Advertisement

EEG signal classification using LSTM and improved neural network algorithms

  • P. NagabushanamEmail author
  • S. Thomas George
  • S. Radha
Methodologies and Application
  • 65 Downloads

Abstract

Neural network (NN) finds role in variety of applications due to combined effect of feature extraction and classification availability in deep learning algorithms. In this paper, we have chosen SVM, logistic regression machine learning algorithms and NN for EEG signal classification. Two-layer LSTM and four-layer improved NN deep learning algorithms are proposed to improve the performance in EEG classification. Novelty lies in one-dimensional gradient descent activation functions with radial basis operations used in the initial layers of improved NN which help in achieving better performance. Statistical features namely mean, standard deviation, kurtosis and skewness are extracted for input EEG collected from Bonn database and then applied for various classification techniques. Accuracy, precision, recall and F1 score are the performance metrics used for analyzing the algorithms. Improved NN and LSTM give better performance compared to all other architectures. The simulations are carried out with variety of activation functions, optimizers and loss models to analyze the performance using Python in keras.

Keywords

LSTM Neural network (NN) Improved NN Logistic regression EEG Accuracy 

Notes

Compliance with ethical standards

Conflict of interest

Data used for this research are collected from Bonn university database. The authors thank them for this.

Human and animals rights

This article does not contain any studies with human participants or animals performed by any of the authors.

Informed consent

Informed consent was obtained from all individual participants included in the study.

References

  1. Aboalayon KAI, Faezipour M, Almuhammadi WS, Moslehpour S (2016) Sleep stage classification using EEG signal analysis: a comprehensive survey and new investigation. Entropy 18:272.  https://doi.org/10.3390/e18090272 CrossRefGoogle Scholar
  2. Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H (2017) Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput Biol Med 100:270–278CrossRefGoogle Scholar
  3. Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H, Subha DP (2018) Automated EEG-based screening of depression using deep convolutional neural network. Comput Methods Program Biomed 161:103–113CrossRefGoogle Scholar
  4. Afrakhteh S, Mosavi MR, Khishe M, Ayatollahi A (2018) Accurate classification of EEG signals using neural networks trained by hybrid population-physic-based algorithm. Int J Autom Comput.  https://doi.org/10.1007/s11633-018-1158-3 CrossRefGoogle Scholar
  5. Antoniades A, Spyrou L, Martin-Lopez D, Valentin A, Alarcon G, Sanei S, Took CC (2017) Detection of interictal discharges with convolutional neural networks using discrete ordered multichannel intracranial EEG. IEEE Trans Neural Syst Rehabilit Eng 25(12):1534–4320Google Scholar
  6. Arunkumar N, Mohammed MA, Mostafa SA, Ibrahim DA, Rodrigues JJ, de Albuquerque HCV (2018) Fully automatic model-based segmentation and classification approach for MRI brain tumor using artificial neural networks. Concurr Comput Pract Exp.  https://doi.org/10.1002/cpe.4962 CrossRefGoogle Scholar
  7. Asharindavida F, Shamim Hossain M, Thacham A, Khammari H, Ahmed I, Alraddady F, Masud M (2018) A forecasting tool for prediction of epileptic seizures using a machine learning approach. Concurr Comput Pract Exp.  https://doi.org/10.1002/cpe.5111 CrossRefGoogle Scholar
  8. Asim Y, Raza B, Malik AK, Rathore S, Hussain L, Iftikhar MA (2017) A multi-modal, multi-atlas-based approach for Alzheimer detection via machine learning. Int J Imaging Syst Technol 2018:1–11Google Scholar
  9. Bajaj V, Taran S, Tanyildizi E, Sengur A (2018) Robust approach based on convolutional neural networks for identification of focal EEG signals. In: IEEE sensors letters, pp 2475–1472Google Scholar
  10. Bertrand A (2015) Distributed signal processing for wireless EEG sensor networks. In: IEEE transactions on neural systems and rehabilitation engineering, pp 1534–4320Google Scholar
  11. Bevi AR, Tumu S, Prasad NV (2018) Design and investigation of a chaotic neural network architecture for cryptographic applications. Comput Electr Eng 72:179–190CrossRefGoogle Scholar
  12. Chunhui Z, Bing G, Lejun Z, Xiaoqing W (2018) Classification of hyperspectral imagery based on spectral gradient, SVM and spatial random forest. Infrared Phys Technol 95:61–69CrossRefGoogle Scholar
  13. Cui Z, Zheng X, Shao X, Cui L (2018) Automatic sleep stage classification based on convolutional neural network and fine-grained segments. Hindawi Complex 2018:9248410.  https://doi.org/10.1155/2018/9248410 CrossRefGoogle Scholar
  14. Doborjeh MG, Wang GY, Kasabov NK (2015) A spiking neural network methodology and system for learning and comparative analysis of EEG data from healthy versus addiction treated versus addiction not treated subjects. In: IEEE transactions on biomedical engineering, pp 0018-9294Google Scholar
  15. Doborjeh ZG, Doborjeh MG, Kasabov N (2017) Attentional bias pattern recognition in spiking neural networks from spatio-temporal EEG data. Cognit Comput.  https://doi.org/10.1007/s12559-017-9517-x CrossRefGoogle Scholar
  16. Ertas G (2018) Detection of high GS risk group prostate tumors by diffusion tensor imaging and logistic regression modeling. Magn Reson Imaging 50:125–133CrossRefGoogle Scholar
  17. Gomez-Pilar J, Poza J, Gómez C, Northoff G, Lubeiro A, Cea-Cañas BB, Molina V, Hornero R (2018) Altered predictive capability of the brain network EEG model in schizophrenia during cognition. Schizophr Res 201:120–129CrossRefGoogle Scholar
  18. Hajinoroozi M, Mao Z, Jung T-P, Lin C-T, Huang Y (2016) EEG-based prediction of driver’s cognitive performance by deep convolutional neural network. Signal Process Image Commun 47:549–555CrossRefGoogle Scholar
  19. Hamada A, Hassanien AE, Fahmy AA, Houssein EH (2018) A hybrid automated detection of epileptic seizures in EEG based on wavelet and machine learning techniques. Elsevier, AmsterdamGoogle Scholar
  20. Hussein R, Palangi H, Ward RK, Wang ZJ (2018) Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals. Clin Neurophys 130:25–37CrossRefGoogle Scholar
  21. Ieracitano C, Mammone N, Bramanti A, Hussain A, Morabito FC (2018) A convolutional neural network approach for classification of dementia stages based on 2D-spectral representation of EEG recordings. Neurocomputing 323:96–107CrossRefGoogle Scholar
  22. Iturrate I, Chavarriaga R, Pereira M, Zhang H, Corbet T, Leeb R, del Millán JR (2018) Human EEG reveals distinct neural correlates of power and precision grasping types. NeuroImage 181:635–644CrossRefGoogle Scholar
  23. Jiao Z, Gao X, Wang Y, Li J, Xu H (2017) Deep convolutional neural networks for mental load classification based on EEG data. Pattern Recognit 76:582–595CrossRefGoogle Scholar
  24. Juárez-Guerra E, Alarcon-Aquino V, Gómez-Gil P, Ramírez-Cortés JM, García-Treviño ES (2019) A new wavelet-based neural network for classification of epileptic-related states using EEG. J Signal Process Syst.  https://doi.org/10.1007/s11265-019-01456-7 CrossRefGoogle Scholar
  25. Kadota T, Hatogai K, Yano T, Fujita T, Kojima T, Daiko H, Fujii S (2018) Pathological tumor regression grade of metastatic tumors in lymph node predicts prognosis in esophageal cancer patients. Cancer Sci 109:1–10CrossRefGoogle Scholar
  26. Khairunnahara L, Hasibb MA, Rezanurb RHB, Islamb MR, Hosain MK (2019) Classification of malignant and benign tissue with logistic regression. Inf Med Unlocked 16:100189CrossRefGoogle Scholar
  27. Khosrowabadi R, Quek C, Ang KK, Wahab A (2014) ERNN: a biologically inspired feed forward neural network to discriminate emotion from EEG signal. In: IEEE transactions on neural networks and learning systems, vol 25, No. 3, pp 2162–237xCrossRefGoogle Scholar
  28. Kinney-Lang E, Yoong M, Hunter M, Tallur KK, Shetty J, McLellan A, Chin RF, Escudero J (2019) Analysis of EEG networks and their correlation with cognitive impairment in preschool children with epilepsy. Epilepsy Behav 90:45–56CrossRefGoogle Scholar
  29. Koda S, Member AZ, Melgani F, Nishii R (2018) Spatial and structured SVM for multilabel image classification. In: IEEE transactions on geoscience and remote sensing, IEEE, pp 0196–2892Google Scholar
  30. Kozlova LI, Bezmaternykh DD, Mel’nikov ME, Savelov AA, Petrovskii ED, Shtark MB (2017) Dynamics of interaction of neural networks in the course of EEG alpha biofeedback. Bull Exp Biol Med 162(11):619–623CrossRefGoogle Scholar
  31. Kumar Y, Dewal ML, Anand RS (2012) Epileptic seizures detection in EEG using DWT-based ApEn and artificial neural network. SIViP.  https://doi.org/10.1007/s11760-012-0362-9 CrossRefGoogle Scholar
  32. Lajnef T, Chaibi S, Ruby P, Aguera P-E, Eichenlaub J-B, Samet M, Kachouri A, Jerbi K (2015) Learning machines and sleeping brains: automatic sleep stage classification using decision-tree multi-class support vector machines. Comput Neurosci J Neurosci Methods 250:94–105CrossRefGoogle Scholar
  33. Li X, La R, Wang Y, Niu J, Zeng S, Sun S, Zhu J (2019) EEG-based mild depression recognition using convolutional neural network. Med Biol Eng Comput.  https://doi.org/10.1007/s11517-019-01959-2 CrossRefGoogle Scholar
  34. Liu L (2019) Recognition and analysis of motor imagery EEG signal based on improved bp neural network. Special section on new trends in brain signal processing and analysis. Dig Object Identif.  https://doi.org/10.1109/ACCESS.2019.2910191 CrossRefGoogle Scholar
  35. Liu Y-T, Lin YY, Wu S-L, Chuang C-H, Lin C-T (2016) Brain dynamics in predicting driving fatigue using a recurrent self-evolving fuzzy neural network. IEEE Trans Neural Netw Learn Syst 27(2):347–360CrossRefGoogle Scholar
  36. Long Z, Zhou X, Zhang X, Wang R, Wu X (2018) Recognition and classification of wire bonding joint via image feature and SVM model. In: IEEE transactions on components, packaging and manufacturing technology, IEEE, pp 2156–3950Google Scholar
  37. Michielli N, Acharya UR, Molinari F (2019) Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals. Comput Biol Med 106:71–81CrossRefGoogle Scholar
  38. Nejedly P, Cimbalnik J, Klimes P, Plesinger F, Halamek J, Kremen V, Viscor I, Brinkmann BH, Pail M, Brazdil M, Worrell G (2018) Intracerebral EEG artifact identification using convolutional neural networks. Neuroinformatics.  https://doi.org/10.1007/s12021-018-9397-6 CrossRefGoogle Scholar
  39. Öztürk S, Akdemir B (2019) HIC-net: a deep convolutional neural network model for classification of histopathological breast images. Comput Electr Eng 76:299–310CrossRefGoogle Scholar
  40. Pang JC, Robinson PA (2018) Neural mechanisms of the EEG alpha-BOLD anticorrelation. NeuroImage 181:461–470CrossRefGoogle Scholar
  41. Rajesh K, Ramaswamy V, Kannan K, Arunkumar N (2018) Satellite cloud image classification for cyclone prediction using dichotomous logistic regression based fuzzy hypergraph model. Future Gener Comput Syst 98:688–696CrossRefGoogle Scholar
  42. Ranjan R, Arya R, Fernandes SL, Sravya E, Jain V (2018) A fuzzy neural network approach for automatic K-complex detection in sleep EEG signal. Pattern Recognit Lett 115:74–83CrossRefGoogle Scholar
  43. Sacca V, Campolo M, Mirarchi D, Gambardella A, Veltri P, Morabito FC (2018) On the classification of EEG signal by using an SVM based algorithm. In: Smart innovation, systems and technologies, Springer, p 69Google Scholar
  44. Satapathy SK, Dehuri S, Jagadev AK (2016) EEG signal classification using PSO trained RBF neural network for epilepsy identification. Inf Med Unlocked 6:1–11Google Scholar
  45. Sezer E, Işik H, Saracoğlu E (2010) Employment and comparison of different artificial neural networks for epilepsy diagnosis from EEG signals. J Med Syst 2012(36):347–362.  https://doi.org/10.1007/s10916-010-9480-5 CrossRefGoogle Scholar
  46. Shepelev IE, Lazurenko DM, Kiroy VN, Aslanyan EV, Bakhtin OM, Minyaeva NR (2018) A novel neural network approach to creating a brain–computer interface based on the EEG patterns of voluntary muscle movements. Neurosci Behav Physiol 48(9):1145–1157CrossRefGoogle Scholar
  47. Shtark MB, Kozlova LI, Bezmaternykh DD, Ye M, Mel’nikov AA, Savelov AA, Sokhadze EM (2018) Neuro imaging study of Alpha and Beta EEG biofeedback effects on neural networks. Appl Psychophysiol Biofeedback.  https://doi.org/10.1007/s10484-018-9396-2 CrossRefGoogle Scholar
  48. Sors A, Bonnet S, Mirek S, Vercueil L, Payen J-F (2017) A convolutional neural network for sleep stage scoring from rawsingle-channel EEG. Biomed Signal Process Control 42:107–114CrossRefGoogle Scholar
  49. Sturm I, Lapuschkin S, Samek W, Müller K-R (2016) Interpretable deep neural networks for single-trial EEG classification. J Neurosci Methods 274:141–145CrossRefGoogle Scholar
  50. Sudalaimani C, Sivakumaran N, Elizabeth TT, Rominus VS (2018) Automated detection of the preseizure state in EEG signal using neural networks. Biocybern Biomed Eng 39:160–175CrossRefGoogle Scholar
  51. Sun L, Jin B, Yang H, Tong J, Liu C, Xiong H (2018) Unsupervised EEG feature extraction based on echo state network. Inf Sci 475:1–17CrossRefGoogle Scholar
  52. Sundar R, Punniyamoorthy M (2019) Performance enhanced Boosted SVM for Imbalanced datasets. Appl Soft Comput J 83:105601CrossRefGoogle Scholar
  53. Supratak A, Dong H, Wu C, Guo Y (2017) DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG. In: IEEE transactions on neural systems and rehabilitation engineering, IEEE, pp 1534–4320Google Scholar
  54. Tang Z, Li C, Sun S (2017) Single-trial EEG classification of motor imagery using deep convolutional neural networks. Optik 130:11–18CrossRefGoogle Scholar
  55. Vimala C, Priya PA (2019) Artificial neural network based wavelet transform technique for image quality enhancement. Comput Electr Eng 76:258–267CrossRefGoogle Scholar
  56. Wan S, Liang Y, Zhang Y (2019) Deep convolutional neural networks for diabetic retinopathy detection by image classification. Comput Electr Eng 72:274–282CrossRefGoogle Scholar
  57. Wang L, Pedersen PC, Agu E, Strong D, Tulu B (2016) Area determination of diabetic foot ulcer images using a cascaded two-stage SVM based classification. In: IEEE transactions on biomedical engineering, IEEEGoogle Scholar
  58. Wang Z, Cao L, Zhang Z, Gong X, Sun Y, Wang H (2017) Short time Fourier transformation and deep neural networks for motor imagery brain computer interface recognition. Concurr Comput Pract Exp.  https://doi.org/10.1002/cpe.4413 CrossRefGoogle Scholar
  59. Wang JS, Mehmood I, Pan C, Chen Y, Zhang Y-D (2018) Cerebral micro-bleeding identification based on a nine-layer convolutional neural network with stochastic pooling. Concurr Comput Pract Exp.  https://doi.org/10.1002/cpe.5130 CrossRefGoogle Scholar
  60. Wei S, Wu W, Jeon G, Ahmad A, Yang X (2018) Improving resolution of medical images with deep dense convolutional neural network. Concurr Comput Pract Exp.  https://doi.org/10.1002/cpe.5084 CrossRefGoogle Scholar
  61. Wu M, Krishna S, Thornhill RE, Flood TA, McInnes DF, Schieda N (2019) Transition zone prostate cancer: logistic regression and machine-learning models of quantitative ADC, shape and texture features are highly accurate for diagnosis. In: International society for magnetic resonance in medicineGoogle Scholar
  62. Zeng W, Li M, Yuan C, Wang Q, Liu F, Wang Y (2019) Classification of focal and non focal EEG signals using empirical mode decomposition (EMD), phase space reconstruction (PSR) and neural networks. Artif Intell Rev 52:625–647CrossRefGoogle Scholar
  63. Zhang C, Yao L, Song S, Wen X, Zhao X, Long Z (2017) Euler elastica regularized logistic regression for whole-brain decoding of fMRI data. In: IEEE transactions on biomedical engineering, IEEE, pp 0018–9294Google Scholar
  64. Zhang P, Wang X, Zhang W, Chen J (2018a) Learning spatial-spectral-temporal EEG features with recurrent 3D convolutional neural networks for cross-task mental workload assessment. In: IEEE Transactions on neural systems and rehabilitation engineering, pp 1534–4320Google Scholar
  65. Zhang Z, Duan F, Solé-casals J, Dinarès-Ferran J, Cichocki A, Yang Z, Sun Z (2018b) A novel deep learning approach with data augmentation to classify motor imagery signals. IEEE access on digital object identifier, pp 2169–3536,  https://doi.org/10.1109/access.2019.2895133 CrossRefGoogle Scholar
  66. Zhao G, Liu S, QiWang TH, Chen Y, Lin L, Zhao D (2018) Deep convolutional neural network for drowsy student state Detection. Concurr Comput Pract Exp.  https://doi.org/10.1002/cpe.4457 CrossRefGoogle Scholar
  67. Zhou B, Li W, Hu J (2016) A new segmented oversampling method for imbalanced data classification using quasi-linear SVM. IEEE J Trans Electr Electron Eng 12:891–898CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of EEEKarunya Institute of Technology and SciencesCoimbatoreIndia
  2. 2.Department of EIEKarunya Institute of Technology and SciencesCoimbatoreIndia
  3. 3.Department of ECEKarunya Institute of Technology and SciencesCoimbatoreIndia

Personalised recommendations