• Journal of the Korean Statistical Society
• /
• v.31 no.1
• /
• pp.63-75
• /
• 2002

Most attempts at Bayesian analysis of neural networks involve hierarchical modeling. We believe that similar results can be obtained with simpler models that require less computational effort, as long as appropriate restrictions are placed on parameters in order to ensure propriety of posterior distributions. In particular, we adopt a model first introduced by Lee (1999) that utilizes an improper prior for all parameters. Straightforward Gibbs sampling is possible, with the exception of the bias parameters, which are embedded in nonlinear sigmoidal functions. In addition to the problems posed by nonlinearity, direct sampling from the posterior distributions of the bias parameters is compounded due to the duplication of hidden nodes, which is a source of multimodality. In this regard, we focus on sampling from the marginal posterior distribution of the bias parameters with Markov chain Monte Carlo methods that combine traditional Metropolis sampling with a slice sampler described by Neal (1997, 2001). The methods are illustrated with data examples that are largely confined to the analysis of nonparametric regression models.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.176-179
• /
• 2011

본 논문은 IEEE 802.11기반 무선 멀티홉 환경에서 은닉 노드가 존재할 때 전체 시스템의 효율 저하를 최소화 하면서도 평균 시간 지연 요구를 만족할 수 있는 경쟁 윈도우 제어 알고리즘을 제안한다. 이에 적용되는 최소 경쟁 윈도우 기준값을 주어진 topology에 따라 도출하고 각 트래픽 플로어의 QoS 요구조건 만족과 은닉노드가 존재할 경우에 성능개선을 위한 경쟁 윈도우 제어 패턴을 조절한다. 제안하는 경쟁 윈도우 제어 기법을 ns-2 시뮬레이션을 통해 검증하고, 모든 QoS 요구를 수용하면서 전체 성능 개선을 보이는 결과를 구하였다.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.45 no.2
• /
• pp.45-57
• /
• 2003

An artificial neural network model was developed to analyze and forecast Short-term river runoff from the Naju watershed, in Korea. Error back propagation neural networks (EBPN) of hourly rainfall and runoff data were found to have a high performance In forecasting runoff. The number of hidden nodes were optimized using total error and Bayesian information criterion. Model forecasts are very accurate (i.e., relative error is less than 3% and $R^2$is greater than 0.99) for calibration and verification data sets. Increasing the time horizon for application data sets, thus mating the model suitable for flood forecasting. decreases the accuracy of the model. The resulting optimal EBPN models for forecasting hourly runoff consists of ten rainfall and four runoff data(ANN0410 model) and ten rainfall and ten runoff data(ANN1010 model). Performances of the ANN0410 and ANN1010 models remain satisfactory up to 6 hours (i.e., $R^2$is greater than 0.92).

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2000.10a
• /
• pp.384-389
• /
• 2000

A artificial neural network model was developed to analyze and forecast the flow fluctuation at small streams in the Balan watershed. Backpropagation neural networks were found to perform very well in forecasting daily streamflows. In order to deal with slow convergence and an appropriate structure, two algorithms were proposed for speeding up the convergence of the backpropagation method, and the Bayesian Information Criterion(BIC) was proposed for obtaining the optimal number of hidden nodes. From simulations using daily flows at the HS#3 watershed of the Balan Watershed Project, which is 412,5 ㏊ in size and relatively steep in landscape, it was found that those algorithms perform satisfactorily.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10c
• /
• pp.475-477
• /
• 2003

본 논문에서는 IEEE 802.11 을 기반으로 하는 무선 Ad Hoc 망에서 데이터의 송신자 노드와 목적지 노드의 중간 노드들의 전송을 방해하고 채널을 경쟁하는 경쟁노드들이 Shortest­path 라우팅 경로 설정에 미치는 영향을 분석한다. 데이터를 전송하는 중간 노드들이 다수의 경쟁노드를 가지고 있을 경우 MAC delay 가 큰 변수로 작용하며 multi­hop 환경이기 때문에 hidden terminal 문제가 발생한다. 또한 AODV 와 같은 on­demand 라우팅 알고리즘은 경로를 찾기 위해서 Route Request 패킷을 브로드캐스트 하는데 이때 브로드캐스트 패킷의 성공적인 전송이 보장되지 않기 때문에 경쟁노드의 방해가 심한 경우 경로를 찾는데 실패할 가능성이 높아진다. 본 논문에서는 이러한 특성들을 근거로 경쟁노드의 수와 분포가 라우팅 경로 선택에 영향을 미친다는 것을 지적한다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.6
• /
• pp.67-75
• /
• 1993

ECG pattern was classified using a back-propagation neural network. An improved feature extractor of ECG is proposed for better classification capability. It is consisted of preprocessing ECG signal by an FIR filter faster than conventional one by a factor of 5. QRS complex recognition by moving-window integration, and peak extraction by quadratic approximation. Since the FIR filter had a periodic frequency spectrum, only one-fifth of usual processing time was required. Also, segmentation of ECG signal followed by quadratic approximation of each segment enabled accurate detection of both P and T waves. When improtant features were extracted and fed into back-propagation neural network for pattern classification, the required number of nodes in hidden and input layers was reduced compared to using raw data as an input, also reducing the necessary time for study. Accurate pattern classification was possible by an appropriate feature selection.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.1
• /
• pp.94-101
• /
• 1992

The multilayer perceptron, trained by the error back-propagation learning rule, has been known as a mapping network which can represent arbitrary functions. However depending on the complexity of a function and the initial weights of the multilayer perceptron, the error back-propagation learning may fall into a local minimum or a flat area which may require a long learning time or lead to unsuccessful learning. To solve such difficulties in training the multilayer perceptron by standard error back-propagation learning rule, the paper proposes a learning method which progressively enlarges the learning domain from a small area to the entire region. The proposed method is devised from the investigation on the roles of hidden nodes and connection weights in the multilayer perceptron which approximates a function of one variable. The validity of the proposed method was illustrated through simulations for a function of one variable and a function of two variable with many extremal points.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.9 no.4
• /
• pp.193-203
• /
• 2014

This paper implements a weather monitoring system based on wireless sensor network. The wireless sensor network protocol proposed in this paper adopts a TDMA styled MAC. The protocol is designed to balance the energy consumption among sensor nodes. Other purposes of the protocol are to avoid the hidden terminal problem in 2-hop star topology, and to allow a CSMA styled communication in a given time slot to support emergent messages. Also, this paper develops the hardware of sensor node, gateway and electric generator based on solar and windy energy. The test results on the implemented system show that the time slot of each node is shifted in circular manner to balance the waiting time for transmission, and the reliability of wireless communication is over 99%.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2414-2416
• /
• 2003

In this raper, we present a Wavelet Neural Network(WNN) approach to the solution of the tracking problem for mobile robots that possess complexity, nonlinearity and uncertainty. The neural network is constructed by the wavelet orthogonal decomposition to form a wavelet neural network that can overcome the problems caused by local minima of optimization and various uncertainties. This network structure is helpful to determine the number of the hidden nodes and the initial value of weights with compact structure. In our control method, the control signals are directly obtained by minimizing the difference between the reference track and the pose of a mobile robot that is controlled through a wavelet neural network. The control process is a dynamic on-line process that uses the wavelet neural network trained by the gradient-descent method. Through computer simulations, we demonstrate the effectiveness and feasibility of the proposed control method.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2046-2048
• /
• 2003

In this paper, a neural disturbance observer(NDO) is developed and its application to the control of a nonlinear system with the internal and/or external disturbances is presented. To construct the NDO, a parameter tuning method is proposed and shown to be useful in adjusting the parameters of the NDO. The tuning method employes the disturbance observation error to guarantee that the NDO monitors unknown disturbances. Each of the nodes of the hidden layer in the NDO network is a radial basis function(RBF). In addition, the relationships between the suggested NDO-based control and the conventional adaptive controls reported in the previous literatures are discussed. And it is shown in a rigorous manner that the disturbance observation error converges to a region of which size can be kept arbitrarily small. Finally, an example and some computer simulation results are presented to illustrate the effectiveness and the applicability of the NDO.