• 한국인터넷방송통신학회논문지
• /
• 제21권1호
• /
• pp.69-77
• /
• 2021

본 논문은 사용자가 입력한 PDF 악보를 사용자가 원하는 조(chord)의 MIDI 파일로 제공하는 앱의 개발을 다룬다. 이 앱은 사용자가 PDF 악보 파일과 바꾸고자 하는 조를 입력하면 조 변환을 위해 PDF 파일을 PNG 파일로 변환한다. 이를 영상 처리 알고리즘을 통해 악보의 음계를 인식하여 구분하고, 딥러닝을 통해 악보 음표의 박자를 인식하여 구분한다. 이를 통해 사용자가 원하는 조와 기존 악보의 MIDI 파일을 제공한다. 개발한 영상 처리 알고리즘과 딥러닝은 2, 4, 8, 16분 음표, 2, 4, 8, 16분 쉼표, 잇단 음표, 화음 음표가 인식 가능하다. 실험결과 악보의 음표 인식률 100%, 딥러닝 모델을 통한 박자 인식률은 90% 이상인 것을 확인하였다.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제6권3호
• /
• pp.31-39
• /
• 2016

컴퓨터 기술이 발달하면서 악보 편집 작업을 할 수 있는 사보 프로그램도 많이 발전했다. 음표, 코드, 악보 기호 등을 편리하게 넣을 수 있을 뿐만 아니라 미리 들어볼 수 있는 재생기능도 제공하여 현재 만들고 있는 악보를 연주하면 어떤 음악이 나올지 알 수 있다. 현재 상용화 되어 있는 사보 프로그램들은 악보를 보기 좋게 만들어주고 음표 재생도 VSTi(Virtual Studio Technology instrument)를 이용하여 잘 해주지만, 코드(Chord) 반주 기능은 상대적으로 취약하여 표기한 코드가 맞는지 알아보는 것이 힘들다. 따라서 음악 코드를 적절하게 반주해줄 수 있으면 멜로디와 코드 중심으로 이루어진 밴드 음악 악보를 만드는데 좋은 참고가 될 수 있다. 본 연구에서는 기존 사보 프로그램의 코드재생 기능을 강화하기 위하여 피아노 코드 톤을 적절히 선택하는 알고리즘을 제시하고 프로그램으로 구현하였다. 이를 활용하면 코드 연주 기능이 강화되어 밴드 음악 악보를 만드는 악보 편집자들이 더 편하게 악보를 제작할 수 있다.

• 대한수학회지
• /
• 제47권2호
• /
• pp.277-288
• /
• 2010

The mixed chord-integrals are defined. The Fenchel-Aleksandrov inequality and a general isoperimetric inequality for the mixed chordintegrals are established. Furthermore, the dual general Bieberbach inequality is presented. As an application of the dual form, a Brunn-Minkowski type inequality for mixed intersection bodies is given.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2004년도 봄 학술발표논문집 Vol.31 No.1 (A)
• /
• pp.517-519
• /
• 2004

Chord(6)는 N개의 노드로 이루어진 P2P(Peer-to-Peer)네트워크에서 검색에 사용되는 메시지를 O(logN)으로 줄인 P2P 검색 알고리즘이다. 하지만 모바일 Ad-hoc 네트워크에 이를 적용할 경우 검색 성공률이 매우 떨어져 (1000개의 노드가 도보속도(2m/s)로 움직이는 경우： 검색 성공률 30%이하)P2P 검색이 거의 이루어지지 않는 문제점이 발생한다. 본 논문에서는 이 같은 문제점을 극복하기 위한 알고리즘인 Backtracking Chord을 제안한다. Backtracking Chord 방식은 O(logN)메시지를 사용하여 순차적으로 t번까지 검색을 요청함으로써(t： Timeout의 횟수(0 < t< logN)) t에 따라 최고 88%(t>4)까지 검색 성공률을 높일 수 있다.

• 한국공작기계학회논문집
• /
• 제10권2호
• /
• pp.18-28
• /
• 2001

Super computers has been utilized to carry out vehicle dynamics in real time. This research propose an implicit integra-tion method for vehicle state variables. Newton chord method is empolyed to solve the equations of motion and con-straints. The equations of motion and constraints are formulated such that the Jacobian matrix for Newton chord method is needed to be computed only once for a dynamic analysis. Numerical experiments showed that the Jacobian matrix generat-ed at the initial time could have been utilized for the Newton chord iterations throughout simulations under various driving conditions. Convergence analysis of Newton chord method with the proposed Jacobian updating method is carried out. The proposed algorithm yielded accurate solutions for a prototype vehicle multibody model in realtime on a 400 MHz PC compatible.

• 한국멀티미디어학회논문지
• /
• 제21권3호
• /
• pp.391-399
• /
• 2018

In this paper, we construct and compare various guitar chord classification systems using perceptron neural network and convolutional neural network without pre-processing other than Fourier transform to identify the optimal chord classification system. Conventional guitar chord classification schemes use, for better feature extraction, computationally demanding pre-processing techniques such as stochastic analysis employing a hidden markov model or an acoustic data filtering and hence are burdensome for real-time chord classifications. For this reason, we construct various perceptron neural networks and convolutional neural networks that use only Fourier tranform for data pre-processing and compare them with dataset obtained by playing an electric guitar. According to our comparison, convolutional neural networks provide optimal performance considering both chord classification acurracy and fast processing time. In particular, convolutional neural networks exhibit robust performance even when only small fraction of low frequency components of the data are used.

• 한국멀티미디어학회논문지
• /
• 제18권11호
• /
• pp.1358-1366
• /
• 2015

This paper proposes an automatic composition method using the training capability of artificial neural networks and chord progression rules that are widely used by human composers. After training a given song, the new melody is generated by the trained artificial neural networks through applying a different initial melody to the neural networks. The generated melody should be modified to fit the rhythm and chord progression rules for generating natural melody. In order to achieve this object, we devised a post-processing method such as chord candidate generation, chord progression, and melody correction. From some tests we could find that the melody after the post-processing was very improved from the melody generated by artificial neural networks. This enables our composition system to generate a melody which is similar to those generated by human composers.

• 한국항해항만학회지
• /
• 제41권2호
• /
• pp.33-38
• /
• 2017

A marine flapped rudder is designed to improve the effective lift generated by the rudder; this also improves the maneuverability of the ship. The flap is a high lift device installed at the trailing edge of the rudder to augment lift. In this paper, the characteristics of a thick flapped rudder are analyzed at a low Reynolds number with various ratios of flap chord length to total chord length and various aspect ratios, based on the computational fluid dynamics technique. The performance of the rudder with respect to lift, drag, and center of pressure are investigated, and the efficient ratio of flap chord length to total chord length and improved aspect ratio are determined. Ed: highlight - or 'superior'. As a case study, the flow on the flapped rudder of an NACA0021 section shape in free stream condition is simulated. The standard k-epsilon turbulence model is used to model the flow around the flapped rudder. The results indicate that the efficient ratio of the flap chord length to total chord length and aspect ratio are 0.3 and 1.4, respectively.

• 한국유체기계학회 논문집
• /
• 제19권5호
• /
• pp.5-11
• /
• 2016

The purpose of this study is to design the transonic centrifugal compressor impeller with splitter blades and analyze the flow fields with respect to various splitter blades. Seven impellers with different splitter chord length or pitchwise location were tested by using CFD method. To investigate aerodynamic performance, Mach number distribution and entropy distribution were confirmed. As a result, it is found that the size of transonic region and shock wave location are related to the splitter chord length and pitchwise location. Also the impeller with long chord length of splitter shows higher total pressure ratio but lower efficiency than those of the impeller with short chord length of splitter. In terms of pitchwise location, the impeller with the splitter located in mid-pitch of main blades shows the best performance with respect to pressure ratio and efficiency.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 춘계학술대회 논문집
• /
• pp.1647-1652
• /
• 2008

Track geometry consists of tangent and curved lines, which caused undesirable changes in initial track geometry by traffic loads. The bigger the changes are, the worse the riding comfort and running stability of train. This is so-called track irregularity and is the most important quality parameters of ballasted track. To be able to objectively assess track irregularity, track geometry should be able to be measured. Practically, railway companies use moving chord method, this method determine versine values via a chord. The versine is the vertical distance to curve measured in the middle of the chord. This type of method measures only versine of track irregularity curve by transfer function from specific property of measuring tool. In this report, review the characteristics of two types of measuring tools by comparing the measurements. The one is GRP-1000 system, optical surveying system with Total station and lazar prism trolly. This calculates track geometry by surveying absolute coordinates of two points each on both rail heads. The other is Trackmaster, measures versine with 2m of chord length.