• Journal of Electrical Engineering and Technology
• /
• v.13 no.6
• /
• pp.2468-2478
• /
• 2018

We propose the Sparse Feature Convolutional Neural Network (SFCNN) to reduce the volume of convolutional neural networks (CNNs). Despite the superior classification performance of CNNs, their enormous network volume requires high computational cost and long processing time, making real-time applications such as online-training difficult. We propose an advanced network that reduces the volume of conventional CNNs by producing a region-based sparse feature map. To produce the sparse feature map, two complementary region-based value extraction methods, cluster max extraction and local value extraction, are proposed. Cluster max is selected as the main function based on experimental results. To evaluate SFCNN, we conduct an experiment with two conventional CNNs. The network trains 59 times faster and tests 81 times faster than the VGG network, with a 1.2% loss of accuracy in multi-class classification using the Caltech101 dataset. In vehicle classification using the GTI Vehicle Image Database, the network trains 88 times faster and tests 94 times faster than the conventional CNNs, with a 0.1% loss of accuracy.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.705-709
• /
• 1995

The objective of this study is to design a multi-layer neural network which controls the position of excavator's attachment. In this paper, a dynamic controller has been developed based on an error back-propagation(BP) neural network. Since the neural network can model an arbitrary nonlinear mapping, it was used as a commanded feedforward input generator. A PD feedback controller is used in parallel with the feedforward neural network to train the system. The neural network was trained by the current state of the excavator as well as the PD feedback error. By using the BP network as a feedforward controller, no a priori knowledge on system dynamics is need. Computer simulation results demonstrate such powerful characteristics of the proposed controller as adaptation to changing environment, robustness to disturbancen and performance improvement with the on-line learning in the position control of excavator attachment.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.91-92
• /
• 2019

본 논문에서는 IoT 기기의 각 센서로부터 획득된 데이터에 대한 수집 및 효율적 라우팅 기법을 기반으로 대용량 데이터 수집의 효율성 및 신뢰도 향상을 위해 In-network 데이터 병합 기반 데이터 전처리 기법을 제안한다. 기존의 Wireless Sensor Network에서는 모든 단말 노드가 스스로 라우팅 된 하위 센서 노드들의 데이터를 병합하는 In-network 병합기법을 사용한다. 이 기법은 이벤트가 발생하지 않거나 필요한 쿼리가 없어도 주기적으로 라우팅에 필요한 메시지를 전송하므로 불필요한 에너지 소모를 야기 시키며 데이터 전송 에러가 발생할 확률이 높다. 기존 In-Network 데이터 병합 기법의 효율성 및 정확성을 향상시키기 위해, 본 논문에서는 조건 병합 기반의 In-network 병합 기법을 제안한다.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.5
• /
• pp.1070-1076
• /
• 2016

• Journal of Electrical Engineering and Technology
• /
• v.9 no.6
• /
• pp.1822-1831
• /
• 2014

Micro-grid is connected to the main power grid through a static switch. One of the critical issues in micro-grids is protection which must disconnect the micro-grid from the network in short-circuit contingencies. Protective methods of micro-grid mainly follow the model of distribution system protection. This protection scheme suffers from improper operation due to the presence of single-phase loads, imbalance of three-phase loads and occurrence of power swings in micro-grid. In this paper, a new method which prevents from improper performance of static micro-grid protection is proposed. This method works based on artificial neural network (ANN) and able to differentiate short circuit from power swings by measuring impedance and the rate of impedance variations in PCC bus. This new technique provides a protective system with higher reliability.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.4
• /
• pp.1548-1555
• /
• 2017

This paper attempts to employ and investigate neural based approaches as interpolation tools for modeling of Switched Reluctance Motor (SRM) drive. Precise modeling of SRM is essential to analyse the performance of control strategies for variable speed drive application. In this work the suitability of Generalized Regression Neural Network (GRNN) and Extreme Learning Machine (ELM) in addition to conventional neural network are explored for improving the modeling accuracy of SRM. The neural structures are trained with the data obtained by modeling of SRM using Finite Element Analysis (FEA) and the trained neural network is incorporated in the model of SRM drive. The results signify the modeling accuracy with GRNN model. The closed loop drive simulation is performed in MATLAB/Simulink environment and the closeness of the results in comparison with the experimental prototype validates the modeling approach.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.293-295
• /
• 1995

In this article a fuzzy controller and neural network adaptive observer is proposed and applied to the case of induction motor control. The proposed observer which comprises neural network flux observer and neural network torque observer is trained to learn the flux dynamics and torque dynamics and subjected to further on-line training by means of a backpropagation algorithm. Therefore it has been shown that the robust control of induction motor neglects the rotor time constant variations.

• Transactions on Electrical and Electronic Materials
• /
• v.7 no.4
• /
• pp.210-214
• /
• 2006

In this paper, two sampling methods which are Latin hypercube sampling (LHS) and simple random sampling were. compared to improve the modeling speed of neural network model. Sampling method was used to generate initial weights and bias set. Electrical characteristic data for $HfO_2$ thin film was used as modeling data. 10 initial parameter sets which are initial weights and bias sets were generated using LHS and simple random sampling, respectively. Modeling was performed with generated initial parameters and measured epoch number. The other network parameters were fixed. The iterative 20 minimum epoch numbers for LHS and simple random sampling were analyzed by nonparametric method because of their nonnormality.

• Proceedings of the KIEE Conference
• /
• 1995.07a
• /
• pp.39-41
• /
• 1995

The inherent performance of Ultrasonic Motor(USM) which is on of highlighted a directly-driven positioning servo motor/actuator. In this paper, the speed of control USM based on neural network control. The neural network control can roughly be classified as the direct control and indirect control schemes. An indirect control scheme is adopted for Ultrasonic Motor speed control. A back propagation algorithm is used to train neural network controller. The Simulation results show that this neural network control system can provide good dynamical responses.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.34-37
• /
• 2002

This paper presents a new stochastic binary neural network based on the Hopfield model. We apply the proposed network to TSP and compare it with other methods by computer simulations. Furthermore, we apply 2-opt to the proposed network to improve the performance.