This report analyzes the existing problems in terminology referring to clinical symptoms of traditional Chinese medicine(TCM)from the viewpoint of data sharing and elaborates the necessity of establishing a standard d...This report analyzes the existing problems in terminology referring to clinical symptoms of traditional Chinese medicine(TCM)from the viewpoint of data sharing and elaborates the necessity of establishing a standard directory of clinical data elements of TCM.We evaluated the principles and methods of data element extraction according to the status quo of the clinical information system and characteristics of symptoms for TCM and consequently proposed a three-layer model for optimal extraction.展开更多
文摘WML-kN N(weighted multi-label k nearest neighbor)算法中近邻点个数取固定值,而没有考虑样本数据的实际特点,可能会将相似度高的点排除在近邻集外,或者将相似度低的点包含在近邻集内,这些都会影响分类器的性能。而中医(traditional Chinese medicine,TCM)临床获得的关于疾病的数据很可能是多标记的,同时由于病例的特殊性,每个病例可能具有不同的相似近邻集。因此,对WML-kNN算法进行了改进,提出WML-GkN N(WML-granular kNN)算法。该算法通过粒计算对粒度空间进行控制,从而确定近邻点集,使得邻域内的样本点有高相似性。在中医临床采集的经络电阻数据上的实验结果显示,WML-GkNN算法提高了分类性能。
基金funding support from the Innovation Platform Open Fund Project of Hunan Provincial Universities (No. 13K076)National Key Discipline Open Fund Project of TCM diagnostics in Hunan University of Chinese Medicine (2015zyzd18)
文摘This report analyzes the existing problems in terminology referring to clinical symptoms of traditional Chinese medicine(TCM)from the viewpoint of data sharing and elaborates the necessity of establishing a standard directory of clinical data elements of TCM.We evaluated the principles and methods of data element extraction according to the status quo of the clinical information system and characteristics of symptoms for TCM and consequently proposed a three-layer model for optimal extraction.
