Smart Healthcare: Machine Learning-Based Classification of Epileptic Seizure Disease Using EEG Signal Analysis
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V2I3P107Keywords:
Epileptic Seizure Detection, EEG Signal Analysis, Convolutional Neural Network (CNN), Machine Learning, Seizure Prediction, UCI Epileptic Seizure DatasetAbstract
At the moment, epileptic disease (ED) is regarded as one of the progressive disorders that affect brain function over a number of months or years. The main prevalent cause of eating disorders is a seizure state. This study employs a Convolutional Neural Network (CNN)-based method to predict epileptic seizures by analyzing EEG data. The approach utilizes the UCI Epileptic Seizure Recognition dataset, with preprocessing steps including outlier removal and Min-Max normalization to enhance data quality. Raw time-series EEG data were used directly for classification, removing the requirement for feature engineering by hand. The suggested CNN model achieved 99% accuracy, 99% precision, 99% recall, and 99% F1-score, demonstrating outstanding performance. Comparative analysis with baseline models Fully Connected Neural Network (FCNN), Random Forest (RF), and Support Vector Classifier (SVC) demonstrated the superior accuracy of the CNN model. These results highlight its potential for integration into real-time smart healthcare systems, enabling proactive patient monitoring and timely intervention in clinical settings
References
[1] V. Kolluri, “Machine Learning in Managing Healthcare Supply Chains: How Machine Learning,” J. Emerg. Technol. Innov. Res., vol. 3, no. 6, 2016.
[2] M. A. Sayeed, S. P. Mohanty, E. Kougianos, and H. P. Zaveri, “eSeiz: An Edge-Device for Accurate Seizure Detection for Smart Healthcare,” IEEE Trans. Consum. Electron., vol. 65, no. 3, pp. 379–387, 2019, doi: 10.1109/TCE.2019.2920068.
[3] R. B. Pachori and V. Bajaj, “Analysis of normal and epileptic seizure EEG signals using empirical mode decomposition,” Comput. Methods Programs Biomed., vol. 104, no. 3, pp. 373–381, 2011, doi: https://doi.org/10.1016/j.cmpb.2011.03.009.
[4] Κ. Tsiouris, V. C. Pezoulas, M. Zervakis, S. Konitsiotis, D. D. Koutsouris, and D. I. Fotiadis, “A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals,” Comput. Biol. Med., 2018, doi: 10.1016/j.compbiomed.2018.05.019.
[5] V. Kolluri, “An Innovative Study Exploring Revolutionizing Healthcare with AI: Personalized Medicine: Predictive Diagnostic Techniques and Individualized Treatment,” J. Emerg. Technol. Innov. Res., vol. 3, no. 11, 2016.
[6] A. K. Jaiswal and H. Banka, “Epileptic seizure detection in EEG signal using machine learning techniques,” Australas. Phys. Eng. Sci. Med., vol. 41, no. 1, pp. 81–94, 2018, doi: 10.1007/s13246-017-0610-y.
[7] A. Pumsirirat and L. Yan, “Credit Card Fraud Detection using Deep Learning based on Auto-Encoder and Restricted Boltzmann Machine,” Int. J. Adv. Comput. Sci. Appl., vol. 9, no. 1, 2018, doi: 10.14569/IJACSA.2018.090103.
[8] V. Kolluri, “A Pioneering Approach To Forensic Insights: Utilization AI for Cybersecurity Incident Investigations,” Int. J. Res. Anal. Rev., vol. 3, no. 3, 2016.
[9] N. Ahammad, T. Fathima, and P. Joseph, “Detection of Epileptic Seizure Event and Onset Using EEG,” Biomed Res. Int., vol. 2014, pp. 1–7, 2014, doi: 10.1155/2014/450573.
[10] G. Xun, X. Jia, and A. Zhang, “Detecting epileptic seizures with electroencephalogram via a context-learning model,” BMC Med. Inform. Decis. Mak., vol. 16, no. S2, p. 70, Jul. 2016, doi: 10.1186/s12911-016-0310-7.
[11] S. A. Grabat, A. S. Ashour, M. M. A. Elnaby, and F. E. A. El-Samie, “S-Transform-Based Electroencephalography Seizure Detection and Prediction,” in 2019 7th International Japan-Africa Conference on Electronics, Communications, and Computations, (JAC-ECC), 2019, pp. 111–115. doi: 10.1109/JAC-ECC48896.2019.9051320.
[12] L. Billeci, A. Tonacci, M. Varanini, P. Detti, G. Z. M. de Lara, and G. Vatti, “Epileptic seizures prediction based on the combination of EEG and ECG for the application in a wearable device,” in 2019 IEEE 23rd International Symposium on Consumer Technologies (ISCT), 2019, pp. 28–33. doi: 10.1109/ISCE.2019.8900998.
[13] A. A. Gaho, M. A. Jatoi, S. H. A. Musavi, and M. Shafiq, “Brain Mapping of Cortical Epileptogenic Zones and Their EEG Source Localization,” in 2019 2nd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), IEEE, Jan. 2019, pp. 1–6. doi: 10.1109/ICOMET.2019.8673488.
[14] V. Rajendran and S. Kumar, “Performance Analysis of Epileptic Seizure Detection System Using Neural Network Approach,” in 2019 International Conference on Computational Intelligence in Data Science (ICCIDS), IEEE, Feb. 2019, pp. 1–5. doi: 10.1109/ICCIDS.2019.8862158.
[15] U. R. Acharya, S. L. Oh, Y. Hagiwara, J. H. Tan, and H. Adeli, “Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals,” Comput. Biol. Med., vol. 100, pp. 270–278, Sep. 2018, doi: 10.1016/j.compbiomed.2017.09.017.
[16] M. Zhou et al., “Epileptic Seizure Detection Based on EEG Signals and CNN,” Front. Neuroinform., vol. 12, Dec. 2018, doi: 10.3389/fninf.2018.00095.
[17] G. A. Maggiotti, “EEG-Based Brain Disorders Diagnosis through Deep Neural Networks,” KDD Conf., 2019.
[18] A. H. Osman and A. A. Alzahrani, “New Approach for Automated Epileptic Disease Diagnosis Using an Integrated Self-Organization Map and Radial Basis Function Neural Network Algorithm,” IEEE Access, vol. 7, pp. 4741–4747, 2019, doi: 10.1109/ACCESS.2018.2886608.
[19] A. Bhowmick, T. Abdou, and A. Bener, “Predictive Analytics in Healthcare Epileptic Seizure Recognition,” in CASCON ’18: Proceedings of the 28th Annual International Conference on Computer Science and Software Engineering, 2018, pp. 323–330.
[20] Kalla, D., & Samiuddin, V. (2020). Chatbot for medical treatment using NLTK Lib. IOSR J. Comput. Eng, 22, 12.
[21] Kuraku, S., & Kalla, D. (2020). Emotet malware a banking credentials stealer. Iosr J. Comput. Eng, 22, 31-41.
