• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.382-382
• /
• 2020

과거 많은 연구에서 다수의 모형의 결과를 이용한 앙상블 방법론은 인공지능 모형 (artificial neural network)의 예측 능력에 향상을 갖고 온다 논하였다. 본 연구에서는 미계측유역의 저수량(low flow)의 예측을 위하여 Jittering을 기반으로 한 인공지능 모형을 제시하고자 한다. 기본적인 방법론은 설명변수들에게 백색 잡음(white noise)를 삽입하여 훈련되는 자료를 증가시키는 것이다. Jittering을 기반으로 한 인공지능 모형에 대한 효과를 검증하기 위하여 본 연구에서는 Multi-output neural network model을 기반으로 모형을 구축하였다. 다음으로 Jittering을 기반으로 한 앙상블 모형을 variable importance measuring algorithm과 결합시켜서 유역특성치와 예측되는 저수량의 특성치들의 관계를 추론하였다. 본 연구에서 사용되는 방법론들의 효용성을 평가하기 위해서 미동북부에 위치하고 있는 총 207개의 유역을 사용하였다. 결과적으로 본 연구에서 제시한 Jittering을 기반으로 한 인공지능 앙상블 모형은 단일예측모형 (single modeling approach)을 정확도 측면에서 우수한 것으로 확인되었다. 또한, 적은 숫자의 앙상블 모형에서도 그 정확성이 단일예측모형보다 우수한 것을 확인하였다. 마지막으로 본 연구에서는 유역특성치들의 효과가 살펴보고자 하는 저수량의 특성치들에 따라서 일관적으로 영향을 미치거나 그 중요도가 변화하는 것을 확인하였다.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.5
• /
• pp.91-97
• /
• 2004

A digital over-sampling noise-shaping coder to achieve the processing accuracy for the audio signal bandwidth is designed. In order to implement an optimized design of the noise-shaping coder as a form of U (intellectual property), circuit design techniques that optimize the multiplication and the ROM architectures are proposed with emphasis on the low-voltage operation under 2.0 V and the minimization of the hardware resources. In the design and verification methodology, the overall architectures and the internal bit width have been determined through behavioral simulations. The overall performances including timing margin have been estimated through transistor-level simulations. Furthermore, the test results of the implemented chip using a 0.35-${\mu}{\textrm}{m}$ standard CMOS process proposed the validity of the proposed circuits and the design methodology.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.1 no.1
• /
• pp.1-9
• /
• 2002

In this paper, a DRO (Dielectric Resonator Oscillator) with high stability in DSRC(Dedicated Short Range Communication) is designed and fabricated. The DRO shows the phase noise characteristic of -109.3 dBc/Hz at 100 kHz offset from the fundamental frequency. The output power of 11.53 dBm, and the second harmonic suppression of 55.33 dBc for the DRO are obtained. This DRO with high stability of the phase noise characteristic can be used for the system in DSRC.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.1-6
• /
• 2021

In the field of speech recognition, as the DNN is applied, the use of speech recognition is increasing, but the amount of calculation for parallel training needs to be larger than that of the conventional GMM, and if the amount of data is small, overfitting occurs. To solve this problem, we propose an efficient method for robust voice feature extraction and voice signal noise removal even when the amount of data is small. Speech feature extraction efficiently extracts speech energy by applying the difference in frame energy for speech and the zero-crossing ratio and level-crossing ratio that are affected by the speech signal. In addition, in order to remove noise, the noise of the speech signal is removed by removing the noise of the speech signal with an average predictive improved LMS filter with little loss of speech information while maintaining the intrinsic characteristics of speech in detection of the speech signal. The improved LMS filter uses a method of processing noise on the input speech signal by adjusting the active parameter threshold for the input signal. As a result of comparing the method proposed in this paper with the conventional frame energy method, it was confirmed that the error rate at the start point of speech is 7% and the error rate at the end point is improved by 11%.

• Journal of the Society of Disaster Information
• /
• v.16 no.1
• /
• pp.133-143
• /
• 2020

Purpose: This study aims to derive a predictive empirical equation for PGV prediction from P-wave using earthquake records in Korea and to verify the reliability of Onsite EEW. Method: The noise of P wave is removed from the observations of 627 seismic events in Korea to derive an empirical equation with PGV on the base rock, and reliability of Onsite alarms is verified from comparing PGV's predictions and observations through simulation using the empirical equation. Result: P-waves were extracted using the Filter Picker from earthquake observation records that eliminated noises, a linear regression with PGV was used to derive a predictive empirical equation for Onsite EEW. Through the on-site warning simulation we could get a success rate of 80% within the MMI±1 error range above MMI IV or higher. Conclusion: Through this study, the design feasibility and performance of Onsite EEWS using domestic earthquake records were verified. In order to increase validity, additional medium-sized seismic observations from abroad are required, the mis-detection of P waves is controlled, and the effect of seismic amplification on the surface is required.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.36D no.9
• /
• pp.13-20
• /
• 1999

A 2-stage MMIC(monolithic Microwave Integrated Circuits) LNA(Low Noise Amplifiers) at 30GHz hand has been designed and fabricated for the Ka-band Satellite Communications. The $0.15 {\mu}m$ with the width of $80 {\mu}m$ pHEMT technology was used for the fabrication of this MMIC LNA. Using the series feedback technique, ultra low noise and excellent S11 could be obtained at the same time without the cost of gain at 30GHz-band. The stability factors(Ks) for each stage and overall stage are greater than 1 at full frequency bands by the bias circuits and stabilization circuit. The measured performances, which agree well with the predicted performances, show this 2-stage MMIC LNA has the gain of more than 15.7dB and noise figure of less than 2.09dB over 29GHz to 33GHz.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.987-994
• /
• 2020

In this paper, we studied the effect of kernel size of CNN layer on performance in acoustic noise attenuators. This system uses a deep learning algorithm using a neural network adaptive prediction filter instead of using the existing adaptive filter. Speech is estimated from a single input speech signal containing noise using a 100-neuron, 16-filter CNN filter and an error back propagation algorithm. This is to use the quasi-periodic property in the voiced sound section of the voice signal. In this study, a simulation program using Tensorflow and Keras libraries was written and a simulation was performed to verify the performance of the noise attenuator for the kernel size. As a result of the simulation, when the kernel size is about 16, the MSE and MAE values are the smallest, and when the size is smaller or larger than 16, the MSE and MAE values increase. It can be seen that in the case of an speech signal, the features can be best captured when the kernel size is about 16.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.625-632
• /
• 2021

This paper studies the effect of the number of filters in the CNN (Convolutional Neural Network) layer on the performance of a noise attenuator. Speech is estimated from a noised speech signal using a 64-neuron, 16-kernel CNN filter and an error back-propagation algorithm. In this study, in order to verify the performance of the noise attenuator with respect to the number of filters, a program using Keras library was written and simulation was performed. As a result of simulation, it can be seen that this system has the smallest MSE (Mean Squared Error) and MAE (Mean Absolute Error) values when the number of filters is 16, and the performance is the lowest when there are 4 filters. And when there are more than 8 filters, it was shown that the MSE and MAE values do not differ significantly depending on the number of filters. From these results, it can be seen that about 8 or more filters must be used to express the characteristics of the speech signal.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.9
• /
• pp.657-662
• /
• 2022

In this paper, the calculation using simulation and two measurement methods for G/T of the telemetry are analyzed. Antenna gain and noise temperature are calculated by using ICARA and Antenna Noise Temperature Calculator. System G/T were calculated by using Antenna gain/noise temperature, LNA gain/noise temperature, cable loss. The first G/T measurement method is Y-factor measurement method, which is to calculate G/T by comparing LNA noise temperature and a signal level difference when an antenna and a 50ohm termination are respectively connected to an LNA input terminal Second method is Solar calibration measurement method that is to calculate G/T by comparing noise level difference when looking at the sun and lowest level point. Finally, the accuracy was reviewed by comparing the G/T calculation results with the two measurement methods, and the optimal measurement method according to antenna performance and operating environment was presented.

• Journal of Broadcast Engineering
• /
• v.16 no.6
• /
• pp.1058-1068
• /
• 2011

Video FRUC (Frame Rate Up Conversion) is one of the main issues that have arisen in recent years with the explosive growth of video sources and display formats in consumer electronics. Most advanced FRUC algorithms adopt an efficient motion interpolation technique to determine the motion vector field of interpolated frames. But, in some application areas such as post processing in receiver side, it is necessary to evaluate how well the MCI (Motion Compensated Interpolation) frame was reconstructed. In order to achieve this aim, first, this paper introduces some cost functions to estimate the reliability of a block in the MCI frame. Then, by using these functions, this paper proposes two distortion estimation models for evaluating how much noise was produced in the MCI frame. Through computer simulations, it is shown that the proposed estimation methods perform effectively in estimating the noises of the MCI frame.