• Journal of KIISE:Software and Applications
• /
• v.37 no.9
• /
• pp.706-711
• /
• 2010

In the applications of a human speech interface, reducing the error rate in recognition is the one of the main research issues. Many previous studies attempted to correct errors using post-processing, which is dependent on a manually constructed corpus and correction patterns. We propose an automatically learnable post-processing method that is independent of the characteristics of both the domain and the speech recognizer. We divide the entire post-processing task into two steps: error detection and error correction. We consider the error detection step as a classification problem for which we apply the conditional random fields (CRFs) classifier. Furthermore, we apply transformation-based learning (TBL) to the error correction step. Our experimental results indicate that the proposed method corrects a speech recognizer's insertion, deletion, and substitution errors by 25.85%, 3.57%, and 7.42%, respectively.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.23 no.1
• /
• pp.6-11
• /
• 2016

Purpose: This study was done to describe level of knowledge and performance of pain management by nurses in general hospitals. Methods: The study was conducted from August 1 to 28, 2014 with 141 nurses from a general hospital in B city. Data were analyzed using descriptive statistics, t-test, one-way ANOVA, and Pearson correlation coefficient with SPSS 20.0. Results: Average correct response rate for knowledge was 62.7%, indicating poor knowledge of pain management. Mean score for knowledge of pain management was $31.33{\pm}3.24$ out of 50(general knowledge about pain $14.02{\pm}2.18$ out of 20, knowledge on use of analgesics $9.21{\pm}1.97$ out of 20, knowledge on analgesic classification $8.16{\pm}1.00$ out of 10). Mean score for performance of pain management was $3.19{\pm}.44$ out of 4. There was significant difference in knowledge of pain management by age. Performance of pain management differed significantly according to age and type of working unit. No significant relationship was found between knowledge and performance of pain management. Conclusion: These findings show that nurses who have good knowledge do not always have good performance of pain management. Therefore, it is necessary to develop new strategies to promote performance as well as continued pain management education to increase ability of nurses to manage pain.

• Journal of IKEEE
• /
• v.5 no.2 s.9
• /
• pp.190-200
• /
• 2001

This paper is addressed to welding defect feature vector selection and implementation method of welding defect classifier using fuzzy techniques. We compare IAV, zero-crossing number as time domain analysis, power spectrum coefficient as frequency domain, histogram as both domain for welding defect feature selection. We choose histogram as feature vector by graph analysis and find out that maximum frequent occurrence number and section of corresponding signal scale in relative histogram show obvious difference between normal welding and voiding with penetration depth defect. We implement a fuzzy welding defect classifier using these feature vector, test it to verify its effectiveness for 695 welding data frame which consist of 4000 sampled data. As result of test, correct classification rate is 92.96%. Lab experimental results show a effectiveness of fuzzy welding defect classifier using relative histogram for practical Laser welding monitoring system in industry.

• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.571-580
• /
• 2008

The logistic regression analysis is widely used in the area of customer relationship management and credit risk management. It is well known that the maximum likelihood estimation is not appropriate when multicollinearity exists among the regressors. Thus we propose the logistic principal components regression to deal with the multicollinearity problem. In particular, new method is suggested to select proper principal components. The selection method is based on the condition index instead of the eigenvalue. When a condition index is larger than the upper limit of cutoff value, principal component corresponding to the index is removed from the estimation. And hypothesis test is sequentially employed to eliminate the principal component when a condition index is between the upper limit and the lower limit. The limits are obtained by a linear model which is constructed on the basis of the conjoint analysis. The proposed method is evaluated by means of the variance of the estimates and the correct classification rate. The results indicate that the proposed method is superior to the existing method in terms of efficiency and goodness of fit.

• The Korean Journal of Applied Statistics
• /
• v.22 no.3
• /
• pp.531-539
• /
• 2009

Logistic regression is widely used as a datamining technique for the customer relationship management. The maximum likelihood estimator has highly inflated variance when multicollinearity exists among the regressors, and it is not robust against outliers. Thus we propose the robust principal components logistic regression to deal with both multicollinearity and outlier problem. A procedure is suggested for the selection of principal components, which is based on the condition index. When a condition index is larger than the cutoff value obtained from the model constructed on the basis of the conjoint analysis, the corresponding principal component is removed from the logistic model. In addition, we employ an algorithm for the robust estimation, which strives to dampen the effect of outliers by applying the appropriate weights and factors to the leverage points and vertical outliers identified by the V-mask type criterion. The Monte Carlo simulation results indicate that the proposed procedure yields higher rate of correct classification than the existing method.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.4
• /
• pp.47-55
• /
• 2010

In this paper, we proposed a recognition system of smile facial expression for smile treatment training. The proposed system detects face candidate regions by using Haar-like features from camera images. After that, it verifies if the detected face candidate region is a face or non-face by using SVM(Support Vector Machine) classification. For the detected face image, it applies illumination normalization based on histogram matching in order to minimize the effect of illumination change. In the facial expression recognition step, it computes facial feature vector by using PCA(Principal Component Analysis) and recognizes smile expression by using a multilayer perceptron artificial network. The proposed system let the user train smile expression by recognizing the user's smile expression in real-time and displaying the amount of smile expression. Experimental result show that the proposed system improve the correct recognition rate by using face region verification based on SVM and using illumination normalization based on histogram matching.

• Journal of Korean Academy of Nursing
• /
• v.46 no.1
• /
• pp.149-158
• /
• 2016

Purpose: This study was done to develop of the Korean intensive care delirium screening tool (KICDST). Methods: The KICDST was developed in 5 steps: Configuration of conceptual frame, development of preliminary tool, pilot study, reliability and validity test, development of final KICDST. Reliability tests were done using degree of agreement between evaluators and internal consistency. For validity tests, CVI (Content Validity Index), ROC (Receiver Operating Characteristics) analysis, known group technique and factor analysis were used. Results: In the reliability test, the degree of agreement between evaluators showed .80~1.00 and the internal consistency was KR-20=.84. The CVI was .83~1.00. In ROC analysis, the AUC (Area Under the ROC Curve) was .98. Assessment score was 4 points. The values for sensitivity, specificity, correct classification rate, positive predictive value, and negative predictive value were found to be 95.0%, 93.7%, 94.4%, 95.0% and 93.7%, respectively. In the known group technique, the average delirium screening tool score of the non-delirium group was $1.25{\pm}0.99$ while that of delirium group was $5.07{\pm}1.89$ (t= - 16.33, p <.001). The factors were classified into 3 factors (cognitive change, symptom fluctuation, psychomotor retardation), which explained 67.4% of total variance. Conclusion: Findings show that the KICDST has high sensitivity and specificity. Therefore, this screening tool is recommended for early identification of delirium in intensive care patients.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.6-11
• /
• 2011

In this paper, we propose a gait-based human identification system using eigenfeature regularization and extraction (ERE). First, a gait feature for human identification which is called gait energy image (GEI) is generated from walking sequences acquired from a camera sensor. In training phase, regularized transformation matrix is obtained by applying ERE to the gallery GEI dataset, and the gallery GEI dataset is projected onto the eigenspace to obtain galley features. In testing phase, the probe GEI dataset is projected onto the eigenspace created in training phase and determine the identity by using a nearest neighbor classifier. Experiments are carried out on the CASIA gait dataset A to evaluate the performance of the proposed system. Experimental results show that the proposed system is better than previous works in terms of correct classification rate.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.2
• /
• pp.172-177
• /
• 2013

With Brain Computer Interface (BCI) system, a person with disabled limb could use this direct brain signal like electroencephalography (EEG) to control a device such as the artifact arm. The precise force control for the artifact arm is necessary for this artificial limb system. To understand the relationship between control EEG signal and the gripping force of hands, We proposed a study by measuring EEG changes of three grades (25%, 50%, 75%) of hand grip MVC (Maximal Voluntary Contract). The acquired EEG signal was filtered to obtain power of three wave bands (alpha, beta, gamma) by using fast fourier transformation (FFT) and computed power spectrum. Then the power spectrum of three bands (alpha, beta and gamma) of three classes (MVC 25%, 50%, 75%) was classified by using PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis). The result showed that the power spectrum of EEG is increased at MVC 75% more than MVC 25%, and the correct classification rate was 52.03% for left hand and 77.7% for right hand.

• Journal of Korean Academy of Nursing Administration
• /
• v.6 no.3
• /
• pp.357-374
• /
• 2000

The purpose of this study was to validate knowledge outcomes included Nursing Outcomes Classification(NOC) developed by Johnson and Maas at the University of Iowa. A sample of 71 nurse experts working in university affiliated hospitals participated in this study. They were asked to rate indicators that examplified the outcomes on a scale of 1(indicator is not all characteristic) to 5(indicator is very characteristic). A questionnaire with an adaptation of Fehring's methodology was used to establish the content validity of outcomes. The results were as follow: 1. All indicators were considered to be 'supporting' and no indicators were considered to be 'nonsupporting'. 2. 'Knowledge: Treatment Regimen' attained and OCV score of 0.816 and was the highest OCV score among outcomes. 3. 'Knowledge: Energy Conservation' attained an OCV score of 0.748 and was the lowest OCV score among abuse outcomes. 4. 'Knowledge: Breastfeeding' attained an OCV score of 0.790 and was the highest indicator was 'description of benefits of breastfeeding'. 5. 'Knowledge: Child Safety' attained an OCV score of 0.778 and was the highest indicator was 'demonstration of first aids techniques'. 6. 'Knowledge: Diet' attained an OCV score of 0.779 and was the highest indicator was 'performance of self-monitoring activities'. 7. 'Knowledge: Disease Process' attained an OCV score of 0.815 and was the highest indicator was 'description of signs and symptoms'. 8. 'Knowledge: Health Behaviors' attained an OCV score of 0.800 and was the highest indicator was 'description of safe use of prescription drugs'. 9. 'Knowledge: Health Resources' attained an OCV score of 0.794 and was the highest indicator was 'description of need for follow-up care'. 10. 'Knowledge: Infection Control' attained an OCV score of 0.793 and was the highest indicator was 'description of signs and symptoms'. 11. 'Knowledge: Medication' attained an OCV score of 0.789 and was the highest indicator was 'description of correct administration of medication'. 12. 'Knowledge: Personal Safety' attained an OCV score of 0.804 and was the highest indicator was 'description of measures to reduce risk of accidental injury'. 13. 'Knowledge: Prescribed Activity' attained an OCV score of 0.810 and was the highest indicator was 'proper performance of exercise'. 14. 'Knowledge: Substance Use Control' attained an OCV score of 0.809 and was the highest indicator was 'description of signs of dependence during substance withdrawl'. 15. 'Knowledge: Treatment Procedure(s)' attained an OCV score of 0.795 and was the highest indicator was 'description of appropriate action for complications'. 16. 'Knowledge: Treatment Regimen' attained an OCV score of 0.816 and was the highest indicator was 'description of self-care responsibilities for emergency situations'. More outcomes need to be validated and outcomes sensitive to Korean culture need to be developed.