• Journal of Korean Medicine for Obesity Research
• /
• v.9 no.1
• /
• pp.37-44
• /
• 2009

The study was to investigate the distribution for the diagnosis of pattern identification questionnaire and agreement rate between diagnosis of pattern identification based on obesity pattern identification questionnaire and the clinical diagnosis of pattern' identification by medical specialist. The distribution for the diagnosis of pattern identification based on obesity pattern identification questionnaire was shown in order of stagnation of liver Gi, retention of undigested food, deficiency of Yang at scale of 5, 3, 2 score and the diagnosis rate of single pattern identification at scale of 5, 3, 2 score was 89.96%, 79.33%, 54.64%, respectively the agreement rate between the diagnosis of pattern identification based on obesity pattern identification questionnaire and the clinical diagnosis of pattern identification by medical specialist was 0.1013. Therefore, the complementary management in CRF questionnaires with consultation from experts and the study for score difference of pattern identification will improve the accuracy and agreement rate, which will will be helpful for pattern identification of obesity by clinical experts.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.17 no.1
• /
• pp.29-44
• /
• 2013

Objectives This study is aimed at assessing the reliability of the Pattern identification questionnaire (PIQ) developed by Korea Institute of Oriental Medicine and examining the validity of the PIQ by comparing the pattern identification scores of different groups. Methods We conducted a survey of 258 participants (79 teachers and 179 graduate students at one School of Korean Medicine) using self-reported questionnaire and all the samples were retested. The test-retest reliability was assessed by Kappa coefficient(${\kappa}$) and Pearson correlation coefficient. Also we compared the differences in pattern identification scores according to sex, age and occupation. Results 1. One of 116 questions are impossible to calculate; 22 of them (18.97%) scored under 0.4 in ${\kappa}$; 90(77.59%) ranged from 0.4 to 0.8 in ${\kappa}$; and three questions (3.58%) scored 0.8 or over in ${\kappa}$. 2. Pearson correlation coefficients between test score and retest score of all pattern identification items are 0.4 or over. 3. The mean score for pattern identification in women was generally higher than that in men, particularly in patterns of blood-deficiency, blood-stasis, yang-deficiency and kidney disease. 4. The mean score for pattern identification in the graduate student group was generally higher than that in the teacher group. Conclusion In test-retest reliability, the PIQ showed relatively high reliability. The mean pattern identification score showed differences in regards to retaining knowledge about Korean medicine. Therefore, future research involving modification of questionnaire items and confirming the validity of this questionnaire is required.

• Journal of Society of Preventive Korean Medicine
• /
• v.21 no.2
• /
• pp.55-60
• /
• 2017

Objectives : This study was conducted to analysis correlation of pattern identification and body mass index (BMI) in obese adolescents. Methods : A total of 228 middle school students, 226 students were agreed and included study and two were excluded because of disagreement. It was conducted cold-heat pattern questionnaire, phlegm pattern questionnaire and after height and weight were measured. Firstly, out of 24 who did not respond to all of questionnaires. Secondary, out of 159 who are normal range on international obesity standard(BMI < $30kg/m^2$) Results : The average height and weight of 43 subjects was $159.65{\pm}9.45cm$, $70.10{\pm}8.47kg$ respectively. The average score of pattern identification was cold pattern score(CPS) was $2.70{\pm}1.61$, heat pattern score(HPS) was $3.30{\pm}1.99$, phlegm pattern score(PPS) was $3.95{\pm}5.02$. There was no significant correlation with BMI and CPS, HPS, PPS. Conclusions : In this study, there was no significant correlation of pattern identification and BMI in obese adolescents.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.8
• /
• pp.375-382
• /
• 2006

This paper is about how to identify emotional information and how to detect a specific emotion from speech signals. For emotion identification and detection task. we use long-term acoustic feature parameters and select the optimal Parameters using the feature selection technique based on F-score. We transform the conventional SVM into probabilistic output SVM for our emotion identification and detection system. In this paper we propose three approximation methods for log-likelihoods in a hypothesis test and compare the performance of those three methods. Experimental results using the SUSAS database showed the effectiveness of both feature selection and Probabilistic output SVM in the emotion identification task. The proposed methods could detect anger emotion with 91.3% correctness.

• 대한상한금궤의학회지
• /
• v.8 no.1
• /
• pp.109-119
• /
• 2016

Objective : The purpose of this paper is to report the effect of Daehamhyung-tang(DHHT) on tinnitus with panic disorder from the disease pattern identification diagnostic system based on Shanghanlun provisions. Methods : According to a disease pattern identification diagnostic system based on Shanghanlun provisions, the patient was diagnosed with 'Taeyang-byung Gyeolhyung'. He took DHHT for 82 days. This paper evaluated the results of treatment on tinnitus by Tinnitus Handicap Inventory(THI) and Verbal Numercial Rating Scale(VNRS). To assess the mental state of anxiety, this paper used Hamilton Anxiety Rating Scale(HAM-A) Results : The THI score was declined from 58 to 6 And the VNRS score was declined from 6 to 1. HAM-A score was declined from 28 to 3. Conclusions : This case study suggests that DHHT has effectiveness on a patient suffers from tinnitus with panic disorder and diagnosed with 'Taeyang-byung Gyeolhyung'.

• Speech Sciences
• /
• v.14 no.4
• /
• pp.145-156
• /
• 2007

The performance of speaker identification is severely degraded in noisy environments. Recently probability weighting method based on observation membership was proposed for overcoming the noise problem[1]. In the paper[1] the observation confidence was calculated from SNR with sigmoid function. However, estimating SNR needs additive calculation amount and estimated SNR is corrupted in dynamic noisy environments. In this paper we propose estimation methods of the observation confidence based on score-based reliabilities (SBR) of entropy and dispersion measures. Generally SBRs are obtained from speaker models' probabilities. The proposed methods are evaluated with ETRI speaker recognition DB. We compared the performances of the proposed methods with those in [1][8]. The experimental results show that the proposed methods can be successfully applied for the case where SNR is not available.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.220-226
• /
• 2015

Semantic role labeling (SRL) systems determine the semantic role labels of the arguments of predicates in natural language text. An SRL system usually needs to perform four tasks in sequence: Predicate Identification (PI), Predicate Classification (PC), Argument Identification (AI), and Argument Classification (AC). In this paper, we use the Korean Propbank to develop our Korean semantic role labeling system. We describe our Korean semantic role labeling system that uses sequence labeling with structured Support Vector Machine (SVM). The results of our experiments on the Korean Propbank dataset reveal that our method obtains a 97.13% F1 score on Predicate Identification and Classification (PIC), and a 76.96% F1 score on Argument Identification and Classification (AIC).

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.35-42
• /
• 2021

In this paper, we propose a deep learning-based person re-identification method using a three-dimensional RGB-Depth Xtion2 camera considering joint coordinates and dynamic features(velocity, acceleration). The main idea of the proposed identification methodology is to easily extract gait data such as joint coordinates, dynamic features with an RGB-D camera and automatically identify gait patterns through a self-designed one-dimensional convolutional neural network classifier(1D-ConvNet). The accuracy was measured based on the F1 Score, and the influence was measured by comparing the accuracy with the classifier model (JC) that did not consider dynamic characteristics. As a result, our proposed classifier model in the case of considering the dynamic characteristics(JCSpeed) showed about 8% higher F1-Score than JC.

• The Journal of Korean Obstetrics and Gynecology
• /
• v.28 no.1
• /
• pp.102-112
• /
• 2015

Objectives: This study was performed to obtain reference data of traditional Korean medicine diagnostic methods for the practical usage in women infertility. Methods: The study involved 38 female patients of age 20-38 years that had diagnosed of infertility. All the subjects answered to pattern identification questionnaire and Questionnaire for the Sasang Constitution Classification (QSCC II). Pattern identification scores and constitution types have been analyzed with variables of infertility factors and age. Statistical analysis was performed by adopting descriptive and inferential tests. Results: In pattern identification questionnaire analysis, the patterns were observed in order of frequency: liver stasis; blood deficiency; kidney-yang deficiency; kidney-yin deficiency; damp-heat; blood stasis; and phlegm. The group, less than 35 years old, had the higher average score of liver stasis (p<0.05). Also, the group with tubal and peritoneal factors, had the higher average score of blood deficiency (p<0.05). In QSCC II analysis, So-yang type had the higher average score of liver stasis, kidney-yang deficiency, and kidney-yin deficiency. So-eum type had the higher average score of liver stasis, kidney-yang deficiency, kidney-yin deficiency, and blood deficiency. While, Tae-um type had the higher average score of liver stasis and phlegm. Conclusions: We would accumulate the clinical data for the practical usage of traditional Korean medicine diagnostic methods in women infertility.

• The Journal of Korean Medicine
• /
• v.35 no.1
• /
• pp.124-134
• /
• 2014

Objectives: Metabolic syndrome is considered a coronary heart disease risk factor and its prevalence rate is increasing in Korea. Because obesity is relevant to metabolic syndrome, we investigated the relationship between metabolic syndrome and the Obesity Pattern Identification Questionnaire in middle-aged health check-up examinees. Methods: This was a cross-sectional study with 125 patients who visited a health promotion center of university hospital from October 2012 to January 2013. We analyzed the association of Obesity Pattern Identification Questionnaire and the diagnostic criteria of metabolic syndrome. Results: Pi deficiency (脾虛), phlegm (痰飮), liver stasis (肝鬱) and food accumulation (食積) pattern showed significantly highs score in the group with hypertriglyceridemia. Also, females demonstrated significantly high scores of liver stasis (肝鬱) and food accumulation (食積) in the group with hypertriglyceridemia. The questions of Pattern Identification that showed especially significant high score in the group of hypertriglyceridemia are as follows: 'Easily get annoyed', 'Usually worried', 'Frequently overeating or bingeing', and 'Having more after getting full'. There are positive correlations between triglyceride and the score of Pi deficiency (脾虛), phlegm (痰飮) and food accumulation (食積) pattern. Conclusions: Obesity Pattern Identification Questionnaire can be used for the management of hypertriglyceridemia in an effort to prevent metabolic syndrome.