To enhance the classification performance of real-time brain-machine interface applications, we present a new clustering-based ensemble technique called CluSem to mitigate the problem. To obtain MI-EEG brain signals, we built an application program manipulating Emotiv SDK.

We have achieved superior performance on CluSem and it significantly outperforms previously used classifiers for this task. It also brings new potentials to the health and rehabilitation industry.

Publication: Journal of Neuroscience Methods, Elsevier, Impact Factor: 2.785

Datasets, Source Code

We have proposed an ensemble method to enhance the prediction accuracy of real-time electroencephalogram signals classification and developed a system that can distinguish different human thoughts.

We have applied the proposed classifier for developing a brain game to evaluate the classification performance of real-time MI movements. In this game, real-time EEG signal classification and prediction tabulation through animated balls are controlled via threads. By playing this game, users can control the movements of the balls via the brain signals of MI movements without using any traditional input devices.

Publication: TENSYMP 2019, IEEE

Datasets, Source Code

We have introduced a new method for improving the detection rate to classify minority-class network attacks/ intrusions using cluster-based under-sampling with a Random Forest classifier.

The proposed method is a multi-layer classification approach, which can process the highly imbalanced big data to identify correctly the minority/ rare class intrusions. We have used a cluster-based under-sampling technique to deal with the class imbalance problem and popular ensemble classifier Random Forest for addressing the overfitting problem.

Publication: ICASERT 2019, IEEE

Datasets, Source Code