• International Journal of Internet, Broadcasting and Communication
• /
• 제12권1호
• /
• pp.144-150
• /
• 2020

Reinforcement learning is a technology that can present successful and creative solutions in many areas. This reinforcement learning technology was used to deploy containers from cloud servers to fog servers to help them learn the maximization of rewards due to reduced traffic. Leveraging reinforcement learning is aimed at predicting traffic in the network and optimizing traffic-based fog computing network environment for cloud, fog and clients. The reinforcement learning system collects network traffic data from the fog server and IoT. Reinforcement learning neural networks, which use collected traffic data as input values, can consist of Long Short-Term Memory (LSTM) neural networks in network environments that support fog computing, to learn time series data and to predict optimized traffic. Description of the input and output values of the traffic-based reinforcement learning LSTM neural network, the composition of the node, the activation function and error function of the hidden layer, the overfitting method, and the optimization algorithm.

• 환경영향평가
• /
• 제10권1호
• /
• pp.1-8
• /
• 2001

Detection of red tides by satellite remote sensing can be done either by detecting enhanced level of chlorophyll pigment or by detecting changes in the spectral composition of pixels. Using chlorophyll concentration, however, is not effective currently due to the facts: 1) Chlorophyll-a is a universal pigment of phytoplankton, and 2) no accurate algorithm for chlorophyll in case 2 water is available yet. Here, red band algorithm, classification and PCA (Principal Component Analysis) techniques were applied for detecting patches of Cochlodinium polykrikoides red tides which occurred in Korean waters in 1995. This dinoflagellate species appears dark red due to the characteristic pigments absorbing lights in the blue and green wavelength most effectively. In the satellite image, the brightness of red tide pixels in all the three visible bands were low making the detection difficult. Red band algorithm is not good for detecting the red tide because of reflectance of suspended sediments. For supervised classification, selecting training area was difficult, while unsupervised classification was not effective in delineating the patches from surrounding pixels. On the other hand, PCA gave a good qualitative discrimination on the distribution compared with actual observation.

• 한국콘텐츠학회논문지
• /
• 제15권3호
• /
• pp.1-10
• /
• 2015

멜로디를 바탕으로 코드 악보를 생성해주는 작업은 음악의 채보 및 편곡과 직결되는 중요한 악보 작업이다. 하지만 자연스러운 코드악보 생성을 위해서는 풍부한 화성학적 배경 지식이 요구되기 때문에 음악 입문자들이 수행하기에는 큰 어려움이 따른다. 본 연구에서는 이러한 문제점을 해결하기 위해 멜로디 악보를 입력받아 자동으로 코드 악보를 생성하는 프로그램 'ACGP(Automatic Chord Generating Program)'를 개발하였다. ACGP는 유전알고리즘에 기반을 두어 다양한 화성학적 요인들과 사용자가 원하는 곡의 분위기를 효율적으로 고려할 수 있으며 이를 통해 더욱 화성학적으로 안정된 완성도 높은 코드 악보를 생성할 수 있다. 또한 편리한 사용자 인터페이스를 통하여 음악에 처음 접하는 비전문가들도 손쉽게 작업할 수 있도록 구현되었다. 또한 ACGP로 생성된 코드악보와 일반적으로 통용되는 코드악보를 비교 분석함으로 써 프로그램의 적절성을 입증하였다.

• 정보처리학회논문지D
• /
• 제10D권2호
• /
• pp.221-232
• /
• 2003

본 논문은 XML 기반의 데이터베이스 통합 방법론 중에서 관계형 데이터베이스 모델에 대한 랩퍼 시스템의 질의어 처리에 대하여 논한다. 관계형 데이터베이스의 내용은 W3C에서 제안된 XML Schema로 표현되며, 사용자는 XML Schema에 대하여 XML 질의어인 XQuery로써 질의를 한다. 그리고, 개발된 랩퍼 시스템은 사용자가 정의한 XML 뷰를 지원한다. XML 뷰 정의 언어는 XQuery이다. 이러한 환경에서 본 논문은 새로운 XML 질의 처리 모델을 제시한다. XML 뷰와 사용자 질의어의 합성 알고리즘, XQuery를 SQL로 변환하는 알고리즘, 그리고 XML 문서 생성을 위한 템플릿 구성 알고리즘을 제시한다.

• 대한기계학회논문집A
• /
• 제32권11호
• /
• pp.997-1002
• /
• 2008

This paper is mainly concerned with the development of a remotely operated vehicle for investigation of the coastal sea. For this, we have designed and constructed a vehicle entitled KMU-ROV(Korea Maritime University Remotely Operated Vehicle), for purpose of investigation mission under 50(m) of the sea surface. We have designed six independent waterproof actuators and the housing of the controller for underwater operation. For six degree-of-freedom motion, we have analyzed the dynamics of the KMU-ROV and have designed a new composition of six actuators including the driving system. For motion control, we have composed a concurrent velocity control algorithm for controlling the speed of all the actuating motors. The control system for the KMU-ROV is composed of a master DSP controller, DSP controller for the motor control and various sensors. We composed the PID control algorithm and a network system for controlling motors using the CAN communication. The performance of the KMU-ROV was presented by testing the developed control algorithm and control system under the water.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2002년도 춘계공동학술대회
• /
• pp.179-184
• /
• 2002

We consider the heterogeneous fleet vehicle routing problem (HVRP), a variant of the classical vehicle routing problem (VRP). The HVRP differs from the classical VRP in that it deals with a heterogeneous fleet of vehicles having various capacities, fixed costs, and variables costs. Therefore the HVRP is to find the fleet composition and a set of routes with minimum total cost. We give an integer programming formulation of the problem and propose an algorithm to solve it. Although the formulation has exponentially many variables, we can efficiently solve the linear programming relaxation of it by using the column generation technique. To generate profitable columns we solve a shortest path problem with capacity constraints using dynamic programming. After solving the linear programming relaxation, we apply a branch-and-bound procedure. We test the proposed algorithm on a set of benchmark instances. Test results show that the algorithm gives best-known solutions to almost all instances.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 춘계학술대회 학술발표 논문집
• /
• pp.65-68
• /
• 2001

RBFN has some problem that because the basis function isnt orthogonal to each others the number of used basis function goes to big. In this reason, the Wavelet Neural Network which uses the orthogonal basis function in the hidden node appears. In this paper, we propose the composition method of the actual function in hidden layer with the scaling function which can represent the region by which the several wavelet can be represented. In this method, we can decrease the size of the network with the pure several wavelet function. In addition to, when we determine the parameters of the scaling function we can process rough approximation and then the network becomes more stable. The other wavelets can be determined by the global solutions which is suitable for the suggested problem using the genetic algorithm and also, we use the back-propagation algorithm in the learning of the weights. In this step, we approximate the target function with fine tuning level. The complex neural network suggested in this paper is a new structure and important simultaneously in the point of handling the determination problem in the wavelet initialization.

• 한국컴퓨터정보학회논문지
• /
• 제12권1호
• /
• pp.261-267
• /
• 2007

최근 교통문제 해결을 위한 하나의 방안으로 첨단교통체계(ITS)에 관한 연구가 활발히 진행 중이다. 또한 도로 상에서 차량을 검출하기 위한 다양한 방법들이 제시되고 있다. 본 논문에서는 영상처리 기술을 이용하여 이동하는 차량을 검출하는 차량검지 시스템을 개발하여 도로 이용자에게 신속한 정보를 제공하고자 한다. 또한 차량을 검출하기 위해 효율적이고 하드웨어로 구현이 쉬운 알고리즘을 개발하는데 목적이 있다. CCD 카메라를 이용하여 도로 영상을 촬영하고, 모폴로지 기법을 적용하여 영상으로부터 특징점을 추출하고, 추출된 특징점 간의 이동벡터를 구하여 움직이는 차량영역을 검출한다. 제안된 알고리즘을 실제 도로 영상에서 실험한 결과 처리시간이 단축되었으며, 차량 검출에서 좋은 결과를 얻을 수 있었다.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제1권2호
• /
• pp.95-100
• /
• 2009

As ships become larger, thicker and higher tensile steel plate are used in shipyard. Though special chemical compositions are required for high-tensile steels, recently they are made by the TMCP (Thermo-Mechanical control process) methodology. The increased Yield / Tensile strength of TMCP steels compared to the normalized steel of same composition are induced by suppressing the formation of Ferrite and Pearlite in favor of strong and tough Bainite while being transformed from Austenite. But this Bainite phase could be vanished by another additional thermal cycle like welding and heating. As thermal deformations are deeply related by yield stress of material, the study for prediction of plate deformation by heating should niflect the principle of TMCP steels. The present study is related to the development of an algorithm which could calculate inherent strain. In this algorithm, not only the mechanical principles of thermal deformations, but also the initial portion of Bainite is considered when calculating inherent strain. Distortion analysis results by these values showed good agreements with experimental results for normalized steels and TMCP steels during welding and heating. This algorithm has also been used to create an inherent strain database of steels in Class rule.

• Nuclear Engineering and Technology
• /
• 제52권5호
• /
• pp.1008-1012
• /
• 2020

In order to make reasonable design for the improvement of comprehensive mechanical properties of RAFM steels, the design system with both machine learning and high-throughput optimization algorithm was established. As the basis of the design system, a dataset of RAFM steels was compiled from previous literatures. Then, feature engineering guided random forests regressors were trained by the dataset and NSGA II algorithm were used for the selection of the optimal solutions from the large-scale solution set with nine composition features and two treatment processing features. The selected optimal solutions by this design system showed prospective mechanical properties, which was also consistent with the physical metallurgy theory. This efficiency design mode could give the enlightenment for the design of other metal structural materials with the requirement of multi-properties.