http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
한의진단명과 진단요건의 표준화 연구 III : 3차년도 연구결과 보고
최선미,양기상,최승훈,박경모,박종현,심범상,김성우,노석선,이인선,정진홍,이진용,김달래,임형호,김윤범,박성식,송태원,김종우,이승기,최윤정,신순식 한국한의학연구원 1997 한국한의학연구원논문집 Vol.3 No.1
The diagnostic requirements were suggested and explained regarding the systems of differentiation of symptoms and signs in the third year study of standardization and unification of the terms and conditions used for diagnosis in oriental medicine. The systems were as follows : - analyzing and differentiating of epidemic febrile disease - analyzing and differentiating in accordance with the Sasang constitution medicine based on four-type recognition - differentiation of disease according to pathological changes of Chong and Ren channels - standards for diagnosis of women's disease - standards for diagnosis of children's disease - standards for diagnosis of motor and sensor disturbance (-muscle. born, joint, etc.) - standards for diagnosis of neuropsychiatric disease - standards for diagnosis of five sense organ disease - standards for diagnosis of external disease The indivisual diagnosis pattern was arranged by the diagnostic requirements in the following order : another name, notion of diagnosis pattern, index of differentiation of symptoms and signs, the main point of diagnosis, analysis of diagnosis pattern, discrimination of diagnosis pattern, prognosis, a way of curing a disease, prescription, herbs in common use, disease appearing the diagnosis pattern, documents. The standards for diagnosis of each disease was arranged by the diagnostic requirements in the following order : another name, notion of disease, the main point of diagnosis, analyzing and differentiating of disease, analysis of disease, discrimination of disease, prognosis, a way of curing and prescription of disease, disease in western medicine appearing the disease in oriental medicine, documents.
Fuzzy Learning Vector Quantization based on Fuzzy k-Nearest Neighbor Prototypes
Roh, Seok-Beom,Jeong, Ji-Won,Ahn, Tae-Chon Korean Institute of Intelligent Systems 2011 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.11 No.2
In this paper, a new competition strategy for learning vector quantization is proposed. The simple competitive strategy used for learning vector quantization moves the winning prototype which is the closest to the newly given data pattern. We propose a new learning strategy based on k-nearest neighbor prototypes as the winning prototypes. The selection of several prototypes as the winning prototypes guarantees that the updating process occurs more frequently. The design is illustrated with the aid of numeric examples that provide a detailed insight into the performance of the proposed learning strategy.