• Journal of the Korean Institute of Intelligent Systems
• /
• 제19권6호
• /
• pp.755-759
• /
• 2009

The ability to recognize human emotion is one of the hallmarks of human-robot interaction. Especially, speaker-independent emotion recognition is a challenging issue for commercial use of speech emotion recognition systems. In general, speaker-independent systems show a lower accuracy rate compared with speaker-dependent systems, as emotional feature values depend on the speaker and his/her gender. Hence, this paper describes the realization of speaker-independent emotion recognition by rejection using confidence measure to make the emotion recognition system be homogeneous and accurate. From comparison of the proposed methods with conventional method, the improvement and effectiveness of proposed methods were clearly confirmed.

• The Journal of Korean Academic Society of Nursing Education
• /
• 제21권3호
• /
• pp.350-360
• /
• 2015

Purpose: The purpose of this study was to evaluate the effectiveness and retention period of immediate remediation for infant cardiopulmonary resuscitation (CPR) in child care teachers. Methods: This study used a nonequivalent comparison pre- and post-test design to measure knowledge about and confidence in infant CPR and an interrupted time-series design to determine skill performance. The experimental group (n=25) received both immediate remediation and video learning for infant CPR, and the comparison group (n=28) received video learning only. Knowledge and confidence were measured before and after 4 weeks. Their skill performance was tested immediately, and 4 weeks, 8 weeks, 12 weeks, and 24 weeks after intervention. Data analysis consisted of ${\chi}^2$ tests, t-tests, paired t-tests, and a generalized linear mixed model. Results: There were significant increases in knowledge and confidence within the experimental group. Skill performance showed a significant difference according to the group factor (F=10.81, p=.002) and measurement time (F=146.80, p<.001). The experimental group maintained significantly higher skill performance than did the comparison group. Conclusion: These findings support the necessity of immediate remediation education for infant CPR to maintain skill performance. In addition, appropriate renewal time and the improvement of training programs for child care teachers are necessary.

• The Journal of Korean Medicine
• /
• 제40권2호
• /
• pp.106-118
• /
• 2019

Objectives: The aim of this study is to survey on the effect of Korean medicine health promotion program for maternal health. Methods: We conducted Korean medicine health promotion program for maternal health to pregnant women who agreed to participate in this program among 10 public health center. Before and after program, we surveyed the Knowledge Score of Maternal Health Care, Practice of Health Behavior, (Traditional) Child Care Recognition, Depression, Child Caring Confidence and analyzed DID(Difference In Difference). Results: The Knowledge Score of Maternal Health Care of intervention group was improved about 1 point. The improvement of (Traditional) Child Care Recognition was significant. Depression score of intervention group was improved high significantly. The Child Caring Confidence of intervention group was improved about 1.3 point. Conclusion: As a result of analyzing the effect of Korean medicine health promotion program for maternal health, it is confirmed that this program can have an impact on improving Knowledge Score of Maternal Health Care, (Traditional) Child Care Recognition, Depression, Child Caring Confidence. It will be necessary to continue and develop this program widely.

• MALSORI
• /
• 제46호
• /
• pp.103-115
• /
• 2003

In this paper, we proposed Background Model Set algorithm used in the speaker verification to improve calculating confidence measure(CM) in speech recognition. CM is to display relative likelihood between recognized models and antiphone models. In previous method calculating of CM, we calculated probability and standard deviation using all phonemes in composition of antiphone models. At this process, antiphone CM brought bad recognition result. Also, recognition time increases. In order to solve this problem, we studied about method to reconstitute average and standard deviation using BMS algorithm in CM calculation.

• Phonetics and Speech Sciences
• /
• 제1권1호
• /
• pp.55-62
• /
• 2009

This paper proposes an improved method to verify a keyword segment that results from a word spotting system. First a baseline word spotting system is implemented. In order to improve performance of the word spotting systems, we use a two-pass structure which consists of a word spotting system and an utterance verification system. Using the basic likelihood ratio test (LRT) based utterance verification system to verify the keywords, there have been certain problems which lead to performance degradation. So, we propose a method which uses phone-level log-likelihood ratios (PLLR) patterns in computing confidence measures for each keyword. The proposed method generates weights according to the PLLR patterns and assigns different weights to each phone in the process of generating confidence measures for the keywords. This proposed method has shown to be more appropriate to word spotting systems and we can achieve improvement in final word spotting accuracy.

• Proceedings of the KSPS conference
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.79-82
• /
• 2003

In this paper, we proposed Backgorund Model Set algorithm for the speaker verification to improve the shortcoming of calculating process in conventional confidence measure(CM). CM is to display relative likelihood between recognized models and unrecognized models. Unrecognized models is known as antiphone models. Calculate probability and standard deviation using all phonemes at process that compose antiphone model. At this process, antiphone CM brought bad result. Also, recognition time increases. In order problem, we studied about method to reconstitute average and standard deviation taking BMS algorithm using antiphoneme that near phoneme of CM calculation.

• IEMEK Journal of Embedded Systems and Applications
• /
• 제16권5호
• /
• pp.195-200
• /
• 2021

In this paper, we propose a method for a mobile robot to estimate a specific location of a service provision target using a beacon-tag for the purpose of providing location-based services (LBS) to users in an indoor environment. To estimate the location, the irregular characteristics and error factors of the received signal strength indicator (RSSI) generated from the beacon are analyzed, and the distance conversion function is derived from the RSSI data extracted by applying a Gaussian filter. Then, the distance data converted from the plurality of beacons estimates an indoor location through a triangulation technique. After that, the improvement in the location estimation is analyzed by applying the temporal confidence reasoning technique. The possibility of providing a LBS of a mobile robot was confirmed through a location estimation experiment for a plurality of designated locations in an indoor environment.

• Asian-Australasian Journal of Animal Sciences
• /
• 제33권5호
• /
• pp.704-711
• /
• 2020

Objective: Muscle fiber types, numbers and area are crucial aspects associated with meat production and quality. However, there are few studies of pig muscle fibre traits in terms of the detection power, false discovery rate and confidence interval precision of whole-genome quantitative trait loci (QTL). We had previously performed genome scanning for muscle fibre traits using 183 microsatellites and detected 8 significant QTLs in a White Duroc×Erhualian F₂ population. The confidence intervals of these QTLs ranged between 11 and 127 centimorgan (cM), which contained hundreds of genes and hampered the identification of QTLs. A whole-genome sequence imputation of the population was used for fine mapping in this study. Methods: A whole-genome sequences association study was performed in the F₂ population. Genotyping was performed for 1,020 individuals (19 F₀, 68 F₁, and 933 F₂). The whole-genome variants were imputed and 21,624,800 single nucleotide polymorphisms (SNPs) were identified and examined for associations to 11 longissimus dorsi muscle fiber traits. Results: A total of 3,201 significant SNPs comprising 7 novel QTLs showing associations with the relative area of fiber type I (I_RA), the fiber number per square centimeter (FN) and the total fiber number (TFN). Moreover, one QTL on pig chromosome 14 was found to affect both FN and TFN. Furthermore, four plausible candidate genes associated with FN (kinase non-catalytic C-lobe domain containing [KNDC1]), TFN (KNDC1), and I_RA (solute carrier family 36 member 4, contactin associated protein like 5, and glutamate metabotropic receptor 8) were identified. Conclusion: An efficient and powerful imputation-based association approach was utilized to identify genes potentially associated with muscle fiber traits. These identified genes and SNPs could be explored to improve meat production and quality via marker-assisted selection in pigs.

• Journal of Korean Academy of Nursing
• /
• 제42권5호
• /
• pp.671-679
• /
• 2012

Purpose: This study was conducted to evaluate the effectiveness of a mother/infant-toddler health program developed to enhance parenting knowledge, behavior and confidence in low income mothers and home environment. Methods: A one-group pretest-posttest quasi-experimental design was used. Sixty-nine dyads of mothers and infant-toddlers (aged 0-36 months) were provided with weekly intervention for seven session. Each session consisted of three parts; first, educating to increase integrated knowledge related to the development of the infant/toddler including nutrition, first aid and home environment; second, counseling to share parenting experience among the mothers and to increase their nurturing confidence; third, playing with the infant/toddler to facilitate attachment-based parenting behavior for the mothers. Results: Following the programs, there were significant increases in parenting knowledge on nutrition and first aid. A significant improvement was found in attachment-based parenting behavior, but not in home safety practice. Nurturing confidence was not significantly increased. The program led to more positive home environment for infant/toddler's health and development. Conclusion: The findings provide evidence for mother-infant/toddler health program to improve parenting knowledge, attachment-based parenting behavior and better home environment in low income mothers. Study of the long term effectiveness of this program is recommended for future research.

• Korean Journal of Health Education and Promotion
• /
• 제24권1호
• /
• pp.63-74
• /
• 2007

Objectives: This study aimed to evaluate the educational effect of the Field Epidemiology Specialist Training Program for School Nurse which composed of 18hours curriculum. Method: The subjects were 797 who participated in the 2005 training program. Data was collected with structured questionnaires(knowledge on the control of communicable disease 15 items, attitude 15 items, and confidence in practice 14 items, demographic characteristics 4 items) before (January) and after (July to October) programs in 2005. Results: Knowledge on the control of communicable disease was improved from 9.7 points (possible range : 0-15) before program to 11.9 points after program. Attitude was improved from 53.6 points (possible range : 15-60) before program to 55.7 points after program. Confidence in practice was changed from 45.9 points (possible range : 14-56) before program to 50.0 points after program. Even though all three areas were improved after educational program, knowledge showed the largest change among them. Conclusion: We can conclude the educational program was effective because knowledge, attitude, and confidence in practice on the control of communicable were statistically significantly improved after educational program. Further educational program is recommended to be operated to get more improvement in attitude and confidence in practice. And short-term continuing educational program is needed to maintain and refresh the information on the control of communicable diseases in schools.