Özet:

Abstract The electroencephalography (EEG) signal is a crucial part of Brain-Computer Interface (BCI) technology. Simply put, the BCI is a non-muscular channel for information transfer between the brain and other devices. The primary goal of BCIs is to restore some level of social interaction for those who are unable to use their mouths or hands because of neurological impairments. Classification of EEG signals is essential for many uses, including imaging of motor imagery, diagnosis of pharmacological effects, identification of emotions, prediction of seizures, detection of eye states, and many others. As a result, the construction of an autonomous solution in the medical arena necessitates a powerful classification model capable of efficiently processing the EEG information. Accurate diagnosis of an eye disease using EEG data is a challenging but essential task in medicine and daily life. The fundamental goal of this study is to develop a hybrid model based on machine learning that improves the accuracy with which the ocular status of stroke patients may be detected from EEG data. It can aid in finding and eliminating anomalies, and it can help in developing the robotic or smart machine-based answer to societal problems. To determine its usefulness and accuracy, this hybrid categorization model was compared to state-of-the-art machine learning methods. The experimental analysis proves that the suggested hybrid classification model outperforms the competition. The suggested hybrid model outperforms the state-of-the-art on every test and validation metric.

Anahtar Kelimeler: