On Transfer Learning for Naive Brain Computer Interface Users

Liu, Ruofan; Kumar, Satyam; Alawieh, Hussein; Carnahan, Evan; Millán, José del R.

doi:10.1109/ner52421.2023.10123866

Cited by 1 publication

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One recording session consisted of four runs of MI task performance, with one run comprising 20 trials-10-10 for left and right directions-in a randomized order. This dataset was also analyzed and verified in previous studies (Liu et al, 2023;Kumar et al, 2024). In the online demonstration, subjects performed four offline runs to collect calibration data for training the decoder, then performed five runs online on the same day (Figure 1, right), hence to reduce the effects of between-session non-stationarities.…”

Section: Materials and Methods Participants And Experimental Proceduressupporting

confidence: 72%

“…Furthermore, this adaptation can be carried out online in a completely unsupervised manner, i.e., without knowing ground truth labels of the incoming test examples (Kumar et al, 2024). Combining rebiasing with DCCA, our proposed approach managed to achieve a between-session performance comparable to those obtained with sophisticated deep learning models evaluated on the same exact dataset (Liu et al, 2023).…”

Section: The Dcca-riemannian-mdm Approachmentioning

confidence: 77%

“…In consequence, our intent was not to propose a decoder with state-of-the-art best performance. Detection accuracy could likely be further improved with the introduction of additional processing steps, such as Fisher Geodesic Filtering (Barachant et al, 2010b ), or utilizing classification schemes more elaborate than simple MDM, such as RBNNet (Liu et al, 2023 ). It is widely recognized that the ability to control a BCI in the BCI-näive population varies greatly, with often studies retrospectively sorting their cohort as “good-” and “bad-performing” participants (Ahn and Jun, 2015 ).…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Combining detrended cross-correlation analysis with Riemannian geometry-based classification for improved brain-computer interface performance

Racz,

Kumar,

Kaposzta

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

Riemannian geometry-based classification (RGBC) gained popularity in the field of brain-computer interfaces (BCIs) lately, due to its ability to deal with non-stationarities arising in electroencephalography (EEG) data. Domain adaptation, however, is most often performed on sample covariance matrices (SCMs) obtained from EEG data, and thus might not fully account for components affecting covariance estimation itself, such as regional trends. Detrended cross-correlation analysis (DCCA) can be utilized to estimate the covariance structure of such signals, yet it is computationally expensive in its original form. A recently proposed online implementation of DCCA, however, allows for its fast computation and thus makes it possible to employ DCCA in real-time applications. In this study we propose to replace the SCM with the DCCA matrix as input to RGBC and assess its effect on offline and online BCI performance. First we evaluated the proposed decoding pipeline offline on previously recorded EEG data from 18 individuals performing left and right hand motor imagery (MI), and benchmarked it against vanilla RGBC and popular MI-detection approaches. Subsequently, we recruited eight participants (with previous BCI experience) who operated an MI-based BCI (MI-BCI) online using the DCCA-enhanced Riemannian decoder. Finally, we tested the proposed method on a public, multi-class MI-BCI dataset. During offline evaluations the DCCA-based decoder consistently and significantly outperformed the other approaches. Online evaluation confirmed that the DCCA matrix could be computed in real-time even for 22-channel EEG, as well as subjects could control the MI-BCI with high command delivery (normalized Cohen's κ: 0.7409 ± 0.1515) and sample-wise MI detection (normalized Cohen's κ: 0.5200 ± 0.1610). Post-hoc analysis indicated characteristic connectivity patterns under both MI conditions, with stronger connectivity in the hemisphere contralateral to the MI task. Additionally, fractal scaling exponent of neural activity was found increased in the contralateral compared to the ipsilateral motor cortices (C4 and C3 for left and right MI, respectively) in both classes. Combining DCCA with Riemannian geometry-based decoding yields a robust and effective decoder, that not only improves upon the SCM-based approach but can also provide relevant information on the neurophysiological processes behind MI.

show abstract

Section: Materials and Methods Participants And Experimental Proceduressupporting

confidence: 72%

Section: The Dcca-riemannian-mdm Approachmentioning

confidence: 77%