• Journal of the Korea Computer Graphics Society
• /
• v.25 no.1
• /
• pp.23-32
• /
• 2019

Cybersickness is a symptom of dizziness that occurs while experiencing Virtual Reality (VR) technology and it is presumed to occur mainly by crosstalk between the sensory and cognitive systems. However, since the sensory and cognitive systems cannot be measured objectively, it is difficult to measure cybersickness. Therefore, methodologies for measuring cybersickness have been studied in various ways. Traditional studies have collected answers to questionnaires or analyzed EEG data using machine learning algorithms. However, the system relying on the questionnaires lacks objectivity, and it is difficult to obtain highly accurate measurements with the machine learning algorithms. In this work, we apply Deep Neural Network (DNN) deep learning algorithm for objective cybersickness measurement from EEG data. We also propose a data preprocessing for learning and network structures allowing us to achieve high performance when learning EEG data with the deep learning algorithms. Our approach provides cybersickness measurement with an accuracy up to 98.88%. Besides, we analyze video characteristics where cybersickness occurs by examining the video segments causing cybersickness in the experiments. We discover that cybersickness happens even in unusually persistent changes in the darkness such as the light in a room keeps switching on and off.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1542-1550
• /
• 2019

Legacy studies for classifying arrhythmia have been studied to improve the accuracy of classification, Neural Network, Fuzzy, etc. Deep learning is most frequently used for arrhythmia classification using error backpropagation algorithm by solving the limit of hidden layer number, which is a problem of neural network. In order to apply a deep learning model to an ECG signal, it is necessary to select an optimal model and parameters. In this paper, we propose optimal parameter extraction method based on a deep learning. For this purpose, R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval segment is modelled. And then, the weights were learned by supervised learning method through deep learning and the model was evaluated by the verification data. The detection and classification rate of R wave and PVC is evaluated through MIT-BIH arrhythmia database. The performance results indicate the average of 99.77% in R wave detection and 97.84% in PVC classification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1341-1347
• /
• 2020

Legacy studies for classifying arrhythmia have been studied in order to improve the accuracy of classification, Neural Network, Fuzzy, Machine Learning, etc. In particular, deep learning is most frequently used for arrhythmia classification using error backpropagation algorithm by solving the limit of hidden layer number, which is a problem of neural network. In order to apply a deep learning model to an ECG signal, it is necessary to select an optimal model and parameters. In this paper, we propose parameter extraction based on AR and arrhythmia classification through a deep learning. For this purpose, the R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval is modelled. And then, the weights were learned by supervised learning method through deep learning and the model was evaluated by the verification data. The classification rate of PVC is evaluated through MIT-BIH arrhythmia database. The achieved scores indicate arrhythmia classification rate of over 97%.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2334-2340
• /
• 2021

Radioactive particle tracking (RPT) is a minimally invasive nuclear technique that tracks a radioactive particle inside a volume of interest by means of a mathematical location algorithm. During the past decades, many algorithms have been developed including ones based on artificial intelligence techniques. In this study, RPT technique is applied in a simulated test section that employs a simplified mixer filled with concrete, six scintillator detectors and a¹³⁷Cs radioactive particle emitting gamma rays of 662 keV. The test section was developed using MCNPX code, which is a mathematical code based on Monte Carlo simulation, and 3516 different radioactive particle positions (x,y,z) were simulated. Novelty of this paper is the use of a location algorithm based on a deep learning model, more specifically a 6-layers deep rectifier neural network (DRNN), in which hyperparameters were defined using a Bayesian optimization method. DRNN is a type of deep feedforward neural network that substitutes the usual sigmoid based activation functions, traditionally used in vanilla Multilayer Perceptron Networks, for rectified activation functions. Results show the great accuracy of the DRNN in a RPT tracking system. Root mean squared error for x, y and coordinates of the radioactive particle is, respectively, 0.03064, 0.02523 and 0.07653.

• Journal of Astronomy and Space Sciences
• /
• v.40 no.2
• /
• pp.79-88
• /
• 2023

On Aug. 4, 2022, at 23:08:48 (UTC), the Korea Pathfinder Lunar Orbiter (KPLO), also known as Danuri, was launched using a SpaceX Falcon 9 launch vehicle. Currently, KPLO is successfully conducting its science mission around the Moon. The National Aeronautics and Space Administration (NASA)'s Deep Space Network (DSN) was utilized for the successful flight operation of KPLO. A great deal of joint effort was made between the Korea Aerospace Research Institute (KARI) and NASA DSN team since the beginning of KPLO ground system design for the success of the mission. The efficient utilization and management of NASA DSN in deep space exploration are critical not only for the spacecraft's telemetry and command but also for tracking the flight dynamics (FD) operation. In this work, the top-level DSN interface architecture, detailed workflows, DSN support levels, and practical lessons learned from the joint team's efforts are presented for KPLO's successful FD operation. Due to the significant joint team's efforts, KPLO is currently performing its mission smoothly in the lunar mission orbit. Through KPLO cooperative operation experience with DSN, a more reliable and efficient partnership is expected not only for Korea's own deep space exploration mission but also for the KARI-NASA DSN joint support on other deep space missions in the future.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.303-306
• /
• 2016

In this paper, we propose a method to accelerate convolutional neural network by utilizing a GPGPU. Convolutional neural network is a sort of the neural network learning features of images. Convolutional neural network is suitable for the image processing required to learn a lot of data such as images. The convolutional layer of the conventional CNN required a large number of multiplications and it is difficult to operate in the real-time on the embedded environment. In this paper, we reduce the number of multiplications through Winograd convolution operation and perform parallel processing of the convolution by utilizing SIMT-based GPGPU. The experiment was conducted using ModelSim and TestDrive, and the experimental results showed that the processing time was improved by about 17%, compared to the conventional convolution.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.46.2-46.2
• /
• 2021

We present solar event auto detection using deep-learning-based object detection algorithms and DeepSDO event dataset. DeepSDO event dataset is a new detection dataset with bounding boxed as ground-truth for three solar event (coronal holes, sunspots and prominences) features using Solar Dynamics Observatory data. To access the reliability of DeepSDO event dataset, we compared to HEK data. We train two representative object detection models, the Single Shot MultiBox Detector (SSD) and the Faster Region-based Convolutional Neural Network (R-CNN) with DeepSDO event dataset. We compared the performance of the two models for three solar events and this study demonstrates that deep learning-based object detection can successfully detect multiple types of solar events. In addition, we provide DeepSDO event dataset for further achievements event detection in solar physics.

• Journal of Astronomy and Space Sciences
• /
• v.31 no.1
• /
• pp.51-61
• /
• 2014

In this work, the preliminary analysis on both the tracking schedule and measurements characteristics for the spacecraft on the phase of lunar transfer and capture is performed. To analyze both the tracking schedule and measurements characteristics, lunar transfer and capture phases' optimized trajectories are directly adapted from former research, and eleven ground tracking facilities (three Deep Space Network sties, seven Near Earth Network sites, one Daejeon site) are assumed to support the mission. Under these conceptual mission scenarios, detailed tracking schedules and expected measurement characteristics during critical maneuvers (Trans Lunar Injection, Lunar Orbit Insertion and Apoapsis Adjustment Maneuver), especially for the Deajeon station, are successfully analyzed. The orders of predicted measurements' variances during lunar capture phase according to critical maneuvers are found to be within the order of mm/s for the range and micro-deg/s for the angular measurements rates which are in good agreement with the recommended values of typical measurement modeling accuracies for Deep Space Networks. Although preliminary navigation accuracy guidelines are provided through this work, it is expected to give more practical insights into preparing the Korea's future lunar mission, especially for developing flight dynamics subsystem.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1291-1298
• /
• 2017

Optical coherence tomography (OCT) is the most common medical imaging device with the ability to image the retina in eyes at micrometer resolution and to visualize the pathological indicators of many retinal diseases such as Age-Related Macular Degeneration (AMD) and diabetic retinopathy. Accordingly, there have been research activities to analyze and process OCT images to identify those indicators and make medical decisions based on the findings. In this paper, we use a deep convolutional neural network for analysis of OCT volume data to distinguish AMD from normal patients. We propose a novel approach where images in each OCT volume are grouped together into sub-volumes and the network is trained by those sub-volumes instead of individual images. We conducted an experiment using public data set to evaluate the performance of the proposed approach. The experiment confirmed performance improvement of our approach over the traditional image-by-image training approach.

• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1182-1194
• /
• 2018

The Dynamic Adaptive Streaming over HTTP(DASH) is envisioned to evolve to meet an increasing demand on providing seamless video streaming services in the near future. The DASH performance heavily depends on the client's adaptive quality selection algorithm that is not included in the standard. The existing conventional algorithms are basically based on a procedural algorithm that is not easy to capture and reflect all variations of dynamic network and traffic conditions in a variety of network environments. To solve this problem, this paper proposes a novel quality selection mechanism based on the Deep Q-Network(DQN) model, the DQN-based DASH Adaptive Bitrate(ABR) mechanism. The proposed mechanism adopts a new reward calculation method based on five major performance metrics to reflect the current conditions of networks and devices in real time. In addition, the size of the consecutive video segment to be downloaded is also considered as a major learning metric to reflect a variety of video encodings. Experimental results show that the proposed mechanism quickly selects a suitable video quality even in high error rate environments, significantly reducing frequency of quality changes compared to the existing algorithm and simultaneously improving average video quality during video playback.