• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.243-246
• /
• 1994

In this paper, a self-learning fuzzy controller is designed with a fuzzy approximation of an inverse model. The aim of an identification is to find an input command which is control of a system output. It is intuitional and easy to use a classical adaptive inverse modeling method for the identification, but it is difficult and complex to implement it. This problem can be solved with a fuzzy approximation of an inverse modeling. The fuzzy logic effectively represents the complex phenomena of the real world. Also fuzzy system could be represented by the neural network that is useful for a learning structure. The rule of a fuzzy inverse model is modified by the gradient descent method. The goal is to be obtained that makes the design of fuzzy controller less complex, and then this self-learning fuzz controller can be used for nonlinear dynamic system. We have applied this scheme to a nonlinear Ball and Beam system.

• Proceedings of the KIPE Conference
• /
• 1999.07a
• /
• pp.526-530
• /
• 1999

This paper presents a newly developed speed sensorless drive using Neural Network algorithm. Neural Network algorithm can be divided into three categories. In the first one, a Back Propagation-based NN algorithm is well-known to gradient descent method. In the second scheme, a Extended Kalman Filter-based NN algorithm has just the time varying learning rate. In the last scheme, a Recursive Least Square-based NN algorithm is faster and more stable than the classical back-propagation algorithm for training multilayer perceptrons. The number of iterations required to converge and the mean-squared error between the desired and actual outputs is compared with respect to each method. The theoretical analysis and experimental results are discussed.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.103.1-103
• /
• 2002

In variable structure control algorithms, The control law used to realized the desired sliding mode dynamics is discontinuous on the switching manifold. However, due to imperfections in switching, such as time delays, the system trajectory chatters instead of sliding along the switching manifold. This chattering is undesirable because it may excite unmodeled high frequency dynamics in the physical system. In this paper, to overcome this drawback a self-organizing fuzzy sliding mode control algorithm using gradient descent method is proposed. The proposed method has the characteristics which are viewed in conventional VSC, e.g. insensitivity to a class of disturbance, parameter variations and uncertainties ill the sliding mode. To demonstrate its performance, the proposed control algorithm is applied to an inverted pendulum system. The results show that both alleviation of chattering and performance are achieved.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1235-1239
• /
• 2006

Fractal manufacturing system (FrMS) distinguishes itself from other manufacturing systems by the fact that there is a fractal repeated at every scale. A fractal is a volatile organization which consists of goal-oriented agents referred to as AIR-units (autonomous and intelligent resource units). AIR-units unrestrictedly reconfigure fractals in accordance with their own goals. Their goals can be dynamically changed along with the environmental status. Since goals of AIR-units are represented as fuzzy models, an AIR-unit itself is a fuzzy logic controller. This paper presents a goal regulation mechanism in the FrMS. In particular, a reinforcement learning method is adopted as a regulating mechanism of the fuzzy goal model, which uses only weak reinforcement signal. Goal regulation is achieved by building a feedforward neural network to estimate compatibility level of current goals, which can then adaptively improve compatibility by using the gradient descent method. Goal-oriented features of AIR-units are also presented.

• Speech Sciences
• /
• v.7 no.4
• /
• pp.11-26
• /
• 2000

In this paper, we propose the HMM with the MIN module. Because initial and re-estimated variance vectors are important elements for performance in HMM recognition systems, we propose a method which compensates for the mismatched statistical feature of training and test data. The MIN module function is a differentiable function similar to the sigmoid function. Unlike a continuous density function, it does not include variance vectors of the data set. The proposed hybrid HMM/MIN module is a unified network in which the observation probability in the HMM is replaced by the MIN module neural network. The parameters in the unified network are re-estimated by the gradient descent method for the Maximum Likelihood (ML) criterion. In estimating parameters, the variance vector is not estimated because there is no variance element in the MIN module function. The experiment was performed to compare the performance of the proposed HMM and the conventional HMM. The experiment measured an isolated number for speaker independent recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3029-3045
• /
• 2017

The main processes of a cognitive radio system include spectrum sensing, spectrum decision, spectrum sharing, and spectrum conversion. Experimental results show that these stages introduce a time delay that affects the spectrum sensing accuracy, reducing its efficiency. To reduce the time delay, the frequency spectrum prediction was proposed to alleviate the burden on the spectrum sensing. In this paper, the deep recurrent neural network (DRNN) was proposed to predict the spectrum of multiple time slots, since the existing methods only predict the spectrum of one time slot. The continuous state of a channel is divided into a many time slots, forming a time series of the channel state. Since there are more hidden layers in the DRNN than in the RNN, the DRNN has fading memory in its bottom layer as well as in the past input. In addition, the extended Kalman filter was used to train the DRNN, which overcomes the problem of slow convergence and the vanishing gradient of the gradient descent method. The spectrum prediction based on the DRNN was verified with a WiFi signal, and the error of the prediction was analyzed. The simulation results proved that the multiple slot spectrum prediction improved the spectrum efficiency and reduced the energy consumption of spectrum sensing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.2027-2046
• /
• 2024

Reconfigurable Intelligent Surface (RIS) is an innovative technique to precisely control the phase of incident signals with the help of low-cost passive reflective elements. It shows excellent potential in the sixth generation of mobile communication systems, which not only extends wireless coverage but also boosts channel capacity. Considering that multipath propagation and a high number of antennas are involved in RIS in assisted mega multiple-input multiple-output (MIMO) systems, it suffers from severe channel fading and multipath effects, which in turn lead to signal instability and degradation of transmission performance. To overcome this obstacle, this essay suggests an improved gradient optimization algorithm to dynamically and optimally adjust the phase of the reflective elements to counteract channel fading and multipath effects as a strategy. In order to overcome the optimization problem of falling into local minima, this paper proposes an adaptive learning rate algorithm based on Adagrad improvement, which searches for the global optimal solution more efficiently and improves the robustness of the optimization algorithm. The suggested technique helps to enhance the estimate of channel efficiency of RIS-assisted large MIMO systems, according to simulation results.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.127-132
• /
• 2022

As the IoT technology is more developed, it is more important for the accuracy of IoT data. Since the IoT data supports a different formats and protocols, it is often happened that the IoT system is failed or the incorrect data is generated with the unreliable IoT devices(sensor, actuator). Because the abnormality of IoT device or the user situation is not detected correctly, this problem makes the user to be unsatisfied with the IoT system. This study proposes the decision methodology of IoT data consistency whether the IoT data is generated in normal range or not by using the mathematical functions('gradient descent function' and 'linear regression function'). It may be concluded that the gradient function method is suitable for the IoT data which the 'increasing velocity' is related with the next generated pattern(eg. sensor devices), the linear regression function method is suitable for the IoT data which the 'the difference from linear regression function' is related with the next generated pattern in case the data has a linear pattern(eg. water meter, electric meter).

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.4
• /
• pp.145-154
• /
• 1994

This paper proposes an efficient method for improving the training performance of the neural network by using a hybrid of a stochastic approximation and a backpropagation algorithm. The proposed method improves the performance of the training by appliying a global optimization method which is a hybrid of a stochastic approximation and a backpropagation algorithm. The approximate initial point for a stochastic approximation and a backpropagation algorihtm. The approximate initial point for fast global optimization is estimated first by applying the stochastic approximation, and then the backpropagation algorithm, which is the fast gradient descent method, is applied for a high speed global optimization. And further speed-up of training is made possible by adjusting the training parameters of each of the output and the hidden layer adaptively to the standard deviation of the neuron output of each layer. The proposed method has been applied to the parity checking and the pattern classification, and the simulation results show that the performance of the proposed method is superior to that of the backpropagation, the Baba's MROM, and the Sun's method with randomized initial point settings. The results of adaptive adjusting of the training parameters show that the proposed method further improves the convergence speed about 20% in training.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2498-2501
• /
• 2003

In this paper, we present a wavelet neural network (WNN) approach to the solution of the path tracking problem for mobile robots that possess complexity, nonlinearity and noise. First, we discuss a WNN based control system where the control signals are directly obtained by minimizing the difference between the reference track and the pose of a mobile robot. This compact network structure is helpful to determine the number of hidden nodes and the initial value of weights. Then, the data with various noises provided by odometric and external sensors are here fused together by means of an Extended Kalman Filter (EKF) approach for the pose estimation problem of mobile robots. This control process is a dynamic on-line process that uses the wavelet neural network trained via the gradient-descent method with estimates from EKF. Finally, we verify the effectiveness and feasibility of the proposed control system through simulations.