A novel EEG-complexity-based feature and its application on the epileptic seizure detection
- 15 Downloads
The neurophysiology system is a complex network of nerves and cells, which carries messages to and from the brain and spinal cord to various parts of the body. Exploring complexity of the system can be contributed to understand diverse neurophysiological abnormalities, which may further result in different kinds of neurological disorders. In this paper, we present a novel analyzing framework to characterize the complexity of neurophysiological system, under which a specific weighted FPE-complexity-based feature (W-FPE-F) is extracted from EEG and then applied into the automated epileptic seizure detection. Combining with extreme learning machine (ELM) and support vector machine (SVM), performances of the proposed method are finally verified on two open EEG databases. Simulation results show that the proposed method does a good job in detecting the epileptic seizure, particularly, it is able to avoid the undesirable detection performance caused by individual divergence effectively.
KeywordsNeurophysiology system Complexity analysis Feature extraction Feature weighting Automated seizure detection Electroencephalography (EEG)
This work was supported by the National Natural Science Foundation of China under Grant 61473223 and the Natural Science Foundation of Shaanxi Province, China under Grant 2017JM1043.
- 1.Song J-L, Zhang R (2016) Automatic seizure detection using a novel eeg feature based on nonlinear complexity. In: 2016 international joint conference on neural networks (IJCNN), pp 1686–1693Google Scholar
- 2.de la Torre-Luque A, Bornas X, Balle M, Fiol-Veny A (2016) Complexity and nonlinear biomarkers in emotional disorders: a meta-analytic study. Neurosci Biobehav Rev 68:410422Google Scholar
- 11.Wackermann J (1996) Beyond mapping: estimating complexity of multichannel eeg recordings. Acta Neurobiol Exp 56:197–208Google Scholar
- 19.Zhang X, Wang T, Liang X, ao F, Li Y (2012) A class-based feature weighting method for text classification. J Comput Inf Syst 3:965–972Google Scholar
- 20.Wang Q, Ye Y, Huang J (2008) Fuzzy k-means with variable weighting in high dimensional data analysis. In: Proceedings of web-age information management, pp 365–372Google Scholar
- 23.Shoeb AH. Application of machine learning to epileptic seizure onset detection and treatment. Phd thesis, Massachusetts Institute of TechnologyGoogle Scholar
- 25.Wang X, Cao W, Non-iterative approaches in training feed-forward neural networks and their applications. Soft Computing. https://doi.org/10.1007/s00500-018-3203-0