• Proceedings of the KIPE Conference
• /
• 2011.07a
• /
• pp.471-472
• /
• 2011

본 논문에서는 상 절체와 같은 급작스러운 위상천위 발생시에도 위상추정에 의한 계통연계를 위한 고속 PLL 알고리즘을 제안하였다. 제안된 고속 PLL 알고리즘은 2상 정지좌표계에서 취득한 위상정보의 불안정성을 보상하기 위함으로 저주파 필터를 이용한 정지좌표계상의 위상정보를 feed-forward로 사용한 결과, 외란에 강인한 위상각을 추정하는 알고리즘을 구현하였으며, PSIM을 이용한 시뮬레이션을 통하여 제안한 알고리즘의 타당성을 검증하였다.

• International Journal of Contents
• /
• v.10 no.1
• /
• pp.18-22
• /
• 2014

Hidden nodes have a key role in the information processing of feed-forward neural networks in which inputs are processed through a series of weighted sums and nonlinear activation functions. In order to understand the role of hidden nodes, we must analyze the effect of the nonlinear activation functions on the weighted sums to hidden nodes. In this paper, we focus on the effect of nonlinear functions in a viewpoint of information theory. Under the assumption that the nonlinear activation function can be approximated piece-wise linearly, we prove that the entropy of weighted sums to hidden nodes decreases after piece-wise linear functions. Therefore, we argue that the nonlinear activation function decreases the uncertainty among hidden nodes. Furthermore, the more the hidden nodes are saturated, the more the entropy of hidden nodes decreases. Based on this result, we can say that, after successful training of feed-forward neural networks, hidden nodes tend not to be in linear regions but to be in saturated regions of activation function with the effect of uncertainty reduction.

• International Journal of Contents
• /
• v.10 no.1
• /
• pp.23-28
• /
• 2014

When developing a classifier using various objective functions, it is important to compare the performances of the classifiers. Although there are statistical analyses of objective functions for classifiers, simulation results can provide us with direct comparison results and in this case, a comparison criterion is considerably critical. A Receiver Operating Characteristics (ROC) graph is a simulation technique for comparing classifiers and selecting a better one based on a performance. In this paper, we adopt the ROC graph to compare classifiers trained by mean-squared error, cross-entropy error, classification figure of merit, and the n-th order extension of cross-entropy error functions. After the training of feed-forward neural networks using the CEDAR database, the ROC graphs are plotted to help us identify which objective function is better.

• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.225-232
• /
• 2017

Understanding actions in videos is an important task. It helps in finding the anomalies present in videos such as fights. Detection of fights becomes more crucial when it comes to sports. This paper focuses on finding fight scenes in Hockey sport videos using blur & radon transform and convolutional neural networks (CNNs). First, the local motion within the video frames has been extracted using blur information. Next, fast fourier and radon transform have been applied on the local motion. The video frames with fight scene have been identified using transfer learning with the help of pre-trained deep learning model VGG-Net. Finally, a comparison of the methodology has been performed using feed forward neural networks. Accuracies of 56.00% and 75.00% have been achieved using feed forward neural network and VGG16-Net, respectively.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.2
• /
• pp.64-70
• /
• 2009

A 6-Gbps feed-forward equalizer having a 6.2-dB gain at 3GHz is designed in 0.13-um CMOS technology and the equalizer helps error-free data recovery over a 7-m SATA cable with 14.7dB loss. Based on a differentially-connected varactor, the proposed equalizer uses only a one-fourth varactor size of a conventional equalizer, which enables the equalizer's integration in a pad-frame, high operating frequency, and low power dissipation of 3.6mW.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2009.04a
• /
• pp.627-632
• /
• 2009

This paper proposes a new haptic cue vehicle accelerator pedal device using magnetorheological (MR) brake. As a first step, an MR fluid-based haptic cue device is devised to be capable of rotary motion of accelerator pedal. Under consideration of spatial limitation, design parameters are optimally determined to maximize control torque using finite element method. The proposed haptic cue device is then manufactured and integrated with accelerator pedal. Its field-dependant torque is experimentally evaluated. Vehicle system emulating gear shifting and engine speed is constructed in virtual environment and communicated with the haptic cue device. Haptic cue algorithm using the feed-forward control algorithm is formulated to achieve optimal gear shifting in driving. Control performances are experimentally evaluated via feed-forward control strategy and presented in time domain.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.2 no.1
• /
• pp.69-76
• /
• 2013

This paper is concerned with speed tracking control problem for permanent-magnet synchronous drives (PMSM) in the presence of an variable load torque and unknown model parameters. The disturbance of speed control caused by inaccuracy of model parameters has been investigated. A load torque observer has been proposed to observe the load torque and estimate the disturbance caused by inaccuracy of model parameters. Both inertia and friction coefficient are identified in gradient descent approach. The stability condition of the observer has also been studied. Furthermore an improved feed-forward control has been introduced to reduce the speed track error. The proposed control strategy has been verified by both simulation and experimental results.

• Journal of Advanced Marine Engineering and Technology
• /
• v.28 no.2
• /
• pp.228-236
• /
• 2004

In this paper. we present a neuro-fuzzy controller which unifies both fuzzy logic and multi-layered feed forward neural networks. Fuzzy logic provides a means for converting linguistic control knowledge into control actions. On the other hand. feed forward neural networks provide salient features. such as learning and parallelism. In the proposed neuro-fuzzy controller. the parameters of membership functions in the antecedent part of fuzzy inference rules are identified by using the error back propagation algorithm as a learning rule. while the coefficients of the linear combination of input variables in the consequent part are determined by using the least square estimation method. Finally. the effectiveness of the proposed controller is verified through computer simulation for an inverted pole system.

• International Journal of Contents
• /
• v.8 no.4
• /
• pp.30-35
• /
• 2012

Error surfaces provide us with very important information for training of feed-forward neural networks (FNNs). In this paper, we draw the contour plots of various error or objective functions for training of FNNs. Firstly, when applying FNNs to classifications, the weakness of mean-squared error is explained with the viewpoint of error contour plot. And the classification figure of merit, mean log-square error, cross-entropy error, and n-th order extension of cross-entropy error objective functions are considered for the contour plots. Also, the recently proposed target node method is explained with the viewpoint of contour plot. Based on the contour plots, we can explain characteristics of various error or objective functions when training of FNNs proceeds.

• Journal of Advanced Marine Engineering and Technology
• /
• v.33 no.5
• /
• pp.713-720
• /
• 2009

Numerous applications of position controlling devices using servoing technique and transmission of energy through belt drives are practiced in the industry. Belt drive is a simple, lightweight, low cost power transmission system. Belt drives provide freedom to position the motor relative to the load and this phenomenon enables reduction of the robot arm inertia. It also facilitates quick response when employed in robotics. In this paper, precision positioning of a belt driven mechanism using a feed-forward compensator under maximum acceleration and velocity constraints is proposed. The proposed method plans the desired trajectory and modifies it to compensate delay dynamics and vibration. Being an offline method, the proposed method could be easily and effectively adopted to the existing systems without any modification of the hardware setup. The effectiveness of the proposed method is demonstrated through computer simulation and experimental results.