• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.237-240
• /
• 2020

The fine-tuned neural network (NN) model for a whole temporal portion in a video does not always yield the best quality (e.g., PSNR) performance over all regions of each frame in the temporal period. For certain regions (usually homogeneous regions) in a frame for super-resolution (SR), even a simple bicubic interpolation method may yield better PSNR performance than the fine-tuned NN model. When there are multiple NN models available at the receivers where each NN model is trained for a group of images having a specific category of image characteristics, the performance of Quality enhancement can be improved by selectively applying an appropriate NN model for each image region according to its image characteristic category to which the NN model was dedicatedly trained. In this case, it is necessary to signal which NN model is applied for each region. This is very advantageous for image restoration and quality enhancement (IRQE) applications at user terminals with limited computing capabilities.

• Smart Structures and Systems
• /
• v.16 no.6
• /
• pp.1133-1145
• /
• 2015

A new neural network (NN) predictive controller (NNPC) algorithm has been developed and tested in the computer simulation of active control of a nonlinear structure. In the present method an NN is used as a predictor. This NN has been trained to predict the future response of the structure to determine the control forces. These control forces are calculated by minimizing the difference between the predicted and desired responses via a numerical minimization algorithm. Since the NNPC is very time consuming and not suitable for real-time control, it is then used to train an NN controller. To consider the effectiveness of the controller on probability of damage, fragility curves are generated. The approach is validated by using simulated response of a 3 story nonlinear benchmark building excited by several historical earthquake records. The simulation results are then compared with a linear quadratic Gaussian (LQG) active controller. The results indicate that the proposed algorithm is completely effective in relative displacement reduction.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.512-514
• /
• 2011

본 논문에서는 스펙트럼 회복의 수단으로써 신경회로망을 사용하여 푸리에변환(FFT) 진폭성분 및 위상성분을 복원하는 알고리즘을 제안한다. 본 논문에서는 먼저 각 프레임의 FFT 진폭성분들을 유성음 구간과 무성음 구간으로 검출한 후, 유성음 및 무성음 구간에 대해서 각 프레임의 FFT 진폭성분들을 저역, 중역 및 고역으로 각각 분리한 후에 각 대역의 FFT 진폭성분들을 저역용 신경회로망(NN), 중역용 NN, 그리고 고역용 NN의 입력으로 하여 각 NN에 학습시킴으로써 최종 FFT 진폭성분들을 구한다. 본 실험에서는 Aurora2 데이터베이스를 사용하여 FFT의 진폭성분을 복원하는 잡음제거의 알고리즘을 사용하여 여러 잡음에 대해서 본 알고리즘의 유효성을 실험적으로 확인한다.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1996.11a
• /
• pp.361-364
• /
• 1996

Aging diagnosis system using partial discharge(PD) is being highlighted as a research area. But the application of PD requires complicated analysis method because the PD has complex progressing forms. In this paper, It has been developed to the PD diagnosis system using neural network(NN). As a result after NN learning, the recognized rate was represented about 85%. The safety area is possible to express the second output of NN in this experiments.

• 한국컴퓨터산업교육학회:학술대회논문집
• /
• 2003.11a
• /
• pp.59-64
• /
• 2003

Principal component analysis(PCA) and neural network(NN) are used in reducing external noise in magnetocadiography. The PCA technique turns out to be very effective in reducing pulse noise in some SQUID channels and the NN find noise component automatically. Some experimental results obtained from 61 channel MCG system are shown.

• Journal of information and communication convergence engineering
• /
• v.6 no.4
• /
• pp.448-453
• /
• 2008

This study describes design and development techniques of estimation models for process modeling. One case study is undertaken to design a model using standard gas furnace data. Neural networks (NN) and genetic programming (GP) are each employed to model the crucial relationships between input factors and output responses. In the case study, two models were generated by using 70% training data and evaluated by using 30% testing data for genetic programming and neural network modeling. The model performance was compared by using RMSE values, which were calculated based on the model outputs. The average RMSE for training and testing were 0.8925 (training) and 0.9951 (testing) for the NN model, and 0.707227 (training) and 0.673150 (testing) for the GP model, respectively. As concern the results, the NN model has a strong advantage in model training (using the all data for training), and the GP model appears to have an advantage in model testing (using the separated data for training and testing). The performance reproducibility of the GP model is good, so this approach appears suitable for modeling physical fabrication processes.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.12
• /
• pp.1218-1225
• /
• 2008

This paper presents the design of a neural network based adaptive control for missile is presented. The application model is Exocet MM40, which is derived from missile DATCOM database. Acceleration of missile by tail Fin control cannot be controllable by DMI (Dynamic Model Inversion) directly because it is non-minimum phase system. So, the inner loop consists of DMI and NN (Neural Network) and the outer loop consists of PI controller. In order to satisfy the performances only with PI controller, it is necessary to do some additional process such as gain tuning and scheduling. In this paper, all flight area would be covered by just one PI gains without tuning and scheduling by applying mixture control technique of conventional controller and NN to the outer loop. Also, the simulation model is designed by considering non-minimum phase system and compared the performances to distinguish the validity of control law with conventional PI controller.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.700-705
• /
• 2018

In this paper, we propose the gas classifier based on restricted column energy neural network (RCE-NN) and present its hardware implementation results for real-time learning and classification. Since RCE-NN has a flexible network architecture with real-time learning process, it is suitable for gas classification applications. The proposed gas classifier showed 99.2% classification accuracy for the UCI gas dataset and was implemented with 26,702 logic elements with Intel-Altera cyclone IV FPGA. In addition, it was verified with FPGA test system at an operating frequency of 63MHz.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.6
• /
• pp.522-530
• /
• 2002

This paper introduces a neural network (NN) -based nonlinear predictor for the LP (Linear Prediction) residual. To evaluate the effectiveness of the NN-based nonlinear predictor for LP-residual, we first compared the average prediction gain of the linear long-term predictor with that of the NN-based nonlinear long-term predictor. Then, the effects on the quantization noise of the nonlinear prediction residuals were investigated for the NN-based nonlinear predictor A new NN predictor takes into consideration not only prediction error but also quantization effects. To increase robustness against the quantization noise of the nonlinear prediction residual, a constrained back propagation learning algorithm, which satisfies a Kuhn-Tucker inequality condition is proposed. Experimental results indicate that the prediction gain of the proposed NN predictor was not seriously decreased even when the constrained optimization algorithm was employed.

• Wind and Structures
• /
• v.9 no.1
• /
• pp.37-58
• /
• 2006

The paper describes a study about effects of upstream hills on design wind loads using two mathematical approaches: Computational Fluid Dynamics (CFD) and Artificial Neural Network (NN for short). For this purpose CFD and NN tools have been developed using an object-oriented approach and C++ programming language. The CFD tool consists of solving the Reynolds time-averaged Navier-Stokes equations and $k-{\varepsilon}$ turbulence model using body-fitted nearly-orthogonal coordinate system. Subsequently, design wind load parameters such as speed-up ratio values have been generated for a wide spectrum of two-dimensional hill geometries that includes isolated and multiple steep and shallow hills. Ground roughness effect has also been considered. Such CFD solutions, however, normally require among other things ample computational time, background knowledge and high-capacity hardware. To assist the enduser, an easier, faster and more inexpensive NN model trained with the CFD-generated data is proposed in this paper. Prior to using the CFD data for training purposes, extensive validation work has been carried out by comparing with boundary layer wind tunnel (BLWT) data. The CFD trained NN (CFD-NN) has produced speed-up ratio values for cases such as multiple hills that are not covered by wind design standards such as the Commentaries of the National Building Code of Canada (1995). The CFD-NN results compare well with BLWT data available in literature and the proposed approach requires fewer resources compared to running BLWT experiments.