A systematic approach to seizure prediction using genetic and classifier based feature selection

M. D'Alessandre; G. Vachtseyanos; R. Esteller; J. Echauz; D. Sewell; B. Litt

doi:10.1109/ICDSP.2002.1028162

A systematic approach to seizure prediction using genetic and classifier based feature selection

M. D'Alessandre
, G. Vachtseyanos
, R. Esteller
, J. Echauz
, D. Sewell
, B. Litt

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

Currently, there is no standard approach for evaluating the intiacranial encephalography signals for seizure prediction. This study evaluates the IEEG signals by applying a systematic approach to feature selection, classification and validation to predict seizures. After preprocessing and processing, a genetic algorithm selects reasonable features off-line from a preselected group of features to serve as inputs to the classifier based feature selection process. A probabilistic neural network is used to select the optimal feature vector using a feed forward sequential approach on the training data followed by classification, A study of four patients resulted in a 62.5% average probability of prediction and a block false positive rate of0.2775 false positive predictions per hour.

Original language	English (US)
Title of host publication	2002 14th International Conference on Digital Signal Processing Proceedings, DSP 2002
Editors	A.N. Skodras, A.G. Constantinides
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	603-606
Number of pages	4
ISBN (Electronic)	0780375033
DOIs	https://doi.org/10.1109/ICDSP.2002.1028162
State	Published - 2002
Externally published	Yes
Event	14th International Conference on Digital Signal Processing, DSP 2002 - Santorini, Hellas, Greece Duration: Jul 1 2002 → Jul 3 2002

Publication series

Name	International Conference on Digital Signal Processing, DSP
Volume	2
ISSN (Print)	1546-1874
ISSN (Electronic)	2165-3577

Other

Other	14th International Conference on Digital Signal Processing, DSP 2002
Country/Territory	Greece
City	Santorini, Hellas
Period	7/1/02 → 7/3/02

Bibliographical note

Publisher Copyright:
© 2002 IEEE.

Publisher link

10.1109/ICDSP.2002.1028162

Find It

Find It at U of M Libraries

Cite this

D'Alessandre, M., Vachtseyanos, G., Esteller, R., Echauz, J., Sewell, D., & Litt, B. (2002). A systematic approach to seizure prediction using genetic and classifier based feature selection. In A. N. Skodras, & A. G. Constantinides (Eds.), 2002 14th International Conference on Digital Signal Processing Proceedings, DSP 2002 (pp. 603-606). Article 1028162 (International Conference on Digital Signal Processing, DSP; Vol. 2). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDSP.2002.1028162

A systematic approach to seizure prediction using genetic and classifier based feature selection. / D'Alessandre, M.; Vachtseyanos, G.; Esteller, R. et al.
2002 14th International Conference on Digital Signal Processing Proceedings, DSP 2002. ed. / A.N. Skodras; A.G. Constantinides. Institute of Electrical and Electronics Engineers Inc., 2002. p. 603-606 1028162 (International Conference on Digital Signal Processing, DSP; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

D'Alessandre, M, Vachtseyanos, G, Esteller, R, Echauz, J, Sewell, D & Litt, B 2002, A systematic approach to seizure prediction using genetic and classifier based feature selection. in AN Skodras & AG Constantinides (eds), 2002 14th International Conference on Digital Signal Processing Proceedings, DSP 2002., 1028162, International Conference on Digital Signal Processing, DSP, vol. 2, Institute of Electrical and Electronics Engineers Inc., pp. 603-606, 14th International Conference on Digital Signal Processing, DSP 2002, Santorini, Hellas, Greece, 7/1/02. https://doi.org/10.1109/ICDSP.2002.1028162

D'Alessandre M, Vachtseyanos G, Esteller R, Echauz J, Sewell D, Litt B. A systematic approach to seizure prediction using genetic and classifier based feature selection. In Skodras AN, Constantinides AG, editors, 2002 14th International Conference on Digital Signal Processing Proceedings, DSP 2002. Institute of Electrical and Electronics Engineers Inc. 2002. p. 603-606. 1028162. (International Conference on Digital Signal Processing, DSP). doi: 10.1109/ICDSP.2002.1028162

D'Alessandre, M. ; Vachtseyanos, G. ; Esteller, R. et al. / A systematic approach to seizure prediction using genetic and classifier based feature selection. 2002 14th International Conference on Digital Signal Processing Proceedings, DSP 2002. editor / A.N. Skodras ; A.G. Constantinides. Institute of Electrical and Electronics Engineers Inc., 2002. pp. 603-606 (International Conference on Digital Signal Processing, DSP).

@inproceedings{d6be0813a3b54b359e1ede344699f32a,

title = "A systematic approach to seizure prediction using genetic and classifier based feature selection",

abstract = "Currently, there is no standard approach for evaluating the intiacranial encephalography signals for seizure prediction. This study evaluates the IEEG signals by applying a systematic approach to feature selection, classification and validation to predict seizures. After preprocessing and processing, a genetic algorithm selects reasonable features off-line from a preselected group of features to serve as inputs to the classifier based feature selection process. A probabilistic neural network is used to select the optimal feature vector using a feed forward sequential approach on the training data followed by classification, A study of four patients resulted in a 62.5\% average probability of prediction and a block false positive rate of0.2775 false positive predictions per hour.",

author = "M. D'Alessandre and G. Vachtseyanos and R. Esteller and J. Echauz and D. Sewell and B. Litt",

note = "Publisher Copyright: {\textcopyright} 2002 IEEE.; 14th International Conference on Digital Signal Processing, DSP 2002 ; Conference date: 01-07-2002 Through 03-07-2002",

year = "2002",

doi = "10.1109/ICDSP.2002.1028162",

language = "English (US)",

series = "International Conference on Digital Signal Processing, DSP",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "603--606",

editor = "A.N. Skodras and A.G. Constantinides",

booktitle = "2002 14th International Conference on Digital Signal Processing Proceedings, DSP 2002",

}

TY - GEN

T1 - A systematic approach to seizure prediction using genetic and classifier based feature selection

AU - D'Alessandre, M.

AU - Vachtseyanos, G.

AU - Esteller, R.

AU - Echauz, J.

AU - Sewell, D.

AU - Litt, B.

PY - 2002

Y1 - 2002

N2 - Currently, there is no standard approach for evaluating the intiacranial encephalography signals for seizure prediction. This study evaluates the IEEG signals by applying a systematic approach to feature selection, classification and validation to predict seizures. After preprocessing and processing, a genetic algorithm selects reasonable features off-line from a preselected group of features to serve as inputs to the classifier based feature selection process. A probabilistic neural network is used to select the optimal feature vector using a feed forward sequential approach on the training data followed by classification, A study of four patients resulted in a 62.5% average probability of prediction and a block false positive rate of0.2775 false positive predictions per hour.

AB - Currently, there is no standard approach for evaluating the intiacranial encephalography signals for seizure prediction. This study evaluates the IEEG signals by applying a systematic approach to feature selection, classification and validation to predict seizures. After preprocessing and processing, a genetic algorithm selects reasonable features off-line from a preselected group of features to serve as inputs to the classifier based feature selection process. A probabilistic neural network is used to select the optimal feature vector using a feed forward sequential approach on the training data followed by classification, A study of four patients resulted in a 62.5% average probability of prediction and a block false positive rate of0.2775 false positive predictions per hour.

UR - https://www.scopus.com/pages/publications/84948683815

UR - https://www.scopus.com/pages/publications/84948683815#tab=citedBy

U2 - 10.1109/ICDSP.2002.1028162

DO - 10.1109/ICDSP.2002.1028162

M3 - Conference contribution

AN - SCOPUS:84948683815

T3 - International Conference on Digital Signal Processing, DSP

SP - 603

EP - 606

BT - 2002 14th International Conference on Digital Signal Processing Proceedings, DSP 2002

A2 - Skodras, A.N.

A2 - Constantinides, A.G.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th International Conference on Digital Signal Processing, DSP 2002

Y2 - 1 July 2002 through 3 July 2002

ER -

A systematic approach to seizure prediction using genetic and classifier based feature selection

Abstract

Publication series

Other

Bibliographical note

Publisher link

Find It

Other files and links

Fingerprint

Cite this