穿戴式跌倒检测中特征向量的提取和降维研究

Abstract: In wearable fall detection of the elderly, too much characteristics will cause the curse of dimensionality, and affect the accuracy of subsequent fall detection. To solve this problem, this paper uses time domain analysis method to extract feature vector. Then the proposed improved kernel principal component analysis (IKPCA) algorithm is used to reduce the feature vectors, so as to obtain high-quality feature vectors, which makes the subsequent classification more effective. IKPCA algorithm firstly uses the I-RELIEF algorithm to select the initial feature vectors, then calculate the information measure and similarity measure of the falling feature vectors. Finally, according to the similarity measurement of the falling feature vectors, the invalid falling feature vectors are eliminated. The IKPCA algorithm not only keeps better dimensionality reduction ability of the Kernel Principle Component Analysis (KPCA) algorithm, but also expands better classification ability. It experiments on real data sets. The comparative analysis shows that, compared with other algorithms, the IKPCA algorithm can obtain higher-quality feature vector data set.