR) of fish fed diets containing various concentrations of Asterias amurensis extract were measured. There were no significant differences in SGR, FCR, CF, and SR among the experimental groups. This result was produced because experimental diets were coated to prevent repellent action of fish. To investigate the effects of Asterias amurensis extract on the metabolism, the contents of glucose, glutamic oxaloacetic transaminase (GOT), and total cholesterol in serum were measured. The contents of glucose and total cholesterol in serum increased dose-dependently and serum GOT content showed no significant difference among the experimental groups, suggesting that Asterias amurensis extract was non-toxic material. To confirm the effects of Asterias amurensis extract on the immune system of fish, superoxide production of phagocytes was measured. Asterias amurensis extract caused a dose-dependent increase of superoxide production of phagocytes. When considering these results, Asterias amurensis extract could be utilized as an additive to augment immune function in diets.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.449-460
• /
• 2021

ASVspoof 2017 deals with detection of replay attacks and aims to classify real human voices and fake voices. The spoofed voice refers to the voice that reproduces the original voice by different types of microphones and speakers. data augmentation research on image data has been actively conducted, and several studies have been conducted to attempt data augmentation on voice. However, there are not many attempts to augment data for voice replay attacks, so this paper explores how audio modification through data augmentation techniques affects the detection of replay attacks. A total of 7 data augmentation techniques were applied, and among them, dynamic value change (DVC) and pitch techniques helped improve performance. DVC and pitch showed an improvement of about 8% of the base model EER, and DVC in particular showed noticeable improvement in accuracy in some environments among 57 replay configurations. The greatest increase was achieved in RC53, and DVC led to an approximately 45% improvement in base model accuracy. The high-end recording and playback devices that were previously difficult to detect were well identified. Based on this study, we found that the DVC and pitch data augmentation techniques are helpful in improving performance in the voice spoofing detection problem.