• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.180-186
• /
• 2004

The presence of noise in speech signals degrades the performance of recognition systems in which there are mismatches between the training and test environments. To make a speech recognizer robust, it is necessary to compensate these mismatches. In this paper, we studied about an improvement of stochastic feature extraction based on band-SNR for robust speech recognition. At first, we proposed a modified version of the multi-band spectral subtraction (MSS) method which adjusts the subtraction level of noise spectrum according to band-SNR. In the proposed method referred as M-MSS, a noise normalization factor was newly introduced to finely control the over-estimation factor depending on the band-SNR. Also, we modified the architecture of the stochastic feature extraction (SFE) method. We could get a better performance when the spectral subtraction was applied in the power spectrum domain than in the mel-scale domain. This method is denoted as M-SFE. Last, we applied the M-MSS method to the modified stochastic feature extraction structure, which is denoted as the MMSS-MSFE method. The proposed methods were evaluated on isolated word recognition under various noise environments. The average error rates of the M-MSS, M-SFE, and MMSS-MSFE methods over the ordinary spectral subtraction (SS) method were reduced by 18.6%, 15.1%, and 33.9%, respectively. From these results, we can conclude that the proposed methods provide good candidates for robust feature extraction in the noisy speech recognition.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.20 no.2
• /
• pp.123-135
• /
• 2016

This article deals with the pricing of Asian options under a constant elasticity of variance (CEV) model as well as a stochastic elasticity of variance (SEV) model. The CEV and SEV models are underlying asset price models proposed to overcome shortcomings of the constant volatility model. In particular, the SEV model is attractive because it can characterize the feature of volatility in risky situation such as the global financial crisis both quantitatively and qualitatively. We use an asymptotic expansion method to approximate the no-arbitrage price of an arithmetic average Asian option under both CEV and SEV models. Subsequently, the zero and non-zero constant leverage effects as well as stochastic leverage effects are compared with each other. Lastly, we investigate the SEV correction effects to the CEV model for the price of Asian options.

• International Journal of Advanced Culture Technology
• /
• v.6 no.4
• /
• pp.292-302
• /
• 2018

This study proposes a Bayesian stochastic frontier model that is well-suited to productivity/efficiency analysis particularly using panel data. A unique feature of our proposal is that both production frontier and efficiency are estimable for each individual firm and their linkage to various firm characteristics enriches our understanding of the source of productivity/efficiency. Empirical application of the proposed analysis to Human Capital Corporate Panel data enables identification and quantification of the effects of Human Resource factors on firm efficiency in tandem with those of firm types on production frontier. A comprehensive description of the Markov Chain Monte Carlo estimation procedure is forwarded to facilitate the use of our proposed stochastic frontier analysis.

• Wind and Structures
• /
• v.18 no.6
• /
• pp.693-715
• /
• 2014

Stochastic processes are used to represent phenomena in many diverse fields. Numerical simulation method is widely applied for the solution to stochastic problems of complex structures when alternative analytical methods are not applicable. In some practical applications the stochastic processes show non-Gaussian properties. When the stochastic processes deviate significantly from Gaussian, techniques for their accurate simulation must be available. The various existing simulation methods of non-Gaussian stochastic processes generally can only simulate super-Gaussian stochastic processes with the high-peak characteristics. And these methodologies are usually complicated and time consuming, not sufficiently intuitive. By revealing the inherent coupling effect of the phase and amplitude part of discrete Fourier representation of random time series on the non-Gaussian features (such as skewness and kurtosis) through theoretical analysis and simulation experiments, this paper presents a novel approach for the simulation of non-Gaussian stochastic processes with the prescribed amplitude probability density function (PDF) and power spectral density (PSD) by amplitude modulation and phase reconstruction. As compared to previous spectral representation method using phase modulation to obtain a non-Gaussian amplitude distribution, this non-Gaussian phase reconstruction strategy is more straightforward and efficient, capable of simulating both super-Gaussian and sub-Gaussian stochastic processes. Another attractive feature of the method is that the whole process can be implemented efficiently using the Fast Fourier Transform. Cases studies demonstrate the efficiency and accuracy of the proposed algorithm.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Transactions on Control, Automation and Systems Engineering
• /
• v.4 no.3
• /
• pp.239-243
• /
• 2002

Multi-valued decision making for transitional stochastic events was newly derived based on conditional probability of knowledge database which included experts'knowledge and experience. The proposed multi-valued decision making was successfully adopted to the determination of the five levels of the vigilance of a subject during the EEG (electroencephalogram) recording; awake stage (stage W), and sleep stages (stage REM (rapid eye movement), stage 1, stage 2, stage $\sfrac{3}{4}$). Innovative feature of the proposed method is that the algorithm of decision making can be constructed only by use of the knowledge database, inspected by experts. The proposed multi-valued decision making with a mathematical background of the probability can also be applicable widely, in industries and in other medical fields for purposes of the multi-valued decision making.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.6
• /
• pp.1199-1215
• /
• 2011

Relaxing an unrealistic assumption of a representative percolation model, this paper demonstrates that herd behavior leads to a high increase in volatility but not trading volume, in contrast with information flows that give rise to increases in both volatility and trading volume. Although detecting herd behavior has posed a great challenge due to its empirical difficulty, this paper proposes a new methodology for detecting trading days with herding. Furthermore, this paper suggests a herd-behavior-stochastic-volatility model, which accounts for herding in financial markets. Strong evidence in favor of the model specification over the standard stochastic volatility model is based on empirical application with high frequency data in the Korean equity market, strongly supporting the intuition that herd behavior causes excess volatility. In addition, this research indicates that strong persistence in volatility, which is a prevalent feature in financial markets, is likely attributed to herd behavior rather than news.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.1210-1215
• /
• 2000

Investigation is performed on the stability of general form of dynamic system under colored noise random disturbance whose damping and stiffness are varying in irregular manner along time, which is a preliminary result in the course of research on the characteristic and the control of the stochastic system. Adopted physical model is airfoil under random atmospheric disturbance, which becomes a "time-varying system" whose the governing equation is derived via F-P-K approach in stochastic sense. Control performance and effect of 'Heo-stochastic controller for colored noise' is studied. Also stochastic feature of flutter boundary is discussed as well.

• Journal of Korea Multimedia Society
• /
• v.13 no.12
• /
• pp.1778-1785
• /
• 2010

This paper proposes a new video-based method of analyzing human gait which is a highly variable dynamic process. It captures a human gait of varying directions as a trajectory in the phase space. The proposed method includes two options of a stochastic process model and a self-organizing feature map as the tool of feature space representation and analysis. Test results show that the model is highly intuitive and we believe it can contribute to our understanding of human activity as well as gait behavior.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.113-120
• /
• 2015

In this paper, we propose a feature extraction method using the stacked autoencoders which consist of restricted Boltzmann machines. The stacked autoencoders is a sort of deep networks. Restricted Boltzmann machines (RBMs) are probabilistic graphical models that can be interpreted as stochastic neural networks. In terms of pattern classification problem, the feature extraction is a key issue. We use the stacked autoencoders networks to extract new features which have a good influence on the improvement of the classification performance. After feature extraction, fuzzy k-nearest neighbors algorithm is used for a classifier which classifies the new extracted data set. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.