• ETRI Journal
• /
• v.32 no.5
• /
• pp.801-809
• /
• 2010

This paper presents a statistical model-based noise suppression approach for voice recognition in a car environment. In order to alleviate the spectral whitening and signal distortion problem in the traditional decision-directed Wiener filter, we combine a decision-directed method with an original spectrum reconstruction method and develop a new two-stage noise reduction filter estimation scheme. When a tradeoff between the performance and computational efficiency under resource-constrained automotive devices is considered, ETSI standard advance distributed speech recognition font-end (ETSI-AFE) can be an effective solution, and ETSI-AFE is also based on the decision-directed Wiener filter. Thus, a series of voice recognition and computational complexity tests are conducted by comparing the proposed approach with ETSI-AFE. The experimental results show that the proposed approach is superior to the conventional method in terms of speech recognition accuracy, while the computational cost and frame latency are significantly reduced.

• The Korean Journal of Applied Statistics
• /
• v.17 no.1
• /
• pp.173-184
• /
• 2004

A statistical software for nonlinear regression analysis, NLIN2000, is introduced. This software, operated tinder the Window systems, has many user-friendly functions and Provides various statistics. As an upgraded version of the Previous Program operated under the DOS system, NLIN2000 provides easier steps for model specification and fitting process than any other statistical packages. Also it has a database system for model functions which has addition and deletion options. While it can be a useful research tool for statisticians, NLIN2000 can be used practically also by researchers in many other scientific fields, who needs nonlinear regression analysis for their study.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.486-490
• /
• 2003

Software qualify models can predict the risk of faults in the software early enough for cost-effective prevention of problems. This paper introduces a least squares support vector machine (LS-SVM) as a fuzzy regression method for predicting fault ranges in the software under development. This LS-SVM deals with the fuzzy data with crisp inputs and fuzzy output. Predicting the exact number of bugs in software is often not necessary. This LS-SVM can predict the interval that the number of faults of the program at each session falls into with a certain possibility. A case study on software reliability problem is used to illustrate the usefulness of this LS -SVM.

• Communications for Statistical Applications and Methods
• /
• v.5 no.2
• /
• pp.353-359
• /
• 1998

Factorial designs with two-level factors represent the smallest factorial experiments. The system of notation and confounding and fractional factorial schemes developed for the $2^N$system are found in standard textbooks of experimental designs. Just as in the $2^N$ system, the general confounding and fractional factorial schemes are possible in $3^N,5^N$, .... , and $\rho^N$ where $\rho$ is a prime number. Hence, we have the $\rho^N$ system. In this article, the author proposes a new algorithm for constructing fractional factorial plans in the $\rho^N$ system.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.05a
• /
• pp.233-238
• /
• 2005

S${\"{a}}$rndal (1996) and Knottnerus (2003) had a critical look at the well known variance estimator of Sen (1953) and Yates and Grundy (1953) in probability proportional to size sampling. In this paper, we point out that although their approaches can avoid the difficulties in variance estimation with respect to the joint probabilities, there exist the disadvantages in practice. Also, we describe a sampling procedure available in statistical software that are useful for the variance estimation.

• The Korean Journal of Applied Statistics
• /
• v.3 no.2
• /
• pp.17-25
• /
• 1990

We will compare several statistical package programs on aspects of exploratory data analysis(EDA). Specifically, PC versions of Minitab, NCSS, SAS, SPSS/PC+, Statgraphics, and SYSTAT are reviewed.

• International Journal of Computer Science & Network Security
• /
• v.21 no.2
• /
• pp.120-130
• /
• 2021

The spinal cord or CSF surgery is a very complex process. It requires continuous pre and post-surgery evaluation to have a better ability to diagnose the disease. To detect automatically the suspected areas of tumors and symptoms of CSF leakage during the development of the tumor inside of the brain. We propose a new method based on using computer software that generates statistical results through data gathered during surgeries and operations. We performed statistical computation and data collection through the Google Source for the UK National Cancer Database. The purpose of this study is to address the above problems related to the accuracy of missing hybrid KNN values and finding the distance of tumor in terms of brain cancer or CSF images. This research aims to create a framework that can classify the damaged area of cancer or tumors using high-dimensional image segmentation and Laplace transformation method. A high-dimensional image segmentation method is implemented by software modelling techniques with measures the width, percentage, and size of cells within the brain, as well as enhance the efficiency of the hybrid KNN algorithm and Laplace transformation make it deal the non-zero values in terms of missing values form with the using of Frobenius Matrix for deal the space into non-zero values. Our proposed algorithm takes the longest values of KNN (K = 1-100), which is successfully demonstrated in a 4-dimensional modulation method that monitors the lighting field that can be used in the field of light emission. Conclusion: This approach dramatically improves the efficiency of hybrid KNN method and the detection of tumor region using 4-D segmentation method. The simulation results verified the performance of the proposed method is improved by 92% sensitivity of 60% specificity and 70.50% accuracy respectively.

• The Korea Genome Conference
• /
• 2005.09a
• /
• pp.92-92
• /
• 2005

• Journal of Integrative Natural Science
• /
• v.7 no.3
• /
• pp.193-199
• /
• 2014

As the requirement on the quality of the system has increased, the reliability is very important part in terms of enhance stability and to provide high quality services to customers. Many statistical models have been developed in the past years for the estimation of software reliability. We consider the functions for NHPP software reliability model and time series model in software failure data. We estimate parameters for the proposed models from three data sets. The values of SSE and MSE is presented from three data sets. We compare the predicted number of faults with the actual three data sets using the NHPP software reliability model and time series model.

• Journal of Korean Society for Quality Management
• /
• v.13 no.2
• /
• pp.61-65
• /
• 1985

The quality of a final SOFTWARE PACKAGE depends on many complicated factors in the software development process. This paper describes ststistical methods for establishing relationships between final quality and development process factors. The final software quality is represented by the number of errors through the system test phase. The data presented here were gathered during the course of a real IS-month development project. Regression theory is used for data analysis. Some of the interesting results include the observation that specification changes during the development process have an adverse effect on final software quality.