Grasshopper optimization algorithm-based approach for the optimization of ensemble classifier and feature selection to classify epileptic EEG signals

被引:23
作者
Singh, Gurwinder [1 ]
Singh, Birmohan [2 ]
Kaur, Manpreet [3 ]
机构
[1] Bhai Sangat Singh Khalsa Coll, Dept Comp Sci, Banga, Punjab, India
[2] St Longowal Inst Engn & Technol, Dept Comp Sci & Engn, Longowal, Punjab, India
[3] St Longowal Inst Engn & Technol, Dept Elect & Instrumentat Engn, Longowal, Punjab, India
关键词
Epilepsy; Intrinsic mode functions; Empirical mode decomposition; k-Nearest neighbor; Extreme learning machine; Random forest; Support vector machine; Artificial neural network; Grasshopper optimization algorithm; DISCRETE WAVELET TRANSFORM; ARTIFICIAL NEURAL-NETWORK; EXTREME LEARNING-MACHINE; SEIZURE DETECTION; APPROXIMATE ENTROPY; AUTOMATIC RECOGNITION; FEATURE-EXTRACTION; TIME; MODEL; DIAGNOSIS;
D O I
10.1007/s11517-019-01951-w
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Epilepsy is one of the most common neurological disease worldwide. It is diagnosed by analyzing a long electroencephalogram (EEG) recording in a clinical environment, which may be much prone to errors and a time-consuming task. In this paper, a methodology for the classification of an epileptic seizure is proposed for analyzing EEG signals. EEG signal is decomposed into intrinsic mode functions (IMFs) using empirical mode decomposition (EMD). A fusion, of the extracted non-linear and spike-based features from each of the IMF signals, is made. The parameters of five machine learning algorithms; k-nearest neighbor (k-NN), extreme learning machine (ELM), random forest (RF), support vector machine (SVM), and artificial neural network (ANN) are optimized, as well as a set of the significant features is chosen using grasshopper optimization algorithm (GOA). These classifiers with their optimized parameters are ensembled together for the classification of epileptic seizures. The results show that ensemble classifier performs better than individual classifier. A comparison of the proposed methodology with state of the art epileptic seizure detection techniques is also made for validation.
引用
收藏
页码:1323 / 1339
页数:17
相关论文
共 119 条
[1]   AUTOMATED DIAGNOSIS OF EPILEPSY USING CWT, HOS AND TEXTURE PARAMETERS [J].
Acharya, U. Rajendra ;
Yanti, Ratna ;
Wei, Zheng Jia ;
Krishnan, M. Muthu Rama ;
Hong, Tan Jen ;
Martis, Roshan Joy ;
Min, Lim Choo .
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2013, 23 (03)
[2]   Automated diagnosis of epileptic EEG using entropies [J].
Acharya, U. Rajendra ;
Molinari, Filippo ;
Sree, S. Vinitha ;
Chattopadhyay, Subhagata ;
Ng, Kwan-Hoong ;
Suri, Jasjit S. .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2012, 7 (04) :401-408
[3]   Multiple classifier system for EEG signal classification with application to brain-computer interfaces [J].
Ahangi, Amir ;
Karamnejad, Mehdi ;
Mohammadi, Nima ;
Ebrahimpour, Reza ;
Bagheri, Nasoor .
NEURAL COMPUTING & APPLICATIONS, 2013, 23 (05) :1319-1327
[4]   Detection of Seizure and Epilepsy Using Higher Order Statistics in the EMD Domain [J].
Alam, S. M. Shafiul ;
Bhuiyan, M. I. H. .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2013, 17 (02) :312-318
[5]   Simultaneous Feature Selection and Support Vector Machine Optimization Using the Grasshopper Optimization Algorithm [J].
Aljarah, Ibrahim ;
Al-Zoubi, Ala M. ;
Faris, Hossam ;
Hassonah, Mohammad A. ;
Mirjalili, Seyedali ;
Saadeh, Heba .
COGNITIVE COMPUTATION, 2018, 10 (03) :478-495
[6]   Shape quantization and recognition with randomized trees [J].
Amit, Y ;
Geman, D .
NEURAL COMPUTATION, 1997, 9 (07) :1545-1588
[7]   Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state [J].
Andrzejak, RG ;
Lehnertz, K ;
Mormann, F ;
Rieke, C ;
David, P ;
Elger, CE .
PHYSICAL REVIEW E, 2001, 64 (06) :8-061907
[8]  
[Anonymous], 1974, Electroencephalogr Clin Neurophysiol, V37, P538
[9]  
[Anonymous], 2017, ENTROPY SWITZ, DOI [DOI 10.3390/e19030099, DOI 10.3390/E19030099]
[10]  
[Anonymous], 2015, SCI WORLD J