• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권10호
• /
• pp.4214-4230
• /
• 2020

This paper introduces a pilot allocation scheme for massive MIMO systems based on deep convolutional neural network (CNN) learning. This work is an extension of a prior work on the basic deep learning framework of the pilot assignment problem, the application of which to a high-user density nature is difficult owing to the factorial increase in both input features and output layers. To solve this problem, by adopting the advantages of CNN in learning image data, we design input features that represent users' locations in all the cells as image data with a two-dimensional fixed-size matrix. Furthermore, using a sorting mechanism for applying proper rule, we construct output layers with a linear space complexity according to the number of users. We also develop a theoretical framework for the network capacity model of the massive MIMO systems and apply it to the training process. Finally, we implement the proposed deep CNN-based pilot assignment scheme using a commercial vanilla CNN, which takes into account shift invariant characteristics. Through extensive simulation, we demonstrate that the proposed work realizes about a 98% theoretical upper-bound performance and an elapsed time of 0.842 ms with low complexity in the case of a high-user-density condition.

• Geomechanics and Engineering
• /
• 제1권2호
• /
• pp.121-142
• /
• 2009

The paper deals with the applications of spectral finite element method to the dynamic analysis of framed foundations supporting high speed machines. Comparative performance of approximate dynamic stiffness methods formulated using static stiffness and lumped or consistent or average mass matrices with the exact spectral finite element for a three dimensional Euler-Bernoulli beam element is presented. The convergence of response computed using mode superposition method with the appropriate dynamic stiffness method as the number of modes increase is illustrated. Frequency proportional discretisation level required for mode superposition and approximate dynamic stiffness methods is outlined. It is reiterated that the results of exact dynamic stiffness method are invariant with reference to the discretisation level. The Eigen-frequencies of the system are evaluated using William-Wittrick algorithm and Sturm number generation in the $LDL^T$ decomposition of the real part of the dynamic stiffness matrix, as they cannot be explicitly evaluated. Major's method for dynamic analysis of machine supporting structures is modified and the plane frames are replaced with springs of exact dynamic stiffness and dynamically flexible longitudinal frames. Results of the analysis are compared with exact values. The possible simplifications that could be introduced for a typical machine induced excitation on a framed structure are illustrated and the developed program is modified to account for dynamic constraint equations with a master slave degree of freedom (DOF) option.

• Journal of Ubiquitous Convergence Technology
• /
• 제2권1호
• /
• pp.18-26
• /
• 2008

The invariance relation existing in the non-negative matrix factorization (NMF) is used for constructing robust image hashes in this work. The image is first re-scaled to a fixed size. Low-pass filtering is performed on the luminance component of the re-sized image to produce a normalized matrix. Entries in the normalized matrix are pseudo-randomly re-arranged under the control of a secret key to generate a secondary image. Non-negative matrix factorization is then performed on the secondary image. As the relation between most pairs of adjacent entries in the NMF's coefficient matrix is basically invariant to ordinary image processing, a coarse quantization scheme is devised to compress the extracted features contained in the coefficient matrix. The obtained binary elements are used to form the image hash after being scrambled based on another key. Similarity between hashes is measured by the Hamming distance. Experimental results show that the proposed scheme is robust against perceptually acceptable modifications to the image such as Gaussian filtering, moderate noise contamination, JPEG compression, re-scaling, and watermark embedding. Hashes of different images have very low collision probability. Tampering to local image areas can be detected by comparing the Hamming distance with a predetermined threshold, indicating the usefulness of the technique in digital forensics.

• 한국정보통신학회논문지
• /
• 제11권4호
• /
• pp.826-832
• /
• 2007

고속 통신 시스템의 채널 등화에 순환 신경망이 자주 이용되고 있다. 기존의 등화방법은 대부분 시불변 채널을 주로 다루었다. 그러나 이동통신과 같은 현대의 통신환경은 페이딩으로 인하여 시변특성을 갖는다. 본 논문에서는 비선형 시변 시스템에 적용하여 성능이 우수한 결정 피드백 순환신경망을 채널등화기로 이용하며, 또한 채널 등화에 빠른 수렴속도와 우수한 추적성능을 지니는 확장된 칼만필터와 시그마 포인트 칼만필터를 이용한 두 종류의 훈련 알고리즘을 제안한다. 확장된 칼만필터를 이용한 경우 비선형 시스템의 1차 선형화 과정에서 커다란 오차를 유발할 수도 있으며, 이에 대한 대안으로 시그마 포인트 칼만필터를 이용하여 이러한 문제점을 극복할 수 있다.

• Communications for Statistical Applications and Methods
• /
• 제30권1호
• /
• pp.37-48
• /
• 2023

Shape analysis is a method for measuring, describing and comparing the shape of objects in geometric space. An important aspect is to obtain Procrustes distance based on least square method. We note that the shape is all the geometrical information that remains when location, scale and rotational effects are filtered out from an object. However, and unfortunately, when we cannot measure some landmarks which are some biologically or geometrically meaningful points of any object, it is not possible to measure the variation of all shapes of an object, including that of the incomplete object. Hence, we need to replace the missing landmarks. In particular, Albers and Gower (2010) studied the missing rows of configurations in Procrustes analysis. They noted that the convergence of their approach can be quite slow. In this study, alternatively, we derive an algorithm for estimating the missing landmarks based on the pre-shapes. The pre-shape is invariant under the location and scaling of the original configuration with the centroid size of the pre-shape being one. Therefore we expect that we can reduce the amount of total computing time for obtaining the estimate of the missing landmarks.

• 한국정보전자통신기술학회논문지
• /
• 제12권6호
• /
• pp.537-546
• /
• 2019

본 논문에서는 휴대하기 편하고 3D 콘텐츠 제작이 용이한 트윈 카메라 모듈 시스템을 구현하고자 하였다. 제안한 트윈 카메라 모듈 시스템은 2D 스테레오 카메라로 부터 입력되는 영상을 변환하여 3차원 영상으로 출력할 수 있는 시스템이다. 본 눈문에서 제안한 시스템의 성능평가를 위해 Test Platform을 이용하여 좌, 우 두 개의 렌즈로 촬영된 스테레오 입체 영상의 좌, 우 영상 간의 시차에 따른 회전(Rotation), 기울기(Tilt)에 대한 보정을 평가하였다. 또한 SIFT(Scale Invariant Feature Transform) 알고리즘을 이용하여 3D 입체 영상의 거리오차(Depth Error)를 검증하여 트윈 카메라 모듈 시스템의 효율성을 검증하고자 하였다. 본 논문에서 제안한 트윈 카메라 모듈 시스템은 촬영된 영상을 3D 입체 영상과 준비 영상으로 변화하여 외부에 출력하면 각기 다른 3D 입체 영상 제작 방식에 따른 출력장치에 맞춰 디스플레이가 가능하다. 또한 생성된 영상을 준비 영상과 입체 영상을 각기 다른 채널을 통해 출력하여 많은 제품에 적용하기 쉽고 간편하게 3D 입체 영상 콘텐츠를 제작하는데 이용할 수 있을 거라 기대한다.

• 디지털융복합연구
• /
• 제11권12호
• /
• pp.295-302
• /
• 2013

사람 검출은 정지된 영상 혹은 동영상으로부터 사람의 움직임이나 자세를 추정하고, 사람이 찾아질 경우 영상 내 사람의 좌표, 동작 인식, 보안관련 인증 등을 알아내는 기술로 정의된다. 이러한 사람 검출은 다른 객체의 검출이나 사람과 컴퓨터와의 상호작용, 동작 인식 등의 기초 기술로서 해당 시스템의 성능에 영향을 미치는 매우 중요한 변수 중에 하나이다. 그러나 영상 내의 사람은 움직임, 자세, 크기, 빛의 방향 및 밝기, 다른 객체와의 중복 등의 환경적 변화로 인해 사람 모양이 다양해지므로 정확하고 빠른 검출이 어렵다. 따라서 본 논문에서는 피셔의 선형 판별 분석을 이용하여 몇 가지 환경적 조건을 극복한 정확하고 빠른 사람 검출 방법을 제안한다. 제안된 방법은 사람 움직임 및 자세와 배경에 무관하게 빠른 시간 안에 사람을 검출하는 것이 가능하다. 이를 위해 계층적인 방법으로 사람 검출을 수행하며, 휴리스틱한 방법, 피셔의 판별 분석을 이용하여 사람 검출을 수행하고, 검색 영역의 축소와 선형 결정의 계산 시간의 단축으로 검출 응답 시간을 빠르게 하였다. 추출된 사람 영상에서 사람의 자세를 추정하고 사람의 영역을 검출함으로써 사람 정보의 사용에 있어 보다 많은 정보를 추출할 수 있도록 하였다.

• 한국음향학회지
• /
• 제37권3호
• /
• pp.156-162
• /
• 2018

LMF(Least Mean Fourth) 알고리즘은 특히 비정규 잡음 상황에서 안정성 및 빠른 수렴성을 나타낼 뿐만아니라 추정 오차도 낮은 것으로 잘 알려져 있다. 최근 LMS (Least Mean Square) 알고리즘 분야에서는 가변 스텝 크기를 적용한 알고리즘들에 대한 관심이 증대되어 왔다. 그 이유는 가변 스텝 크기 LMS가 다양한 환경에서 고정 스텝 크기 LMS보다 우수한 결과를 내기 때문이다. 본 논문에선 LMF에 대한 가변 스텝 크기의 한 방법으로 기울기 평균 벡터를 사용한 가변 스텝 크기를 사용하는 LMF 알고리즘을 제안한다. 제안된 방법은 가변 스텝 크기 LMS와 마찬가지로 고정 스텝 크기 LMF보다 우수할 것이 예상된다. 본 논문은 그 우수성을 시불변 채널과 시변 채널 각각의 채널 환경하에서 시뮬레이션을 통하여 보인다.

• 한국멀티미디어학회논문지
• /
• 제19권9호
• /
• pp.1679-1689
• /
• 2016

Recently, due to the rapid development of multimedia technologies, as image data has been extensive and large-scaled, the problem of increasing the time needed to retrieve the desired image is gradually critical. Image retrieval system that allows users to quickly and accurately search for the desired image information has been researched for a long time. However, in the case of content-based image retrieval representative Color Histogram, Color Coherence Vectors (CCV), Scale Invariant Feature Transform (SIFT) used in sensitive to changes in brightness, rotation, there is a problem that can occur misrecognized division off the power. In this paper, in order to evaluate the video retrieval system proposed, no change in brightness, respectively 0°, 90°, 180°, 270° rotated brightness up based on the case of changing, when the brightness down the results were compared with the performance evaluation of the system is an average of about 2% to provide the difference in performance due to changes in brightness, color histogram is an average of about 12.5%, CCV is an average of about 12.25%, it appeared in the SIFT is an average of about 8.5%, Thus, the proposed system of the variation width of the smallest in average about 2%, was confirmed to be robust to changes in the brightness and rotation than the existing systems.

• 공학교육연구
• /
• 제24권6호
• /
• pp.67-78
• /
• 2021

This study is an analysis of the life of Max Planck (1858-1947), the in view of engineering literacy education. Some expressions describing Planck include "the father of German science", "the namer of Quantum". Furthermore, he is the scientist who permanently engraved his name in a scientific invariant called the Planck Constant. Planck had already made remarkable scientific achievements in his mid-ages, which became the springboard of quantum mechanics, but he went on to achieve much more in his old age. Between 1910s and 1930s, he was the director of the Kaiser-Wilhelm Gesellschaft, the Berlin Academy, and the German Physics Society, which is the German core research group. In the 1910s, he endured the terrible personal suffering of losing his three children and then succeeded in rebuilding German science in the 1920s in his golden age of 70s. His achievement was great not only as a scientist but also as a science administrator. His life was contradictory in several ways. While fundamentally being a conservative, he initiated a great scientific revolution. While making efforts to preserve traditional values, he was in the center of great many upheavals and destruction. While being the incarnation of honesty, he was also given to extremely delicate political positions. In his long career, Planck lived with all his might as a leader of the German science organizations and permanently left his name on the institute representing Germany. Planck succeeded in his work for the institutional development of science, philosophical understanding of science, and as a role model of exemplary scientist. His long life was accompanied by both achievements and failures, intangible and difficult to judge. Today, as research and development management and scientific leadership have become increasingly important, Planck's life may be a good example of engineering literacy education.