{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T10:11:24Z","timestamp":1784542284707,"version":"3.55.0"},"reference-count":51,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T00:00:00Z","timestamp":1681862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T021063\/1"],"award-info":[{"award-number":["EP\/T021063\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper presents a trainable hybrid approach involving a shallow autoencoder (AE) and a conventional classifier for epileptic seizure detection. The signal segments of a channel of electroencephalogram (EEG) (EEG epochs) are classified as epileptic and non-epileptic by employing its encoded AE representation as a feature vector. Analysis on a single channel-basis and the low computational complexity of the algorithm allow its use in body sensor networks and wearable devices using one or few EEG channels for wearing comfort. This enables the extended diagnosis and monitoring of epileptic patients at home. The encoded representation of EEG signal segments is obtained based on training the shallow AE to minimize the signal reconstruction error. Extensive experimentation with classifiers has led us to propose two versions of our hybrid method: (a) one yielding the best classification performance compared to the reported methods using the k-nearest neighbor (kNN) classifier and (b) the second with a hardware-friendly architecture and yet with the best classification performance compared to other reported methods in this category using a support-vector machine (SVM) classifier. The algorithm is evaluated on the Children\u2019s Hospital Boston, Massachusetts Institute of Technology (CHB-MIT), and University of Bonn EEG datasets. The proposed method achieves 98.85% accuracy, 99.29% sensitivity, and 98.86% specificity on the CHB-MIT dataset using the kNN classifier. The best figures using the SVM classifier for accuracy, sensitivity, and specificity are 99.19%, 96.10%, and 99.19%, respectively. Our experiments establish the superiority of using an AE approach with a shallow architecture to generate a low-dimensionality yet effective EEG signal representation capable of high-performance abnormal seizure activity detection at a single-channel EEG level and with a fine granularity of 1 s EEG epochs.<\/jats:p>","DOI":"10.3390\/s23084112","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T02:01:11Z","timestamp":1681956071000},"page":"4112","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["A Shallow Autoencoder Framework for Epileptic Seizure Detection in EEG Signals"],"prefix":"10.3390","volume":"23","author":[{"given":"Gul Hameed","family":"Khan","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Lahore University of Management Sciences (LUMS), Lahore 54792, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nadeem Ahmad","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Lahore University of Management Sciences (LUMS), Lahore 54792, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3615-3546","authenticated-orcid":false,"given":"Muhammad Awais Bin","family":"Altaf","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Lahore University of Management Sciences (LUMS), Lahore 54792, Pakistan"},{"name":"Engineering and Design Department, Western Washington University, Bellingham, WA 98225, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7097-9969","authenticated-orcid":false,"given":"Qammer","family":"Abbasi","sequence":"additional","affiliation":[{"name":"Communications Sensing and Imaging Research Group, James Watt School of Engineering, University of Glasgow, Glasgow G12 8QQ, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Malekzadeh, A., Zare, A., Yaghoobi, M., Kobravi, H.R., and Alizadehsani, R. (2021). Epileptic Seizures Detection in EEG Signals Using Fusion Handcrafted and Deep Learning Features. Sensors, 21.","DOI":"10.3390\/s21227710"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1109\/JBHI.2020.3022211","article-title":"An Ensemble of Hyperdimensional Classifiers: Hardware-Friendly Short-Latency Seizure Detection With Automatic iEEG Electrode Selection","volume":"25","author":"Burrello","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1109\/TNSRE.2020.2973434","article-title":"Epileptic Seizure Detection in EEG Signals Using a Unified Temporal-Spectral Squeeze-and-Excitation Network","volume":"28","author":"Li","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103671","DOI":"10.1016\/j.compbiomed.2020.103671","article-title":"Selection of features for patient-independent detection of seizure events using scalp EEG signals","volume":"119","author":"Yang","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3241056","article-title":"Applying Deep Learning for Epilepsy Seizure Detection and Brain Mapping Visualization","volume":"15","author":"Hossain","year":"2019","journal-title":"Acm Trans. Multimed. Comput. Commun. Appl."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/JBHI.2017.2703873","article-title":"Adaptive Seizure Onset Detection Framework Using a Hybrid PCA\u2013CSP Approach","volume":"22","author":"Khanmohammadi","year":"2018","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1109\/TNSRE.2021.3055276","article-title":"Seizure Onset Detection Using Empirical Mode Decomposition and Common Spatial Pattern","volume":"29","author":"Li","year":"2021","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"12941","DOI":"10.1109\/JSEN.2020.3003733","article-title":"Optimal Selection of Customized Features for Implementing Seizure Detection in Wearable Electroencephalography Sensor","volume":"20","author":"Jiang","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"T\u0103u\u0163an, A.M., Dogariu, M., and Ionescu, B. (2019, January 23\u201327). Detection of Epileptic Seizures using Unsupervised Learning Techniques for Feature Extraction. Proceedings of the 41st International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany.","DOI":"10.1109\/EMBC.2019.8856315"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Tang, Z., Zhang, C., Song, Y., and Zhang, M. (2021, January 22\u201328). Design of a Seizure Detector Using Single channel EEG Signal. Proceedings of the 2021 IEEE International Symposium on Circuits and Systems (ISCAS), Daegu, Republic of Korea.","DOI":"10.1109\/ISCAS51556.2021.9401209"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zanetti, R., Aminifar, A., and Atienza, D. (2020, January 20\u201324). Robust Epileptic Seizure Detection on Wearable Systems with Reduced False-Alarm Rate. Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Glasgow, UK.","DOI":"10.1109\/EMBC44109.2020.9175339"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1109\/JBHI.2019.2906400","article-title":"Patient-Specific Seizure Detection Using Nonlinear Dynamics and Nullclines","volume":"24","author":"Zabihi","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"9377","DOI":"10.1109\/JSEN.2021.3057076","article-title":"Deep Learning for Patient-Independent Epileptic Seizure Prediction Using Scalp EEG Signals","volume":"21","author":"Dissanayake","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5422","DOI":"10.1109\/JSEN.2023.3237383","article-title":"Automatic Eyeblink and Muscular Artifact Detection and Removal From EEG Signals Using k-Nearest Neighbor Classifier and Long Short-Term Memory Networks","volume":"23","author":"Ghosh","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ahmed, M.Z.I., Sinha, N., Ghaderpour, E., Phadikar, S., and Ghosh, R. (2023). A Novel Baseline Removal Paradigm for Subject-Independent Features in Emotion Classification Using EEG. Bioengineering, 10.","DOI":"10.3390\/bioengineering10010054"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Alkanhal, I., Kumar, B.V.K.V., and Savvides, M. (2018, January 17\u201320). Automatic Seizure Detection via an Optimized Image-Based Deep Feature Learning. Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA.","DOI":"10.1109\/ICMLA.2018.00086"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1717","DOI":"10.1109\/TNSRE.2018.2864306","article-title":"Denoising Sparse Autoencoder-Based Ictal EEG Classification","volume":"26","author":"Qiu","year":"2018","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Khan, G.H., Khan, N.A., Altaf, M.A.B., and Abid, M.R. (2021, January 1\u20135). Classifying Single Channel Epileptic EEG data based on Sparse Representation using Shallow Autoencoder. Proceedings of the 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Guadalajara, Mexico.","DOI":"10.1109\/EMBC46164.2021.9630714"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Khan, G.H., Khan, N.A., and Altaf, M.A.B. (2022, January 6\u20138). Shallow Sparse Autoencoder Based Epileptic Seizure Prediction. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Las Vegas, NV, USA.","DOI":"10.1109\/BIBM55620.2022.9995059"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/TNSRE.2015.2505238","article-title":"Analysis of High-Dimensional Phase Space via Poincar\u00e9 Section for Patient-Specific Seizure Detection","volume":"24","author":"Zabihi","year":"2016","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"16919","DOI":"10.1109\/ACCESS.2017.2736014","article-title":"Mallat\u2019s Scattering Transform Based Anomaly Sensing for Detection of Seizures in Scalp EEG","volume":"5","author":"Ahmad","year":"2017","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"638036","DOI":"10.1155\/2015\/638036","article-title":"Comparative Analysis of Classifiers for Developing an Adaptive Computer-Assisted EEG Analysis System for Diagnosing Epilepsy","volume":"2015","author":"Ahmad","year":"2015","journal-title":"Biomed Res. Int."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LSENS.2021.3086755","article-title":"Ramanujan Periodic Subspace Based Epileptic EEG Signals Classification","volume":"5","author":"Mathur","year":"2021","journal-title":"IEEE Sens. Lett."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"056004","DOI":"10.1088\/1741-2552\/aaceb1","article-title":"Patient-specific seizure detection in long-term EEG using signal derived empirical mode decomposition based dictionary approach","volume":"46","author":"Kaleem","year":"2018","journal-title":"J. Neural Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"104004","DOI":"10.1016\/j.compbiomed.2020.104004","article-title":"Scalable and energy efficient seizure detection based on direct use of compressively-sensed EEG data on an ultra low power multi-core architecture","volume":"125","author":"Aghazadeh","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"26","DOI":"10.3390\/signals1010003","article-title":"Modeling Volatility Characteristics of Epileptic EEGs using GARCH Models","volume":"1","author":"Follis","year":"2020","journal-title":"Signals"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"101930","DOI":"10.1016\/j.bspc.2020.101930","article-title":"Time domain implementation of pediatric epileptic seizure detectionsystem for enhancing the performance of detection and easymonitoring of pediatric patients","volume":"59","author":"Chakrabarti","year":"2020","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1109\/TBCAS.2014.2386891","article-title":"A 1.83 \u03bc J\/Classification, 8-Channel, Patient-Specific Epileptic Seizure Classification SoC Using a Non-Linear Support Vector Machine","volume":"10","author":"Yoo","year":"2016","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.1007\/s11517-017-1613-2","article-title":"Epileptic seizure classifications of single-channel scalp EEG data using wavelet-based features and SVM","volume":"55","author":"Janjarasjitt","year":"2017","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sopic, D., Aminifar, A., and Atienza, D. (2018, January 27\u201330). e-Glass: A Wearable System for Real-Time Detection of Epileptic Seizures. Proceedings of the 2018 IEEE International Symposium on Circuits and Systems (ISCAS), Florence, Italy.","DOI":"10.1109\/ISCAS.2018.8351728"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ambati, R., Raja, S., Al-Hameed, M., John, T., Arjoune, Y., and Shekhar, R. (2022). Neuromorphic architecture accelerated automated seizure detection in multi-channel scalp EEG. Sensors, 22.","DOI":"10.3390\/s22051852"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/s10916-019-1234-4","article-title":"Patient-Specific Seizure Detection Method using Hybrid Classifier with Optimized Electrodes","volume":"43","author":"Selvakumari","year":"2019","journal-title":"J. Med. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1109\/JETCAS.2018.2842761","article-title":"Integer Convolutional Neural Network for Seizure Detection","volume":"8","author":"Truong","year":"2018","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Boo, Y., Shin, S., and Sung, W. (2020, January 20\u201322). Quantized Neural Networks: Characterization and Holistic Optimization. Proceedings of the 2020 IEEE Workshop on Signal Processing Systems (SiPS), Coimbra, Portugal.","DOI":"10.1109\/SiPS50750.2020.9195245"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ouichka, O., Echtioui, A., and Hamam, H. (2022). Deep Learning Models for Predicting Epileptic Seizures Using iEEG Signals. Electronics, 11.","DOI":"10.3390\/electronics11040605"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"114630","DOI":"10.1016\/j.eswa.2021.114630","article-title":"Detection of epileptic seizures from compressively sensed EEG signals for wireless body area networks","volume":"172","author":"Aghababaei","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_37","unstructured":"Shoeb, A. (2009). Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment. [Ph.D. Thesis, Massachusetts Institute of Technology]."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"104250","DOI":"10.1016\/j.compbiomed.2021.104250","article-title":"Automatic seizure detection using orthogonal matching pursuit, discrete wavelet transform, and entropy based features of EEG signals","volume":"131","author":"Zarei","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_39","first-page":"061907","article-title":"Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state","volume":"64","author":"Andrzejac","year":"2021","journal-title":"Phys. Rev."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"102854","DOI":"10.1016\/j.bspc.2021.102854","article-title":"Analysis of epileptic seizures based on EEG using recurrence plot images and deep learning","volume":"69","author":"Shankar","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1109\/TNSRE.2016.2611601","article-title":"LMD Based Features for the Automatic Seizure Detection of EEG Signals Using SVM","volume":"25","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wang, X., Gong, G., and Li, N. (2019). Automated Recognition of Epileptic EEG States Using a Combination of Symlet Wavelet Processing, Gradient Boosting Machine, and Grid Search Optimizer. Sensors, 19.","DOI":"10.3390\/s19020219"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Draszawka, K., and Szyma\u0144ski, J. (2017, January 27\u201329). Analysis of Denoising Autoencoder Properties Through Misspelling Correction Task. Proceedings of the International Conference on Computational Collective Intelligence (ICCCI), Nicosia, Cyprus.","DOI":"10.1007\/978-3-319-67077-5_42"},{"key":"ref_44","unstructured":"Nguyen, T.V., Wong, R.K.W., and Hegde, C. (2019, January 16\u201318). On the Dynamics of Gradient Descent for Autoencoders. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), Naha, Japan."},{"key":"ref_45","unstructured":"Roche, F., Hueber, T., Limier, S., and Girin, L. (2018). Autoencoders for music sound modeling: A comparison of linear, shallow, deep, recurrent and variational models. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"213619","DOI":"10.1109\/ACCESS.2020.3040169","article-title":"Systems Thinking in Software Projects an Artificial Neural Network Approach","volume":"8","year":"2020","journal-title":"IEEE Access"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/JBHI.2018.2871678","article-title":"A Multi-View Deep Learning Framework for EEG Seizure Detection","volume":"23","author":"Yuan","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Akbulut, Y., Sengur, A., Guo, Y., and Smarandache, F. (2017). NS-k-NN: Neutrosophic Set-Based k-Nearest Neighbors Classifier. Symmetry, 9.","DOI":"10.3390\/sym9090179"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1109\/TBCAS.2020.3004544","article-title":"ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification","volume":"14","author":"Zhu","year":"2020","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_50","unstructured":"Page, A., Turner, J.T., Mohsenin, T., and Oates, T. (2014, January 21\u201323). Comparing Raw Data and Feature Extraction for Seizure Detection with Deep Learning Methods. Proceedings of the Twenty-Seventh International Florida Artificial Intelligence Research Society Conference (FLAIRS), Pensacola Beach, FL, USA."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"2728","DOI":"10.1109\/JSSC.2015.2482498","article-title":"A 16-Channel Patient-Specific Seizure Onset and Termination Detection SoC with Impedance-Adaptive Transcranial Electrical Stimulator","volume":"50","author":"Altaf","year":"2015","journal-title":"IEEE J.-Solid-State Circuits"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/4112\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:19:18Z","timestamp":1760123958000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/8\/4112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,19]]},"references-count":51,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["s23084112"],"URL":"https:\/\/doi.org\/10.3390\/s23084112","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,19]]}}}