RESEARCH PAPER Improved Patient-Independent Seizure Detection Using Hybrid Feature Extraction Approach with Atomic Function-Based Wavelets Durgesh Nandini 1 • Jyoti Yadav 1 • Asha Rani 1 • Vijander Singh 1 • Oleg V. Kravchenko 2 • Neeru Rathee 3 Received: 2 January 2023 / Accepted: 5 July 2023 Ó The Author(s), under exclusive licence to Shiraz University 2023 Abstract The rapidly rising seizure cases and poor patient-to-neurologist ratio necessitate the development of an efficient automatic seizure detection system. The most commonly used seizure detection systems adopt the patient-dependent approach and lack scalability. Therefore, this work presents an epilepsy seizure detection system using a segment-based patient-inde- pendent approach. The designed system is tested on a publicly available Children’s Hospital Boston-Massachusetts Institute of Technology Electroencephalogram database. The scheme utilizes a hybrid two-layer feature extraction tech- nique comprising a novel wavelet-based on atomic function, time-domain and nonlinear methods to investigate the EEG signals’ ictal and interictal seizure stages. Consequently, the resultant feature set is classified into seizure and non-seizure classes using machine learning algorithms, i.e. K-nearest neighbours, random forest and support vector machine, tuned using the grid search optimization technique. The performance of the proposed system is further improved by the novel ensemble feature selection method, which utilizes the majority voting obtained from different feature selection methods. The distinctiveness of the optimized features is verified by the analysis of variance statistical test. The adaptability and generalizability of the developed patient-independent system is validated on the Neurology and Sleep Centre database. The proposed patient-independent system involving the multi-domain feature extraction and ensemble feature selection pro- vides the highest accuracy of 99.00% using the random forest classifier. Hence, the proposed model proves to be an efficient method for epileptic seizure detection. Keywords Epilepsy  Patient-independent  Wavelet based on atomic functions  Ensemble feature selection  Random forest  Machine learning 1 Introduction Epilepsy is a chronic neurological disease that poses a global challenge to around 70 million people worldwide, with five million cases rising yearly (Zabihi et al. 2020). In epilepsy, the patient suffers from seizures, which are caused due to abrupt changes in the brain’s electrical activities. An epileptic seizure is marked by an involuntary recurrent intermittent convulsive movement of either a part of the body or the whole body. The severity of epileptic seizures ranges from unpredictable sensations to severe injuries leading to death. Traditionally, neurologists & Durgesh Nandini durgesh.ic18@nsut.ac.in Jyoti Yadav bmjyoti@gmail.com Asha Rani asha.rani@nsut.ac.in Vijander Singh vijaydee@nsut.ac.in Oleg V. Kravchenko ok@bmstu.ru Neeru Rathee neeru1rathee@gmail.com 1 Department Instrumentation and Control Engineering, Netaji Subhas University of Technology, Sector 3, Dwarka, New Delhi, India 2 FRC CSC RAS, Moscow, Russian Federation 3 ECE Department, Maharaja Surajmal Institute of Technology, New Delhi, India 123 Iranian Journal of Science and Technology, Transactions of Electrical Engineering https://doi.org/10.1007/s40998-023-00644-3