English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the zaia usage as premium feature

ZAIA

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the access of premium content as premium feature

Premium Content

Zendy Tools

Zendy Open

Electroencephalography is frequently used for diagnostic evaluation ofvarious brain-related disorders due to its excellent resolution, non-invasivenature and low cost. However, manual analysis of EEG signals could be strenuousand a time-consuming process for experts. It requires long training time forphysicians to develop expertise in it and additionally experts have lowinter-rater agreement (IRA) among themselves. Therefore, many Computer AidedDiagnostic (CAD) based studies have considered the automation of interpretingEEG signals to alleviate the workload and support the final diagnosis. In thispaper, we present an automatic binary classification framework for brainsignals in multichannel EEG recordings. We propose to use Wavelet PacketDecomposition (WPD) techniques to decompose the EEG signals into frequencysub-bands and extract a set of statistical features from each of the selectedcoefficients. Moreover, we propose a novel method to reduce the dimension ofthe feature space without compromising the quality of the extracted features.The extracted features are classified using different Gradient BoostingDecision Tree (GBDT) based classification frameworks, which are CatBoost,XGBoost and LightGBM. We used Temple University Hospital EEG Abnormal CorpusV2.0.0 to test our proposed technique. We found that CatBoost classifierachieves the binary classification accuracy of 87.68%, and outperformsstate-of-the-art techniques on the same dataset by more than 1% in accuracy andmore than 3% in sensitivity. The obtained results in this research provideimportant insights into the usefulness of WPD feature extraction and GBDTclassifiers for EEG classification.

Automatic detection of abnormal EEG signals using wavelet feature extraction and gradient boosting decision tree