Brain signal which helps in cataloguing has turn out to be a critical fact in the area of research zone in biomedical engineering and artificial intelligence, making it predominant for sleuthing and detecting the neurological disorders in the human brain and also considering and understanding cognitive states. The Electroencephalogram i.e. EEG method is a non-invasive technique which is not painful and used to identify, detect and capture electrical signals as well as activity of the brain with high temporal tenacity features. However, the raw EEG signals are intricate and multifaceted which are non-stationary and complex to interpret or understood directly. This research paper represents an AI-based framework for categorizing the brain signals using EEG spectrogram images. This anticipated approach transforms the EEG time-series signals converted into time–frequency spectrogram depictions and also applies Convolutional Neural Networks (CNNs) for automatic feature extraction of the images and further doing classification. The model is basically assessed using typical performance metrics calculation including accuracy, precision, recall, F1-score and confusion matrix. The experimental discoveries reveal and demonstrate that spectrogram-based image which deep learning meaningfully improvises the classification of the performance compared to traditional or old dated machine learning methodology. This study highlights the potential and benefits of AI-driven EEG report analysis in medical diagnostics, brain and computer interfaces and cognitive reasoning of state monitoring.

This research paper represents a inclusive AI-based outline for brain signal cataloguing using images of EEG spectrogram. This is done by altering EEG signals into time–frequency depictions and more enhancing them and leveraging them into CNN models. The system accomplishes high sorting the performance while minimalizing manual feature engineering. This methodology proves the strong probability in healthcare diagnostics, neurotechnology and brain–computer interface applications. With the progressions in lightweight architectures and explicable AI, the EEG-based deep learning systems are more projected to perform a critical part in the area of next-generation intellectual healthcare resolutions.

[1] S. Sanei and J. A. Chambers, *EEG Signal Processing*. Hoboken, NJ, USA: Wiley-IEEE Press, 2007. [2] A. Subasi, “EEG signal classification using wavelet feature extraction and a mixture of expert model,” *Expert Systems with Applications*, vol. 32, no. 4, pp. 1084–1093, May 2007. [3] Z. Li, M. Zhang, H. Wang, and L. Zhang, “EEG feature extraction and recognition for emotion evaluation,” in *Proc. IEEE Int. Conf. Systems, Man and Cybernetics*, 2018, pp. 1213–1218. [4] Y. Yang, Z. Liu, W. Liu, and X. Duan, “Time–frequency analysis of EEG signal for motor imagery classification,” *IEEE Access*, vol. 6, pp. 16698–16709, 2018. [5] Z. Huang, J. Zhang, and Y. Wang, “EEG signal classification based on a deep convolution network,” in *Proc. IEEE Int. Conf. Bioinformatics and Biomedicine*, 2017, pp. 1309–1313. [6] J. Schmidhuber, “Deep learning in neural networks: An overview,” *Neural Networks*, vol. 61, pp. 85–117, Jan. 2015. [7] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in *Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)*, 2016, pp. 770–778. [8] F. Chollet, *Deep Learning with Python*. Shelter Island, NY, USA: Manning Publications, 2018. [9] G. Schalk et al., “BCI2000: A general-purpose brain-computer interface (BCI) system,” *IEEE Trans. Biomedical Engineering*, vol. 51, no. 6, pp. 1034–1043, Jun. 2004. [10] A. Krizhevsky, I. Sutskever, and G. Hinton, “ImageNet classification with deep convolutional neural networks,” in *Proc. Adv. Neural Inf. Process. Syst.*, 2012, pp. 1097–1105. [11] G. Pfurtscheller and F. H. Lopes da Silva, “Event-related EEG/MEG synchronization and desynchronization: Basic principles,” *Clinical Neurophysiology*, vol. 110, no. 11, pp. 1842–1857, Nov. 1999. [12] M. T. Islam, M. Hasan, and M. R. Afrin, “EEG based motor imagery classification using CNN,” *IEEE Access*, vol. 7, pp. 164105–164117, 2019. [13] X. Zhang, F. Zhou, and M. Song, “Spectrogram based convolutional neural network for EEG classification,” *IEEE/ACM Trans. Audio, Speech, and Language Processing*, vol. 28, pp. 345–356, 2020. [14] PhysioNet, “EEG Motor Movement/Imagery Dataset,” *PhysioNet*, 2008. [Online]. Available: https://physionet.org/content/eegmmidb/1.0.0/ [15] Yann LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015. [16] Sepp Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. [17] L. R. Rabiner and B. H. Juang, Fundamentals of Speech Recognition. Englewood Cliffs, NJ, USA: Prentice Hall, 1993. [18] Ingrid Daubechies, Ten Lectures on Wavelets. Philadelphia, PA, USA: SIAM, 1992. [19] S. Acharya, S. L. Oh, Y. Hagiwara, J. H. Tan, and H. Adeli, “Deep convolutional neural network for the automated detection of seizure using EEG signals,” Computers in Biology and Medicine, vol. 100, pp. 270–278, 2018. [20] U. R. Acharya, S. V. Sree, G. Swapna, R. J. Martis, and J. S. Suri, “Automated EEG analysis of epilepsy: A review,” Knowledge-Based Systems, vol. 45, pp. 147–165, 2013. [21] R. T. Schirrmeister et al., “Deep learning with convolutional neural networks for EEG decoding and visualization,” Human Brain Mapping, vol. 38, no. 11, pp. 5391–5420, 2017.