• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1135-1148
• /
• 2017

Speech recognition is one of the fascinating fields in the area of Computer science. Accuracy of speech recognition system may reduce due to the presence of noise present in speech signal. Therefore noise removal is an essential step in Automatic Speech Recognition (ASR) system and this paper proposes a new technique called combined thresholding for noise removal. Feature extraction is process of converting acoustic signal into most valuable set of parameters. This paper also concentrates on improving Mel Frequency Cepstral Coefficients (MFCC) features by introducing Discrete Wavelet Packet Transform (DWPT) in the place of Discrete Fourier Transformation (DFT) block to provide an efficient signal analysis. The feature vector is varied in size, for choosing the correct length of feature vector Self Organizing Map (SOM) is used. As a single classifier does not provide enough accuracy, so this research proposes an Ensemble Support Vector Machine (ESVM) classifier where the fixed length feature vector from SOM is given as input, termed as ESVM_SOM. The experimental results showed that the proposed methods provide better results than the existing methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.3867-3886
• /
• 2015

This article investigates the problem of opportunistic spectrum access in dynamic environment, in which the signal-to-noise ratio (SNR) is time-varying. Different from existing work on continuous feedback, we consider more practical scenarios in which the transmitter receives an Acknowledgment (ACK) if the received SNR is larger than the required threshold, and otherwise a Non-Acknowledgment (NACK). That is, the feedback is discrete. Several applications with different threshold values are also considered in this work. The channel selection problem is formulated as a non-cooperative game, and subsequently it is proved to be a potential game, which has at least one pure strategy Nash equilibrium. Following this, a multi-agent Q-learning algorithm is proposed to converge to Nash equilibria of the game. Furthermore, opportunistic spectrum access with multiple discrete feedbacks is also investigated. Finally, the simulation results verify that the proposed multi-agent Q-learning algorithm is applicable to both situations with binary feedback and multiple discrete feedbacks.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.1
• /
• pp.95-104
• /
• 2017

This paper deals with solution methods for discrete and multi-valued optimization problems. The objective function of the problem incorporates noise effects generated in case that fitness evaluation is accomplished by computer based experiments such as Monte Carlo simulation or discrete event simulation. Meta heuristics including Genetic Algorithm (GA) and Discrete Particle Swarm Optimization (DPSO) can be used to solve these simulation based multi-valued optimization problems. In applying these population based meta heuristics to simulation based optimization problem, samples size to estimate the expected fitness value of a solution and population (particle) size in a generation (step) should be carefully determined to obtain reliable solutions. Under realistic environment with restriction on available computation time, there exists trade-off between these values. In this paper, the effects of sample and population sizes are analyzed under well-known multi-modal and multi-dimensional test functions with randomly generated noise effects. From the experimental results, it is shown that the performance of DPSO is superior to that of GA. While appropriate determination of population sizes is more important than sample size in GA, appropriate determination of sample size is more important than particle size in DPSO. Especially in DPSO, the solution quality under increasing sample sizes with steps is inferior to constant or decreasing sample sizes with steps. Furthermore, the performance of DPSO is improved when OCBA (Optimal Computing Budget Allocation) is incorporated in selecting the best particle in each step. In applying OCBA in DPSO, smaller value of incremental sample size is preferred to obtain better solutions.

• The KSFM Journal of Fluid Machinery
• /
• v.12 no.3
• /
• pp.19-25
• /
• 2009

InThe purpose of this work is to analyze the flow characteristics and aerodynamic noise generated from a shroud fan at a constant 2,100 rpm using LES and FW-H noise model provided in the commercial code, FLUENT. Velocity distributions around the shroud fan obtained by using FLUENT code show good agreement with experimental results. The sound pressure level is decreased by about 6 dB as the distance from the fan increases twice. The directivity at 1st BPF shows a tendency of increasing SPL toward the axis of rotation.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.11 s.116
• /
• pp.1149-1157
• /
• 2006

Donoho et al. suggested a wavelet thresholding denoising method based on discrete wavelet transform. This paper proposes an improved denoising method using a new thresholding function based on translation-invariant wavelet for underwater acoustic measurement. The conventional wavelet thresholding denoising method causes Pseudo-Gibbs phenomena near singularities due to the lack of translation-invariant of the wavelet basis. To suppress Pseudo-Gibbs phenomena, a denoising method combining a new thresholding function based on the translation-invariant wavelet transform is proposed in this paper. The new thresholding function is a modified hard-thresholding to each node according to the discriminated threshold so as to reject unknown external noise and white gaussian noise. The experimental results show that the proposed method can effectively eliminate noise, extract characteristic information of radiated noise signals.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.7
• /
• pp.891-897
• /
• 2013

The power system frequency plays an important role in monitoring and controlling the power system. The frequency can be measured through discrete Fourier transform (DFT) coefficients of its positive fundamental frequency. The accuracy of the frequency estimate is severely affected by noise in the power system signal and the leakage effect of the negative fundamental frequency in DFT. This paper proposes a DFT-based frequency estimation algorithm to cope with the noise as well as the leakage effect. In this algorithm, two suitable digital filters are introduced to reduce efficiently frequency estimate error due to the noise. These filters are designed to use a digital bandpass filter and a second-degree integrator. The effectiveness of the proposed algorithm in reduction of frequency estimate error is verified through simulations on noise, harmonics and frequency deviation.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1998.04a
• /
• pp.465-470
• /
• 1998

A cross-flow fan often generates discrete noise call blade passing frequency tones. Several methods have been investigated to reduce this BPF noise, where the random distribution of blades is the most promising one. A simple and effective algorithm to determine a random distribution of blades is proposed which considers fan. performance as well as noise characteristics. The proposed method is verified by a simple numerical model and is applied in manufacturing cross-flow fan samples. Also some experiments are carried out and the experimental results are analyzed.

• Journal of the Korean Magnetic Resonance Society
• /
• v.4 no.2
• /
• pp.103-115
• /
• 2000

Wavelet transforms are introduced as a new tool to distinguish real peaks from the noise contaminated NMR data in this paper. New algorithms of two wavelet transforms including Daubechies wavelet transform as a discrete and orthogonal wavelet transform (DWT) and Morlet wavelet transform as a continuous and nonorthogonal wavelet transform(CWT) were developed fer noise elimination. DWT and CWT method were successfully applied to the noise reduction in spectrum. The inevitable distortion of NMR spectral baseline and the imperfection in noise elimination were observed in DWT method while CWT method gives a better baseline ahape and a well noise suppressed spectrum.

• International Journal of Fluid Machinery and Systems
• /
• v.2 no.2
• /
• pp.136-146
• /
• 2009

Small axial fans have become widely used as cooling devices in recent years. Because of their increasing importance, studies have been conducted on ways to improve the performance and reduce the noise of such fans. In this report, a small axial fan with a diameter of 85 mm (a type popularity used in personal computer or workstation) was selected for further examination. The influence on aerodynamic performance and noise of such frame design parameters as blade tip clearance results in a decrease of discrete frequency noise and an increase of broad-spectrum noise. As for the most suitable design refinement in terms of fan efficiency, we found that the treatment of outlet corner roundness and altering spoke skew to the direction counter to that of fan rotation was effective.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.11a
• /
• pp.972-975
• /
• 2004

In order to reduce the noise of BLDC motor, a systematic optimization procedure for rotor structure is presented. The noise index is defined as the sum of volume velocity of FE-model that are calculated at the dominant frequencies during dehydration process, which is based on the principle of radiation simple volume source. Then, the five design variables are selected to represent the shape and layout or rotor structure. This discrete design optimization problem for minimizing the noise index is solved by 3-level orthogonal array based effect analysis. Finally, the response surface method (RSM) combined optimization approach is employed for more refining the approximate optimum.