• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.543-546
• /
• 2004

Bishop과 Nabney에 의해 소개된 기존의 혼합 밀도 네트워크(Mixture Density Network)에서는 조건부 확률밀도 함수의 매개변수들(parameters)이 하나의 MLP(multi-layer perceptron)의 출력 벡터로 주어진다. 최근에는 변형된 혼합 밀도 네트워크(Modified Mixture Density Network)라고 하는 이름으로 조건부 확률밀도 함수의 선분포(priors), 조건부 평균(conditional means), 그리고 공분산(covariances) 등이 각각 독립적인 MLP의 출력벡터로 주어지는 경우를 다룬 연구가 보고된 바 있다. 본 논문에서는 조건부 평균이 입력에 관해 선형인 경우를 위한 버전에 대한 이론과 매트랩 프로그램 개발 및 적용을 다룬다. 본 논문에서는 우선 일반적인 혼합 밀도 네트워크에 대해 간단히 설명하고, 혼합 밀도 네트워크의 출력인 다층 퍼셉트론의 매개변수를 각각 다른 다층 퍼셉트론에서 학습시키는 변형된 혼합 밀도 네트워크를 설명한 후, 각각 다른 다층 퍼셉트론을 통해 매개변수를 얻는 것은 동일하나 평균값은 선형함수를 통해 얻는 혼합 밀도 네트워크 버전을 소개한다. 그리고, 모의실험을 통하여 이러한 혼합 밀도 네트워크를의 적용가능성에 대해 알아본다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.847-851
• /
• 2004

In the original mixture density network(MDN), which was introduced by Bishop and Nabney, the parameters of the conditional probability density function are represented by the output vector of a single multi-layer perceptron. Among the recent modification of the MDNs, there is the so-called modified mixture density network, in which each of the priors, conditional means, and covariances is represented via an independent multi-layer perceptron. In this paper, we consider a further simplification of the modified MDN, in which the conditional means are linear with respect to the input variable together with the development of the MATLAB program for the simplification. In this paper, we first briefly review the original mixture density network, then we also review the modified mixture density network in which independent multi-layer perceptrons play an important role in the learning for the parameters of the conditional probability, and finally present a further modification so that the conditional means are linear in the input. The applicability of the presented method is shown via an illustrative simulation example.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.517-517
• /
• 2012

높은 전력 효율과 간단한 매칭 네트워크의 구조 등 많은 장점을 갖고 있는 직경 560 mm 페라이트 챔버가 대면적 웨이퍼에 대응하기 위해 개발 되었다. 플라즈마 소스원이 챔버 외곽에 위치해 있는 구조적 특성으로 인하여 아르곤 가스 방전 시 플라즈마 밀도 분포는 챔버 중앙부가 낮게 나타나는 볼록한 모양으로 형성 되는데 헬륨 가스를 적절히 혼합할 시에 밀도 분포가 변화가 관찰된다. 헬륨 가스 혼합 비에 따라 플라즈마 밀도 분포는 균일도가 매우 높아 질 수 있으며 60% 이상의 혼합비에서는 중앙 부분의 밀도가 최대치로 역전되는 오목한 밀도 분포가 나타나기도 한다. 이는 헬륨 가스의 대표적인 특징인 가벼운 질량과 높은 이온화 에너지 등에 기인하는데 이러한 특징을 갖는 헬륨 가스를 주입하게 되면 전자의 energy relaxation length가 늘어나게 되며 ambipolar diffusion 계수가 증가하게 된다. 랑뮈어 프로브를 이용하여 측정된 플라즈마 밀도 분포 변화는 앞서 계산 된 energy relaxation length 및 ambipolar diffusion 계수들의 변화로 설명된다.

• Electronics and Telecommunications Trends
• /
• v.17 no.5 s.77
• /
• pp.37-46
• /
• 2002

이동통신에서는 무선자원의 효율적인 사용을 위하여 variable rate vocoder 및 VoX 기법을 이용한 음성 전송이 일반적 추세이며, 버스티 특성을 갖는 패킷 트래픽의 경우 statistical multiplexing을 이용하여 무선 채널의 사용을 극대화 시킨다. 트래픽 밀도를 나타내는 Erlang 용량은 일정속도의 회선교환 트래픽에 대하여 동시에 점유할 수 있는 dedicated circuit의 수에 기초하는 개념이므로 statistical multiplexing으로 처리되는 데이터 패킷의 트래픽 밀도는 queuing model에 근거한 데이터 스루풋이 현실적이다. 그러나 이동통신 시스템에서 트래픽 특성을 달리하는 circuit 및 패킷 타입의 혼합 서비스가 동시에 제공될 경우 네트워크 planning을 위한 구성 시스템의 용량산정을 위해 트래픽 밀도의 통합적인 표현을 요구한다. 따라서 Erlang 용량과 데이터 스루풋의 상호 변환을 통하여 네트워크 구성요소의 용량 산정에 적당한 용량표현을 선택할 수 있다. 본 고에서는 트래픽 처리기로서의 통신시스템을 기술하기 위하여 일반적인 텔레트래픽 시스템 모델과 파라미터를 정의한다. 또한 음성 및 비음성 서비스의 혼합 트래픽 환경에서 트래픽 밀도계산을 위한 Erlang 용량과 데이터 스루풋의 상호 변환 관계를 소개한다. 마지막으로 3G1x 무선접속환경에서 음성 및 HSPD 서비스가 공존할 경우 기지국 CE dimensioning에 필요한 혼합 트래픽 Erlang 용량 산출 방법을 기술한다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.169-174
• /
• 2014

Practical deployment methods for sensor nodes are demanding as applications using sensor nodes increase. In particular, node connectivity is crucial not only for the network longevity but also for direct impacts on sensing and data collection capability. Economic requirement at building sensor networks and often limited access for sensor fields due to hostile environment force to remain at random deployment from air. However, random deployment often result in lost connection problem and inefficient network topology issue due to node irregularity. In this paper, mixed deployment of key nodes that have better communication capability is proposed to support the original deployment into working in an efficient way. Node irregularity is improved by introducing mixed nodes and an efficient mixed node density is also analyzed. Simulation results show that the mixed deployment method has better performance than the existing deployment methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.186-190
• /
• 2015

Intelligent vehicle plans motion and navigate itself based on the surrounding environment perception. Hence, the precise environment recognition is an essential part of self-driving vehicle. There exist many vulnerable road users (e.g. vehicle, pedestrians) on vehicular driving environment, the vehicle must percept all the dynamic obstacles accurately for safety. In this paper, we propose an multiple vehicle tracking algorithm using microwave radar. Our proposed system includes various special features. First, exceptional radar measurement model for vehicle, concentrated on the corner, is described by mixture density network (MDN), and applied to particle filter weighting. Also, to conquer the curse of dimensionality of particle filter and estimate the time-varying number of multi-target states, reversible jump markov chain monte carlo (RJMCMC) is used to sampling step of the proposed algorithm. The robustness of the proposed algorithm is demonstrated through several computer simulations.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.35 no.12
• /
• pp.1257-1264
• /
• 2011

This paper presents 3D simulation by STAR-CCM+ for lean premixed combustion in a stationary gas turbine combustor with separate pilot and main nozzles. The constant for the source term in the flame area density transport equation was modified to account for a low global equivalence ratio and validated against measurement data. A Partially-premixed Coherent Flame Model(PCFM) involves propagation of a laminar premixed flame with the predicted flame surface density and equilibrium assumption in the burned gas with spatial inhomogeneity. The conditions for cooling by radiation and convection are considered for accurate determination of the heat flux on the wall. A parametric study is of the pilot-fuel-to-total-fuel-ratio is carried out. A chemical reactor network (CRN) was constructed on the basis of the 3D simulation results and compared against measurements of NOx.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.1
• /
• pp.32-38
• /
• 2012

Each sensor node can know its location in several ways, if the node process the information based on its geographical position in sensor networks. In the localization scheme using GPS, there could be nodes that don't know their locations because the scheme requires line of sight to radio wave. Moreover, this scheme is high costly and consumes a lot of power. The localization scheme without GPS uses a sophisticated mathematical algorithm estimating location of sensor nodes that may be inaccurate. AHLoS(Ad Hoc Localization System) is a hybrid scheme using both GPS and location estimation algorithm. In AHLoS, the GPS node, which can receive its location from GPS, broadcasts its location to adjacent normal nodes which are not GPS devices. Normal nodes can estimate their location by using iterative triangulation algorithms if they receive at least three beacons which contain the position informations of neighbor nodes. But, there are some cases that a normal node receives less than two beacons by geographical conditions, network density, movements of nodes in sensor networks. We propose an indirect localization scheme for low-density sensor nodes which are difficult to receive directly at least three beacons from GPS nodes in wireless network.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.4
• /
• pp.765-773
• /
• 2009

Currently Telematics traffic information services have been various because we can collect real-time traffic information through Intelligent Transport System. In this paper, we proposed and implemented a short-term traffic information prediction model for giving to guarantee the traffic information with high quality in the near future. A Short-term prediction model is for forecasting traffic flows of each segment in the near future. Our prediction model gives an average speed on the each segment from 5 minutes later to 60 minutes later. We designed a Bayesian network for each segment with some casual nodes which makes an impact to the road situation in the future and found out its joint probability density function on the supposition of GMM(Gaussian Mixture Model) using EM(Expectation Maximization) algorithm with training real-time traffic data. To validate the precision of our prediction model we had conducted various experiments with real-time traffic data and computed RMSE(Root Mean Square Error) between a real speed and its prediction speed. As the result, our model gave 4.5, 4.8, 5.2 as an average value of RMSE about 10, 30, 60 minutes later, respectively.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.227-240
• /
• 2011

New concepts and ideas often result from extensive recombination of existing concepts or ideas. Both researchers and developers build on existing concepts and ideas in published papers or registered patents to develop new theories and technologies that in turn serve as a basis for further development. As the importance of patent increases, so does that of patent analysis. Patent analysis is largely divided into network-based and keyword-based analyses. The former lacks its ability to analyze information technology in details while the letter is unable to identify the relationship between such technologies. In order to overcome the limitations of network-based and keyword-based analyses, this study, which blends those two methods, suggests the keyword network based analysis methodology. In this study, we collected significant technology information in each patent that is related to Light Emitting Diode (LED) through text mining, built a keyword network, and then executed a community network analysis on the collected data. The results of analysis are as the following. First, the patent keyword network indicated very low density and exceptionally high clustering coefficient. Technically, density is obtained by dividing the number of ties in a network by the number of all possible ties. The value ranges between 0 and 1, with higher values indicating denser networks and lower values indicating sparser networks. In real-world networks, the density varies depending on the size of a network; increasing the size of a network generally leads to a decrease in the density. The clustering coefficient is a network-level measure that illustrates the tendency of nodes to cluster in densely interconnected modules. This measure is to show the small-world property in which a network can be highly clustered even though it has a small average distance between nodes in spite of the large number of nodes. Therefore, high density in patent keyword network means that nodes in the patent keyword network are connected sporadically, and high clustering coefficient shows that nodes in the network are closely connected one another. Second, the cumulative degree distribution of the patent keyword network, as any other knowledge network like citation network or collaboration network, followed a clear power-law distribution. A well-known mechanism of this pattern is the preferential attachment mechanism, whereby a node with more links is likely to attain further new links in the evolution of the corresponding network. Unlike general normal distributions, the power-law distribution does not have a representative scale. This means that one cannot pick a representative or an average because there is always a considerable probability of finding much larger values. Networks with power-law distributions are therefore often referred to as scale-free networks. The presence of heavy-tailed scale-free distribution represents the fundamental signature of an emergent collective behavior of the actors who contribute to forming the network. In our context, the more frequently a patent keyword is used, the more often it is selected by researchers and is associated with other keywords or concepts to constitute and convey new patents or technologies. The evidence of power-law distribution implies that the preferential attachment mechanism suggests the origin of heavy-tailed distributions in a wide range of growing patent keyword network. Third, we found that among keywords that flew into a particular field, the vast majority of keywords with new links join existing keywords in the associated community in forming the concept of a new patent. This finding resulted in the same outcomes for both the short-term period (4-year) and long-term period (10-year) analyses. Furthermore, using the keyword combination information that was derived from the methodology suggested by our study enables one to forecast which concepts combine to form a new patent dimension and refer to those concepts when developing a new patent.