{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:30:54Z","timestamp":1772832654023,"version":"3.50.1"},"reference-count":60,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T00:00:00Z","timestamp":1668729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland Centre for Research Training in Digitally-Enhanced Reality (d-real)","doi-asserted-by":"publisher","award":["18\/CRT\/6224"],"award-info":[{"award-number":["18\/CRT\/6224"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Electroencephalography (EEG) signals can be analyzed in the temporal, spatial, or frequency domains. Noise and artifacts during the data acquisition phase contaminate these signals adding difficulties in their analysis. Techniques such as Independent Component Analysis (ICA) require human intervention to remove noise and artifacts. Autoencoders have automatized artifact detection and removal by representing inputs in a lower dimensional latent space. However, little research is devoted to understanding the minimum dimension of such latent space that allows meaningful input reconstruction. Person-specific convolutional autoencoders are designed by manipulating the size of their latent space. A sliding window technique with overlapping is employed to segment varied-sized windows. Five topographic head-maps are formed in the frequency domain for each window. The latent space of autoencoders is assessed using the input reconstruction capacity and classification utility. Findings indicate that the minimal latent space dimension is 25% of the size of the topographic maps for achieving maximum reconstruction capacity and maximizing classification accuracy, which is achieved with a window length of at least 1 s and a shift of 125 ms, using the 128 Hz sampling rate. This research contributes to the body of knowledge with an architectural pipeline for eliminating redundant EEG data while preserving relevant features with deep autoencoders.<\/jats:p>","DOI":"10.3390\/make4040053","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T04:39:59Z","timestamp":1669005599000},"page":"1042-1064","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["On the Dimensionality and Utility of Convolutional Autoencoder\u2019s Latent Space Trained with Topology-Preserving Spectral EEG Head-Maps"],"prefix":"10.3390","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6472-1339","authenticated-orcid":false,"given":"Arjun Vinayak","family":"Chikkankod","sequence":"first","affiliation":[{"name":"Artificial Intelligence and Cognitive Load Lab, The Applied Intelligence Research Centre, School of Computer Science, Technological University Dublin (TU Dublin), D07 EWV4 Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5153-4243","authenticated-orcid":false,"given":"Luca","family":"Longo","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Cognitive Load Lab, The Applied Intelligence Research Centre, School of Computer Science, Technological University Dublin (TU Dublin), D07 EWV4 Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e35237","DOI":"10.7554\/eLife.35237","article-title":"Whole brain comparative anatomy using connectivity blueprints","volume":"7","author":"Mars","year":"2018","journal-title":"eLife"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Cohen, M.X. (2014). Analyzing Neural Time Series Data: Theory and Practice, MIT Press.","DOI":"10.7551\/mitpress\/9609.001.0001"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.neucom.2016.08.050","article-title":"Multi-Category EEG Signal Classification Developing Time-Frequency Texture Features Based Fisher Vector Encoding Method","volume":"218","author":"Siuly","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_4","unstructured":"Stober, S., Sternin, A., Owen, A.M., and Grahn, J.A. (2015). Deep Feature Learning for EEG Recordings. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3047","DOI":"10.1002\/hbm.25834","article-title":"Beyond broadband: Towards a spectral decomposition of electroencephalography microstates","volume":"43","author":"Seeber","year":"2022","journal-title":"Hum. Brain Mapp."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1016\/j.neucom.2017.09.069","article-title":"1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data","volume":"275","author":"Abdeljaber","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal component analysis","volume":"2","author":"Abdi","year":"2010","journal-title":"Wires Comput. Stat."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2812","DOI":"10.1039\/C3AY41907J","article-title":"Principal component analysis","volume":"6","author":"Bro","year":"2014","journal-title":"Anal. Methods"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.knosys.2013.02.014","article-title":"Automated EEG analysis of epilepsy: A review","volume":"45","author":"Acharya","year":"2013","journal-title":"Knowl. Based Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2017.01.005","article-title":"A New Method for Quantifying the Performance of EEG Blind Source Separation Algorithms by Referencing a Simultaneously Recorded ECoG Signal","volume":"93","author":"Oosugi","year":"2017","journal-title":"Neural Netw."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Korats, G., Cam, S.L., Ranta, R., and Hamid, M.R. (2012, January 1\u20134). Applying ICA in EEG: Choice of the Window Length and of the Decorrelation Method. Proceedings of the International Joint Conference on Biomedical Engineering Systems and Technologies\u2014BIOSTEC, Vilamoura, Portugal.","DOI":"10.1007\/978-3-642-38256-7_18"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1016\/j.patrec.2007.01.002","article-title":"Spatial Filtering and Selection of Optimized Components in Four Class Motor Imagery EEG Data Using Independent Components Analysis","volume":"28","author":"Brunner","year":"2007","journal-title":"Pattern Recogn. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"37","DOI":"10.3389\/fnbot.2019.00037","article-title":"SAE+LSTM: A New Framework for Emotion Recognition From Multi-Channel EEG","volume":"13","author":"Xing","year":"2019","journal-title":"Front. Neurorobot."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3127641","article-title":"Efficient Rejection of Artifacts for Short-Term Few-Channel EEG Based on Fast Adaptive Multidimensional Sub-Bands Blind Source Separation","volume":"70","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_15","first-page":"1","article-title":"Real-Time Adaptive EEG Source Separation Using Online Recursive Independent Component Analysis","volume":"24","author":"Hsu","year":"2015","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"You, S.D., and Li, Y.C. (2020, January 1\u20133). Predicting Viewer\u2019s Preference for Music Videos Using EEG Dataset. Proceedings of the 2020 IEEE International Conference on Consumer Electronics\u2014Asia (ICCE-Asia), Seoul, Republic of Korea.","DOI":"10.1109\/ICCE-Asia49877.2020.9277435"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Arabshahi, R., and Rouhani, M. (2020, January 29\u201330). A convolutional neural network and stacked autoencoders approach for motor imagery based brain-computer interface. Proceedings of the 2020 10th International Conference on Computer and Knowledge Engineering (ICCKE), Mashhad, Iran.","DOI":"10.1109\/ICCKE50421.2020.9303717"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/TNSRE.2018.2884641","article-title":"Learning Spatial\u2013Spectral\u2013Temporal EEG Features with Recurrent 3D Convolutional Neural Networks for Cross-Task Mental Workload Assessment","volume":"27","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Yao, Y., Plested, J., and Gedeon, T. (2018, January 13\u201316). Deep Feature Learning and Visualization for EEG Recording Using Autoencoders. Proceedings of the 25th International Conference, ICONIP 2018, Siem Reap, Cambodia. Proceedings, Part VII.","DOI":"10.1007\/978-3-030-04239-4_50"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3051996","article-title":"A sliding window common spatial pattern for enhancing motor imagery classification in EEG-BCI","volume":"70","author":"Gaur","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1109\/TCDS.2019.2924648","article-title":"Affective EEG-based person identification using the deep learning approach","volume":"12","author":"Wilaiprasitporn","year":"2019","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.neucom.2021.06.048","article-title":"One dimensional convolutional neural networks for seizure onset detection using long-term scalp and intracranial EEG","volume":"459","author":"Wang","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.neucom.2017.01.061","article-title":"BHCR: RSVP target retrieval BCI framework coupling with CNN by a Bayesian method","volume":"238","author":"Huang","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.neucom.2016.05.035","article-title":"Improved SFFS method for channel selection in motor imagery based BCI","volume":"207","author":"Qiu","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.neucom.2015.11.065","article-title":"Kernel learning over the manifold of symmetric positive definite matrices for dimensionality reduction in a BCI application","volume":"179","author":"Sadatnejad","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.neucom.2020.01.034","article-title":"Deep convolution network based emotion analysis towards mental health care","volume":"388","author":"Fei","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.neucom.2019.08.029","article-title":"Semi-supervised facial expression recognition using reduced spatial features and Deep Belief Networks","volume":"367","author":"Kurup","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.neucom.2020.09.023","article-title":"Deep unsupervised multi-modal fusion network for detecting driver distraction","volume":"421","author":"Chen","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.neucom.2019.02.061","article-title":"Physiological-signal-based mental workload estimation via transfer dynamical autoencoders in a deep learning framework","volume":"347","author":"Yin","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.neucom.2018.09.071","article-title":"A Convolutional Neural Network approach for classification of dementia stages based on 2D-spectral representation of EEG recordings","volume":"323","author":"Ieracitano","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.neucom.2019.12.083","article-title":"Fusing convolutional neural network features with hand-crafted features for osteoporosis diagnoses","volume":"385","author":"Su","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1109\/TNSRE.2018.2813138","article-title":"A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series","volume":"26","author":"Chambon","year":"2018","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.ins.2019.06.008","article-title":"Comparative analysis of features extracted from EEG spatial, spectral and temporal domains for binary and multiclass motor imagery classification","volume":"502","author":"Lee","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, J., Jia, Z., and Lin, Y. (2020, January 17\u201320). Learning Space-Time-Frequency Representation with Two-Stream Attention Based 3D Network for Motor Imagery Classification. Proceedings of the 2020 IEEE International Conference on Data Mining (ICDM), Sorrento, Italy.","DOI":"10.1109\/ICDM50108.2020.00136"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ang, K.K., Chin, Z.Y., Wang, C., Guan, C., and Zhang, H. (2012). Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b. Front. Neurosci., 6.","DOI":"10.3389\/fnins.2012.00039"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"8659","DOI":"10.1016\/j.eswa.2010.06.065","article-title":"EEG signal classification using PCA, ICA, LDA and support vector machines","volume":"37","author":"Subasi","year":"2010","journal-title":"Expert Syst. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"627892","DOI":"10.1155\/2014\/627892","article-title":"EEG-Based Emotion Recognition Using Deep Learning Network with Principal Component Based Covariate Shift Adaptation","volume":"2014","author":"Jirayucharoensak","year":"2014","journal-title":"Sci. World J."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Viola, F.C., Debener, S., Thorne, J., and Schneider, T.R. (2010). Using ICA for the analysis of multi-channel EEG data. Simultaneous EEG and fMRI: Recording, Analysis, and Application: Recording, Analysis, and Application, Oxford Academic.","DOI":"10.1093\/acprof:oso\/9780195372731.003.0008"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1109\/TBME.2005.851521","article-title":"Spatio-spectral filters for improving the classification of single trial EEG","volume":"52","author":"Lemm","year":"2005","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1109\/TPAMI.2014.2330598","article-title":"Probabilistic common spatial patterns for multichannel EEG analysis","volume":"37","author":"Wu","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","first-page":"231","article-title":"Sliding-window technique for the analysis of cerebral evoked potentials","volume":"35","author":"Qi","year":"2003","journal-title":"Health Sci."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.bspc.2017.07.022","article-title":"Performance evaluation of empirical mode decomposition, discrete wavelet transform, and wavelet packed decomposition for automated epileptic seizure detection and prediction","volume":"39","author":"Alickovic","year":"2018","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.eswa.2015.10.049","article-title":"Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers","volume":"47","author":"Atkinson","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"ref_44","first-page":"4","article-title":"EEG source imaging enhances the decoding of complex right-hand motor imagery tasks","volume":"63","author":"Edelman","year":"2016","journal-title":"Ire Trans. Med. Electron."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.seizure.2015.01.012","article-title":"Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis","volume":"26","author":"Faust","year":"2015","journal-title":"Seizure"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/JBHI.2017.2688239","article-title":"DREAMER: A Database for Emotion Recognition Through EEG and ECG Signals From Wireless Low-cost Off-the-Shelf Devices","volume":"22","author":"Katsigiannis","year":"2018","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1007\/s11831-019-09344-w","article-title":"A survey of deep learning and its applications: A new paradigm to machine learning","volume":"27","author":"Dargan","year":"2020","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.1016\/j.drudis.2017.08.010","article-title":"From machine learning to deep learning: Progress in machine intelligence for rational drug discovery","volume":"22","author":"Zhang","year":"2017","journal-title":"Drug Discov. Today"},{"key":"ref_49","unstructured":"Bank, D., Koenigstein, N., and Giryes, R. (2020). Autoencoders. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Li, J., Struzik, Z.R., Zhang, L., and Cichocki, A. (2015). Feature learning from incomplete EEG with denoising autoencoder. arXiv.","DOI":"10.1016\/j.neucom.2014.08.092"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","article-title":"DEAP: A Database for Emotion Analysis; Using Physiological Signals","volume":"3","author":"Koelstra","year":"2012","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref_52","first-page":"1","article-title":"Sparse autoencoder","volume":"72","author":"Ng","year":"2011","journal-title":"CS294A Lect. Notes"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Ahlawat, S., Choudhary, A., Nayyar, A., Singh, S., and Yoon, B. (2020). Improved handwritten digit recognition using convolutional neural networks (CNN). Sensors, 20.","DOI":"10.3390\/s20123344"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"8","DOI":"10.4236\/jcc.2019.73002","article-title":"Image quality assessment through FSIM, SSIM, MSE and PSNR\u2014A comparative study","volume":"7","author":"Sara","year":"2019","journal-title":"J. Comput. Commun."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/TBCAS.2019.2957087","article-title":"Deep Learning Approach for Epileptic Focus Localization","volume":"14","author":"Daoud","year":"2020","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Abdelhameed, A.M., Daoud, H.G., and Bayoumi, M. (2018, January 21\u201324). Epileptic Seizure Detection using Deep Convolutional Autoencoder. Proceedings of the 2018 IEEE International Workshop on Signal Processing Systems (SiPS), Cape Town, South Africa.","DOI":"10.1109\/SiPS.2018.8598447"},{"key":"ref_57","unstructured":"Hussain, Z., Gimenez, F., Yi, D., and Rubin, D. (2017, January 4). Differential data augmentation techniques for medical imaging classification tasks. Proceedings of the AMIA Annual Symposium Proceedings, American Medical Informatics Association, Washington, DC, USA."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"107575","DOI":"10.1109\/ACCESS.2022.3212777","article-title":"Examining the Size of the Latent Space of Convolutional Variational Autoencoders Trained With Spectral Topographic Maps of EEG Frequency Bands","volume":"10","author":"Ahmed","year":"2022","journal-title":"IEEE Access"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.inffus.2021.05.009","article-title":"Notions of explainability and evaluation approaches for explainable artificial intelligence","volume":"76","author":"Vilone","year":"2021","journal-title":"Inf. Fusion"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Vilone, G., and Longo, L. (2021). Classification of Explainable Artificial Intelligence Methods through Their Output Formats. Mach. Learn. Knowl. Extr., 3.","DOI":"10.3390\/make3030032"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/4\/4\/53\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:21:26Z","timestamp":1760145686000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/4\/4\/53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,18]]},"references-count":60,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["make4040053"],"URL":"https:\/\/doi.org\/10.3390\/make4040053","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,18]]}}}