• 한국컴퓨터정보학회논문지
• /
• 제27권3호
• /
• pp.33-43
• /
• 2022

본 논문에서는 기존의 스마트폰 카메라 센서를 사용하여 비접촉식 손바닥 기반 사용자 식별 시스템을 구축하기 위해 Attention U-Net 모델과 사전 훈련된 컨볼루션 신경망(CNN)이 있는 다채널 손바닥 이미지를 이용한 앙상블 모델을 제안한다. Attention U-Net 모델은 손바닥(손가락 포함), 손바닥(손바닥 미포함) 및 손금을 포함한 관심 영역을 추출하는 데 사용되며, 이는 앙상블 분류기로 입력되는 멀티채널 이미지를 생성하기 위해 결합 된다. 생성된 데이터는 제안된 손바닥 정보 기반 사용자 식별 시스템에 입력되며 사전 훈련된 CNN 모델 3개를 앙상블 한 분류기를 사용하여 클래스를 예측한다. 제안된 모델은 각각 98.60%, 98.61%, 98.61%, 98.61%의 분류 정확도, 정밀도, 재현율, F1-Score를 달성할 수 있음을 입증하며, 이는 저렴한 이미지 센서를 사용하고 있음에도 불구하고 제안된 모델이 효과적이라는 것을 나타낸다. 본 논문에서 제안하는 모델은 COVID-19 펜데믹 상황에서 기존 시스템에 비하여 높은 안전성과 신뢰성으로 대안이 될 수 있다.

• 동의신경정신과학회지
• /
• 제22권1호
• /
• pp.25-35
• /
• 2011

Objectives : This case series was conducted to report the efficacy of traditional Korean medicine treatments for Hwa-Byung. Methods : Patients were diagnosed with Hwa-byung through Hwa-Byung diagnostic interview schedule(HBDIS). instrument of pattern identification for Hwa-Byung was applied to develop an individualized traditional Korean medicine treatment plan. SCL-90-R, STAI, STAXI, BDI, and instrument of oriental medical evaluation for Hwa-Byung were measured. After 2 weeks of tradiational Korean medicine treatments and K-MBSR practice, STAI, STAXI, BDI, and instrument of oriental medical evaluation for Hwa-Byung were re-assessed to determine the progress of Hwa-Byung. Results : After treatments, chief complaints have improved. STAI, STAXI, BDI and instrument of oriental medical evaluation for Hwa-Byung score have decreased. Conclusions : According to the study, traditional Korean medicine treatments using instrument of pattern identification for Hwa-Byung have shown positive results in managing Hwa-Byung symptoms evaluated by instrument of oriental medical evaluation for Hwa-Byung.

• 한방재활의학과학회지
• /
• 제21권2호
• /
• pp.279-288
• /
• 2011

Objectives : Our purpose of this study was to evaluate the association between abdominal adipose tissue and oriental obesity pattern identification. Methods : This study was performed in 78 healthy obese(BMI(body mass index)${\geq}25kg/m^2$) women in Seoul. Subjects underwent abdominal CT(computed tomography) scanning and were asked to complete the oriental obesity pattern identification questionnaire. Subjects were given written consent and this study was performed under permission of institutional review board of Kyung-hee East-west Neo medical center. Results : 1. VFA(visceral fat area) and VSR(visceral/subcutaneous adipose tissue ratio) were significantly correlated with stagnation of the liver qi(肝鬱, gan-yu)(p<0.05). But, other patterns were not significantly correlated with oriental obesity pattern identification(p>0.05). 2. We evaluated a difference of oriental obesity pattern identification score in visceral obesity group(n=34) versus non-visceral obesity group(n=44). Scores of all patterns except food accumulation(食積, shi-ji) were significantly higher in the visceral obesity group than in the non-visceral obesity group(p<0.05). Especially, there was a further significant difference in stagnation of the liver qi(肝鬱, gan-yu)(p<0.01). Conclusions : Generally, the stagnation of the liver qi(肝鬱, gan-yu) has a close relation with stress and depression. This study suggests that stress and depression might be correlated with visceral fat, and the use of oriental obesity pattern identification would be helpful for planning a treatment schedule of visceral obesity in the clinic.

• 동의생리병리학회지
• /
• 제32권3호
• /
• pp.165-170
• /
• 2018

The aim of this study was to investigate the predictive validity of the five organ pattern identification questionnaire(FOPIQ). Data collection was conducted from 190 people who were randomly selected from the general population living in D city from October 2016 to June 2017, and the collected data were analyzed by SPSS 23.0 Statistics Program. Pearson correlation coefficient was used to know the relation between the expert's score and FOPIQ's one. The cut-off value, sensitivity and specificity were analyzed through ROC-curve. Significant p was <.05. The pearson correlation coefficient was .735, .756, .762, .736, and .513 between individual score of FOPIQ and that of the experts in liver, heart, spleen, lung, and kidney, respectively. The cut-off value of the FOPIQ was 46.209, 47.276, 45.336, 48.823, and 42.508 in liver, heart, spleen, lung, and kidney respectively. The AUC derived from the cut-off value of the FOPIQ was .907, .854, .888, .902, and .781 respectively. This study suggests that the FOPIQ could be valid to apply for general population in clinics as well as health checkups.

• 대한조선학회논문집
• /
• 제57권3호
• /
• pp.140-151
• /
• 2020

It is important to identify the location of ship hull blocks with exact block identification number when scheduling the shipbuilding process. The wrong information on the location and identification number of some hull block can cause low productivity by spending time to find where the exact hull block is. In order to solve this problem, it is necessary to equip the system to track the location of the blocks and to identify the identification numbers of the blocks automatically. There were a lot of researches of location tracking system for the hull blocks on the stockyard. However there has been no research to identify the hull blocks on the stockyard. This study compares the performance of 5 Convolutional Neural Network (CNN) models with multi-view image set on the classification of the hull blocks to identify the blocks on the stockyard. The CNN models are open algorithms of ImageNet Large-Scale Visual Recognition Competition (ILSVRC). Four scaled hull block models are used to acquire the images of ship hull blocks. Learning and transfer learning of the CNN models with original training data and augmented data of the original training data were done. 20 tests and predictions in consideration of five CNN models and four cases of training conditions are performed. In order to compare the classification performance of the CNN models, accuracy and average F1-Score from confusion matrix are adopted as the performance measures. As a result of the comparison, Resnet-152v2 model shows the highest accuracy and average F1-Score with full block prediction image set and with cropped block prediction image set.

• International Journal of Computer Science & Network Security
• /
• 제24권1호
• /
• pp.163-177
• /
• 2024

The fingerprint image quality relies on the clearness of separated ridges by valleys and the uniformity of the separation. The condition of skin still dominate the overall quality of the fingerprint. However, the identification performance of such system is very sensitive to the quality of the captured fingerprint image. Fingerprint image quality analysis and enhancement are useful in improving the performance of fingerprint identification systems. A fuzzy technique is introduced in this paper for both fingerprint image quality analysis and enhancement. First, the quality analysis is performed by extracting four features from a fingerprint image which are the local clarity score (LCS), global clarity score (GCS), ridge_valley thickness ratio (RVTR), and the Global Contrast Factor (GCF). A fuzzy logic technique that uses Mamdani fuzzy rule model is designed. The fuzzy inference system is able to analyse and determinate the fingerprint image type (oily, dry or neutral) based on the extracted feature values and the fuzzy inference rules. The percentages of the test fuzzy inference system for each type is as follow: For dry fingerprint the percentage is 81.33, for oily the percentage is 54.75, and for neutral the percentage is 68.48. Secondly, a fuzzy morphology is applied to enhance the dry and oily fingerprint images. The fuzzy morphology method improves the quality of a fingerprint image, thus improving the performance of the fingerprint identification system significantly. All experimental work which was done for both quality analysis and image enhancement was done using the DB_ITS_2009 database which is a private database collected by the department of electrical engineering, institute of technology Sepuluh Nopember Surabaya, Indonesia. The performance evaluation was done using the Feature Similarity index (FSIM). Where the FSIM is an image quality assessment (IQA) metric, which uses computational models to measure the image quality consistently with subjective evaluations. The new proposed system outperformed the classical system by 900% for the dry fingerprint images and 14% for the oily fingerprint images.

• 대한한방내과학회지
• /
• 제41권4호
• /
• pp.624-643
• /
• 2020

Objectives: The aim of this study was to analyze the correlation between Ryodoraku and two pattern-identification questionnaires in patients with Burning Mouth Syndrome (BMS). Methods: The study participants were 30 patients with BMS who visited the Oral Diseases Clinic of Kyung Hee Oriental Medicine Hospital from June to November, 2019. The Ryodoraku test and two pattern-identification questionnaires were administered to all patients. Measurements included the average Ryodoraku score, which is called the Total Average (TA), and each score on the Ryodoraku point scale. The degree of Yin-deficiency, Qi-stagnation, and pain were assessed with the Yin-deficiency Questionnaire (YDQ), Qi-stagnation Questionnaire (QSQ), and Visual Analogue Scale (VAS), respectively. Results: The average TA score was 29.90. The LF5 (p=0.013) and RF5 (p=0.016) scores were lower than the TA scores, and the RH5 (p=0.020) and RH6 (p=0.006) scores were higher than the TA scores. A negative correlation was detected between the YDQ scores and the LH1 (r=-0.366, p=0.046), LH2 (r=-0.507, p=0.004), LH3 (r=-0.374, p=0.042), RH1 (r=-0.361, p=0.050), RH2 (r=-0.403, p=0.027) points. The LF5 (p=0.050) and RF2 (p=0.048) scores were lower in the patients with Qi-stagnation patients than without Qi-stagnation. Conclusions: Our results suggest that low TA and Ryodoraku scores on LF5 and RF5 and high Ryodoraku scores on RH5 and RH6 could be quantitative indicators for the diagnosis of BMS. The LH1, LH2, LH3, RH1, RH2, LF5, and RF2 scores could also be an indicators for diagnosis of Yin-deficiency and Qi-stagnation in patients with BMS.

• Journal of Korean Biological Nursing Science
• /
• 제17권3호
• /
• pp.262-270
• /
• 2015

Purpose: The purpose of this study was to explore the correlates of maternal perception (identification and satisfaction) of children's weight, maternal body shape satisfaction, and maternal feeding styles in Korean preschool-aged children. Methods: A cross-sectional survey design was utilized. Participants consisted of 287 pairs of preschool-aged children (3-6 years) and their mothers. Data were analyzed by ${\chi}^2$-test, Fisher's exact test, ANOVA, and the Pearson correlation coefficient. Results: Among the 287 mothers, 47.7% underestimated their children's weight, while 15.7% overestimated it. 46.7% of the mothers wished their children weighed more, while 11.1% of them wished their children weighed less. The mean score of maternal body shape satisfaction was $83.75{\pm}28.77$. The mean score of parent-centered feeding styles was $2.95{\pm}0.54$, and the mean score of child-centered feeding styles was $3.33{\pm}0.42$. There were statistically significant correlations between maternal identification of children's weight and children's body mass index (BMI) (r=-.366, p<.001). In addition, there were statistically significant correlations between maternal satisfaction of children's weight and children's BMI (r=-.484, p<.001), maternal BMI (r=-.126, p=.033), and maternal body shape satisfaction (r=-.127, p=.031). Conclusion: The results of the study suggest that intervention programs for mothers to develop more accurate perception of their child's weight should be established.

• 한방안이비인후피부과학회지
• /
• 제28권1호
• /
• pp.109-118
• /
• 2015

Objectives : We performed a clinical study to investigate characteristics of pattern identifications using nasal endoscopy for allergic rhinitis (AR). Methods : We assessed 32 patients with allergic rhinitis using nasal endoscopy, classifications of allergic rhinitis and it's impact on asthma (ARIA) and total nasal symptom score (TNSS). Results : The watery rhinorrhea score of nasal endoscopy was significantly high in 'persistent and moderate/severe' group (P<0.05). Patients were classified as rhinorrhea group and nasal obstruction group according to nasal endoscopy. TNSS and rhinorrhea score was significantly high in rhinorrhea group (P<0.05). Conclusions : The result may provide that the watery rhinorrhea of nasal endoscopy is useful as 'Cold' and 'Deficiency' pattern identification diagnostic tool.

• Journal of Trauma and Injury
• /
• 제25권4호
• /
• pp.241-246
• /
• 2012

Purpose: The objective of this study was to investigate the appropriateness of the cross table lateral cervical X-ray used in the emergency department for severely traumatized Korean patients. Methods: Patients visiting our institution from May 2011 to May 2012, who had injury severity score (ISS) > 15 and who received a cervical X-ray in the emergency department, were included in this study. Data including demographics, ISS score, GCS score, and place where the x-ray was taken were collected to evaluate their relationship with appropriate coverage of the cervical X-ray. The appropriateness of a cervical cross lateral view X-ray was evaluated using exposure of the basion, and the opisthion, as well as the distal level of exposure. Results: Fifty-two patients were included in this study. The identification rate of the basion was 79.2%, and the identification rate of the opisthion was 88.7%. Complete exposure of C7/T1 was accomplished in 3.8% of the patients. The ISS was higher for X-ray taken in the trauma bay, but the range of exposure showed no difference between the places where the X-rays taken. Patients who had exposure of C 5/6 or more had lower body weight and body mass index (BMI) compared with unexposed patients. Conclusion: In severely traumatized Korean patients, the adequacy of the cross table lateral cervical X-ray was inappropriate in most cases. No difference was observed in the exposure range between the places where the X-rays were taken, and patients with less exposure showed higher body weight and higher BMI.