Ahmed Rehan, Temko Andrey, Marnane William, Boylan Geraldine, Lighbody Gordon
Department of Electrical and Electronic Engineering and the Neonatal Brain Research Group, University College Cork, Ireland.
Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:4919-22. doi: 10.1109/EMBC.2012.6347097.
Neonatal seizures patterns evolve with changing frequency, morphology and propagation. This study is an initial attempt to incorporate the characteristics of temporal evolution of neonatal seizures into our developed neonatal seizure detector. The previously designed SVM-based neonatal seizure detector is modified by substituting the Gaussian kernel with the Gaussian dynamic time warping kernel, to enable the SVM to classify variable length sequences of feature vectors of neonatal seizures. The preliminary results obtained compare favorably with the conventional SVM. The fusion of the two approaches is expected to improve the current state of the art neonatal seizure detection system.
新生儿癫痫发作模式会随着频率、形态和传播方式的变化而演变。本研究是将新生儿癫痫发作的时间演变特征纳入我们开发的新生儿癫痫发作检测器的初步尝试。通过用高斯动态时间规整核替代高斯核，对先前设计的基于支持向量机的新生儿癫痫发作检测器进行了改进，以使支持向量机能对新生儿癫痫发作特征向量的可变长度序列进行分类。所获得的初步结果与传统支持向量机相比具有优势。预计这两种方法的融合将改善当前最先进的新生儿癫痫发作检测系统。
Zotero 插件