Journal of Scientific and Industrial Research

Open Access Open Access  Restricted Access Subscription Access

EEG Signal Classification Automation Using Novel Modified Random Forest Approach


Affiliations
1 Veltech Rangarajan Dr. Sagunthala R & D Institute of science and Technology, Chennai 600 062, India
2 Dept of ECE, KKR & KSR Institute of Technology & Science, Vinjanampadu, Guntur 522 017, India
3 Department of ECE, Kakatiya Institute of technology & science, Warangal 506 371, India
4 Dept of ECE, NRI Institute of Technology, Pothavarapadu (V) Agiripalli, Vijayawada 520 010, India
5 Department of ECE, RVR and JC College of Engineering, Guntur 522 019, India
 

Digitalization and automation are the two aspects in the medical industry that define compliance with industry 4.0. Automation is essential for speeding up the diagnosis process, while digitalization leads to smart medicine and efficient diagnosis. Epilepsy is one such disease that can use these automation techniques. The automatic monitoring of epilepsy EEG is of great significance in clinical medicine. Aiming at the non-stationary characteristics of EEG signals, the classification of EEG signals is based on the combination of overall empirical mode. It is proposed using the random forest method. The EEG signal data set has an epileptic interval over 200 single-channel signals with a seizure period. A total of 819,400 data are used as samples. First, the overall epileptic EEG signal modal is decomposed into multiple intrinsic modal functions. The effective features are extracted from the first-order intrinsic modal function. Finally, random forest and Least Square SVM (LS-SVM) are considered to classify the EEG signals characteristics. The correct recognition rate of random forest and LS-SVM is compared. The results show that random forest classification method has an ideal classification effect on epilepsy EEG signals during and between seizures. The recognition accuracy is 99% and 60%, which is higher than the accuracy of the LS-SVM. The proposed method improves clinical epilepsy. The efficiency of EEG signals analysis.

Keywords

EEG, Ensemble Mode Decomposition, Feature Extraction and Recognition, SVM.
User
Notifications
Font Size

  • Gordon K L, McComas A J & John W O, Clinical Electroencephalography, Butterworth-Heinemann, 2013.

  • Hans B, Über das elektrenkephalogramm des menschen DMW, 60(51) (1934) 1947–1949.

  • Michal T, Fundamentals of EEG measurement, Meas Sci Rev, 2(2) (2002) 1–11.

  • Jones G, Bouwer M S & Gotman J, EEG slow waves and memory performance during the intracarotid amobarbital test, Epilepsia, 35(1) (1994) 61–69.

  • Saab R, McKeown M J, Myers L J & Gharbieh R A, A wavelet based approach for the detection of coupling in EEG signals, Proc 2nd Int IEEE EMBS Conf Neural Eng, 2005, 616−620, doi: 10.1109/CNE.2005.1419700.

  • Gabor A J & Masud S, Automated interictal EEG spike detection using artificial neural networks, Electroencephalogr Clin Neurophysiol, 83(5) (1992) 271–280.

  • Ocak H, Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy, Expert Syst Appl, 36(2) (2009) 2027–2036.

  • Oweis R J & Enas W A, Seizure classification in EEG signals utilizing Hilbert-Huang transform, Biomed Eng 10(1) (2011) 1–15.

  • Li S, Zhou W, Yuan, Geng S & Cai D, Feature extraction and recognition of ictal EEG using EMD and SVM, Comput Biol Med, 43(7) (2013) 807–816.

  • Wang Y, Liu Z, Zhou Q & Chen X, Wavelet packet entropy analysis of resting state electroencephalogram in sleep deprived mental fatigue state, Int Conf Human-Computer Interaction, Springer, Cham, (2019)

  • Chen S, Zhang X, Chen L & Yang Z, Automatic diagnosis of epileptic seizure in electroencephalography signals using nonlinear dynamics features, IEEE Access 7 (2019) 61046–61056.

  • Celka P, Boualem B & Paul C, Preprocessing and time-frequency analysis of newborn EEG seizures, IEEE Eng Med Biol Mag, 20(5) (2001) 30–39.

  • Anderson C W, Erik A S & Sanyogita S, Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks, IEEE. Trans Biomed Eng, 45(3) (1998) 277–286.

  • Jandó G, Ralph M S, Zsolt H & Buzsáki, G, Pattern recognition of the electroencephalogram by artificial neural networks, Electroencephalogr Clin Neurophysiol, 86(2) (1993) 100–109.

  • Fisch B J & Spehlmann R, EEG primer: basic principles of digital and analog EEG, Elsevier Health Sci J, (1999) 23–27.

  • Ying L I & Zhaocheng L V, Recognition of epileptic EEG signals based on EEMD and LS-SVM, J Hunan Univ Nat Sci (2014).

  • Lu P, Yuan D, Lou Y & Liu C, Single-trial identification of motor imagery EEG based on HHT and SVM, Proc 2013 Chinese Intell Automat Conf (Springer, Berlin, Heidelberg) (2013).

  • Mahesh P, Random Forest classifier for remote sensing classification, Int J Remote Sens, 26(1) (2005) 217–222.

  • Farrikh A, R Arya R M & Fanani A Z, Diabetic retinopathy grade classification based on fractal analysis and random forest, 2019 Int Seminar Appl Technol Info Commun (iSemantic) IEEE, (2019).

  • Zhang Y, Liu K, Qin L & An X, Deterministic and probabilistic interval prediction for short-term wind power generation based on variational mode decomposition and machine learning methods, Energy Convers Manag, 112 (2016) 208–219.

  • Zhang C, Jian J C & Xun G, A gear fault diagnosis method based on EMD energy entropy and SVM, Shock Vib, 29(10) (2010) 216–220.


Abstract Views: 51

PDF Views: 56




  • EEG Signal Classification Automation Using Novel Modified Random Forest Approach

Abstract Views: 51  |  PDF Views: 56

Authors

G. Aloy Anuja Mary
Veltech Rangarajan Dr. Sagunthala R & D Institute of science and Technology, Chennai 600 062, India
M Purna kishore
Dept of ECE, KKR & KSR Institute of Technology & Science, Vinjanampadu, Guntur 522 017, India
Sridevi Chitti
Department of ECE, Kakatiya Institute of technology & science, Warangal 506 371, India
Ramesh Babu Vallabhaneni
Dept of ECE, NRI Institute of Technology, Pothavarapadu (V) Agiripalli, Vijayawada 520 010, India
N Renuka
Department of ECE, RVR and JC College of Engineering, Guntur 522 019, India

Abstract


Digitalization and automation are the two aspects in the medical industry that define compliance with industry 4.0. Automation is essential for speeding up the diagnosis process, while digitalization leads to smart medicine and efficient diagnosis. Epilepsy is one such disease that can use these automation techniques. The automatic monitoring of epilepsy EEG is of great significance in clinical medicine. Aiming at the non-stationary characteristics of EEG signals, the classification of EEG signals is based on the combination of overall empirical mode. It is proposed using the random forest method. The EEG signal data set has an epileptic interval over 200 single-channel signals with a seizure period. A total of 819,400 data are used as samples. First, the overall epileptic EEG signal modal is decomposed into multiple intrinsic modal functions. The effective features are extracted from the first-order intrinsic modal function. Finally, random forest and Least Square SVM (LS-SVM) are considered to classify the EEG signals characteristics. The correct recognition rate of random forest and LS-SVM is compared. The results show that random forest classification method has an ideal classification effect on epilepsy EEG signals during and between seizures. The recognition accuracy is 99% and 60%, which is higher than the accuracy of the LS-SVM. The proposed method improves clinical epilepsy. The efficiency of EEG signals analysis.

Keywords


EEG, Ensemble Mode Decomposition, Feature Extraction and Recognition, SVM.

References