• Water for future
• /
• v.25 no.3
• /
• pp.105-113
• /
• 1992

The purpose of this paper is to introduce and to apply the artificial neural network theory to real hydrologic system for forecasting daily streamflows during flood periods. The hydrologic dynamic process of rainfall-runoff is identified by the iterated estimation of system parameters that are determined by adjusting the weights of the network according to the non-linear response characteristics which is formed the model. Back propagation algorithm of neural network model is applied for the estimation of system parameters with past daily rainfall and runoff series data, and streamflows are forecasted using the parameters. The forecasted results are analyzed by statistical methods for the comparison with the observed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.8
• /
• pp.1647-1652
• /
• 2009

Generally the neural network and the fuzzy compensative algorithm are applied to forecast the time series for power demand with a characteristic of non-linear dynamic system, but it has a few prediction errors relatively. It also makes long term forecast difficult for sensitivity on the initial condition. On this paper, we evaluate the chaotic characteristic of electrical power demand with analysis methods of qualitative and quantitative and perform a forecast simulation of electrical power demand in regular sequence, attractor reconstruction, time series forecast for multi dimension using Lyapunov exponent quantitatively. We compare simulated results with the previous method and verify that the purpose one being more practice and effective than it.

• Journal of Astronomy and Space Sciences
• /
• v.34 no.1
• /
• pp.19-30
• /
• 2017

The optical wide-field patrol network (OWL-Net) is a Korean optical surveillance system that tracks and monitors domestic satellites. In this study, a batch least squares algorithm was developed for optical measurements and verified by Monte Carlo simulation and covariance analysis. Potential error sources of OWL-Net, such as noise, bias, and clock errors, were analyzed. There is a linear relation between the estimation accuracy and the noise level, and the accuracy significantly depends on the declination bias. In addition, the time-tagging error significantly degrades the observation accuracy, while the time-synchronization offset corresponds to the orbital motion. The Cartesian state vector and measurement bias were determined using the OWL-Net tracking data of the KOMPSAT-1 and Cryosat-2 satellites. The comparison with known orbital information based on two-line elements (TLE) and the consolidated prediction format (CPF) shows that the orbit determination accuracy is similar to that of TLE. Furthermore, the precision and accuracy of OWL-Net observation data were determined to be tens of arcsec and sub-degree level, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2
• /
• pp.90-94
• /
• 1996

Code Excited Linear Prediction(CELP) vocoder exhibits good performance at data rates below 8 kbps. The major drawback of CELP type coders is a large amount of computation. In this paper, we propose a new pitch searching method that preserves the quality of the CELP vocoder reducing computational complexity. The basic idea is that grasps preliminary pitches using the first formant of speech signal and performs pitch search only about the preliminary pitches. As applying the proposed method to the CELP vocoder, we can reduce complexity by 64% in the pitch search.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.6
• /
• pp.556-562
• /
• 2013

This paper is aimed to improve performance of Band-Selection speech/audio Coder reconstucted band spectrum that is not sent by the comfort noise. To improve the performance, we use the Spectral Band Replication(SBR) technique instead of substitution of Comfort noise. To synthesize SBR signal, the SBR algorithm is referenced in selected signals and the spectrum synthesized by SBR is injected to non-selected band. Each sub-band spectrum has been energy-weighted by real audio signal. We propose the enhanced the Band-Selection Coder that utilizes synthesized SBR signal from selected signal instead of comfort noise.

• Journal of Korea Multimedia Society
• /
• v.20 no.11
• /
• pp.1811-1819
• /
• 2017

As the induction motor is the core production equipment of the industry, it is necessary to construct a fault prediction and diagnosis system through continuous monitoring. Many researches have been conducted on motor fault diagnosis algorithm based on signal processing techniques using Fourier transform, neural networks, and fuzzy inference techniques. In this paper, we propose a fault diagnosis method of induction motor using LPC and DNN. To evaluate the performance of the proposed method, the fault diagnosis was carried out using the vibration data of the induction motor in steady state and simulated various fault conditions. Experimental results show that the learning time of our proposed method and the conventional spectrum+DNN method is 139 seconds and 974 seconds each executed on the experimental PC, and our method reduces execution time by 1/8 compared with conventional method. And the success rate of the proposed method is 98.08%, which is similar to 99.54% of the conventional method.

• Journal of Advanced Navigation Technology
• /
• v.14 no.6
• /
• pp.874-881
• /
• 2010

A automatic flight control system(AFCS) of UAS needs to control its flight path along target path exactly as adjusts flight coefficient itself depending on static or dynamic changes of airplane's features such as type, size or weight. In this paper, we propose system which tunes control gain autonomously depending on change of airplane's feature in flight as adding MLM(Machine Learning Module) on AFCS. MLM is designed with Linear Regression algorithm and Reinforcement Learning and it includes EvM(Evaluation Module) which evaluates learned control gain from MLM and verified system. This system is tested on beaver FDC simulator and we present its analysed result.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.171-174
• /
• 2009

Generally the neural network and the fuzzy compensative algorithm are applied to forecast the time series for power demand with a characteristic of non-linear dynamic system, but it has a few prediction errors relatively. It also makes long term forecast difficult for sensitivity on the initial condition. On this paper, we evaluate the chaotic characteristic of electrical power demand with analysis methods of qualitative and quantitative and perform a forecast simulation of electrical power demand in regular sequence, attractor reconstruction, time series forecast for multi dimension using Lyapunov exponent quantitatively. We compare simulated results with the previous method and verify that the purpose one being more practice and effective than it.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.522-539
• /
• 2021

In order to solve the problems of the existing audio fingerprint method when extracting audio fingerprints from long speech segments, such as too large fingerprint dimension, poor robustness, and low retrieval accuracy and efficiency, a robust audio fingerprint retrieval method based on feature dimension reduction and feature combination is proposed. Firstly, the Mel-frequency cepstral coefficient (MFCC) and linear prediction cepstrum coefficient (LPCC) of the original speech are extracted respectively, and the MFCC feature matrix and LPCC feature matrix are combined. Secondly, the feature dimension reduction method based on information entropy is used for column dimension reduction, and the feature matrix after dimension reduction is used for row dimension reduction based on energy feature dimension reduction method. Finally, the audio fingerprint is constructed by using the feature combination matrix after dimension reduction. When speech's user retrieval, the normalized Hamming distance algorithm is used for matching retrieval. Experiment results show that the proposed method has smaller audio fingerprint dimension and better robustness for long speech segments, and has higher retrieval efficiency while maintaining a higher recall rate and precision rate.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.49-56
• /
• 2023

Computer architecture serves as a link between application requirements and underlying technology capabilities such as technical, mathematical, medical, and business applications' computational and storage demands are constantly increasing. Machine learning these days grown and used in many fields and it performed better than traditional computing in applications that need to be implemented by using mathematical algorithms. A mathematical algorithm requires more extensive and quicker calculations, higher computer architecture specification, and takes longer execution time. Therefore, there is a need to improve the use of computer hardware such as CPU, memory, etc. optimization has a main role to reduce the execution time and improve the utilization of computer recourses. And for the importance of execution time in implementing machine learning supervised module linear regression, in this paper we focus on optimizing machine learning algorithms, for this purpose we write a (Diabetes prediction program) and applying on it a Practical Swarm Optimization (PSO) to reduce the execution time and improve the utilization of computer resources. Finally, a massive improvement in execution time were observed.