• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.267-272
• /
• 2020

Macroeconomics are one of the indicators that are preceded and analyzed when analyzing stocks because it shows the movement of a country's economy as a whole. The overall economic situation at the national level, such as national income, inflation, unemployment, exchange rates, currency, interest rates, and balance of payments, has a great affect on the stock market, and economic indicators are actually correlated with stock prices. It is the main source of data for analysts to watch with interest and to determine buy and sell considering the impact on individual stock prices. Therefore, economic indicators that impact on the stock price are analyzed as leading indicators, and the stock price prediction is predicted through deep learning-based prediction, after that the actual stock price is compared. If you decide to buy or sell stocks by analysis of stock prediction, then stocks can be investments, not gambling. Therefore, this research was conducted to enable automated stock trading by using macro-indicators and deep learning algorithms in artificial intelligence.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.10
• /
• pp.97-107
• /
• 2015

The initial X-ray images obtained from a digital X-ray machine have a wide data range and uneven brightness level than normal images. In particular, in Chest X-ray images, it is necessary to improve naturally all of the parts such as ribs, spine, tissue, etc. These X-ray images can not be improved enough from conventional image quality enhancement algorithms because their characteristics are different from ordinary images'. This paper proposes to eliminate unnecessary background from an input image and expand the histogram range of the image. Then, we adjust the weight per frequency band of the image for improvement of contrast and sharpness. Finally, jointly taking the advantages of global contrast enhancement and local contrast enhancement methods we obtain an improved X-ray image suitable for effective diagnosis in comparison with the existing methods. Experimental results show quantitatively that the proposed algorithm provides better X-ray images in terms of the discrete entropy and saturation than the previous works.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.21 no.11
• /
• pp.1248-1258
• /
• 2010

In this paper, a method for simultaneously realizing the sum and difference patterns which are required in the monopulse radar sensor systems, is presented by using single taper array antenna with rectangular microstrip patches. The widths of patches are first determined by the voltage weights which are synthesized for the fundamental array factor patterns to be applied to the monopulse operation by using the sidelobe levels(SLLs) control technique. As the bi-directionally series-fed technique is applied and the lengths of connecting lines between patches are appropriately adjusted, the single array generates two phase-shifted beams which activates out-of-phase and in-phase ports of a $180^{\circ}$ hybrid coupler to synthesize the sum and difference patterns. The simulated results on the configuration designed at 9.5 GHz are compared with measured results showing the validity of the proposed method.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.888-900
• /
• 2015

This paper proposes a blind watermarking scheme using DWT satisfying robustness, invisibility, and security to protect the ownership of digital image contents. This scheme does not determine any watermarking position by local image information. It rather inserts the watermark information into all the four lowest frequency subbands after transforming the host image by n-level 2-dimensional DWT, depending on, the sizes of the host image and the watermark data. Its watermark insertion methodology uses some weighting factors according to the kind of the subband and its energy level to adjust the invisibility and the robustness of the watermark. This method is experimented for various pixel-value change attacks and geometric attacks with various images having different resolutions and aspect ratios. With the experimental results and by comparing with existing methods, we show that the proposed method has a great deal of general usage with good watermark invisibility and good robustness against attacks.

• Journal of Broadcast Engineering
• /
• v.13 no.6
• /
• pp.962-965
• /
• 2008

2-D shape descriptors, which are vectors representing characteristics of shapes, enable comparison and classification of shapes and are mainly applied to image and 3-D model retrieval. Existing descriptors have limitations that they only describe shapes of single closed contours or lack in precision, making it difficult to be applied to shapes with multiple contours. Therefore, in this paper, we propose a new shape descriptor called Multi-Curvature-Scale Space that can be applied to shapes with multiple contours. Specifically, we represent the topology of the sub-contours in the multi-contour along with Curvature-Scale Space descriptors to represent the shapes of each sub-contours. Also, by allowing the weight of each component to be controlled when computing the distance between descriptors the weight, we deal with ambiguities in measuring similarity between shapes. Results of various experiments that prove the effectiveness of proposed descriptor are presented.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.11
• /
• pp.61-66
• /
• 2005

This paper describes a 10-bit 210MHz CMOS current-mode Digital-to-Analog Converter (DAC) consisting of 6 bit MSB current cell matrix Sub-DAC, 2 bit mSB unary current source Sub-DAC, and 2 bit LSB binary weighting Sub-DAC for Wireless LAN application. A new deglitch circuit is proposed to control a crossing point of signals and minimize a glitch energy. The proposed 10-bit CMOS current mode DAC was designed by a $0.35{\mu}m$ CMOS double-poly four-metal technology rate of 210MHz, DNL/INL of ${\pm}0.7LSB/{\pm}1.1LSB$, a glitch energy of $76pV{\cdot}sec$, a SNR of 50dB, a SFDR of 53dB at 200MHz sampling clock and power dissipation of 83mW at 3.3V

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.411-421
• /
• 2001

The generalized symmetry transform evaluates symmetry without segmentation and extracts regions of interest in an image by combining locality and reflectional symmetry The demand that the symmetry transform be local is reflected by the distance weight function. When calculating large regions-of-interest, we should select a large standard deviation of distance weight function. But such a large standard deviation makes the execution time increase in the second power of r, which is a radius of search area. In this paper we propose modified scan line based GST with selectively directional attention to improve time complexity The symmetry map of our proposed GST is found to be very similar to that of the existing GST. However the computation time of the proposed GST increases linearly with respect to r because our proposed GST evaluates symmetry between a pair of edge pixels along the scan lines. The GST computation decreases considerably when the proposed GST is peformed with selectively directional attention in case of large r. Several experiments in this paper demonstrate the time efficiency and the usefulness of our proposed GST.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.11
• /
• pp.56-63
• /
• 2012

In this paper, adaptive unsharp masking using bilateral filter, edge-preserving smoothing filter is proposed to reduce the overshoot and jagging artifact in sharpening images. Previous image enhancement methods including unsharp masking(UM) can emphasize high-frequency details strongly, but often cause several artifacts such as overshooting, noise, jagging and so on. Proposed image enhancement method preserves edges well because of using bilateral filter and sensitively controls a weight according to edge's directions. Therefore, it enhances sharpness and effectively reduces overshoot and jagging artifacts. Simulation results comparing output of previous AUM with proposed method show that proposed algorithm makes images properly enhanced, and we know that overshoot and jagging artifacts are many reduced.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.121-124
• /
• 2001

음성 합성기의 합성음의 자연감을 높이기 위해 자연음에 내재하는 정확한 운율 법칙을 구하여 음성합성 시스템에서 이를 구현해 주어야 한다 무제한 어휘 음성합성 시스템의 문-음성 합성기에서 필요한 운율 법칙은 언어학적 정보를 이용해 구하거나, 자연음에서 추출하고 있다 그러나 추출한 운율 법칙이 자연음에 내재하는 모든 운율 법칙을 반영하지 못했거나, 잘못 구현되는 경우에는 합성음의 자연성이 떨어지게 된다. 이런 점을 고려하여 본 논문에서는 한국어 자연음을 분석하여 추출한 운율 정보를 인공 신경망이 학습하도록 하고 훈련을 마친 인공 신경망에 문장을 입력하고, 출력으로 나오는 운율 정보와 자연음의 운율 정보를 비교한 결과 제안한 인공 신경망이 자연음에 내재하고 있는 운율을 학습할 수 있음을 알 수 있었다. 운율의 3대 요소는 피치 , 지속시간, 크기의 변화이다. 제안한 인공 신경망이 한국어 문장의 음소 열을 입력으로 받아들이고, 각 음소의 지속시간에 따른 피치변화와 크기 변화를 출력으로 내보내면 자연음을 분석해 구한 각 음소의 운율 정보인 목표 패턴과 출력 패턴 의 오차를 최소화하도록 인공 신경망의 가중치를 조절할 수 있도록 설계하였다. 지속시간에 따른 각 음소의 피치와 크기 변화를 학습시키기 위해 피치 및 크기 인공 신경망을 구성하였다. 이들 인공 신경망을 훈련시키기 위해 먼저 음소 균형 문장 군을 구축하여야 하고, 이들 언어 자료를 특정 화자가 일정 환경에서 읽고 이를 녹음하여 , 분석하여 구한운율 정보를 운율 데이터베이스로 구축하였다. 문장 내의 각 음소에 대해 지속 시간과 피치 변화 그리고 크기 변화를 구하고, 곡선 적응 방법을 이용하여 각 변화 곡선에 대한 다항식 계수와 초기 값을 구해 운율 데이터베이스를 구축한다. 이 운율 데이터베이스의 일부는 인공 신경망을 훈련시키는데 이용하고, 나머지로 인공 신경망의 성능을 평가하여 인공 신경망이 운율 법칙을 학습할 수 있었다. 언어 자료의 문장 수를 늘리고 발음 횟수를 늘려 운율 데이터베이스를 확장하면 인공 신경망의 성능을 높일 수 있고, 문장 내의 음소의 수를 감안하여 인공 신경망의 입력 단자의 수는 계산량과 초분절 요인을 감안하여 결정해야 할 것이다

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.263-272
• /
• 2007

This paper proposes a skeleton-based hierarchical shape description scheme, called a skeleton tree, for accurate shape-based image retrieval. A skeleton tree represents an object shape as a hierarchical tree where high-level nodes describe parts of coarse trunk regions and low-level nodes describe fine details of boundary regions. Each node refines the shape of its parent node. Most of the noise disturbances are limited to bottom level nodes and the boundary noise is reduced by decreasing weights on the bottom levels. The similarity of two skeleton trees is computed by considering the best match of a skeleton tree to a sub-tree of another skeleton tree. The proposed method uses a hybrid similarity measure by employing both Fourier descriptors and moment invariants in computing the similarity of two skeleton trees. Several experimental results are presented demonstrating the validity of the skeleton tree scheme for the shape description and indexing.