EEG signal classification using LSTM and improved neural network algorithms
- 65 Downloads
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.
KeywordsLSTM Neural network (NN) Improved NN Logistic regression EEG Accuracy
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 was obtained from all individual participants included in the study.
- 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
- 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
- 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
- Bertrand A (2015) Distributed signal processing for wireless EEG sensor networks. In: IEEE transactions on neural systems and rehabilitation engineering, pp 1534–4320Google Scholar
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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