• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.61.1-61.1
• /
• 2017

As the application of deep-learning methods has been succeeded in various fields, they have a high potential to be applied to space weather forecasting. Convolutional neural network, one of deep learning methods, is specialized in image recognition. In this study, we apply the AlexNet architecture, which is a winner of Imagenet Large Scale Virtual Recognition Challenge (ILSVRC) 2012, to the forecast of daily solar flare occurrence using the MatConvNet software of MATLAB. Our input images are SOHO/MDI, EIT $195{\AA}$, and $304{\AA}$ from January 1996 to December 2010, and output ones are yes or no of flare occurrence. We consider other input images which consist of last two images and their difference image. We select training dataset from Jan 1996 to Dec 2000 and from Jan 2003 to Dec 2008. Testing dataset is chosen from Jan 2001 to Dec 2002 and from Jan 2009 to Dec 2010 in order to consider the solar cycle effect. In training dataset, we randomly select one fifth of training data for validation dataset to avoid the over-fitting problem. Our model successfully forecasts the flare occurrence with about 0.90 probability of detection (POD) for common flares (C-, M-, and X-class). While POD of major flares (M- and X-class) forecasting is 0.96, false alarm rate (FAR) also scores relatively high(0.60). We also present several statistical parameters such as critical success index (CSI) and true skill statistics (TSS). All statistical parameters do not strongly depend on the number of input data sets. Our model can immediately be applied to automatic forecasting service when image data are available.

• Journal of Korean Society for Geospatial Information Science
• /
• v.7 no.2 s.14
• /
• pp.143-153
• /
• 1999

GIS have become easier to use and very popular. In recent year digital photogrammetric systems ire becoming cost-effective tools to build and update GIS databases. In close-range photogrammetry for the acquisition of geospatial data, the bundle adjustment needs both initial approximate values and control points to solve the exterior orientation parameters. This paper gives a review of applied and potential algorithms for estimating Initial approximate values before the bundle adjustment, develope new algorithms for determine the exterior orientation parameters, and gives a cost-effective methods for close-range digital photogrammetric system Modifications of existing DLT algorithm were made in this study for providing an efficient, economic, and more accurate photogrammetric data reduction technique. These modifications include robust approaches for automatic detection and elimination of all lands of gross errors in the measurement data, and incorporation of GPS to reduce the number of control points necessary for a DLT solution. Also, this paper derives a new method for space resection from a monocular image. A major advantage of proposed method is that the solution can be uniquely and analytically determined without initial approximate values of exterior orientation parameters and without iterative computation.

• Journal of Power System Engineering
• /
• v.20 no.3
• /
• pp.22-28
• /
• 2016

Energy consumption rapidly increases with industrial development. therefore an interest in the efficiency of various power converters is increasing. Especially, the field of high-efficiency small motors widely distributed for industrial and family use is considered a very important field in terms of efficient energy usage, and accordingly, in the field of small electric equipment, the use of BLDC that allows high-efficiency drive in an inductor gradually increases. However, for the BLDC drive, information on the position of the rotor is essential. Both methods using a magnetic encoder and an optical encoder to detect the information on the position of the rotor obtain the information by three position sensitive devices, and if any one of these position sensitive devices fails to function, no positional information can be obtained, so there is a limitation in implementing a position sensor with high reliability. In the paper, proposes a new type of encoder that can obtain the positional information on the position of the rotor using a single position sensor in order to overcome the issues that it has to use numerous signal flows and that the reliability is reduced for the acquisition of positional information generated by using multiple position detectors. The encoder in the proposed method replaced the function of generating positional information from multiple sensors with the shape of the encoder plate and the capture function of MICOM. In order to verify the validity of the position detection technique by the proposed encoder, a prototype was produced, and an experiment using the capture function of DSP was conducted through this.

• Korean Journal of Food Science and Technology
• /
• v.25 no.4
• /
• pp.391-394
• /
• 1993

For the automation of Tackjoo fermentation, a sensor measurable gas production during brewing and a controller were built. The performance tests were carried out at 10 litter Tackjoo fermentor, The sensor was consisted of a transparent acryl cell for bubble formation and photo-interrupter for the detection of bubbles of 0.018ml size. The fermentation controller was fabricated with a single chip microcomputer (MC68705R3) and provided with both the monitoring module of temperature measurement and the valve controling device for the cooling water circulation in coil type heat exchanger. The operation programs were developed and systemized in ROM. With this computer system, the gas production amount and rate were acquired during the Tackjoo fermentation. The fermentation curve based on the gas production rate showed a good agreement with that of alcohol concentration. The maximum rate of gas production was found after 24 hr at $30^{\circ}C$. The correlation equation between the gas production and alcohol concentration was established and used as the control algorithm of the fermentation.

• Korean Journal of Computational Design and Engineering
• /
• v.13 no.6
• /
• pp.403-411
• /
• 2008

The alignment of facial images is crucial for 2D face recognition. This is the same to facial meshes for 3D face recognition. Most of the 3D face recognition methods refer to 3D alignment but do not describe their approaches in details. In this paper, we focus on describing an automatic 3D alignment in viewpoint of quantitative analysis. This paper presents a framework of 3D face alignment and normalization based on feature points obtained by Active Shape Models (ASMs). The positions of eyes and mouth can give possibility of aligning the 3D face exactly in three-dimension space. The rotational transform on each axis is defined with respect to the reference position. In aligning process, the rotational transform converts an input 3D faces with large pose variations to the reference frontal view. The part of face is flopped from the aligned face using the sphere region centered at the nose tip of 3D face. The cropped face is shifted and brought into the frame with specified size for normalizing. Subsequently, the interpolation is carried to the face for sampling at equal interval and filling holes. The color interpolation is also carried at the same interval. The outputs are normalized 2D and 3D face which can be used for face recognition. Finally, we carry two sets of experiments to measure aligning errors and evaluate the performance of suggested process.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.8
• /
• pp.81-87
• /
• 1999

In general, feature detection and tracking algorithms is classified by EBGM using Garbor-jet, NNC-R and STK algorithm using pixel eigenvalue. In those algorithms, EBGM and NCC-R detect features with feature model, but STK algorithm has a characteristics of an automatic feature selection. In this paper, to solve the initial problem of NR tracking in STK algorithm, we detected features using STK algorithm in modelled feature region and tracked features with NR method. In tracking, to improve the tracking accuracy for features by NR method, we proposed BMA-NR method. We evaluated that BMA-NR method was superior to NBMA-NR in that feature tracking accuracy, since BMA-NR method was able to solve the local minimum problem due to search window size of NR.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.31 no.6
• /
• pp.485-492
• /
• 2019

The observation system has been developed to investigate the rip currents at Haeundae beach using X-band marine radar. X-band radar system can observe shape, size, and velocity of rip currents, which is difficult to obtain through field observation by conventional device. Algorithms which automatically detect locations, shapes, and magnitudes of rip currents were developed using time averaged X-band radar sea clutter images. X-band sea clutter images are transformed through 3D FFT into 2D wave number spectrum and frequency spectrum. Rip current velocities were estimated using differences in wave-number spectra and wave frequency spectra due to Doppler shift. The algorithm was verified by drift experiments. At Haeundae beach, the radar system exactly located the rip currents and found to be sustained for 1-2 days at fixed locations.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.28 no.1
• /
• pp.64-69
• /
• 2008

In order to detect the internal defects which occur in welding parts of pressure vessel and structures, radiographic testing and ultrasonic testing is applied. However, because of the risks of radiation exposure and film processing, radiographic testing takes a relatively long time to verify the test results and it has affected in the production process. Typically, the manual ultrasonic testing is not easy to reproduce the result and it is highly dependent on the tester's skills. The TOFD technique, one of the automatic ultrasonic testings is spreading alternatively. This research describes the comparing test results by applying radiographic testing and TOFD technique to a mock-up specimen incruding the flaws. The TOFD technique will contribute to improve the objective reliability of the ultrasonic technique.

• Journal of The Korean Astronomical Society
• /
• v.50 no.6
• /
• pp.157-165
• /
• 2017

$H_2O$ maser emission at 22 GHz in the circumstellar envelope is one of the good tracers of detailed physics and kinematics in the mass loss process of asymptotic giant branch stars. Long-term monitoring of an $H_2O$ maser spectrum with high time resolution enables us to clarify acceleration processes of the expanding shell in the stellar atmosphere. We monitored the $H_2O$ maser emission of the semi-regular variable R Crt with the Kagoshima 6-m telescope, and obtained a large data set of over 180 maser spectra over a period of 1.3 years with an observational span of a few days. Using an automatic peak detection method based on least-squares fitting, we exhaustively detected peaks as significant velocity components with the radial velocity on a $0.1kms^{-1}$ scale. This analysis result shows that the radial velocity of red-shifted and blue-shifted components exhibits a change between acceleration and deceleration on the time scale of a few hundred days. These velocity variations are likely to correlate with intensity variations, in particular during flaring state of $H_2O$ masers. It seems reasonable to consider that the velocity variation of the maser source is caused by shock propagation in the envelope due to stellar pulsation. However, it is difficult to explain the relationship between the velocity variation and the intensity variation only from shock propagation effects. We found that a time delay of the integrated maser intensity with respect to the optical light curve is about 150 days.

• Journal of Aquaculture
• /
• v.15 no.2
• /
• pp.87-93
• /
• 2002

To improve the efficiency of biological filters used for treating recycled wastewater of aquaculture, the conventional and advanced DynaSand Filters were tested. Applying the fluid mechanics and physical chemistry theories to wastewater treatment plant, the advanced filter focuses on detection of wastewater characteristics and automatic operation of DynaSand Filter to improve backwashing, oxygen transport, turbidity removal and continuous head loss. The Filter removes COD, ammonia, and suspended solids (SS), the major pollutants in aquaculture wastewater. The total volume of the DynaSand Filter is 70 L, while the working volume is 35 L per cycle. The removal efficiency of the advanced DynaSand Filter is 71 % for SS (as against 55 % for the conventional filter), 84 % for ammonia, 85 % for T-P, and 88 % for SRP.