Epileptical Seizure Detection: Performance analysis of gamma band in EEG signal Using Short-Time Fourier Transform

被引：13

作者：

Sameer, Mustafa ^{[1
]}

Gupta, Akash Kumar ^{[2
]}

Chakraborty, Chinmay ^{[2
]}

Gupta, Bharat ^{[1
]}

机构：

[1] Natl Inst Technol Patna, Dept Elect & Commun Engn, Patna, Bihar, India

[2] Birla Inst Technol, Dept Elect & Commun Engn, Jharkhand, India

来源：

2019 22ND INTERNATIONAL SYMPOSIUM ON WIRELESS PERSONAL MULTIMEDIA COMMUNICATIONS (WPMC) | 2019年

关键词：

Electroencephalogram; seizure detection; short-time fourier transform; gamma hand; random forest; t-f statistical features; WAVELET TRANSFORM;

D O I：

10.1109/wpmc48795.2019.9096119

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

The EEG signal consist various frequency bands, which represents human activities like emotion, attention sleep stage etc. For the detection of epileptical seizures, it is required to perform classification on the basis of various EEG segments. This paper, presents performance analysis of gamma band in EEG signal using short-time fourier transform (STFT). It also gives comparison of various classification methods and achieves very good accuracy with some classification techniques. Analysis has been performed with following stages like STFT, extraction of gamma frequency band, statistical features extraction and finally applied to classifier. This paper deals with extraction of statistical features from obtained 2-Dimensional data using STFT and performed classification in high frequency band for epilepsy. Here, proposed Random Forest (RF) classifier achieved accuracy of 90%.

引用

页数：6

共 32 条

[1]

Ac N., 2004, AUTOMATIC SPIKE DETE, V34, P561

[2] 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

[3]

Bhattacharjee Snehashish, 2019, Emerging Technologies in Data Mining and Information Security. Proceedings of IEMIS 2018. Advances in Intelligent Systems and Computing (AISC 814), P377, DOI 10.1007/978-981-13-1501-5_32

[4] Tunable-QWavelet Transform Based Multiscale Entropy Measure for Automated Classification of Epileptic EEG Signals [J].

Bhattacharyya, Abhijit ;

Pachori, Ram Bilas ;

Upadhyay, Abhay ;

Acharya, U. Rajendra .

APPLIED SCIENCES-BASEL, 2017, 7 (04)

[5] Principles of time-frequency feature extraction for change detection in non-stationary signals: Applications to newborn EEG abnormality detection [J].

Boashash, Boualem ;

Azemi, Ghasem ;

Khan, Nabeel Ali .

PATTERN RECOGNITION, 2015, 48 (03) :616-627

[6] Telemedicine Supported Chronic Wound Tissue Prediction Using Classification Approaches [J].

Chakraborty, Chinmay ;

Gupta, Bharat ;

Ghosh, Soumya K. ;

Das, Dev K. ;

Chakraborty, Chandan .

JOURNAL OF MEDICAL SYSTEMS, 2016, 40 (03) :1-12

[7] Comprehensive evaluation of environ-economic benefits of anaerobic digestion technology in an integrated food waste-based methane plant using a fuzzy mathematical model [J].

Chen, Ting ;

Shen, Dongsheng ;

Jin, Yiying ;

Li, Hailong ;

Yu, Zhixin ;

Feng, Huajun ;

Long, Yuyang ;

Yin, Jun .

APPLIED ENERGY, 2017, 208 :666-677

[8] TIME FREQUENCY-DISTRIBUTIONS - A REVIEW [J].

COHEN, L .

PROCEEDINGS OF THE IEEE, 1989, 77 (07) :941-981

[9]

Gajic D, 2015, FRONT COMPUT NEUROSC, V9, DOI [10.3389/fncom.7015.00038, 10.3389/fncom.2015.00038]

[10]

Harpale V., 2018, J. King Saud Univ. - Comput. Inf. Sci

← 1 2 3 4 →