We propose a new method for tumor classification from gene expression data, which mainly contains three steps. Firstly, the original DNA microarray gene expression data are modeled by independent component analysis （...We propose a new method for tumor classification from gene expression data, which mainly contains three steps. Firstly, the original DNA microarray gene expression data are modeled by independent component analysis （ICA）. Secondly, the most discriminant eigenassays extracted by ICA are selected by the sequential floating forward selection technique. Finally, support vector machine is used to classify the modeling data. To show the validity of the proposed method, we applied it to classify three DNA microarray datasets involving various human normal and tumor tissue samples. The experimental results show that the method is efficient and feasible.展开更多
高血压是危害人类健康的首要疾病,方便准确的血压测量方法将有助于高血压的防控。本文提出了一种基于面部视频信号的连续血压测量方法。采用颜色失真滤波与独立成分分析法提取面部视频信号中感兴趣区域的视频脉搏波,基于时频域以及生理...高血压是危害人类健康的首要疾病,方便准确的血压测量方法将有助于高血压的防控。本文提出了一种基于面部视频信号的连续血压测量方法。采用颜色失真滤波与独立成分分析法提取面部视频信号中感兴趣区域的视频脉搏波,基于时频域以及生理学原理对脉搏波进行多维特征提取;设计了一种集成特征选择方法提取具有通用性的最优特征子集;比较基于粒子群优化的Elman神经网络、支持向量机与深度信念网络所建立的单人血压测量模型;采用支持向量回归算法构建通用血压预测模型,并与真实血压值进行比较与评价。实验结果表明:基于面部视频的血压测量结果与标准血压值具有较好的一致性,由视频估计出的收缩压与标准收缩压的平均绝对误差(MAE)为4.9 mm Hg,标准差(STD)为5.9 mm Hg;舒张压的MAE为4.6 mm Hg,STD为5.0 mm Hg,符合AAMI标准。本文所提出的基于视频流的非接触式血压检测方法可以用于血压的测量。展开更多
基金the National Natural Sci-ence Foundation of China (No. 30700161)the Na-tional High-Tech Research and Development Program(863 Program) of China (No. 2007AA01Z167 and2006AA02Z309)+1 种基金China Postdoctoral Science Foun-dation (No. 20070410223)Doctor Scientific Re-search Startup Foundation of Qufu Normal University(No. Bsqd2007036).
文摘We propose a new method for tumor classification from gene expression data, which mainly contains three steps. Firstly, the original DNA microarray gene expression data are modeled by independent component analysis （ICA）. Secondly, the most discriminant eigenassays extracted by ICA are selected by the sequential floating forward selection technique. Finally, support vector machine is used to classify the modeling data. To show the validity of the proposed method, we applied it to classify three DNA microarray datasets involving various human normal and tumor tissue samples. The experimental results show that the method is efficient and feasible.
文摘高血压是危害人类健康的首要疾病,方便准确的血压测量方法将有助于高血压的防控。本文提出了一种基于面部视频信号的连续血压测量方法。采用颜色失真滤波与独立成分分析法提取面部视频信号中感兴趣区域的视频脉搏波,基于时频域以及生理学原理对脉搏波进行多维特征提取;设计了一种集成特征选择方法提取具有通用性的最优特征子集;比较基于粒子群优化的Elman神经网络、支持向量机与深度信念网络所建立的单人血压测量模型;采用支持向量回归算法构建通用血压预测模型,并与真实血压值进行比较与评价。实验结果表明:基于面部视频的血压测量结果与标准血压值具有较好的一致性,由视频估计出的收缩压与标准收缩压的平均绝对误差(MAE)为4.9 mm Hg,标准差(STD)为5.9 mm Hg;舒张压的MAE为4.6 mm Hg,STD为5.0 mm Hg,符合AAMI标准。本文所提出的基于视频流的非接触式血压检测方法可以用于血压的测量。
