An Effective Cluster-Based Outlier Detection with Optimized Deep Neural Network for Epileptic Seizure Detection and Classification Model
|International Journal of Engineering Trends and Technology (IJETT)||
|© 2021 by IJETT Journal|
|Year of Publication : 2021|
|Authors : P. Suguna, B. Kirubagari, R. Umamaheswari
|DOI : 10.14445/22315381/IJETT-V69I3P214|
MLA Style: P. Suguna, B. Kirubagari, R. Umamaheswari "An Effective Cluster-Based Outlier Detection with Optimized Deep Neural Network for Epileptic Seizure Detection and Classification Model" International Journal of Engineering Trends and Technology 69.3(2021):76-84.
APA Style:P. Suguna, B. Kirubagari, R. Umamaheswari. An Effective Cluster-Based Outlier Detection with Optimized Deep Neural Network for Epileptic Seizure Detection and Classification Model International Journal of Engineering Trends and Technology, 69(3),76-84.
Epileptic seizure diagnosis using Electroencephalogram (EEG) signal is an essential process in the healthcare sector to detect the abnormal growth of brain activities. Since epileptic seizure detection by physicians requires more time, it is needed to design an automated epileptic detection model. Due to the advancements in the Deep Learning (DL) models, it can be employed in the diagnosis of epileptic seizures from EEG signals. This paper presents a new hierarchical clustering with adaptive momentum (ADAM) optimized Deep Neural Network (DNN), called the HC-DNN-ADAM model. The presented model involves HC-based outlier detection to remove the unwanted data from the input dataset; thereby, the classifier results can be improved. In addition, the HC-DNN-ADAM model utilizes DNN for the classification process where the hyperparameters of DNN are tuned by ADAM optimizer. For examining the effectual classifier results analysis of the HC-DNN-ADAM model, a benchmark Epileptic Seizure Recognition dataset is utilized. The application of HC and ADAM paves a way to achieve better classification outcomes. The performance of the HC-DNN-ADAM model has been validated using a benchmark dataset. The simulation outcomes signified that the HC-DNN-ADAMmodel has resulted in maximum detection performance with an accuracy of 99.74% on the classification of multiple classes of seizures.
 Emilia Ciupan, Mihai Ciupan, Daniela-Corina Jucan., Determining the Mechanical Properties of a New Composite Material using Artificial Neural Networks., International Journal of Engineering Trends and Technology 66(2)(2018) 103-108.
 R. Sathish Kumar, M. Nivetha, G. Madhumita, P. Santhoshy., Image Enhancement using NHSI Model Employed in Color Retinal Images, International Journal of Engineering Trends and Technology (IJETT), V58(1)(2018) 14-19. ISSN:2231-5381.
 Wang D, Miao D, Xie C. Best basis-based wavelet packet entropy feature extraction and hierarchical EEG classification for epileptic detection. Expert Syst Appl. (2011) 38:14314–20. doi: 10.1016/j.eswa.2011.05.096.
 Acharya UR, SreeSV, Suri JS. Automatic detection of epileptic EEG signals using higher order cumulant features. Int J Neural Syst. (2011) 21:403–14. doi: 10.1142/S0129065711002912
 Song Y, Crowcroft J, Zhang J. Automatic epileptic seizure detection in EEGs based on optimized sample entropy and extreme learning machine. J Neurosci Methods. (2012) 210:132–46. doi: 10.1016/j.jneumeth.2012.07.003.
 Williamson JR, Bliss DW, Browne DW, Narayanan JT. Seizure prediction using EEG spatiotemporal correlation structure. Epilepsy Behav. (2012) 25:230–8. doi: 10.1016/j.yebeh.2012.07.007.
 Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. ComputBiol Med. (2018) 100:270–8. doi: 10.1016/j.compbiomed.2017.09.017.
 Hu W, Cao J, Lai X, Liu J. Mean amplitude spectrum based epileptic state classification for seizure prediction using convolutional neural networks. J Ambient Intell Hum Comput. (2019) 1–11. doi: 10.1007/s12652-019-01220-6.
 Truong ND, Nguyen AD, Kuhlmann L, Bonyadi MR, Yang J, Ippolito S, et al. Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. Neural Netw. (2018) 105:104–111. doi: 10.1016/j.neunet.2018.04.018
 Khan H, Marcuse L, Fields M, Swann K, Yener B. Focal onset seizure prediction using convolutional networks. IEEE Trans Biomed Eng. (2017) 65:2109–118. doi: 10.1109/TBME.2017.2785401
 Everitt, B.S., Landau, S., Leese, M., Stahl, D., Cluster Analysis, fifth ed. Wiley, United Kingdom., (2011).
 D’Urso, P. and Vitale, V., A robust hierarchical clustering for georeferenced data. Spatial Statistics, 35(2020) 100407.
 Chen, L. and Chen, J., Deep Neural Network for Automatic Classification of Pathological Voice Signals. Journal of Voice., (2020).
 LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature (2015) 521, 436.
 P. Suguna, B. Kirubagari, R. Umamaheswari, Epileptic Seizure Detection using Simulated Annealing based Optimal Feature Subset Selection with Kernel Extreme Learning Machine Classification Model, 9(4)(2020) 6464 – 6470
 Polat, K. and Nour, M., Epileptic Seizure Detection Based on New Hybrid Models with Electroencephalogram Signals. IRBM., (2020).
 Guha, A., Ghosh, S., Roy, A. and Chatterjee, S., Epileptic Seizure Recognition Using Deep Neural Network. In Emerging Technology in Modelling and Graphics (2020) 21-28. Springer, Singapore.
 Bhattacharyya A, Sharma M, PachoriRB, Sircar P, Acharya UR A novel approach for automated detection of focal EEG signals using empirical wavelet transform. Neural ComputAppl (2018) 29:47–57.
 Usman, S.M., Usman, M. and Fong, S., Epileptic seizures prediction using machine learning methods. Computational and mathematical methods in medicine, (2017).
 Kabir, E. and Zhang, Y., Epileptic seizure detection from EEG signals using logistic model trees. Brain informatics, 3(2)(2016) 93-100.
Data classification, Deep learning, Epileptic seizure, Outlier detection.