A New Post-Processing Method Using Latent Structure Influence Models for Channel Fusion in Automatic Sleep Staging

Karimi, Sajjad; Shamsollahi, Mohammad Bagher

doi:10.1109/jbhi.2022.3227407

Cited by 1 publication

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies have existed to fuse data from EEG with EEG as a way to improve the accuracy of interaction intent recognition. For example, Park et al (2022) developed an online BCI appliance control system based on steady-state visual evoked potentials (SSVEP) and electrooculography (EOG); Karimi and Shamsollahi (2022) proposed a fiducial ensemble (Fpz-Cz, Pz-Oz, and EOG) based on latent structural influence models (LSIMs) that exhibited some degree of performance improvement. Therefore, we decided to use both EOG data for classification.…”

Section: Methodsmentioning

confidence: 99%

An N400 identification method based on the combination of Soft-DTW and transformer

Tang²,

Zhou³

et al. 2023

Front. Comput. Neurosci.

View full text Add to dashboard Cite

As a time-domain EEG feature reflecting the semantic processing of the human brain, the N400 event-related potentials still lack a mature classification and recognition scheme. To address the problems of low signal-to-noise ratio and difficult feature extraction of N400 data, we propose a Soft-DTW-based single-subject short-distance event-related potential averaging method by using the advantages of differentiable and efficient Soft-DTW loss function, and perform partial Soft-DTW averaging based on DTW distance within a single-subject range, and propose a Transformer-based ERP recognition classification model, which captures contextual information by introducing location coding and a self-attentive mechanism, combined with a Softmax classifier to classify N400 data. The experimental results show that the highest recognition accuracy of 0.8992 is achieved on the ERP-CORE N400 public dataset, verifying the effectiveness of the model and the averaging method.

show abstract

Section: Methodsmentioning

confidence: 99%