• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.46.3-47
• /
• 2020

Variations in the brightness of asteroids are caused by their spins, irregular shapes and companions. Thus, in principle, the spin state and shape model of a single object or, a combined model of spins, shapes and mutual orbit of a multiple components can be constructed from the analysis of light curves obtained from the time-series photometry. Using ground- and space-based facilities, a number of time-series photometric observations of asteroids have been conducted to find the possible causes of their light variations. Nonetheless, only about 2% of the known asteroids have been confirmed for their rotation periods. Therefore, a follow-on systematic photometric survey of asteroids is essential. We started an asteroid light curve survey for this purpose using Korea Microlensing Telescope Network (KMTNet) during 199 nights between the second half of 2019 and the first half of 2020. We monitored within a 2° × 14° region of the sky per each night with 25 min cadences. In order to observe as many asteroids as possible with a single exposure, we mostly focus on the ecliptic plane. In our survey, 25,925 asteroids were observed and about 8,000 of them were confirmed for their rotation periods. In addition, using KMTNet's 24-hour continuous monitoring, we collected many composite light curves of slow rotating asteroids that were rarely obtained with previous observations. In this presentation, we will introduce the typical light curves of asteroids obtained from our survey and present a statistical analysis of spin states and shapes of the asteroids from this study.

• Journal of Computing Science and Engineering
• /
• v.12 no.1
• /
• pp.24-35
• /
• 2018

Deep convolutional neural network (DCNN) is an advanced technology in image recognition. Because of extreme computing resource requirements, DCNN implementation with software alone cannot achieve real-time requirement. Therefore, the need to implement DCNN accelerator hardware is increasing. In this paper, we present a field programmable gate array (FPGA)-based hardware accelerator design of DCNN targeting handwritten Hangul character recognition application. Also, we present design optimization techniques in SDAccel environments for searching the optimal FPGA design space. The techniques we used include memory access optimization and computing unit parallelism, and data conversion. We achieved about 11.19 ms recognition time per character with Xilinx FPGA accelerator. Our design optimization was performed with Xilinx HLS and SDAccel environment targeting Kintex XCKU115 FPGA from Xilinx. Our design outperforms CPU in terms of energy efficiency (the number of samples per unit energy) by 5.88 times, and GPGPU in terms of energy efficiency by 5 times. We expect the research results will be an alternative to GPGPU solution for real-time applications, especially in data centers or server farms where energy consumption is a critical problem.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.496-502
• /
• 2021

Recently, deep speaker embedding approach has been widely used in text-independent speaker verification, which shows better performance than the traditional i-vector approach. In this work, to improve the deep speaker embedding approach, we propose a novel method called group-based speaker embedding which incorporates group information. We cluster all speakers of the training data into a predefined number of groups in an unsupervised manner, so that a fixed-length group embedding represents the corresponding group. A Group Decision Network (GDN) produces a group weight, and an aggregated group embedding is generated from the weighted sum of the group embeddings and the group weights. Finally, we generate a group-based embedding by adding the aggregated group embedding to the deep speaker embedding. In this way, a speaker embedding can reduce the search space of the speaker identity by incorporating group information, and thereby can flexibly represent a significant number of speakers. We conducted experiments using the VoxCeleb1 database to show that our proposed approach can improve the previous approaches.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.4
• /
• pp.54-62
• /
• 2018

As a part of realization of artificial intelligence signal(AI Signal), this study proposed an actuated signal algorithm based on vehicle queue length that estimates in real time by deep learning. In order to implement the algorithm, we built an API(COM Interface) to control the micro traffic simulator Vissim in the tensorflow that implements the deep learning model. In Vissim, when the link travel time and the traffic volume collected by signal cycle are transferred to the tensorflow, the vehicle queue length is estimated by the deep learning model. The signal time is calculated based on the vehicle queue length, and the simulation is performed by adjusting the signaling inside Vissim. The algorithm developed in this study is analyzed that the vehicle delay is reduced by about 5% compared to the current TOD mode. It is applied to only one intersection in the network and its effect is limited. Future study is proposed to expand the space such as corridor control or network control using this algorithm.

• Journal of The Korean Astronomical Society
• /
• v.56 no.2
• /
• pp.213-224
• /
• 2023

Type II solar radio bursts show frequency drifts from high to low over time. They have been known as a signature of coronal shock associated with Coronal Mass Ejections (CMEs) and/or flares, which cause an abrupt change in the space environment near the Earth (space weather). Therefore, early detection of type II bursts is important for forecasting of space weather. In this study, we develop a deep-learning (DL) model for the automatic detection of type II bursts. For this purpose, we adopted a 1-D Convolution Neutral Network (CNN) as it is well-suited for processing spatiotemporal information within the applied data set. We utilized a total of 286 radio burst spectrum images obtained by Hiraiso Radio Spectrograph (HiRAS) from 1991 and 2012, along with 231 spectrum images without the bursts from 2009 to 2015, to recognizes type II bursts. The burst types were labeled manually according to their spectra features in an answer table. Subsequently, we applied the 1-D CNN technique to the spectrum images using two filter windows with different size along time axis. To develop the DL model, we randomly selected 412 spectrum images (80%) for training and validation. The train history shows that both train and validation losses drop rapidly, while train and validation accuracies increased within approximately 100 epoches. For evaluation of the model's performance, we used 105 test images (20%) and employed a contingence table. It is found that false alarm ratio (FAR) and critical success index (CSI) were 0.14 and 0.83, respectively. Furthermore, we confirmed above result by adopting five-fold cross-validation method, in which we re-sampled five groups randomly. The estimated mean FAR and CSI of the five groups were 0.05 and 0.87, respectively. For experimental purposes, we applied our proposed model to 85 HiRAS type II radio bursts listed in the NGDC catalogue from 2009 to 2016 and 184 quiet (no bursts) spectrum images before and after the type II bursts. As a result, our model successfully detected 79 events (93%) of type II events. This results demonstrates, for the first time, that the 1-D CNN algorithm is useful for detecting type II bursts.

• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.2
• /
• pp.49.2-49.2
• /
• 2016

The number of discovery of asteroids with peculiar rotational states has recently increased, and hence a novel approach for lightcurve analysis is considered to be critical. In order to investigate objects such as Non-Principal Axis (NPA) rotator, we selected a NPA candidate, (5247) Kryolv as our target considering its Principal Axis Rotation (PAR) code and the visibility in early 2016. The observations of Krylov were made using Korea Microlensing Telescope Network (KMTNet) 1.6 m telescopes installed at the three southern sites with TO (Target of Opportunity) observation mode. We conducted R-band time-series photometry over a total of 51 nights from January to April 2016 with several exposures during each allocated run. The ensemble normalization photometry was employed using the AAVSO Photomtric All-Sky Survey (APASS) catalog for the standardization. We successfully confirmed its NPA spin state based on the deviation from the reduced lightcurve, and thus Krylov is recorded as the first NPA rotator of its kind in the main-belt, with its precession and rotation periods, $P{\varphi}=81.18h$ and $P_{\Psi}=67.17h$, respectively. In this paper, we present the spin direction, the 3D shape model and taxonomy of the newly confirmed NPA asteroid (5247) Krylov.

• Journal of The Korean Astronomical Society
• /
• v.52 no.3
• /
• pp.71-82
• /
• 2019

We derive the geometric albedo of a near-Earth asteroid, (4179) Toutatis, to investigate its surface physical conditions. The asteroid has been studied rigorously not only via ground-based photometric, spectrometric, polarimetric, and radar observations but also via in situ observation by the Chinese Chang'e-2 space probe; however, its geometric albedo is not well understood. We conducted V-band photometric observations when the asteroid was at opposition in April 2018 using the three telescopes in the southern hemisphere that compose the Korea Microlensing Telescope Network (KMTNet). The observed time-variable cross section was corrected using the radar shape model. We find that Toutatis has a geometric albedo $p_V=0.185^{+0.045}_{-0.039}$, which is typical of S-type asteroids. We compare the geometric albedo with archival polarimetric data and further find that the polarimetric slope-albedo law provides a reliable estimate for the albedo of this S-type asteroid. The thermal infrared observation also produced similar results if the size of the asteroid is updated to match the results from Chang'e-2. We conjecture that the surface of Toutatis is covered with grains smaller than that of the near-Sun asteroids including (1566) Icarus and (3200) Phaethon.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.11
• /
• pp.441-448
• /
• 2019

Previous researches on automatic spacing of Korean sentences has been researched to correct spacing errors by using n-gram based statistical techniques or morpheme analyzer to insert blanks in the word boundary. In this paper, we propose an end-to-end automatic word spacing by using deep neural network. Automatic word spacing problem could be defined as a tag classification problem in unit of syllable other than word. For contextual representation between syllables, Bi-LSTM encodes the dependency relationship between syllables into a fixed-length vector of continuous vector space using forward and backward LSTM cell. In order to conduct automatic word spacing of Korean sentences, after a fixed-length contextual vector by Bi-LSTM is classified into auto-spacing tag(B or I), the blank is inserted in the front of B tag. For tag classification method, we compose three types of classification neural networks. One is feedforward neural network, another is neural network language model and the other is linear-chain CRF. To compare our models, we measure the performance of automatic word spacing depending on the three of classification networks. linear-chain CRF of them used as classification neural network shows better performance than other models. We used KCC150 corpus as a training and testing data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3712-3729
• /
• 2020

Smoke detection is helpful for early fire detection. With its large coverage area and low cost, vision-based smoke detection technology is the main research direction of outdoor smoke detection. We propose a two-stage smoke detection method combined with block Deep Normalization and Convolutional Neural Network (DNCNN) and visual change image. In the first stage, each suspected smoke region is detected from each frame of the images by using block DNCNN. According to the physical characteristics of smoke diffusion, a concept of visual change image is put forward in this paper, which is constructed by the video motion change state of the suspected smoke regions, and can describe the physical diffusion characteristics of smoke in the time and space domains. In the second stage, the Support Vector Machine (SVM) classifier is used to classify the Histogram of Oriented Gradients (HOG) features of visual change images of the suspected smoke regions, in this way to reduce the false alarm caused by the smoke-like objects such as cloud and fog. Simulation experiments are carried out on two public datasets of smoke. Results show that the accuracy and recall rate of smoke detection are high, and the false alarm rate is much lower than that of other comparison methods.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.5
• /
• pp.515-528
• /
• 2020

Underground concrete structures are usually designed to be used for decades, but in recent years, many of them are nearing their original life expectancy. As a result, it is necessary to promptly inspect and repair the structure, since it can cause lost of fundamental functions and bring unexpected problems. Therefore, personnel-based inspections and repairs have been underway for maintenance of underground structures, but nowadays, objective inspection technologies have been actively developed through the fusion of deep learning and image process. In particular, various researches have been conducted on developing a concrete crack detection algorithm based on supervised learning. Most of these studies requires a large amount of image data, especially, label images. In order to secure those images, it takes a lot of time and labor in reality. To resolve this problem, we introduce a method to increase the accuracy of crack area detection, improved by 0.25% on average by applying adversarial learning in this paper. The adversarial learning consists of a segmentation neural network and a discriminator neural network, and it is an algorithm that improves recognition performance by generating a virtual label image in a competitive structure. In this study, an efficient deep neural network learning method was proposed using this method, and it is expected to be used for accurate crack detection in the future.