Simulating online and offline tasks using hybrid cheetah optimization algorithm for patients affected by...

Area of Science:

• Neuroscience
• Biomedical Engineering
• Computer Science

Background:

• Growing demand for improved care for neurodegenerative diseases.
• Locked-in syndrome (LIS) presents significant communication challenges.
• Brain-Computer Interface (BCI) offers a potential solution for communication restoration.

Purpose of the Study:

• To develop and evaluate a novel BCI system for paralyzed individuals.
• To compare the performance of offline versus online BCI analysis.
• To assess the effectiveness of Welch Power Spectral Density (W-PSD) and a hybrid FFNNCOA algorithm.

Main Methods:

• Utilized Welch Power Spectral Density (W-PSD) for feature extraction from electroencephalogram (EEG) signals.
• Employed a hybrid Feed Forward Neural Network Cheetah Optimization Algorithm (FFNNCOA) for signal classification.
• Conducted experiments in both offline and online modes with eighteen subjects.

Main Results:

• Offline BCI analysis significantly outperformed online analysis in real-time.
• Achieved high accuracies: 95.56% for males and 93.88% for females.
• Subjects found offline task management easier than online BCI operation.

Conclusions:

• The developed offline BCI system shows high potential for improving communication in LIS patients.
• The hybrid FFNNCOA algorithm combined with W-PSD is effective for BCI applications.
• Offline BCI processing offers a more manageable and accurate approach for real-time use.