{"id":"doi:10.1109/tnnls.2019.2946869","kind":"article","title":"Subject-Independent Brain–Computer Interfaces Based on Deep Convolutional Neural Networks","authors":["Oyeon Kwon","Min-Ho Lee","Cuntai Guan","Seong–Whan Lee"],"author_count":4,"year":2019,"published":"2019-11-13","venue":"IEEE Transactions on Neural Networks and Learning Systems","cited_by":351,"doi":"10.1109/tnnls.2019.2946869","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1109/tnnls.2019.2946869","archive_url":"https://space-kitty.com/papers/doi:10.1109/tnnls.2019.2946869","updated":null,"pmid":"31725394","pmcid":null,"openalex_id":"W2986984881","pdf_url":"https://ieeexplore.ieee.org/ielx7/5962385/9212662/08897723.pdf","abstract":"For a brain-computer interface (BCI) system, a calibration procedure is required for each individual user before he/she can use the BCI. This procedure requires approximately 20-30 min to collect enough data to build a reliable decoder. It is, therefore, an interesting topic to build a calibration-free, or subject-independent, BCI. In this article, we construct a large motor imagery (MI)-based electroencephalography (EEG) database and propose a subject-independent framework based on deep convolutional neural networks (CNNs). The database is composed of 54 subjects performing the left- and right-hand MI on two different days, resulting in 21 600 trials for the MI task. In our framework, we formulated the discriminative feature representation as a combination of the spectral-spatial input embedding the diversity of the EEG signals, as well as a feature representation learned from the CNN through a fusion technique that integrates a variety of discriminative brain signal patterns. To generate spectral-spatial inputs, we first consider the discriminative frequency bands in an information-theoretic observation model that measures the power of the features in two classes. From discriminative frequency bands, spectral-spatial inputs that include the unique characteristics of brain signal patterns are generated and then transformed into a covariance matrix as the input to the CNN. In the process of feature representations, spectral-spatial inputs are individually trained through the CNN and then combined by a concatenation fusion technique. In this article, we demonstrate that the classification accuracy of our subject-independent (or calibration-free) model outperforms that of subject-dependent models using various methods [common spatial pattern (CSP), common spatiospectral pattern (CSSP), filter bank CSP (FBCSP), and Bayesian spatio-spectral filter optimization (BSSFO)].","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["EEG and Brain-Computer Interfaces"],"details":null,"provenance":"openalex+europepmc","attribution":"Abstract of \"Subject-Independent Brain–Computer Interfaces Based on Deep Convolutional Neural Networks\" by Oyeon Kwon, Min-Ho Lee, Cuntai Guan et al., https://doi.org/10.1109/tnnls.2019.2946869, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified.","topics":[{"slug":"brain-computer-interfaces","name":"Brain-Computer Interfaces","domain_slug":"neuroscience"},{"slug":"neuroai","name":"NeuroAI & Computational Neuroscience","domain_slug":"neuroscience"}],"cited_in_dossiers":[{"slug":"brain-computer-interfaces","title":"Brain-Computer Interfaces: State of the Field (October 2026)","url":"https://space-kitty.com/dossiers/brain-computer-interfaces"}]}