• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.1-6
• /
• 1990

Neural network is a computational model of ft biological nervous system developed ID exploit its intelligence and parallelism. Applying neural networks so robots creates many advantages over conventional control methods such as learning, real-time control, and continuous performance improvement through training and adaptation. In this paper, dynamic control of a six-link robot will be presented using neural networks. The neural network model used in this paper is the backpropagation network. Simulated control of the PUMA 560 am shows that it can move a high speed as well as adapt to unforseen load changes and sensor noise. The results are compared with the conventional PD control scheme.

• Proceedings of the KIEE Conference
• /
• 1990.07a
• /
• pp.500-503
• /
• 1990

Neural network is a computational model of the biological nervous system developed to exploit its intelligence and parallelism. Applying neural networks to robots creates many advantages over conventional control methods such as learning, real-time control, and continuous performance improvement through training and adaptation. In this paper, dynamic control of a six-link robot will be presented using neural networks. The neural network model used in this paper is the backpropagation network. Simulated control of the PUMA 560 arm shows that it can move at high speed as well as adapt to unforseen load changes. The results are compared with the conventional PD control scheme.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.1183-1188
• /
• 2004

The inverse heat conduction problem (IHCP) is a problem of estimating boundary condition from temperature measurement at one or more interior points. Neural networks are general information processing systems inspired by the connectionist theory of human brain. By properly training the network by the learning rule, the neural network method can handle many non-linear or other complex problems. In this work, neural network is applied to complicated inverse heat conduction problems. Efficiency of the procedure is enhanced by incorporating the radial basis functions (RBF). The RBF is trained faster than other neural network and can find smooth solution. In order to demonstrate the effectiveness of the current scheme, a typical one-dimensional IHCP is considered. At one surface, the temperature as well as the heat flux is known. The unknown temperature of interest is estimated on the other side of the slab. The results from the proposed method based on RBF neural network are compared with the conventional method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.4
• /
• pp.378-384
• /
• 2015

Indoor localization is becoming one of the most important technologies for smart mobile applications with different requirements from conventional outdoor location estimation algorithms. Fingerprinting location estimation techniques based on neural networks have gained increasing attention from academia due to their good generalization properties. In this paper, we propose a novel location estimation algorithm based on an ensemble of multiple neural networks. The neural network ensemble has drawn much attention in various areas where one neural network fails to resolve and classify the given data due to its' inaccuracy, incompleteness, and ambiguity. To the best of our knowledge, this work is the first to enhance the location estimation accuracy in indoor wireless environments based on a neural network ensemble using fingerprinting training data. To evaluate the effectiveness of our proposed location estimation method, we conduct the numerical experiments using the TGn channel model that was developed by the 802.11n task group for evaluating high capacity WLAN technologies in indoor environments with multiple transmit and multiple receive antennas. The numerical results show that the proposed method based on the NNE technique outperforms the conventional methods and achieves very accurate estimation results even in environments with a low number of APs.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.126-129
• /
• 2000

In order to approximate a nonlinear function, wavelet neural networks combining wavelet theory and neural networks have been proposed as an alterantive to coventional multi-layered neural networks. Wavelet neural networks provide better approximating performance than conventional neural networks. In this paper, an effective method to construct an optimal wavelet neural network is proposed using genetic algorithm. This is verified through experimental results.

• 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.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.6
• /
• pp.99-108
• /
• 1998

In this paper, we proposed a multi-layer neural network for direct control method of nonlinear system. The proposed control method uses neural network as the controller to learn inverse model of plant. The neural network used consists of two parts; one part is for identification of linear part, and the other is for identification of nonlinear part of inverse system. The neural network has to be learned the liner part with RLS algorithm and the nonlinear part with error of plant. From the simulation and experiment of tracking control to use one link manipulator as plant, we proved usefulness of the proposed control method to comparing to conventional direct neural network control method. By comparing the two methods, from simulation and experiment, we were convinced that the proposed control method is more simple and accuracy than the conventional method. Moreover, number of weight and bias to be controller parameter are small, and it has smaller steady state error than conventional method.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.5 no.2
• /
• pp.16-21
• /
• 2006

In this study, the analytic realization of chatter mechanism using radial basis neural network(RBNN) was introduced and compared with the conventional stability analysis. In this regard, the FFT and time series spectrum analysis was used as a criterion for the existence of chatter in end-milling force. The desired coded outputs of chatter was trained and finally converged to desired outputs. The output of the RBNN match well with the conventional desired stability lobe. Using this trained data, the stability boundary of the radial basis neural network was acquired using the contour plotting. As a result, the proposed stability lobe boundary using RBNN consists well with the conventional analytical boundary that is calculated in characteristic equation of transfer function in chatter dynamics. In this RBNN analysis, two input and three output parameters were used in this paper.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2004.10a
• /
• pp.542-549
• /
• 2004

The compressive strength of concrete is commonly used criterion in producing concrete. However, the tests on the compressive strength are complicated and time-consuming. More importantly, it is too late to make improvement even if the test result does not satisfy the required strength, since the test is usually performed at the 28th day after the placement of concrete at the construction site. Therefore, accurate and realistic strength estimation before the placement of concrete is being highly required. In this study, the estimation of the compressive strength of concrete was performed by probabilistic neural network (PNN) on the basis of concrete mix proportions. The estimation performance of PNN was improved by considering the correlation between input data and targeted output value. Adaptive probabilistic neural network (APNN) was proposed to automatically calculate the smoothing parameter in the conventional PNN by using the scheme of dynamic decay adjustment algorithm. The conventional PNN and APNN were applied to predict the compressive strength of concrete using actual test data of a concrete company. APNN showed better results than the conventional PNN in predicting the compressive strength of concrete.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.43 no.6
• /
• pp.877-884
• /
• 1994

In the power system state estimation, the J(x)-index test and normalized residuals ${\gamma}$S1NT have been the presence of bad measurements and identify their location. But, these methods require the complete re-estimation of system states whenever bad data is identified. This paper presents back-propagation neural network medel using autoregressive filter for identification of bad measurements. The performances of neural network method are compared with those of conventional mehtods and simulation results show the geed performance in the bad data identification based on the neural network under sample power system.