Document Detail

Low complexity algorithm for seizure prediction using Adaboost.
MedLine Citation:
PMID:  23366078     Owner:  NLM     Status:  MEDLINE    
This paper presents a novel low-complexity patient-specific algorithm for seizure prediction. Adaboost algorithm is used in two stages of the algorithm: feature selection and classification. The algorithm extracts spectral power features in 9 different sub-bands from the electroencephalogram (EEG) recordings. We have proposed a new feature ranking method to rank the features. The key (top ranked) features are used to make a prediction on the seizure event. Further, to reduce the complexity of classification stage, a non-linear classifier is built based on the Adaboost algorithm using decision stumps (linear classifier) as the base classifier. The proposed algorithm achieves a sensitivity of 94.375% for a total of 71 seizure events with a low false alarm rate of 0.13 per hour and 6.5% of time spent in false alarms using an average of 5 features for the Freiburg database. The low computational complexity of the proposed algorithm makes it suitable for an implantable device.
Manohar Ayinala; Keshab K Parhi
Related Documents :
23492958 - A behavioral study of daily mean turnover times and first case of the day start tardiness.
24804628 - Combining information from two data sources with misreporting and incompleteness to ass...
24294948 - Endocervical and high vaginal quantitative fetal fibronectin in predicting preterm birth.
24876618 - Continuous glucose monitoring in newborn infants: how do errors in calibration measurem...
25473018 - Does coping style predict optimization? an experimental test in a wild passerine bird.
8959028 - Extrapolation from animals to man. the integration of pharmacokinetics and pharmacodyna...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference     Volume:  2012     ISSN:  1557-170X     ISO Abbreviation:  Conf Proc IEEE Eng Med Biol Soc     Publication Date:  2012  
Date Detail:
Created Date:  2013-01-31     Completed Date:  2013-08-06     Revised Date:  2014-08-21    
Medline Journal Info:
Nlm Unique ID:  101243413     Medline TA:  Conf Proc IEEE Eng Med Biol Soc     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1061-4     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Electrodes, Implanted
Electroencephalography / instrumentation,  methods*
Predictive Value of Tests
Seizures / physiopathology*
Signal Processing, Computer-Assisted*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Nonlinear dynamics measures applied to EEG recordings of patients with attention deficit/hyperactivi...
Next Document:  A universal hybrid decision tree classifier design for human activity classification.