• 제목/요약/키워드: classification skin

검색결과 234건 처리시간 0.024초

농약 품목에 대한 GHS 기준과 농진청 기준에 따른 자극성 산출 후 자극성 분류 차이 비교 (Comparison of Differences between the Results of Irritation Classification after Irritation Calculation with GHS Criteria and RDA Directives in Plant Protection Products)

  • 유아선;오진아;박수진;조유미;이제봉;이난희;이주연;임양빈
    • 농약과학회지
    • /
    • 제20권4호
    • /
    • pp.326-340
    • /
    • 2016
  • 농약의 원제에 대한 GHS 체계 도입에 따라 농약 품목에 대한 GHS 도입 필요성이 대두되고 있어 GHS 도입 시 현행과의 평가 기준을 비교하였다. 농약 59 품목의 독성시험성적에 대하여 농약관리법과 GHS에 따라 피부자극성 및 안점막자극성을 산출 및 분류한 결과, 피부자극성 경도 및 중도로 분류된 품목에서 GHS 기준에 의해 '분류되지 않음'으로 구분된 품목이 전체의 25.5%였고 안점막자극성 경도에서 GHS 기준에 의해 '분류되지 않음'으로 구분된 품목이 45.8%로 나타나 자극성 구분이 완화되었다. 반면 비가역적 반응의 평가에 의해 경도와 중도에서 피부자극성이 피부부식성 구분 1로 보다 높게 평가된 품목이 6.8%, 안점막자극성이 심한 눈손상 구분 1로 보다 높게 평가 된 품목이 5.1%였다. 농약 품목의 시험성적을 이용한 GHS 분류와 품목에 함유된 원제의 자극성 구분과 함유량을 이용하여 GHS 혼합물 분류기준에 따라 분류한 결과를 비교한 결과, 피부자극성에서는 25.5% 품목의 자극성 구분이 완화되었고, 3.4% 품목의 자극성 구분이 강화되었다. 안점막자극성에서는 25.4%의 품목에 대한 자극성 구분이 완화되었고 11.9%의 품목의 자극성 구분이 강화되었다. 농약 품목에 GHS를 도입할 경우, 상이한 분류 결과를 보완할 수 있는 방안 마련이 필요하다고 사료된다.

기계적 평가와 이미지를 이용한 얼굴의 번들거림과 윤기의 분류 기준의 연구 (The Differentiation Criteria between Greasiness and Shininess on The Face Using Mechanical Evaluation and Image)

  • 장윤정;김보라;문태기;김남수;이선화;이혜지
    • 대한화장품학회지
    • /
    • 제44권3호
    • /
    • pp.231-238
    • /
    • 2018
  • 얼굴 피부는 신체 건강을 표현할 뿐만 아니라 매력을 결정하는 요소 중 하나이다. 특히 윤기 나는 피부는 대부분의 사람들이 선호하며 윤기 나는 피부 표현을 위해 다양한 화장품들이 만들어져왔다. 하지만 윤기 있는 피부는 주관적 평가이기 때문에 기름진 피부의 경우 기존의 피부 윤기 평가 방법으로는 명확한 윤기 있는 피부로 평가하기가 어렵다. 더욱이 윤기와 유사하게 광이 있지만 부정적으로 평가되는 번들거리는 피부와 명확한 분류 기준 또한 없는 상황이다. 본 연구에서는 피부측정 파라미터 5개[피부 광채, 피부 보습, 피부 투명도, 피부 피지, 안면 이미지]를 측정하였고, 연구대상자들이 촬영된 안면 이미지를 근거하여 각각의 윤기 있는 피부와 번들거리는 피부의 이미지를 선별하여 피부 측정의 정량화를 통해 비교 분석하였다. 그 결과 번들거리는 피부에서 피부 광채 및 피지 증가, 투명도 감소, 보습 감소를 확인하였다. 그러나 윤기 있는 피부의 경우 피부 광채, 피지, 투명도는 유사한 패턴을 보였지만 보습이 유의차 있게 증가하는 결과를 보였다. 본 연구에서는 기기측정 및 정량적 평가를 통해서 윤기 있는 피부와 번들거리는 피부를 분류하는 객관적 평가 기준을 제시하고자 한다.

Half-Against-Half Multi-class SVM Classify Physiological Response-based Emotion Recognition

  • ;고광은;박승민;심귀보
    • 한국지능시스템학회논문지
    • /
    • 제23권3호
    • /
    • pp.262-267
    • /
    • 2013
  • The recognition of human emotional state is one of the most important components for efficient human-human and human- computer interaction. In this paper, four emotions such as fear, disgust, joy, and neutral was a main problem of classifying emotion recognition and an approach of visual-stimuli for eliciting emotion based on physiological signals of skin conductance (SC), skin temperature (SKT), and blood volume pulse (BVP) was used to design the experiment. In order to reach the goal of solving this problem, half-against-half (HAH) multi-class support vector machine (SVM) with Gaussian radial basis function (RBF) kernel was proposed showing the effective techniques to improve the accuracy rate of emotion classification. The experimental results proved that the proposed was an efficient method for solving the emotion recognition problems with the accuracy rate of 90% of neutral, 86.67% of joy, 85% of disgust, and 80% of fear.

다중 모달 생체신호를 이용한 딥러닝 기반 감정 분류 (Deep Learning based Emotion Classification using Multi Modal Bio-signals)

  • 이지은;유선국
    • 한국멀티미디어학회논문지
    • /
    • 제23권2호
    • /
    • pp.146-154
    • /
    • 2020
  • Negative emotion causes stress and lack of attention concentration. The classification of negative emotion is important to recognize risk factors. To classify emotion status, various methods such as questionnaires and interview are used and it could be changed by personal thinking. To solve the problem, we acquire multi modal bio-signals such as electrocardiogram (ECG), skin temperature (ST), galvanic skin response (GSR) and extract features. The neural network (NN), the deep neural network (DNN), and the deep belief network (DBN) is designed using the multi modal bio-signals to analyze emotion status. As a result, the DBN based on features extracted from ECG, ST and GSR shows the highest accuracy (93.8%). It is 5.7% higher than compared to the NN and 1.4% higher than compared to the DNN. It shows 12.2% higher accuracy than using only single bio-signal (GSR). The multi modal bio-signal acquisition and the deep learning classifier play an important role to classify emotion.

종골 골절의 치료-광범위 외측 접근법 (Calcaneal Fractures-Extended Lateral Approach)

  • 천성광;김학준
    • 대한족부족관절학회지
    • /
    • 제17권2호
    • /
    • pp.79-83
    • /
    • 2013
  • Calcaneus is largest tarsal bone and the fracture of calcaneus is most common tarsal fractures. Calcaneal fractures are divided into extra-articular and intra-articular fractures. Intra-articular calcaneal fractures could be classified as tongue type and joint depression type using simple lateral radiograph (Essex-Lopresti classification), but Sanders suggested new classification according to involving the posterior facet of calcaneus using computed tomography. The involvement of posterior facet was revealed as more complicated than Essex-Lopresti classification. The principle purpose of treatment of calcaneal fractures are restoration of calcaneal height (B$\ddot{o}$hler angle), width, axis, anatomical reduction of joint and restoration of function through the stable fixation. Good visualization of joint and anatomical reduction could be achieved by extended lateral approach. But, skin problem could be occurred after of extended lateral approach.

전이동 78예 및 전이 피부 부속기 28예에 대한 임상 경험 (Experience with 78 Cases with Preauricular Sinus and 28 Cases with Preauricular Skin Tag)

  • 이경근;김민수;정풍만
    • Advances in pediatric surgery
    • /
    • 제9권1호
    • /
    • pp.1-5
    • /
    • 2003
  • Preauricular sinus and preauricular skin tag are common childhood congenital anomalies. It is important for the pediatric surgeon to be familiar with the embryology and differentiation of head and neck structure to accurately diagnose and treat these lesions. Seventy eight patients with preauricular sinus and twenty-eight with preauricular skin tag treated in the Department of Pediatric Surgery at Hanyang University Hospital from January 1981 to May 2002 were reviewed to determine relative frequency, clinical classification and appropriate treatment. The male to female ratio of preauricular sinus was 1:1.2, and preauricular skin tag was 1:1. The most commonly presenting age of sinus and skin tag was before 5 year (62.8%) and before 1 year (53.6%). Twenty nine of 78 cases of preauricular sinuses were on the left, 25 on the right and 24 bilateral. Signs of infection were seen in 73.0% of patients with preauricular sinus at operation. Only 31.3% of lesions were infected in patients less than one year of age, but 89.5% between 3-5 years and 100% between 5-8 years. Cartilage was present in five patients with preauricular skin tag. Although re-operation due to wound infection was necessary in four cases, no recurrences were found. The preauricular sinus is a common anomaly in childhood, and has had a relatively high recurrence rate. But most of the recurrences were due to incomplete resection because of combined infection. Initial proper diagnosis and early operation are very important. Identification of the exact anatomical location of sinus tract is necessary because total excision of the lesions including those tracts is the only way to prevent recurrence.

  • PDF

고령자의 손등피부 탄성 특성을 활용한 체질분류 방법 연구 (Study of Sasang Constitution Classification Method Based on Elasticity Coefficient of Hand Doral Skin of Elderly People)

  • 강남식;이재철;구본초;김종열;김영민
    • 동의생리병리학회지
    • /
    • 제25권6호
    • /
    • pp.1050-1055
    • /
    • 2011
  • This paper presents a novel diagnostic method to determine Sasang Consitution (SC) by elasticity coefficient of hand dorsal skin of elderly people. For this purpose, we carried out a clinical test, in which Our SC diagnostic tool and one Oriental medical doctor with SC medicine expertise participated to categorize 458 healthy subjects into four constitutions. After excluding heavy-noise, we extracted 295 subjects' elasticity coefficient feature data and statistically analyzed their SC relevance with ANOVA test. It resulted in that, Taeum-in has high elasticity coefficient compared to Soeum-in in a significance level of 0.05. There are no differences of elasticity coefficient in genders. This result is supported by the theory of Longevity and Life Preservation in Eastern Medicine(Donguisusebowon, 동의수세보원) which suggested that Taeum-in's flesh is solid and Soeum-in's one is tender. This is the first work which reports the relatedness of skin elasticity coefficient and SC by an objective clinical test.

FACE DETECTION USING SKIN-COLOR MODEL AND SUPPORT VECTOR MACHINE

  • Seld, Yoko;Yuyama, Ichiro;Hasegawa, Hiroshi;Watanabe, Yu
    • 한국방송∙미디어공학회:학술대회논문집
    • /
    • 한국방송공학회 2009년도 IWAIT
    • /
    • pp.592-595
    • /
    • 2009
  • In this paper, we propose a face detection technique for still pictures which sequentially uses a skin-color model and a support vector machine (SVM). SVM is a learning algorithm for solving the classification problem. Some studies on face detection have reported superior results of SVM over neural networks. The SVM method searches for a face in a picture while changing the size of the window. The detection accuracy and the processing time of SVM vary largely depending on the complexity of the background of the picture or the size of the face. Therefore, we apply a face candidate area detection method using a skin-color model as a preprocessing technique. We compared the method using SVM alone with that of the proposed method in respect to face detection accuracy and processing time. As a result, the proposed method showed improved processing time while maintaining a high recognition rate.

  • PDF

인터넷을 통한 건강 상담의 내용 분석 (An Analysis of Health Counseling by the Internet)

  • 안지영
    • 간호행정학회지
    • /
    • 제6권1호
    • /
    • pp.83-96
    • /
    • 2000
  • With the increased use of computers in medical fields, we can consider introducing computer mediated communication into the area of patient care such as medical or health counseling and education. But little was known about what problems can be counseled, what is the main direction of counseling, and what difficulties are met during the computer mediated counseling. So I conducted this study. This is a fundamental study concerning the health counseling by the inter-net. In this study, medical counseling using a method of questioning -answering through a computer mediated communication system was carried out from June 1998 to May 1999. I analyzed the contents of questions and answers by the ICPC classification. The ICPC classification emerged as a standard for information categorization in Primary Health Care within a few years. One of the most prominent features of this classification is the inclusion of the complaints of the patients (symptoms & complaints) and the social problems (Chapter Z). Thus, and for the first time, the demand of patients may be assessed such as it is expressed in the reality. The ICPC list is now an international standard whose validity is not questioned any more. It is translated in more than twenty different languages. The data collected were analyzed by descriptive statistical method, c2 test by cross tabulations. Followings are the results of this study. 1. The 3,054 users composed of 64% of males and 36% of females. The highest number of users was showed in the age group of $25{\sim}29$ (39.4%). 2. During the one-year period, the average number of counseling per user was 2.5 cases and per day was 21.1 cases. 3. In classifying symptoms and complaints by 17 chapter, digestive(17.6%), general and unspecified (12.7%), skin(12.7%) and musculoskeletal system (9.6%) were most common questions. 4. The distribution of diagnosis by 17 chapter, general and unspecified (21.4%), digestive (15.3%), skin (11.9%) and mus- culoskeletal system (8.9%) were most common answers. 5. Many users wanted to know symptoms and complaints(3,609 cases), treatment principles (2,928 cases), prognosis and preventive methods for health problems which were previously diagnosed (284 cases).

  • PDF