• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.43-46
• /
• 1998

본 논문은 컴퓨터 사용에 미숙한 초보자나 키보드나 마우스를 사용할 수 없는 신체적인 조건을 가진 장애인 또는 PC사용에 미숙한 사용자들을 위해 기존의 인터페이스에 추가적으로 음성을 사용하여 더 효율적인 작업 환경을 만들기 위한 음성을 이용한 Window95 환경에서의 음성 인식 시스템 구현에 관한 것이다. 인터페이스 구현을 위해 사용되는 인식 알고리즘으로는 연결어 인식에 사용되는 OSDP[1] 알고리즘을 단독어 인식에 적용하여 사용하였다. 특징 벡터는 화자 독립적인 특성을 지닌 Perceptual Linear Predictive(PLP)[2] 13차 계수를 사용하였다. 인식 대상 어휘는 윈도우 사용자에게 자주 사용되는 60개의 명령어로 설정하였다. 인식된 후 그 결과는 구현된 시스템의 명령 실행 모듈로 전달되어 윈도우 상에서 실제 수행된다. 구현된 시스템에서는 노트북 내장 마이크를 사용하여 음성을 검출하였고 이를 위한 음성 구간 검출 알고리즘을 사용하였다. 기준 패턴은 20대 남성화자 9인이 2회 발성한 데이터를 이용하였고, 화자 독립으로 온라인 인식률은 91.71%이고, 오프라인 인식률은 96.4%의 인식률을 얻었다.

• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.5
• /
• pp.393-402
• /
• 2013

The Mahalanobis-Taguchi System (MTS) is a diagnostic and predictive method for multivariate data. In the MTS, the Mahalanobis space (MS) of reference group is obtained using the standardized variables of normal data. The Mahalanobis space can be used for multi-class classification. Once this MS is established, the useful set of variables is identified to assist in the model analysis or diagnosis using orthogonal arrays and signal-to-noise ratios. And other several techniques have already been used for classification, such as linear discriminant analysis and logistic regression, decision trees, neural networks, etc. The goal of this case study is to compare the ability of the Mahalanobis-Taguchi System and logistic regression using a data set.

• Advances in environmental research
• /
• v.1 no.4
• /
• pp.257-276
• /
• 2012

QSAR models for chlorinated alkenes were developed between $E_{HOMO}$ and their chlorine and carbon content. The aim is to provide valid QSAR model which is statistically validated for $E_{LUMO}$ prediction. Different molecular descriptors, $N_{Cl}$, $N_C$ and $E_{HOMO}$ have been used to take into account relevant information provided by molecular features and physicochemical properties. The best model were selected using Partial Least Square (PLS) and Multiple Linear Regression (MLR) led to models with satisfactory predictive ability for a data set of 15 chlorinated alkene compounds.

• Proceedings of the KIEE Conference
• /
• 1988.11a
• /
• pp.469-472
• /
• 1988

This paper deals with signal processing and pattern recognition for the pulsed doppler radar. In order to identify the class of moving targets detected by radar, linear predictive analysis is utilized to extract reflection coefficients of each radar signal as features, and Bayes decision theory is applied to classify them.

• Journal of Chest Surgery
• /
• v.28 no.4
• /
• pp.371-375
• /
• 1995

Surgical resection of lung cancer or other disease is recently required in patients with severely impaired lung function resulting from chronic obstructive pulmonary disease or disease extension. So prediction of pulmonary function after lung resection is very important in thoracic surgeon. We studied the accuracy of the prediction of postoperative pulmonary function using perfusion lung scan with 99m technetium macroaggregated albumin in 22 patients who received the pneumonectomy. The linear regression line derived from correlation between predicting[X and postoperative measured[Y values of FEV1 and FVC in patients are as follows: 1 Y[ml =0.713X + 381 in FEV1 [r=0.719 ,[P<0.01 2 Y[ml =0.645X + 556 in FVC [r=0.675 ,[P<0.01 In conclusion,the perfusion lung scan is noninvasive and very accurate for predicting postpneumonectomy pulmonary function.

• Journal of Forest and Environmental Science
• /
• v.28 no.2
• /
• pp.63-67
• /
• 2012

Crown ratio is the ratio of live crown length to tree height. It is often used as an important predictor variable for tree growth equation. It indicates tree vigor and is a useful parameter in forest health assessment. The objective of the study was to develop crown ratio prediction models for Tectona grandis. Based on the data set from the temporary sample plots, several non linear equations including logistics, Chapman Richard and exponential functions were tested. These functions were evaluated in terms of coefficient of determination ($R^2$) and standard error of the estimate (SEE). The significance of the estimated parameters was also verified. Plot of residuals against estimated crown ratios were observed. Although the logistic model had the highest $R^2$ and the least SEE, Chapman-Richard and Exponential functions were observed to be more consistent in their predictive ability; and were therefore recommended for predicting crown ratio in the stand.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.637-641
• /
• 1991

One of the most difficult problems in depth control for underwater vehicle is the effect of seaway disturbance. When a underwater vehicle operates in a near surface environment, the seaway generates essentially two types of stochastic disturbances that influence the boat notion. One component of the seaway forces is of large magnitude with a relatively narrow-band, first order component. The other component is generally of somewhat smaller magnitude, second order component. Since the magnitude of the first order component is generally such greater than the compensating force that can be generating by the planes, it is undesirable for the controller to generate a control command. In this paper, we used LPC(Linear Predictive Coding) processing to uncontrollable seaway disturbance. This method can be used extensively in sensor signal processing of underwater vehicles.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.51-58
• /
• 1993

This paper describes the development of a speaker-dependent isolated word recognizer as applied to voice dialing in a car noise environment. for this purpose, several methods to improve performance under such condition are evaluated using database collected in a small car moving at 100km/h The main features of the recognizer are as follow: The endpoint detection error can be reduced by using the magnitude of the signal which is inverse filtered by the AR model of the background noise, and it can be compensated by using variants of the DTW algorithm. To remove the noise, an autocorrelation subtraction method is used with the constraint that residual energy obtainable by linear predictive analysis should be positive. By using the noise rubust distance measure, distortion of the feature vector is minimized. The speech recognizer is implemented using the Motorola DSP56001(24-bit general purpose digital signal processor). The recognition database is composed of 50 Korean names spoken by 3 male speakers. The recognition error rate of the system is reduced to 4.3% using a single reference pattern for each word and 1.5% using 2 reference patterns for each word.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.33A no.5
• /
• pp.172-179
• /
• 1996

In the paper, QCELP (qualcomm code excited linear predictive), CDMA (code division multiple access)'s vocoder algorithm, was analyzed. And then, a ptich parameter seaarch architecture for 16-bit programmable DSP(digital signal processor) for QCELP was designed. Because we speed up the parameter search through high speed DSP using two MACs, we can satisfy speech codec specifiction for the digital celluar. Also, we implemented in FIFO(first-in first-out) memory using register file to increase the access time of data. This DSP was designed using COMPASS, ASIC design tool, by top-down design methodology. Therefore, it is possible to cope with rapid change at mobile communication market.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.10a
• /
• pp.203-206
• /
• 1996

Prediction of firm bankruptcy have been extensively studied in accounting, as all stockholders in a firm have a vested interest in monitoring its financial performance. The objective of this paper is to develop the hybrid models for bankruptcy prediction. The proposed hybrid models are two phase. Phase one are (a) DA-assisted neural network, (b) Logit-assisted neural network, and (c) Genetic-assisted neural network. And, phase two are (a) DA-assisted Case based reasoning, and (b) Genetic-assisted Case based reasoning. In the variables selection, We are focusing on three alternative methods - linear discriminant analysis, logit analysis and genetic algorithms - that can be used empirically select predictors for hybrid model in bankruptcy prediction. Empirical results using Korean medium-sized firms data show that hybrid models are very promising neural network models and case based reasoning for bankruptcy prediction in terms of predictive accuracy and adaptability.