EEG Signal Classification Using Fast Fourier Transform and Convolutional Neural Networks: A Hybrid Deep Learning Approach for Binary Classification of Normal and Abnormal Brain Activity
Aahana Bisoi1, Shashivadhanan Sundaravadhanan2, Achint Krishna3, Ajitav Sahoo4
1Aahana Bisoi, Student, Department of Neurology, Indian School Al Ghubra (International), Muscat (Muscat Governorate), Oman.
2Dr. Shashivadhanan Sundaravadhanan, Professor, Department of Neurosurgery, Aster Advanced Robotic Rehabilitation Hospital, Muscat (Muscat Governorate), Oman.
3Dr. Achint Krishna, Department of Neurology, Aster Advanced Robotic Rehabilitation Hospital, Muscat (Muscat Governorate), Oman.
4Ajitav Sahoo, Department of Software and Systems, Amazon, Al Assalah towers Way no3706 Near Grand Mosque, Citadine hotel Al Ghubra Muscat, Sultanate of Oman. Bellevue (Washington), Oman.
Manuscript received on 05 June 2026 | First Revised Manuscript received on 26 June 2026 | Second Manuscript Accepted on 25 July 2026 | Manuscript Accepted on 15 August 2026 | Manuscript published on 30 August 2026 | PP: 1-6 | Volume-15 Issue-6, August 2026 | Retrieval Number: 100.1/ijeat.E478815050626 | DOI: 10.35940/ijeat.E4788.15060826
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This study presents a prototype that classifies full EEG recordings as either seizure-labelled or non-seizure-labelled. The method first uses Fast Fourier Transform (FFT) to convert each EEG into the frequency domain, then applies a two-dimensional Convolutional Neural Network (2D CNN) for classification. It was observed that many trainees and students found EEG interpretation difficult. Labelling was straightforward: any recording with at least one labelled seizure was marked as seizure labelled, and the rest as non-seizure-labelled. Training used two public datasets from PhysioNet: the pediatric CHB-MIT and adult Siena scalp EEG databases, with seizure labels from patient annotation files. To give the prototype a realistic run, eleven anonymised EEG recordings from Aster Royal Al Raffah Hospital in Muscat, Oman, were taken and used for external validation; out of those eleven, five were labelled as non-seizure recordings and six as seizure recordings. In early tests, the prototype achieved about 88% accuracy, with F1-scores of 0.95 and 0.91 for the two classes, and 82% accuracy on the hospital data. These results are preliminary, and full validation is planned. The tool is designed to help trainees during supervision, not to diagnose patients or identify seizures within recordings.
Keywords: Electroencephalography (EEG); Convolutional Neural Networks (CNN); Fast Fourier Transform (FFT); Spectral Analysis; Binary Classification; Deep Learning;
Scope of the Article: Biomedical Engineering