• ETRI Journal
• /
• v.44 no.6
• /
• pp.915-924
• /
• 2022

In this paper, we present a two-stage scalable channel estimator (TSCE), a deep learning (DL)-based scalable, and robust channel estimator for wireless cellular networks, which is made up of two DL networks to efficiently support different resource allocation sizes and reference signal configurations. Both networks use the transformer, one of cutting-edge neural network architecture, as a backbone for accurate estimation. For computation-efficient global feature extractions, we propose using window and window averaging-based self-attentions. Our results show that TSCE learns wireless propagation channels correctly and outperforms both traditional estimators and baseline DL-based estimators. Additionally, scalability and robustness evaluations are performed, revealing that TSCE is more robust in various environments than the baseline DL-based estimators.

• Biotechnology and Bioprocess Engineering:BBE
• /
• v.11 no.4
• /
• pp.351-356
• /
• 2006

This study developed an artificial neural network (ANN) to estimate the growth of microorganisms during a fermentation process. The ANN relies solely on the cumulative consumption of alkali and the buffer capacity, which were measured on-line from the on/off control signal and pH values through automatic pH control. The two input variables were monitored on-line from a series of different batch cultivations and used to train the ANN to estimate biomass. The ANN was refined by optimizing the network structure and by adopting various algorithms for its training. The software estimator successfully generated growth profiles that showed good agreement with the measured biomass of separate batch cultures carried out between at 25 and $35^{\circ}C$.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.41-44
• /
• 2021

In this paper, we propose an efficient reference-based compression artifact reduction network for 360-degree images in an equi-rectangular projection (ERP) domain. In our insight, conventional image restoration methods cannot be applied straightforwardly to 360-degree images due to the spherical distortion. To address this problem, we propose an adaptive disparity estimator using a deformable convolution to exploit correlation among 360-degree images. With the help of the proposed convolution, the disparity estimator establishes the spatial correspondence successfully between the ERPs and extract matched textures to be used for image restoration. The experimental results demonstrate that the proposed algorithm provides reliable high-quality textures from the reference and improves the quality of the restored image as compared to the state-of-the-art single image restoration methods.

• Journal of Electrical Engineering and Technology
• /
• v.2 no.2
• /
• pp.241-248
• /
• 2007

The accuracy of all the schemes that belong to vector controlled induction machine drives is strongly affected by parameter variations. The aim of this paper is to examine iron losses and magnetic saturation effect in sensorless vector control of induction machines. At first, an approach to induction machine modelling and vector control scheme, which account for both iron loss and saturation, is presented. Then, a model reference adaptive system (MRAS) based speed estimator is developed. The speed estimation is modified in such a way that iron losses and the variation in the saturation level are compensated. Thus by substituting an artificial neural network flux estimator into the MRAS speed estimator. Experimental results are presented to verify the effectiveness of the proposed approach.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1867-1870
• /
• 2002

In the present paper, we will focus on the characterization of the biological network behaviour, in terms of synchronization and desynchronization of the measured signals by Micro Electrode array. We evaluate a easy calculable estimator that implies de/synchronization property of the biological neural network.

• Communications for Statistical Applications and Methods
• /
• v.28 no.3
• /
• pp.281-294
• /
• 2021

In this paper, we propose an adaptive regression method based on the single-layer neural network structure. We adopt a symmetric activation function as units of the structure. The activation function has a flexibility of its form with a parametrization and has a localizing property that is useful to improve the quality of estimation. In order to provide a spatially adaptive estimator, we regularize coefficients of the activation functions via ℓ₁-penalization, through which the activation functions to be regarded as unnecessary are removed. In implementation, an efficient coordinate descent algorithm is applied for the proposed estimator. To obtain the stable results of estimation, we present an initialization scheme suited for our structure. Model selection procedure based on the Akaike information criterion is described. The simulation results show that the proposed estimator performs favorably in relation to existing methods and recovers the local structure of the underlying function based on the sample.

• Journal of Power Electronics
• /
• v.13 no.1
• /
• pp.139-160
• /
• 2013

In this paper, an intelligent robust control system (IRCS) for precision tracking control of permanent-magnet synchronous motor (PMSM) servo drives is proposed. The IRCS comprises a recurrent wavelet-based interval type-2 fuzzy-neural-network controller (RWIT2FNNC), an RWIT2FNN estimator (RWIT2FNNE) and a compensated controller. The RWIT2FNNC combines the merits of a self-constructing interval type-2 fuzzy logic system, a recurrent neural network and a wavelet neural network. Moreover, it performs the structure and parameter-learning concurrently. The RWIT2FNNC is used as the main tracking controller to mimic the ideal control law (ICL) while the RWIT2FNNE is developed to approximate an unknown dynamic function including the lumped parameter uncertainty. Furthermore, the compensated controller is designed to achieve $L_2$ tracking performance with a desired attenuation level and to deal with uncertainties including approximation errors, optimal parameter vectors and higher order terms in the Taylor series. Moreover, the adaptive learning algorithms for the compensated controller and the RWIT2FNNE are derived by using the Lyapunov stability theorem to train the parameters of the RWIT2FNNE online. A computer simulation and an experimental system are developed to validate the effectiveness of the proposed IRCS. All of the control algorithms are implemented on a TMS320C31 DSP-based control computer. The simulation and experimental results confirm that the IRCS grants robust performance and precise response regardless of load disturbances and PMSM parameters uncertainties.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.10-21
• /
• 2023

For various target tracking applications, it is well known that the Kalman filter is the optimal estimator(in the minimum mean-square sense) to predict and estimate the state(position and/or velocity) of linear dynamical systems driven by Gaussian stochastic noise. In the case of nonlinear systems, Extended Kalman filter(EKF) and/or Unscented Kalman filter(UKF) are widely used, which can be viewed as approximations of the(linear) Kalman filter in the sense of the conditional expectation. However, to implement EKF and UKF, the exact dynamical model information and the statistical information of noise are still required. In this paper, we propose the recurrent neural-network based Kalman filter, where its Kalman gain is obtained via the proposed GRU-LSTM based neural-network framework that does not need the precise model information as well as the noise covariance information. By the proposed neural-network based Kalman filter, the state estimation performance is enhanced in terms of the tracking error, which is verified through various linear and nonlinear tracking problems with incomplete model and statistical covariance information.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.6
• /
• pp.49-55
• /
• 2008

Arc welding process is one of the most important technologies to join metal plates. Robotic welding offers the reduced manufacturing cost sought, but its widespread use demands a means of sensing and correcting for inaccuracies in the part, the fixturing and the robot. A number of problems that need to be addressed in robotic arc welding processes include sensing, joint tracking, and lack of adequate models for process parameter prediction and quality control. Problems with parameter settings and quality control occur frequently in the GMA(Gas Metal Arc) welding process due to the large number of interactive process parameters that must be set and accurately controlled. The objectives of this paper are to realize the mapping characteristics of bead width using a sensitivity analysis and develop the neural network and multiple regression method, and finally select the most accurate model in order to control the weld quality(bead width) for fillet welding. The experimental results show that the proposed neural network estimator can predict bead width with reasonable accuracy, and guarantee the uniform weld quality.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.6
• /
• pp.589-595
• /
• 2007

This paper presents a new method on controller design of brushless dc motors. In such drives the current ripples are generated by motor inductance in stator windings and the back EMF. To suppress the current ripples the current controller is generally used. To minimize the size and the cost of the drives it is desirable to control motors without the current controller and the current sensing circuits. To estimate the motor CUlTent it is modeled by a neural network that is contigured as an output-error dynamic system. The identified model is essentially a one step ahead prediction structure in which past inputs and outputs are used to calculate the current output. Using the model, a state feedback controller to compensate the effects of disturbance has been designed. The controller is implemented by a 16-bit microprocessor and the effectiveness of the proposed control method is verified through experiments.