Swami Piyush, Bhatia Manvir, Tripathi Manjari, Chandra Poodipedi Sarat, Panigrahi Bijaya K, Gandhi Tapan K
Centre for Biomedical Engineering, Indian Institute of Technology - Delhi, New Delhi 110 016, India.
Department of Electrical Engineering, Indian Institute of Technology - Delhi, New Delhi 110 016, India.
Healthc Technol Lett. 2019 Jul 26;6(5):126-131. doi: 10.1049/htl.2018.5051. eCollection 2019 Oct.
The significant research effort in the domain of epilepsy has been directed toward the development of an automated seizure detection system. In their usage of the electrophysiological recordings, most of the proposals thus far have followed the conventional practise of employing all frequency bands following signal decomposition as input features for a classifier. Although seemingly powerful, this approach may prove counterproductive since some frequency bins may not carry relevant information about seizure episodes and may, instead, add noise to the classification process thus degrading performance. A key thesis of the work described here is that the selection of frequency subsets may enhance seizure classification rates. Additionally, the authors explore whether a conservative selection of frequency bins can reduce the amount of training data needed for achieving good classification performance. They have found compelling evidence that using spectral components with <25 Hz frequency in scalp electroencephalograms can yield state-of-the-art classification accuracy while reducing training data requirements to just a tenth of those employed by current approaches.
癫痫领域的大量研究工作都致力于开发自动癫痫发作检测系统。在使用电生理记录时，迄今为止的大多数提议都遵循传统做法，即将信号分解后的所有频段作为分类器的输入特征。尽管这种方法看似强大，但可能会适得其反，因为某些频段可能不携带有关癫痫发作事件的相关信息，反而可能会在分类过程中增加噪声，从而降低性能。本文所述工作的一个关键论点是，频率子集的选择可能会提高癫痫发作的分类率。此外，作者还探讨了保守选择频段是否可以减少实现良好分类性能所需的训练数据量。他们发现了令人信服的证据，即在头皮脑电图中使用频率低于25Hz的频谱成分可以产生最先进的分类准确率，同时将训练数据要求降低到当前方法所用数据的十分之一。
