• 지능정보연구
• /
• 제5권1호
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권8호
• /
• pp.3273-3277
• /
• 2015

Network scale up (NSU) is a novel approach to estimate parameters in hard to reach populations through asking people the number of individuals they know in their active social network. Although the method have been used in hidden populations, advantages of NSU indicate that exploration of applicability to disease like cancer might be feasible. The aim of this study was to assess the application of NSU to estimate the size of the population of breast, ovarian/cervical, prostate, and bladder cancers in the South-east of Iran. A total of 3,052 (99% response rate) Kermanian people were interviewed in 2012-2013. Based on NSU, participants were asked about if they know any people on their social network who suffered from breast, ovarian/cervical, prostate, and bladder cancers, if yes, they should enumerate them. A total of 1,650 persons living with four types of cancers (breast, ovary/cervix, prostate, and bladder) were identified by the respondents. Totally, the prevalence of people living with the four types of cancers was 228.4 per 100,000 Kermanian inhabitants. The most prevalent cancer was breast cancer, at 168.9 per 100,000, followed by prostate cancer with 116.9, ovarian/cervical cancer with 99.8, and bladder cancer with 36.3 per 100000 Kerman city population. NSU values provide a usable but not very precise way of estimating the size of subpopulations in the context of the four major cancers (breast, ovary/cervix, prostate, and bladder).

• 한국경영과학회지
• /
• 제21권3호
• /
• pp.215-225
• /
• 1996

For an undirected stochastic network G, the 2-terminal reliability of G, R(G) is the probability that the specific two nodes (called as terminal nodes) are connected in G. A. typical network reliability problem is to compute R(G). It has been shown that the computation problem of R(G) is NP-hard. So, any algorithm to compute R(G) has a runngin time which is exponential in the size of G. If by some means, the problem size, G is reduced, it can result in immense savings. The means to reduce the size of the problem are the reliability preserving reductions and graph decompositions. We introduce a net set of reliability preserving reductions : the $K^{4}$ (complete graph of 4-nodes)-chain reductions. The total number of the different $K^{4}$ types in R(G), is 6. We present the reduction formula for each $K^{4}$ type. But in computing R(G), it is possible that homeomorphic graphs from $K^{4}$ occur. We devide the homemorphic graphs from $K^{4}$ into 3 types. We develop the reliability preserving reductions for s types, and show that the remaining one is divided into two subgraphs which can be reduced by $K^{4}$-chain reductions 7 polygon-to-chain reductions.

• 대한교통학회지
• /
• 제6권1호
• /
• pp.5-16
• /
• 1988

Development is given to an optimal network design method using continuous design variables. Modified Hooke-and-Jeeves algorithm is implemented in order to solve nonlinear programming problem which is approximately equivalent to the real network design problem with system efficiency crieteria and improvement cost as objective function. the method was tested for various forms of initial solution, and dimensions of initial step size of link improvements. At each searching point of evaluating the objective function, a link flow problem was solved with user equilibrium principles using the Frank-Wolfe algorithm. The results obtained are quite promising interms fo numbers of evaluation, and the speed of convergence. Suggestions are given to selections of efficient initial solution, initial step size and convergence criteria. An approximate method is also suggested for reducing computation time.

• 방송공학회논문지
• /
• 제1권2호
• /
• pp.133-141
• /
• 1996

본 논문에서는 차세대 영상 서비스 기술인 VOD(Video-on-Demand)시스템을 LAN을 이용하여 구현하였다. LAN을 이용한 VOD 시스템은 네트워크 병목현상과 이에 따른 시간 지연 때문에 기존의 네트워크 구현으로는 원활한 서비스가 되지 못하므로, 그러한 문제점을 해결하기 위한 방안으로, 본 논문에서는 토팔러지의 변경과 그에 따른 네트워크 장비의 선정, 개선된 프로토콜의 제정 등이 제시되었다. 결론적으로 구현된 시스템은 세그먼트 당 최대 3∼4명의 클라이언트를 수용할 수 있었고, 전송하고자 하는 영상 데이터의 크기에 따라 미리 네트워크 버퍼의 크기를 최적화하는 것이 서비스의 품질을 높이는데 필수적이라는 것을 알 수 있었다.

• 한국경영과학회지
• /
• 제31권4호
• /
• pp.69-87
• /
• 2006

This paper proposes an effective approach for the part-machine grouping(PMG) based on the non-binary part-machine incidence matrix in which real manufacturing factors such as the operation sequences with multiple visits to the same machine and production volumes of parts are incorporated and each entry represents actual moves due to different operation sequences. The proposed approach adopts Fuzzy ART neural network to quickly create the Initial part families and their machine cells. A new performance measure to evaluate and compare the goodness of non-binary block diagonal solution is suggested. To enhance the poor solution due to category proliferation inherent to most artificial neural networks, a supplementary procedure reassigning parts and machines is added. To show effectiveness of the proposed approach to large-size PMG problems, a psuedo-replicated clustering procedure is designed. Experimental results with intermediate to large-size data sets show effectiveness of the proposed approach.

• 한국정보통신학회논문지
• /
• 제15권7호
• /
• pp.1495-1500
• /
• 2011

동적 암호는 키의 크기, 라운드의 수 그리고 평문의 크기가 동시에 측정될 수 있는 특성을 갖고 있다. 본 논문에서는 동적 네트워크에 기반한 대칭적인 블록 암호 알고리즘을 제안한다. 제안하는 동적 암호는 중간충돌공격과 선형 암호해독법에 대해서 안전하다. 또한 동적 암호에 대한 미분 분석이 힘든 것을 보여준다.

• 경영과학
• /
• 제17권2호
• /
• pp.87-95
• /
• 2000

This paper presents two analytical approaches to determine the vehicle fleet size for container shuttle service. The shuttle service can be defined as the repetitive travel between the designated places during working period. In the first approach, the transportation model is adopted in order to determine the number of vehicles required. Its advantages and disadvantages in practical application are also discussed. In the second approach, a logical network which is oriented on job is transformed from a physical network which is focused on demand site. Nodes on the logical network represent jobs which include loaded travel, loading and unloading and arcs represent empty travel for the next jobs which include loaded travel, loading and unloading and arcs represent empty travel for the next job. Then a mathematical formulation is constructed similar to the multiple traveling salesman problem (TSP). A solution procedure is carried out based on the well-known insertion heuristic with the real world data.

• Journal of information and communication convergence engineering
• /
• 제6권1호
• /
• pp.100-104
• /
• 2008

Generally, it is difficult to find constant patterns on identifiers in a container image, since the identifiers are not normalized in color, size, and position, etc. and their shapes are damaged by external environmental factors. This paper distinguishes identifier areas from background noises and removes noises by using an ART2-based quantization method and general morphological information on the identifiers such as color, size, ratio of height to width, and a distance from other identifiers. Individual identifier is extracted by applying the 8-directional contour tracking method to each identifier area. This paper proposes a refined ART2-based RBF network and applies it to the recognition of identifiers. Through experiments with 300 container images, the proposed algorithm showed more improved accuracy of recognizing container identifiers than the others proposed previously, in spite of using shorter training time.

• 한국정보처리학회논문지
• /
• 제7권5호
• /
• pp.1520-1524
• /
• 2000

TCP 프로토콜의 혼잡 제어 알고리즘은 인터넷 망 내로 들어오는 트래픽 량을 조정하여 망이 혼잡 상태에 빠지는 것을 방지하는 기능을 수행한다. 따라서, 망에서는 어떤 TCP에서 발생하는 트래픽이 표준 TCP 흐름 제어 알고리즘을 따르고 있는지 감시할 필요가 있다. 이러한 기능르 수행할 수 있는지 감시할 필요가 있다. 이러한 기능을 수행할 수 있는 몇 가지 방안들이 제안되었으니 이들은 TCP 플로우(flow)의 RTT(round trip time)를 얻지 못하여 실제로 사용될 수 없는 문제를 갖고 있다. 본 연구에서는 인터넷 망 내 라우터에서 각 TCP 플로우의 RTT 값을 측정할 수있는 알고리즘을 제안하고, 시뮬레이션을 통하여 알고리즘의 올바른 동작을 확인하였다.