摘要
基于模糊模式识别的基本理论,阐述了肿瘤周边组织拉曼光谱的预处理、特征提取和选择,根据这些特征改进了梯形分布的偏大型隶属函数,在40例样本的基础上建立了肿瘤周边组织拉曼光谱对恶性肿瘤的隶属函数,并根据此函数进行了分类器的训练学习,经过另40例样本的测试,恶性肿瘤的识别率为82.4%,非恶性肿瘤的识别率为73.9%,识别效果较为理想。
On the basis of some theories about fuzzing pattern recognition, the present article studied the data preprocessing of the Ramam spectrum of tumor peripheral tissue, and feature extraction and selection. According to these features the authors improved the leaning towards the bigger membership function of trapezoidal distribution. The authors built the membership function of Raman spectrum of tumor peripheral tissue which belongs to malignant tumor on the basis of 40 specimens, and designed the elassifier. The test of other 40 specimens showed that the discrimination of malignant tumor is 82.4%, while that of beginning tumor is 73. 9 %.
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
2006年第6期1076-1079,共4页
Spectroscopy and Spectral Analysis
基金
国家自然科学基金(10205013)
河南省高校创新人才基金(1999-125)资助
