A novel approach for automated detection of focal EEG signals using empirical wavelet transform

被引:142
|
作者
Bhattacharyya, Abhijit [1 ]
Sharma, Manish [1 ]
Pachori, Ram Bilas [1 ]
Sircar, Pradip [2 ]
Acharya, U. Rajendra [3 ,4 ,5 ]
机构
[1] Indian Inst Technol Indore, Discipline Elect Engn, Indore 453552, Madhya Pradesh, India
[2] Indian Inst Technol Kanpur, Dept Elect Engn, Kanpur 208016, Uttar Pradesh, India
[3] Ngee Ann Polytech, Dept Elect & Comp Engn, Singapore 599489, Singapore
[4] SIM Univ, Sch Sci & Technol, Dept Biomed Engn, Singapore 599491, Singapore
[5] Univ Malaya, Dept Biomed Engn, Fac Engn, Kuala Lumpur, Malaysia
关键词
Focal EEG signal; Empirical wavelet transform; Reconstructed phase space; Central tendency measure; Least-squares support vector machine; INTRINSIC MODE FUNCTIONS; SUPPORT VECTOR MACHINE; CARDIAC SOUND SIGNALS; TIME-SERIES ANALYSIS; ELECTROENCEPHALOGRAM SIGNALS; ENTROPY MEASURES; CLASSIFICATION; DECOMPOSITION; IDENTIFICATION; LOCALIZATION;
D O I
10.1007/s00521-016-2646-4
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The determination of epileptogenic area is a prime task in presurgical evaluation. The seizure activity can be prevented by operating the affected areas by clinical surgery. In this paper, an automatic approach has been presented to detect electroencephalogram (EEG) signals of non-focal and focal groups. The proposed approach can be used to determine the area linked to the focal epilepsy. In our method, the EEG signal is decomposed into rhythms using empirical wavelet transform technique. The two-dimensional (2D) projections of the reconstructed phase space (RPS) have been obtained for the rhythms. Area measures for various RPS plots are estimated using central tendency measure (CTM) parameter. The area parameters are used with least-squares support vector machine (LS-SVM) classifier to classify the focal and non-focal classes of EEG signals. In this work, we have achieved a maximum classification accuracy of 90%, sensitivity and specificity of 88 and 92%, respectively, using 50 pairs of focal and non-focal EEG signals. The same method has achieved maximum classification accuracy, sensitivity and specificity of 82.53, 81.60 and 83.46%, respectively, with 750 pairs of signals. The developed prototype can be used for the epileptic patients and aid the clinicians to confirm diagnosis.
引用
收藏
页码:47 / 57
页数:11
相关论文
共 50 条
  • [21] Automated detection of abnormal EEG signals using localized wavelet filter banks
    Sharma, Manish
    Patel, Sohamkumar
    Acharya, U. Rajendra
    PATTERN RECOGNITION LETTERS, 2020, 133 : 188 - 194
  • [22] Automated detection and screening of depression using continuous wavelet transform with electroencephalogram signals
    Raghavendra, U.
    Gudigar, Anjan
    Chakole, Yashas
    Kasula, Praneet
    Subha, D. P.
    Kadri, Nahrizul Adib
    Ciaccio, Edward J.
    Acharya, U. Rajendra
    EXPERT SYSTEMS, 2023, 40 (04)
  • [23] Alcoholism Diagnosis from EEG Signals using Continuous Wavelet Transform
    Upadhyay, R.
    Padhy, P. K.
    Kankar, P. K.
    2014 ANNUAL IEEE INDIA CONFERENCE (INDICON), 2014,
  • [24] EEG-based emotion recognition using empirical wavelet transform
    Huang, Dan
    Zhang, Suhua
    Zhang, Yong
    2017 4TH INTERNATIONAL CONFERENCE ON SYSTEMS AND INFORMATICS (ICSAI), 2017, : 1444 - 1449
  • [25] Automated identification system for seizure EEG signals using tunable-Q wavelet transform
    Reddy, G. Ravi Shankar
    Rao, Rameshwar
    ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH, 2017, 20 (05): : 1486 - 1493
  • [26] Automatic focal and non-focal EEG detection using entropy-based features from flexible analytic wavelet transform
    You, Yang
    Chen, Wanzhong
    Li, Mingyang
    Zhang, Tao
    Jiang, Yun
    Zheng, Xiao
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2020, 57
  • [27] Automated Alcoholism Detection Using Fourier-Bessel Series Expansion Based Empirical Wavelet Transform
    Anuragi, Arti
    Sisodia, Dilip Singh
    Pachori, Ram Bilas
    IEEE SENSORS JOURNAL, 2020, 20 (09) : 4914 - 4924
  • [28] AUTOMATED CHARACTERIZATION OF CARDIOVASCULAR DISEASES USING WAVELET TRANSFORM FEATURES EXTRACTED FROM ECG SIGNALS
    Mohsin, Ahmad
    Faust, Oliver
    JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY, 2019, 19 (01)
  • [29] Comparison of variational mode decomposition and empirical wavelet transform methods on EEG signals for motor imaginary applications
    Krishnan, K. Keerthi
    Soman, K. P.
    INTERNATIONAL JOURNAL OF BIOMEDICAL ENGINEERING AND TECHNOLOGY, 2022, 38 (03) : 267 - 285
  • [30] Detection of Epileptic Seizures Using Wavelet Transform, Peak Extraction and PSR from EEG Signals
    Jang, Seok-Woo
    Lee, Sang-Hong
    SYMMETRY-BASEL, 2020, 12 (08):