Total views : 102

Epileptic Seizure Prediction in EEG Records using Parallel Tree Based Learning and Feature Extraction

Affiliations

  • Bharathidasan University, Trichy – 620024, Tamilnadu, India
  • Department of Computer Applications, Alagappa University, Karaikudi – 630003, Tamilnadu, India

Abstract


Objectives: To propose an effective classifier to identify interictal from preictal signals and to reduce the EEG data size to fit into the processing model. Methods/Analysis: The first phase of the processing model identifies several features related to time-series data and identifies the features for data of specific dimension, called the epoch. A set of features are generated for each epoch and the corresponding class details are appended. The obtained data is used by the Classifier for the learning phase, followed by the test phase to identify the effectiveness of the classifier model. Findings: Experiments were conducted on EEG data obtained from American Epilepsy Foundation. The proposed features were extracted and the classifier model is trained and the prediction levels were recorded. It was observed that the true prediction levels of interictal signals showed high accuracy (0.91), while the true prediction levels of preictal signals exhibited moderate accuracy (0.66). The false predictions were identified to range from low to moderate (0.08 and 0.33). The accuracy levels were observed to be 0.75 and F-Measure was found to be 0.77. The architecture also exhibits moderate recall (0.66) and high precision levels (0.93). Novelty/Improvement: The proposed technique enables effective reduction of data by extracting features for an epoch, hence enabling customized data fine-tuning and scalability.

Keywords

Decision Tree, Feature Extraction, Random Forest, Seizure Prediction, EEG.

Full Text:

 |  (PDF views: 86)

References


  • Nandhakumar J, Tyagi MG. Evaluation of seizure activity after phospho-diesterase and adenylate cyclase inhibition (SQ22536) in animal models of epilepsy. Indian Journal of Science and Technology. 2010 Jul; 3(7):710-7.
  • Kwan P, Brodie MJ. Early identification of refractory epilepsy. New England Journal of Medicine. 2000 Feb; 342:314-19. Crossref. PMid:10660394.
  • Camfield P, Camfield C. Idiopathic generalized epilepsy with generalized tonic-clonic seizures (IGE–GTC): a populationbased cohort with N20 year follow up for medical and social outcome. Epilepsy and Behavior. 2010 May; 18(1-2):61-3. Crossref. PMid:20471324.
  • Prince PGK, Hemamalini R, Rajkumar RI. LabVIEW based abnormal muscular movement and fall detection using MEMS Accelerometer during the occurrence of seizure. Indian Journal of Science and Technology. 2014 Oct; 7(10):1625-31.
  • Ramgopal S, Thome-Souza S, Jackson M, Kadish NE, Fernandez IS, Klehm J, Bosl W, Reinsberger C, Schachter S, Loddenkemper T. Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy. Epilepsy and Behavior. 2014 Aug; 37:291-307. Crossref. PMid:25174001.
  • Freestone DR, Karoly PJ, Peterson AD, Kuhlmann L, Lai A, Goodarzy F, Cook MJ. Seizure prediction: science fiction or soon to become reality? Current Neurology and Neuroscience Reports. 2015 Nov; 15(11):1-9. Crossref. PMid:26404726.
  • Hassan AR, Siuly S, Zhang Y. Epileptic seizure detection in EEG signals using tunable-Q factor wavelet transform and bootstrap aggregating. Computer Methods and Programs in Biomedicine. 2016 Dec; 137:247-59. Crossref. PMid:28110729.
  • Ventura A, Franco JM, Ramos JP, Direito B, Dourado A. Epileptic seizure prediction and the dimensionality reduction problem. 19th International Conference on Artificial Neural Networks. 2009 Sep; p. 1-9.
  • Teixeira C, Favaro G, Direito B, Bandarabadi M, Feldwisch-Drentrup H, Ihle M, Alvarado C, Le Van Quyen M, Schelter B, Schulze-Bonhage A, Sales F. Brainatic: A system for real-time epileptic seizure prediction. Brain-Computer Interface Research. 2014; p. 7-17. PMid:24708728 PMCid:PMC3983857.
  • Samiee K, Kovacs P, Gabbouj M. Epileptic seizure detection in long-term EEG records using sparse rational decomposition and local Gabor binary patterns feature extraction. Knowledge-Based Systems. 2017 Feb; 118:228-40. Crossref.
  • Li D, Xie Q, Jin Q, Hirasawa K. A sequential method using multiplicative extreme learning machine for epileptic seizure detection. Neurocomputing. 2016 Nov; 214:692-707. Crossref.
  • Ulate-Campos A, Coughlin F, Gainza-Lein M, Fernandez IS, Pearl PL, Loddenkemper T. Automated seizure detection systems and their effectiveness for each type of seizure. Seizure. 2016 Aug; 40:88-101. Crossref. PMid:27376911.
  • Zamir ZR. Detection of epileptic seizure in EEG signals using linear least squares preprocessing. Computer Methods and Programs in Biomedicine. 2016 Sep; 133:95-109. Crossref. PMid:27393803.
  • Alotaiby TN, Alshebeili SA, Alshawi T, Ahmad I, El-Samie FE. EEG seizure detection and prediction algorithms: a survey. EURASIP Journal on Advances in Signal Processing. 2014 Dec. Crossref.
  • Giannakakis G, Sakkalis V, Pediaditis M, Tsiknakis M. Methods for seizure detection and prediction: an overview. Modern Electroencephalographic Assessment Techniques: Theory and Applications. 2014 Aug; 91:131-57. Crossref.
  • Jory C, Shankar R, Coker D, McLean B, Hanna J, Newman C. Safe and sound? A systematic literature review of seizure detection methods for personal use. Seizure. 2016 Mar; 36:4-15. Crossref. PMid:26859097
  • Fast Fourier transform. Available from: https:// en.wikipedia.org/wiki/Fast_Fourier_transform. Date accessed: 22/06/2017.
  • Borowska M. Entropy-Based Algorithms in the Analysis of Biomedical Signals. Studies in Logic, Grammar and Rhetoric. 2015 Dec; 43(1):21-32.
  • Cross correlation. Available from: https://en.wikipedia.org/ wiki/Cross-correlation. Date accessed: 23/06/2017. Indian J Vol 10 (27) | July 2017 | www.indjst.org ournal of Science and Technology 7 20. Hjorth B. EEG analysis based on time domain properties. Electroencephalography and Clinical Neurophysiology. 1970 Sep; 29(3):306-10. Crossref.
  • Zhang Z, Chen Z, Zhou Y, Du S, Zhang Y, Mei T, Tian X. Construction of rules for seizure prediction based on approximate entropy. Clinical Neurophysiology. 2014 Oct; 125(10):1959-66. Crossref. PMid:24690391.
  • Ho TK. Random decision forests. IEEE, Proceedings of the Third International Conference on Document Analysis and Recognition. 1995 Aug; 2:278-82.
  • Ho TK. The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998 Aug; 20(8):832-44. Crossref.
  • Quinlan JR. Simplifying decision trees. International Journal of Man-Machine Studies. 1987 Sep; 27(3):221-34. Crossref.
  • Breiman L. Random forests. Machine Learning. 2001 Oct; 45(1):5-32. Crossref.
  • Rao MJ, Rao MK. An RTOS based Architecture for Patient Monitoring System with Sensor Networks. Indian Journal of Science and Technology. 2016 May; 9(17):1-5.
  • Patel AD, Moss R, Rust SW, Patterson J, Strouse R, Gedela S, Haines J, Lin SM. Patient-centered design criteria for wearable seizure detection devices. Epilepsy and Behavior. 2016 Nov; 64:116-21. Crossref. PMid:27741462
  • Melbourne University Seizure Prediction. Available from: https://www.kaggle.com/c/melbourne-university-seizureprediction. Date accessed: 02/09/2016
  • Confusion matrix. Available from: https://en.wikipedia.org/wiki/Confusion_matrix. Date accessed: 14/05/2017.
  • Fawcett T. An introduction to ROC analysis. Pattern Recognition Letters. 2006 Jun; 27(8):861-74. Crossref.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.