• 전자공학회논문지SC
• /
• 제43권4호
• /
• pp.11-20
• /
• 2006

본 논문에서는 초분광 형광영상과 반사영상 융합을 이용한 닭의 종양인식방법을 제안하였다. 형광영상에 밴드비율을 적용하여 피부의 정상과 종양부분을 구분한다. 이를 위해 각각 부분의 확률밀도함수의 중첩된 면적을 최소화하는 방법을 사용하였다. 이 방법으로 획득한 4개의 특정영상에 분할-합병법을 적용하여 형광영상 분류결과를 얻었다. 반사영상 분석에서는 단일 밴드가 정보량에 주는 영향에 근거하여 밴드 선택 방법을 제안하였다. 학습데이터에 의해 투영 축을 선택하는 선형변환을 정의함으로써 영상분류에 효과적인 많은 특징을 확보하였다. 이에 따라 반사영상에서도 세밀한 영상의 해석이 가능하였고 특징 선택의 자동화를 실현하였다. 반사영상에서 획득한 특정영상도 분할-합병법으로 분류하였으며 형광영상의 분류결과와 융합하여 종양을 인식하였다. 모의실험을 통해 제안한 방법은 기존의 방법에 비해 오인식이 낮음을 확인하였다.

• 한방안이비인후피부과학회지
• /
• 제33권2호
• /
• pp.112-129
• /
• 2020

Objectives : The aim of this study is to explore the types of pattern identification (PI, 辨證) and the differential points of PI used for the treatment of psoriasis in Traditional Chinese Medicine (TCM) based on the Chinese references and to provide the evidences applying PI for the treatment of psoriasis in clinical practice. Methods : This study extracted patterns of psoriasis through database CNKI (China National Knowledge Infrastructure) and analysis the patterns and classification criteria of the patterns. Those examined in the study are dermal symptoms, general symptoms, formula and herbs which are different depending on the patterns. Results : Total 60 studies were selected and 44 pattern types were extracted from them. We categorized the main pattern types on psoriasis used in TCM as 'blood-heat syndrome(BHS, 血熱證)', blood-stasis syndrome(BSS, 血瘀證), and 'blood-dryness syndrome(BDS, 血燥證)', 'dampness-heat syndrome(DHS, 濕熱證)' and 'yang-deficiency syndrome(YDS, 陽虛證)'. Among these patterns, BHS was the most common. In TCM, the pattern of BHS tended to have skin symptoms and signs related to inflammatory erythema and heat. Both BSS and BDS were characterized by long disease duration and poor healing. In addition, DHS tended to have the skin symptoms and signs such as oozing and severe itching. The symptoms and signs related to coldness mainly showed in YDS. For PI criteria, 'qi-blood-essence criteria(氣血津液辨證)' and 'eight-doctrine criteria(八鋼辨證) are commonly used. Conclusions : Our findings show that each PI on psoriasis in TCM has different characteristics related to dermal and general symptoms or signs. Further studies are needed to develop the diagnostic tool of PI on psoriasis reflecting on clinical practices in Korean Medicine by referring to the findings of this study about PI on psoriasis in TCM.

• 대한간호학회지
• /
• 제29권1호
• /
• pp.72-83
• /
• 1999

The purpose of this study was to classify, from collected home health care records data, nursing diagnoses according to the NANDA system and nursing interventions according to the NIC system, and to link nursing interventions to nursing diagnoses. For this study, 101 home health care records of clients seen between September, 1994 and November, 1996 at Yonsei Medical Center, Seoul, were analyzed. The results of this study are summarized as follows : 1. The most frequent nursing diagnoses were ‘Risk for infection’ and ‘Altered nutrition : Less than body requirements’, then ‘Impaired skin intergrity’ and ‘Ineffective airway clearance’ in the Exchange pattern of NANDA nine human response patterns. 2. The most frequent nursing interventions were the interventions in the Physiological : Complex domain, there were 690(50.7%) interventions among a total 1347 interventions. This results corresponds to Yom, Young Hee(1995)’s research, both Korean and U.S. nurses used the interventions in the Physiological : Complex do main most often on a daily basis. And respiratory nursing interventions were most frequent because 32.7% of the subjects were respiratory patients. 3. The next step was to link the nursing interventions to nursing diagnoses. The most frequent nursing diagnosis was ‘Risk for infection’ and 19 interventions for ‘Risk for infection’ were used 267 times. Then 14 interventions for ‘Impaired skin integrity’ were used 258 times, 12 interventions for ‘Ineffrective airway clearance’ were used 193 times, 12 interventions for ‘Altered nutrition : Less than body requirements’ were used 122 times, 10 interventions for ‘Activity intolerance’ were used 75 times, and 11 interventions for ‘Knowledge deficit’ were used 52 times. 4. The use of standardized classification in the areas of nursing diagnoses and nursing interventions facilitates clinical decision making and prompt nursing activity, and so enhances the effectiveness of nursing care.

• 스마트미디어저널
• /
• 제10권4호
• /
• pp.45-54
• /
• 2021

피부는 외부 오염으로부터 일차적으로 몸을 보호하는 역할을 한다. 피부병이 발생하게 되면 피부의 보호 기능이 저하되므로 신속한 진단과 처치가 필요하다. 최근 인공지능의 발달로 인해 여러 분야에 기술적용을 위한 연구가 이루어지고 있으며, 피부과에서도 인공지능을 활용해 오진율을 줄여 신속한 치료를 받을 수 있는 환경을 만들기 위한 연구가 진행되고 있다. 종래 연구들의 주된 흐름은 발생 빈도가 낮은 피부질환의 진단이었지만, 본 논문에서는 사람들에게 흔히 발생할 수 있고, 개인이 명확히 판별하기 힘든 티눈과 사마귀를 합성곱 신경망을 통해 분류하는 방법을 제안한다. 사용한 데이터셋은 3개의 클래스로 이루어져 있으며, 총 2,515장의 이미지를 가지고 있다, 학습 데이터 부족과 클래스 불균형 문제가 존재한다. 모델의 학습에는 deep metric 손실 함수와 교차 손실 함수를 이용해 각각 성능을 분석하였으며, 정밀도, 재현율, F1 점수, 정확도의 측면에서 비교한 결과 deep metric 손실 함수에서 더 우수한 성능을 보였다.

• 정보처리학회논문지B
• /
• 제15B권1호
• /
• pp.17-24
• /
• 2008

본 논문에서는 사상 체질 분류를 음성 분석 정보값의 비교, 분석을 통해 제안하고자 한다. 이를 위해 본 논문에서는 사상체질의 객관적 지표를 마련하기 위한 전체 시스템 구성 중 1차 단계로써 피부 진단을 통한 소음인의 분류 과정과 연계하여 음성 신호 분석에서 발생하는 정보의 출력값에 의해 태음인을 분류하는 방법을 제안하고자 한다. 우선 각 사상 체질별로 뚜렷한 특징을 보유하고 있는 집단군을 구성하고 이들의 음성 특성을 분류하여 음성학적 요소를 추출하고자 한다. 또한 출력된 결과값을 토대로 체질 집단별 차이점과 유사점을 통하여 태음인을 분류하고자 한다. 끝으로 실험에 의해 제안한 방법의 유용성을 입증하고자 한다.

• Journal of Acupuncture Research
• /
• 제33권1호
• /
• pp.69-77
• /
• 2016

Objectives : The objective of this study is to review external approaches using acupuncture and related treatments of hyperpigmentation disorders and their classification in traditional medicine. Methods and Results : Hyperpigmentation was recorded for the first time in Treatise on the Pathogenesis and Manifestations of All Diseases published in 610 A.D. This suggests that the symptom has already been recognized as an independent disease in East Asia for more than 1,400 years. Over the course of several centuries, there has been a significant evolution in the traditional treatments for hyperpigmentation. There are many different types of therapy, including body acupuncture, intradermal acupuncture, ear acupuncture, ear acupressure, blood-letting treatment, pharmacopuncture, plum-blossom needle therapy, burning acupuncture therapy, moxibustion, and guasha. In addition, the traditional classification of hyperpigmentation has been changing shape. However, no attempts have been made to establish the academic linkage between the modern classification of hyperpigmentation disorders and the traditional one, on account of different concepts and names of the ailment. This study was designed in an attempt to identify the linkage of the categorization of the Korean Standard Classification of Disease (KCD) and the traditional classification. Conclusions : Through this literature review, we found that there has been a significant evolution in the treatment of hyperpigmentation disorders in East Asia. Traditional medical treatment for skin disease, including hyperpigmentation, is expected to be further developed with the advancement of science and technology.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권9호
• /
• pp.1161-1170
• /
• 2004

본 논문에서는 군집화 알고리즘을 사용하여 피부색 영역을 분할하는 방법을 제안한다. 기존의 군집화 알고리즘들의 대부분은 주로 구형의 군집을 검출하고, 배치형으로 수행되며, 군집의 개수를 미리정해야 한다는 문제점을 가지고 있다. 본 논문에서는 대표적인 타원형 군집화 알고리즘인 EM 알고리즘을 변형하여, 온라인으로 학습가능하며, 군집의 개수를 자동적으로 찾아낼 수 있는 EAM 알고리즘을 사용하였다. EAM 알고리즘외 유효성은 피부색 영역 분할에 대해 증명되었다. 실험결과는 군집의 개수가 미리 주어지지 않더라도, EAM 알고리즘은 주어진 영상에 대해 자동적으로 옳은 군집의 개수를 찾아냈고, EM 알고리즘과 비교하여 더 좋은 분할 결과를 보여주고 있다. 영역에 대한 조건부 확률을 이용하여 성공적인 피부색 영역의 탐지 및 분할 결과를 얻었다. 또한 사람이 포함된 영상을 분류하는 문제에도 적용하여 좋은 분류 결과를 얻었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.144-145
• /
• 2012

메이크업이란 신체와 얼굴을 화장품을 이용하여 보호하거나 단점을 보완하여 아름답게 꾸미는 행위를 뜻한다. 본 논문에서는 이러한 메이크업의 분류 및 종류를 현 시대에 맞도록 새롭게 편성해 보았다. 그리고 메이크업의 의미를 새롭게 알아보았다. 메이크업은 외부의 변화로부터 피부를 보호해준다. 그리고 피부의 결점을 감춰주고 아름답게 해주는 미화 기능을 살려준다. 따라서 외모에 자신감을 주어 능동적이고 적극적으로 사회생활을 할 수 있도록 해 준다.

• 재활간호학회지
• /
• 제14권1호
• /
• pp.62-69
• /
• 2011

Purpose: The study assessed whether nurse staffing was associated with 3 nursing sensitive outcomes used in intensive care unit (ICU) nursing care plans. Methods: This study was a retrospective and descriptive study using clinical data extracted from the data warehouse of a large acute care hospital in the Midwest. One-way analysis of variance was used to analyze the records of 578 ICU patients admitted from March 25 to May 31, 2010. Results: 79 Nursing Outcomes Classification (NOC) outcomes were used in the nursing care plans. The 3 most commonly used NOC outcomes (Pain Level, Infection Severity, and Tissue Integrity: Skin and Mucous Membranes) were analyzed to determine their relationship to nurse staffing. As a nurse staffing ratio, the skill mix of nursing caregivers ranged from 0.74 to 1 with an average of 0.90. This skill mix of nursing caregivers significantly differed among the changes in Infection Severity scores. However, the mean difference was only 0.02. Conclusion: The results did not support that greater nurse staffing was associated with better outcomes. More research is still needed to determine the usefulness of Pain Level, Infection Severity, and Tissue Integrity: Skin and Mucous Membranes in evaluating the impact of nurse staffing.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.1252-1255
• /
• 2002

In this paper, face recognition algorithm, by using skin color information of HSI color coordinate collected from face images, elliptical mask, fratures of face including eyes, nose and mouth, and geometrical feature vectors of face and facial angles, is proposed. The proposed algorithm improved face region extraction efficacy by using HSI information relatively similar to human's visual system along with color tone information about skin colors of face, elliptical mask and intensity information. Moreover, it improved face recognition efficacy with using feature information of eyes, nose and mouth, and Θ1(ACRED), Θ2(AMRED) and Θ 3(ANRED), which are geometrical face angles of face. In the proposed algorithm, it enables exact face reading by using color tone information, elliptical mask, brightness information and structural characteristic angle together, not like using only brightness information in existing algorithm. Moreover, it uses structural related value of characteristics and certain vectors together for the recognition method.