Cepstrum Coefficient Analysis from Low-Frequency to High-Frequency Applied to Automatic Epileptic Seizure Detection with Bio-Electrical Signals
Source abstract
Abstract
This study analyzes bioelectrical signals to achieve automatic epileptic seizure detection. Electroencephalographic (EEG) signals were recorded with electrodes on healthy, epileptic seizure-free, and epileptic seizure patients. The challenges in this field are generally regarded to be the impacts of non-stationarity and nonlinearity in EEG signals. To address these challenges, this study attempts to recognize different brain statuses. The idea originated from a novel hypothesis that considers EEG signals as convolution signals and regards itself as the generation mechanism of EEG signals, to some extent. Based on this hypothesis, the nonlinear problem can be viewed as a deconvolution procedure. As such, the method can be simplified into three parts: eliminating non-stationary is used to catch high-frequency to low-frequency signals, which is followed by a local mean decomposition (LMD) algorithm; these signals are deconvoluted to form ultra-high-dimensional feature sets, which is completely terminated by the mel-frequency cepstrum coefficients (MFCC) algorithm; and several classifiers are combined to achieve highly accurate recognition results and to verify the superiority and reasonableness of this method. The publicly available EEG database from the University of Bonn, Germany is employed to demonstrate the effectiveness and outstanding performance of this method. According to the results, the method has the ability to attain a higher average classification accuracy than other methods in all of the four following cases: healthy (datasets A and B) versus epileptic seizure (dataset E), epileptic seizure-free (datasets C and D) versus epileptic seizure (dataset E), healthy (datasets A and B) versus epileptic seizure-free (datasets C and D) versus epileptic seizure (dataset E), and healthy (dataset A) versus healthy (dataset B) versus epileptic seizure-free (dataset C) versus epileptic seizure-free (dataset D) versus epileptic seizure (dataset E).
Source: crossref · Quality: baseline
Research context
OpenAlex topics: EEG and Brain-Computer Interfaces · Blind Source Separation Techniques · Neuroscience and Neural Engineering
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Complex System Safety and Control, Ministry of Education, Chongqing University, Chongqing 400044, China
School of Automation, Chongqing University, Chongqing 400044, China
Collaborative Innovation Center for Brain Science, Chongqing University, Chongqing 400044, China
School of Computer Science and Technology, Huaiyin Normal University, Huai’an 223300, China
Funding
National Natural Science Foundation of China · the Fundamental Research Funds for the Central Universities · the Natural Science Foundation of Chongqing City, China
References (60)
Show source-provided references
1. Application of Entropies for automated diagnosis of epilepsy using EEG signals: A review10.1016/j.knosys.2015.08.004 ↗
2. EEG signal classification for epilepsy diagnosis via optimum path forest-A systematic assessment10.1016/j.neucom.2014.01.020 ↗
3. Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy10.1016/j.yebeh.2014.06.023 ↗
4. Automated EEG analysis of epilepsy: A review10.1016/j.knosys.2013.02.014 ↗
5. An adaptive unsupervised classification of seizure method based on LMD-MSSE with EEG signals
6. A novel robust diagnostic model to detect seizures in electroencephalography10.1016/j.eswa.2016.02.040 ↗
7. Epileptic seizure detection by analyzing EEG signals using different transformation techniques10.1016/j.neucom.2014.05.044 ↗
8. Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier10.1016/j.neucom.2017.02.053 ↗
9. Epileptic seizure detection using DWT based fuzzy approximate entropy and support vector machine10.1016/j.neucom.2013.11.009 ↗
10. Genetic algorithms tuned expert model for detection of epileptic seizures from EEG signatures10.1016/j.asoc.2014.01.029 ↗
11. Epileptic Seizure Classification of EEG time-series using Rational Discrete Short Time Fourier Transform10.1109/TBME.2014.2360101 ↗
12. Automatic EEG seizure detection using dual-tree complex wavelet-Fourier features10.1016/j.eswa.2013.09.037 ↗
13. Automated detection of epileptic EEGs using a novel fusion feature and extreme learning machine10.1016/j.neucom.2015.10.070 ↗
14. Epileptic Focus Localization Using Discrete Wavelet Transform Based on Interictal Intracranial EEG10.1109/TNSRE.2016.2604393 ↗
15. Classification of EEG signals for Epileptic Seizures using hybrid Artificial Neural Network based Wavelet Transforms and Fuzzy Relations10.1016/j.eswa.2017.07.020 ↗
16. A sequential method using multiplicative extreme learning machine for epileptic seizure detection10.1016/j.neucom.2016.06.056 ↗
17. Han, J., Li, Y., Kang, J., Cai, E., Tong, Z., Ouyang, G., and Li, X. (2017). Global Synchronization of Multichannel EEG Based on Rényi Entropy in Children with Autism Spectrum Disorder. Appl. Sci., 7.10.3390/app7030257 ↗
18. Toward Epileptic Brain Region Detection Based on Magnetic Nanoparticle Patterning10.3390/s150924409 ↗
19. Bhattacharyya, A., Pachori, R.B., Upadhyay, A., and Acharya, U.R. (2017). Tunable-Q Wavelet Transform Based Multiscale Entropy Measure for Automated Classification of Epileptic EEG Signals. Appl. Sci., 7.10.3390/app7040385 ↗
20. Correlation between volumetric oxygenation responses and electrophysiology identifies deep thalamocortical activity during epileptic seizures10.1117/1.NPh.4.1.011007 ↗
21. Li, M.A., Zhu, W., Liu, H.N., and Yang, J.F. (2017). Adaptive Feature Extraction of Motor Imagery EEG with Optimal Wavelet Packets and SE-Isomap. Appl. Sci., 7.10.3390/app7040390 ↗
22. EEG and functional ultrasound imaging in mobile rats10.1038/nmeth.3506 ↗
23. Mu, Z., Hu, J., and Min, J. (2017). Driver Fatigue Detection System Using Electroencephalography Signals Based on Combined Entropy Features. Appl. Sci., 7.10.3390/app7020150 ↗
24. Functional ultrasound imaging of the brain
25. Seizure Classification form EEG Signals using Transfer Learning, Semi-Supervised Learning and TSK Fuzzy System10.1109/TNSRE.2017.2748388 ↗
26. LMD based features for the automatic seizure detection of EEG signals using SVM10.1109/TNSRE.2016.2611601 ↗
27. Detection of Epileptic Seizure and Seizure-free EEG Signals Employing Generalized S-Transform10.1049/iet-smt.2016.0443 ↗
28. Electroencephalogram signal classification based on shearlet and contourlet transforms10.1016/j.eswa.2016.09.037 ↗
29. EMD-Based Temporal and Spectral Features for the Classification of EEG Signals Using Supervised Learning10.1109/TNSRE.2015.2441835 ↗
30. Real-Time Epileptic Seizure Detection Using EEG10.1109/TNSRE.2017.2697920 ↗
31. A novel statistical algorithm for multiclass EEG signal classification10.1016/j.engappai.2014.05.011 ↗
32. Chaos Feature Study in Fractional Fourier Domain for Preictal Prediction of Epileptic Seizure10.1016/j.neucom.2017.04.019 ↗
33. Multi-category EEG signal classification developing time-frequency textures based Fisher Vector encoding method10.1016/j.neucom.2016.08.050 ↗
34. A multiwavelet-based time-varying model identification approach for time-frequency analysis of EEG signals10.1016/j.neucom.2016.01.062 ↗
35. Classification of epileptic seizures in EEG signals based on phase space representation of intrinsic mode functions10.1016/j.eswa.2014.08.030 ↗
36. Non-linear classifiers applied to EEG analysis for epilepsy seizure detection10.1016/j.eswa.2017.05.052 ↗
37. Optimal configuration of multilayer perceptron neural network classifier for recognition of intracranial epileptic seizures10.1016/j.eswa.2017.07.029 ↗
38. Bio-geography Based Hybrid Scheme for Automatic Detection of Epileptic Seizures form EEG Signatures10.1016/j.asoc.2016.12.009 ↗
39. Detection of Epilepsy with Electroencephalogram using Rule-based Classifiers10.1016/j.neucom.2016.09.080 ↗
40. Classify Epileptic EEG Signals Using Weighted Complex Networks Based Community Structure Detection10.1016/j.eswa.2017.08.012 ↗
41. Epileptic Seizure Classification of EEGs using Time-Frequency Analysis based Multiscale Radial Basis Functions10.1109/JBHI.2017.2654479 ↗
42. Epileptic Seizure Detection Based on Partial Directed Coherence Analysis10.1109/JBHI.2015.2424074 ↗
43. Time-varying model identification for time-frequency feature extraction from EEG data10.1016/j.jneumeth.2010.11.027 ↗
44. Non-invasive EEG evaluation in epilepsy diagnosis10.1586/14737175.2015.1025382 ↗
45. Neonatal seizure detection using atomic decomposition with a novel dictionary10.1109/TBME.2014.2326921 ↗
46. Identification of Electronic Disguised Voices10.1109/TIFS.2014.2301912 ↗
47. Feature extraction from smart-phone inertial signals for human activity segmentation
48. A novel cepstral-based technique for automatic cognitive load estimation10.1016/j.bspc.2017.07.020 ↗
49. Cepstral Analysis for the Application of Echo-Based Audio Watermark Detection10.1109/TIFS.2015.2431997 ↗
50. High-resolution time-frequency analysis of EEG signals using multiscale radial basis functions10.1016/j.neucom.2015.04.128 ↗
51. Detection and Classification of OFDM Waveforms Using Cepstral Analysis10.1109/TSP.2015.2439236 ↗
52. Time-varying Time-frequency Complexity Measures for Epileptic EEG Data Analysis10.1109/TBME.2017.2761982 ↗
53. Extracting and Selecting Distinctive EEG Features for Efficient Epileptic Seizure Prediction10.1109/JBHI.2014.2358640 ↗
54. Classification of epilepsy seizure phase using interval type-2 fuzzy support vector machines10.1016/j.neucom.2016.03.033 ↗
55. Dynamic Dictionary for Combined EEG Compression and Seizure Detection10.1109/JBHI.2013.2263198 ↗
56. A multivariate approach for patient specific EEG seizure detection using empirical wavelet transform10.1109/TBME.2017.2650259 ↗
57. A Wavelet-Based Artifact Reduction From Scalp EEG for Epileptic Seizure Detection10.1109/JBHI.2015.2457093 ↗
58. An automatic detection of focal EEG signals using new class of time-frequency localized orthogonal wavelet filter banks10.1016/j.knosys.2016.11.024 ↗
59. Comparative evaluation of existing and new methods for correcting ocular artifacts in electroencephalographic recordings10.1016/j.sigpro.2013.11.015 ↗
60. Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications10.1016/j.neucom.2014.09.011 ↗