• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 1996년도 디자인 학 연구 제 4회 춘계학술연구발표대회 개요 집
• /
• pp.59-60
• /
• 1996

• 제어로봇시스템학회논문지
• /
• 제10권12호
• /
• pp.1295-1304
• /
• 2004

In this paper, the Bayesian recurrent neural network is proposed to predict time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one needs to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, the weights vector is set as a state vector of state space method, and its probability distributions are estimated in accordance with the particle filtering process. This approach makes it possible to obtain more exact estimation of the weights. In the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent neural network with Bayesian inference, what we call Bayesian recurrent neural network (BRNN), is expected to show higher performance than the normal neural network. To verify the proposed method, the time series data are numerically generated and various kinds of neural network predictor are applied on it in order to be compared. As a result, feedback structure and Bayesian learning are better than feedforward structure and backpropagation learning, respectively. Consequently, it is verified that the Bayesian reccurent neural network shows better a prediction result than the common Bayesian neural network.

• 제어로봇시스템학회논문지
• /
• 제19권10호
• /
• pp.901-906
• /
• 2013

Chaff is a kind of matter spreading atmosphere with the purpose of preventing aircraft from detecting by radar. The chaff is commonly composed of small aluminum pieces, metallized glass fiber, or other lightweight strips which consists of reflecting materials. The chaff usually appears on the radar images as narrow bands shape of highly reflective echoes. And the chaff echo has similar characteristics to precipitation echo, and it interrupts weather forecasting process and makes forecasting accuracy low. In this paper, the chaff echo recognizing and removing method is suggested using Bayesian network. After converting coordinates from spherical to Cartesian in UF (Universal Format) radar data file, the characteristics of echoes are extracted by spatial and temporal clustering. And using the data, as a result of spatial and temporal clustering, a classification process for analyzing is performed. Finally, the inference system using Bayesian network is applied. As a result of experiments with actual radar data in real chaff echo appearing case, it is confirmed that Bayesian network can distinguish between chaff echo and non-chaff echo.

• Journal of Electrical Engineering and Technology
• /
• 제9권3호
• /
• pp.1060-1071
• /
• 2014

Signals of the Electroencephalogram (EEG) can reflect the electrical background activity of the brain generated by the cerebral cortex nerve cells. This has been the mostly utilized signal, which helps in effective analysis of brain functions by supervised learning methods. In this paper, an approach for improving the accuracy of EEG signal classification is presented to detect epileptic seizures. Moreover, Independent Component Analysis (ICA) is incorporated as a preprocessing step and Short Time Fourier Transform (STFT) is used for denoising the signal adequately. Feature extraction of EEG signals is accomplished on the basis of three parameters namely, Standard Deviation, Correlation Dimension and Lyapunov Exponents. The Artificial Neural Network (ANN) is trained by incorporating Levenberg-Marquardt(LM) training algorithm into the backpropagation algorithm that results in high classification accuracy. Experimental results reveal that the methodology will improve the clinical service of the EEG recording and also provide better decision making in epileptic seizure detection than the existing techniques. The proposed EEG signal classification using feed forward Backpropagation Neural Network performs better than to the EEG signal classification using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier in terms of accuracy, sensitivity, and specificity.

• 한국전자통신학회논문지
• /
• 제8권3호
• /
• pp.397-402
• /
• 2013

다중센서를 이용한 상황인식에서 시간변화는 고려해야 하는 요소이다. 센서가 감지하여 보고한 정보를 바탕으로 상황추론에 도달하고자 하는 경우, 일정 시간 간격별로 묶어서 검토하는 것이 유용하다. 본 논문에서는 시간경과를 고려하는 클러스터링 기법을 이용한 다중센서 데이터융합을 제안한다. 각 센서별로 일정시간 간격동안 수집되어 보고된 센싱 정보를 묶어 1차 데이터융합을 실시하고 그 결과를 대상으로 다시 2차 데이터융합을 실시하였다. Dempster-Shafer이론을 이용하여 다중센서 데이터융합을 실시하고 그 결과를 분석하여 상황을 추론하는데 시간간격을 기준으로 세분화시켜 평가하고 이것을 다시 융합함으로써 향상된 상황 정보를 추론할 수 있다.

• 한국정보기술응용학회:학술대회논문집
• /
• 한국정보기술응용학회 2005년도 6th 2005 International Conference on Computers, Communications and System
• /
• pp.243-246
• /
• 2005

Recent ubiquitous computing environments increasingly impact on our lives using the current technologies of sensor network and ubiquitous services. In this paper, we propose ubiquitous architectural framework for ubiquitous sleep aid service(UbiSAS) in the subset of ubiquitous computing for refreshing of human's sleep. And we examine technical feasibility. Human can recover his health through refreshing sleep from fatigue. Ubiquitous architectural framework for UbiSAS in digital home offers agreeable sleeping environment and improves recovery from fatigue. So we present new concept of ubiquitous architectural framework dissolving stress. Specially, we apply context to context-aware framework module. This context is transferred to context adaptive inference engine which has service invocation function in intelligent agent module. Ubiquitous architectural framework for UbiSAS using context adaptive rule inference engine without user intervention is technical issue. That is to say, we should take sleep comfortably during our sleeping. And sensed information during sleeping is changed to context-aware information. This presents significant information in context adaptive rule inference engine for UbiSAS. This information includes all sleeping state during sleeping in context-aware computing technique. So we propose more effective and most suitable ubiquitous architectural framework using context adaptive rule inference engine for refreshing sleep in this paper.

• 한국정밀공학회지
• /
• 제19권4호
• /
• pp.132-139
• /
• 2002

In GMAW(Gas Metal Arc Welding) processes, bead geometry (penetration, bead width and height) is a criterion to estimate welding quality. Bead geometry is affected by welding current, arc voltage and travel speed, shielding gas, CTWD (contact-tip to workpiece distance) and so on. In this paper, welding process variables were selected as welding current, arc voltage and travel speed. And bead geometry was reasoned from the chosen welding process variables using neuro-fuzzy algorithm. Neural networks was applied to design FL(fuzzy logic). The parameters of input membership functions and those of consequence functions in FL were tuned through the method of learning by backpropagation algorithm. Bead geometry could be reasoned from welding current, arc voltage, travel speed on FL using the results learned by neural networks. On the developed inference system of bead geometry using neuro-furzy algorithm, the inference error percent of bead width was within $\pm$4%, that of bead height was within $\pm$3%, and that of penetration was within $\pm$8%. Neural networks came into effect to find the parameters of input membership functions and those of consequence in FL. Therefore the inference system of welding quality expects to be developed through proposed algorithm.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권9호
• /
• pp.430-438
• /
• 2001

In this study, we introduce the adaptive Polynomial Neuro-Fuzzy Networks(PNFN) architecture generated from the fusion of fuzzy inference system and PNN algorithm. The PNFN dwells on the ideas of fuzzy rule-based computing and neural networks. Fuzzy inference system is applied in the 1st layer of PNFN and PNN algorithm is employed in the 2nd layer or higher. From these the multilayer structure of the PNFN is constructed. In order words, in the Fuzzy Inference System(FIS) used in the nodes of the 1st layer of PNFN, either the simplified or regression polynomial inference method is utilized. And as the premise part of the rules, both triangular and Gaussian like membership function are studied. In the 2nd layer or higher, PNN based on GMDH and regression polynomial is generated in a dynamic way, unlike in the case of the popular multilayer perceptron structure. That is, the PNN is an analytic technique for identifying nonlinear relationships between system's inputs and outputs and is a flexible network structure constructed through the successive generation of layers from nodes represented in partial descriptions of I/O relatio of data. The experiment part of the study involves representative time series such as Box-Jenkins gas furnace data used across various neurofuzzy systems and a comparative analysis is included as well.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2856-2858
• /
• 1999

In this paper, the FPNN(Fuzzy Polynomial Neural Networks) algorithm with multi-layer fuzzy inference structure is proposed for the model identification of a complex nonlinear system. The FPNN structure is generated from the mutual combination of PNN (Polynomial Neural Network) structure and fuzzy inference method. The PNN extended from the GMDH(Group Method of Data Handling) uses several types of polynomials such as linear, quadratic and modifled quadratic besides the biquadratic polynomial used in the GMDH. In the fuzzy inference method, simplified and regression polynomial inference method which is based on the consequence of fuzzy rule expressed with a polynomial such as linear, quadratic and modified quadratic equation are used Each node of the FPNN is defined as a fuzzy rule and its structure is a kind of fuzzy-neural networks. Gas furnace data used to evaluate the performance of our proposed model.

• 방송공학회논문지
• /
• 제25권7호
• /
• pp.1081-1094
• /
• 2020

With the recent development of deep learning, most computer vision-related tasks are being solved with deep learning-based network technologies such as CNN and RNN. Computer vision tasks such as object detection or object segmentation use intermediate features extracted from the same backbone such as Resnet or FPN for training and inference for object detection and segmentation. In this paper, an experiment was conducted to find out the compression efficiency and the effect of encoding on task inference performance when the features extracted in the intermediate stage of CNN are encoded. The feature map that combines the features of 256 channels into one image and the original image were encoded in HEVC to compare and analyze the inference performance for object detection and segmentation. Since the intermediate feature map encodes the five levels of feature maps (P2 to P6), the image size and resolution are increased compared to the original image. However, when the degree of compression is weakened, the use of feature maps yields similar or better inference results to the inference performance of the original image.