• The Journal of Information Systems
• /
• v.27 no.3
• /
• pp.123-140
• /
• 2018

Purpose The purpose of this study is to explore the optimal trading frequency which is useful for stock price prediction by using deep learning for charting image data. We also want to identify the appropriate time for accurate forecasting of stock price when performing pattern analysis. Design/methodology/approach In order to find the optimal trading frequency patterns and forecast timings, this study is performed as follows. First, stock price data is collected using OpenAPI provided by Daishin Securities, and candle chart images are created by data frequency and forecasting time. Second, the patterns are generated by the charting images and the learning is performed using the CNN. Finally, we find the optimal trading frequency patterns and forecasting timings. Findings According to the experiment results, this study confirmed that when the 10 minute frequency data is judged to be a decline pattern at previous 1 tick, the accuracy of predicting the market frequency pattern at which the market decreasing is 76%, which is determined by the optimal frequency pattern. In addition, we confirmed that forecasting of the sales frequency pattern at previous 1 tick shows higher accuracy than previous 2 tick and 3 tick.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.26 no.7
• /
• pp.656-665
• /
• 2015

In this paper, we improved the clarity and quality of the radar imaging by applying motion compensation for time-frequency transform in B-ISAR imaging. The proposed motion compensation algorithm using UWB radar is verified. B-ISAR algorithm procedure and time-frequency transform for improved motion compensation are provided for theoretical ground. The image was created by a UWB Radar B-ISAR imaging algorithm method. Also, creating a B-ISAR imaging algorithm for motion compensation of time-frequency transformation method was used. The B-ISAR Imaging algorithm is implemented using STFT(Short-Time Fourier Transform), GWT(Gabor Wavelet Transform), and WVD(Wigner-Ville Distribution) approaches. The performance of STFT is compared with the GWT and WVD algorithms. It is found that the WVD image shows more clarity and decreased spread phenomenon than other methods.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.6_2
• /
• pp.1055-1062
• /
• 2022

In this study, the mechanical properties of 80% cold-rolled austenitic 316L stainless steel were evaluated using specimens subjected to reverse transformation at 500-750℃ for 20 minutes and reverse transformation at 700℃ for 2-60 minutes. Also, for the elastic wave obtained from the tensile test, the dominant frequency according to the reverse transformation condition was investigated by time-frequency analysis. The SEM image of the 80% cold-rolled material was transformed into martensite and showed line and cross shapes. The TEM image showed that line shapes were shown at the grain, and grain boundary of martensite. The higher the heat treatment temperature and the longer time, the larger the grain. Tensile strength decreased as the heat treatment temperature and time increased, but elongation increased. Hardness was proportional to tensile strength. This is because the grain with different directions showed the same direction due to reverse transformation. The dominant frequency was decreased and then increased as the temperature and time increased. This is because the direction of the grain is different at a low temperature and the same direction is shown at a high temperature.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.4
• /
• pp.26-34
• /
• 2008

This study focus on segmentation process that classifies road surfaces into 5 different categories, dry, wet water, icy, and snowy surfaces by analyzing asphalt-paved road images taken in daylight. By using the polarization coefficients, the proportions of horizontally polarized components to vertically polarized components, regions with over 1.3 polarization coefficients are classified as wet surfaces. Except for wet surfaces, the decision process a lies time-frequency analysis to other parts by using the third order wavelet packet transform. In addition, by using the average frequency characteristics of dry and icy surfaces from image templates, decide which is closer to a test image, and finally identify dry and icy surfaces. It is confirmed that the reposed estimation and segmentation of recognition on various images. This can be interpreted as an indication that image-only mad surface condition supervision is probable.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.55-60
• /
• 2006

The proposed method uses FFT(Fast Fourier Transform) and neural networks in order to extract texts in real time. In general, text areas are found in the higher frequency domain, thus, can be characterized using FFT. The neural network are learned by character region(high frequency) and non character region(low frequency). The candidate text areas can be thus found by applying the higher frequency characteristics to neural network. Therefore, the final text area is extracted by verifying the candidate areas. Experimental results show a perfect candidate extraction rate and about 95% text extraction rate. The strength of the proposed algorithm is its simplicity, real-time processing by not processing the entire image.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.302-305
• /
• 2005

Recently, many methods to analyze signal have been proposed and representative methods are the Fourier transform and wavelet transform. In these methods, the Fourier transform represents signal with combination cosine and sine at all locations in the frequency domain. However, it doesn't provide time information that particular frequency occurs in signal and denpends on only the global feature of the signal. So, to improve these points the wavelet transform which is capable of multiresolution analysis has been applied to many fields such as speech processing, image processing and computer vision. And the wavelet transform, which uses changing window according to scale parameter, presents time-frequency localization. In this paper, we proposed a new approach using a wavelet of cosine and sine type and analyzed features of signal in a limited point of frequency-time plane.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.35D no.1
• /
• pp.1-7
• /
• 1998

In this paper, an incoherent imaging of a conducting cylinder illuminated by the single-frequency time-harmonic plane wave is obtained via the back-projections of the intensity patterns of the forward total electric field scattered from this object in the circular rotational measurement configuration. The pheonmenon that interference fringes generated in the itesity patterns is removed in the back-projection process is interpreted numerically. This imaging method is validated by imagining conducting circular cylinders and the conditions to ge beter image are investigated.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.1
• /
• pp.26-34
• /
• 1996

One of the challenging tasks in visual inspection using CCD camera is to identify surface defects in an image with complex textured backgeound. In microscopic view, the surface of real objects shows regular or random textured patterns. In this paper, we present a visual inspection algorithm to extract abnormal surface defects in an image with textured background. The algorithm uses the space and frequency information at the same time by introducing the Dominant Frequency Map(DFM) which can describe the frequency characteristics of every small local region of an input image. We demonstrate the feasibility and effectiveness of the method through a series of real experiments for a 14" TV CRT mold. The method successfully identifies a variety of infinitesimal defects, whose size is larger than $50\mu\textrm{m}$, of the mold. The experimental results show that the DFM based method is less sensitive to the environmental changes, such as illumination and defocusing, than conventional vision techniques.ques.

• Imaging Science in Dentistry
• /
• v.32 no.4
• /
• pp.213-219
• /
• 2002

Purpose : Computed radiography (CR) has been used in cephalometric radiography and many studies have been carried out to improve image quality using various digital enhancement and filtering techniques, During CR image acquisition, the frequency rank and type affect to the image quality. The aim of this study was to compare the diagnostic quality of conventional cephalometric radiographs to those of computed radiography. Materials and Methods : The diagnostic quality of conventional cephalometric radiographs (MO) and their digital image counterparts were compared, and at the same time, six modalities (M1-M6) of spatial frequency-processed digital images were compared by evaluating the reproducibility of 23 cephalometric landmark locations. Reproducibility was defined as an observer's deviation (in mm) from the mean between all observers. Results and Conclusion: In comparison with the conventional cephalometric radiograph (MO), Ml showed statistically significant differences in 8 locations, M2 in 9, M3 12, M4 in 7, M5 in 12, and M6 showed significant differences in 14 of 23 landmark locations (p < 0.05). The number of reproducible landmarks that each modality possesses were 7 in M6, 6 in M5, 5 in M3, 4 in M4, 3 in M2, 2 in Ml, and 1 location in MO. The image modality that observers selected as having the best image quality was M5.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.20 no.1
• /
• pp.167-181
• /
• 2018

In modern society, men are selecting dress based on physical features as well as individual taste. Through this concern with appearance, new descriptive words have appeared from time to time. Therefore this study aimed to analyze the type of image style expressed in the Paris Men's Fashion Collection during the period of 2001 S/S collections~2010 F/W collections. This study used Frequency and Chi-square tests through SPSS 12.0 program for the analysis of a total of the 1,357 materials shown from nine designers. The results were as follows. As a result of examining the image style according to chronology and season by frequency and the tendency of design works by chi-square test, in the tendency of the image style by chronology, the style emphasizing a sexy and manly appearance is preferred through the tendency that Homme Fataleism has been continually released in foreign men's fashion collections for about ten years. In the tendency of the image style by season, the image style of the Homme Fataleism was highly published in SS and FW season except for SS in 2004 and 2008. In the tendency of design works by chronology and season, the H-silhouette was highly preferred for about a decade. In color, the light brown group was frequently used until 2008 while gray has mainly been of use since 2009.