2016 · 10 citations · 11 references
MedicineNeurosciencePediatricsAutism Spectrum DisordersBiomedical Signal ProcessingEpilepsyElectroencephalogram AnalysisElectroencephalogram Signal ProcessingElectroencephalographyEpilepsy ClassificationEpilepsy In ChildhoodNeurodevelopmental DisordersBinary ClassificationClassification By Electroencephalography PatternsEeg Feature ExtractionElectroencephalogram ClassificationElectroencephalography Feature ExtractionMental State ClassificationNeural Signal ClassificationRecurrence Analysis
The study of Electroencephalogram (EEG) is a noninvasive technique to explore the electrical activity of the brain to recognize brain diseases and also to find the different mental states. Classification of EEG Signals is a remarkable task in BCI applications. Early detection of Autism in children can have treatments with more positive outcomes. Children with Global development delay (GDD) can also have Autism. Clinical patients who are diagnosed for EEG can have different neurological disorder. The aim of this paper is to classify Autism, Epilepsy and GDD neurological disorder. We used features such as Approximate Entropy(ApEn)[10,13], sample entropy (SampEn)[10,13] and recurrence quantification analysis(RQA)[8,10,13] of main signal, wavelet based nonlinear features such as ApEn, SampEn, RQA of main signal, ApEn, energy and Autoregressive Coefficients(AR) of sub bands. We classified three classes and also conducted binary classification of neurological disorders for different combination. The results obtained can be interpreted that different neurological disorder can be classified using the proposed method.
11
EEG complexity as a biomarker for autism spectrum disorder risk
William J. Bosl, Adrienne Tierney, Helen Tager‐Flusberg et al. · BMC Medicine · 2011 · 488 citations · Full text