• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.2
• /
• pp.30-36
• /
• 2002

This paper describes a nonlinear adaptive noise canceler(ANC) using neural networks(NN) based on filter to make up for the drawback of the conventional ANC with the linear adaptive filter. The proposed ANC was tested its noise rejection performance using broadband time-varying noise signal and compared with the ANC of TDL linear filter. Experimental results show that in cases of nonlinear correlations between the noise of primary input and reference input, the neural network based ANC outperforms the linear ANC with respect to mean square error It is also verified that the recurrent NN adaptive filter is superior to the feedforward NN filter. Thus, we identify that the NN adaptive filter is more effective than the linear adaptive filter for rejection of broadband time-varying noise in the ANC.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.1
• /
• pp.84-93
• /
• 2018

In this paper, we propose an Elman recurrent neural network to predict and analyze a time series of power energy consumption. To this end, we consider the volatility of the time series and apply the sample variance and the detrended fluctuation analyses to the volatilities. We demonstrate that there exists a correlation in the time series of the volatilities, which suggests that the power consumption time series contain a non-negligible amount of the non-linear correlation. Based on this finding, we adopt the Elman recurrent neural network as the model for the prediction of the power consumption. As the simplest form of the recurrent network, the Elman network is designed to learn sequential or time-varying pattern and could predict learned series of values. The Elman network has a layer of "context units" in addition to a standard feedforward network. By adjusting two parameters in the model and performing the cross validation, we demonstrated that the proposed model predicts the power consumption with the relative errors and the average errors in the range of 2%~5% and 3kWh~8kWh, respectively. To further confirm the experimental results, we performed two types of the cross validations designed for the time series data. We also support the validity of the model by analyzing the multi-step forecasting. We found that the prediction errors tend to be saturated although they increase as the prediction time step increases. The results of this study can be used to the energy management system in terms of the effective control of the cross usage of the electric and the gas energies.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.71-77
• /
• 2014

In this paper, we propose an improved numeric character recognition method which can recognize numeric characters well under low-illuminated and shade-illuminated environment. The LN(Local Normalization) preprocessing method is used in order to enhance low-illuminated and shade-illuminated image quality. The reading area is detected using line segment information extracted from the illumination-normalized meter images, and then the three-phase procedures are performed for segmentation of numeric characters in the reading area. Finally, an efficient hybrid classifier is used to classify the segmented numeric characters. The proposed numeric character classifier is a combination of multi-layered feedforward neural network and template matching module. Robust heuristic rules are applied to classify the numeric characters. Experiments using meter image database were conducted. Meter image database was made using various kinds of meters under low-illuminated and shade-illuminated environment. The experimental results indicates the superiority of the proposed numeric character recognition method.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.1
• /
• pp.28-36
• /
• 2008

This paper discusses theimplementation of the low-voltage, low-power, third-order, 1-bit switched capacitor delta-sigma modulator of the implantable cardiac pacemaker. The distributed, feed-forward structure and bulk-driven OTA were used in order to achieve an efficient operation under a supply voltage of 1V or lower. The designed modulator has a dynamic range of 49dB at 0.9V supply voltage and consumes 816nW of power. Such a significant reduction in power consumption allows diverse applications, not only in pacemakers, but also in implantable biomedical devices that operate with limited battery power. The core chip size of the modulator is $1000{\mu}m*500{\mu}m$ manufactured, with the $0.18{\mu}m$ CMOS standard process.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.737-745
• /
• 2008

Recent developments of process and measurement technology bring much interest to the online monitoring of process operations such as milling, grinding, broaching, etc. The objective of online monitoring systems is to detect process changes as early as possible. This is helpful in protecting facilities against unexpected failures and then preventing unnecessary loss. This paper investigates, when the process monitoring data are obtained as a profile, the monitoring performances of a statistical $T^2$-statistic and a feedforward neural network by using a wavelet transform. Numerical experiments using cutting force data presented by Axinte show that the proposed wavelet based $T^2$-test has an acceptable power in detecting profile changes. However, its operating characteristic is very sensitive to autocorrelation. On the contrary, compared with $T^2$-test, the neural network has more stable performance in the presence of autocorrelation. This indicates that an adaptive feature to analyze noises should be incorporated into the wavelet based $T^2$-test.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.20 no.6
• /
• pp.517-525
• /
• 2015

A grid connected inverter must be operated as the main electricity source under an isolated condition caused by the grid problem. Conventionally, the dual loop controller is used for the grid inverter, and the controller is used for control under the stand-alone mode. Generally, the PI(Proportional - Integral) controller is highly efficient under a synchronous reference frame, and stable control can be available. However, in this synchronous frame-based control, high-quality DSP is required because many sinusoidal calculations are necessary. When the PI control is conducted under a stationary frame, the controller constructions are made simple so that they work even with a low-price micro controller. However, given the characteristics of the PI controller, it should be designed with the phase of reference voltage considered. Otherwise, the phase delay of the output voltage can occur. Although the current controller also has a higher bandwidth than the voltage controller, distortion of the voltage is difficult to avoid only by the rapid response of the PI controller, as a sudden load change can occur in the nonlinear load. In this study, a new control method that solves the voltage controller bandwidth problem and rapidly copes with it even in the nonlinear load situation is proposed. The validity of the proposed method is proved by simulation and experimental results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.5C
• /
• pp.295-301
• /
• 2011

In [1], it has been shown that the energy spreading transform (EST) based iterative equalizer (IE) could enhance its performance by improving the reliability of the decision feedback symbols without the help of the complicated channel decoder. In the matched filter (MF) based IE proposed in [1], however, its feedforward filter (FFF) has been designed in the frequency domain while its feedback filter (FBF) in the time domain. So its complexity increases proportional to the channel memory length. To solve this problem, in this paper, both FFF and FBF are designed in the frequency domain. This enables the proposed frequency domain IE (FD-IE) to achieve the lower complexity over the conventional method in the highly dispersive channel. In addition, simulation results demonstrate that the BER performance of the proposed method is the same as the conventional.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.9C
• /
• pp.906-914
• /
• 2009

SC-FDMA is employed in the 3GPP-LTE standard as the uplink transmission scheme. SC-FDMA has advantages that the signal has a low PAPR property and a simple equalizer such as FD-LE can be implemented. But FD-LE has inferior performance to Hybrid-DFE composed of frequency-domain feedforward filter and time-domain feedback filter. Recently, several IB-DFE algorithms have been proposed to overcome the disadvantages of implementation and processing complexity of Hybrid-DFE and to obtain superior performance to FD-LE. In this paper, we apply several IB-DFE algorithms to 3GPP-LTE uplink system and compare their performance by calculating BER. We investigate the effects of channel estimation errors and Doppler shift on performance. Finally, by analyzing computational complexity of IB-DFEs, we present some criteria to choose appropriate algorithm and to decide the number of iterative processes.

• Nuclear Engineering and Technology
• /
• v.25 no.1
• /
• pp.110-124
• /
• 1993

A Nonlinear model-based Hybrid Controller (NHC) is developed which consists of the adaptive proportional-integral-feedforward (PIF) gains and variable structure controller. The controller has the robustness against modeling uncertainty and is applied to the trajectory tracking control of single-input, single-output nonlinear systems. The essence of the scheme is to divide the control into four different terms. Namely, the adaptive P-I-F gains and variable structure controller are used to accomplish the specific control actions by each terms. The robustness of the controller is guaranteed by the feedback of estimated uncertainty and the performance specification given by the adaptation of PIF gains using the second method of Lyapunov. The variable structure controller is incorporated to regulate the initial peak of the tracking error during the parameter adaptation is not settled yet. The newly developed NHC method is applied to the power tracking control of a nuclear reactor and the simulation results show great improvement in tracking performance compared with the conventional model-based control methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.12C
• /
• pp.1014-1020
• /
• 2008

Storage devices such as memories are widely used in various electronic products. They require high-density memory and currently the data has been stored in multi-level format, that results in high error rate. In this paper, we apply error correction schemes that are widely used in communication system to the storage devices for satisfying low bit error rate and high code rate. In A WGN channel with average BER $10^{-5}$ and $5{\times}10^{-6}$, we study error correction schemes for 4-1evel cell to achieve target code rate 0.99 and target BER $10^{-11}$ and $10^{-13}$, respectively. Since block codes may perform better than the concatenated codes for high code rate, and it is important to use less degraded inner code even when many bits are punctured. The performance of concatenated codes using general feedforward systematic convolutional codes are worse than the block code only scheme. The simulation results show that RSC codes must be used as inner codes to achieve good performance of punctured convolutional codes for high code rate.