Morphology-preserving reconstruction of times series with missing data for enhancing deep learning-based classification

Bahador, Nooshin; Zhao, Guoying; Jokelainen, Jarno; Mustola, Seppo; Kortelainen, Jukka

doi:10.1016/j.bspc.2021.103052

Cited by 3 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These artifacts with their particular distribution on specific channels create bad data in neighboring N. Bahador and J. Kortelainen are with physiological Signal Analysis Team, Center for Machine Vision and Signal Analysis, MRC Oulu, University of Oulu, Oulu, Finland. channels [4,5] and may have spectral overlap with neurological activity of interest [6]. Therefore, these contaminated epochs are considered as bad epochs and totally removed from dataset.…”

Section: Introductionmentioning

confidence: 99%

“…Besides faulty electrodes, indigenous sources may also cause contamination, being spatially distributed around their neighboring electrodes. These artifacts, with their particular distribution on specific channels, create bad data in neighboring channels [4,5] and may have spectral overlap with neurological activity of interest [6]. Therefore, these contaminated epochs are considered as bad epochs and totally removed from the dataset.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reconstruction of missing channel in electroencephalogram using spatiotemporal correlation-based averaging

et al. 2021

Self Cite

View full text Add to dashboard Cite

Objective. Electroencephalogram (EEG) recordings often contain large segments with missing signals due to poor electrode contact or other artifact contamination. Recovering missing values, contaminated segments and lost channels could be highly beneficial, especially for automatic classification algorithms, such as machine/deep learning models, whose performance relies heavily on high-quality data. The current study proposes a new method for recovering missing segments in EEG. Approach. In the proposed method, the reconstructed segment is estimated by substitution of the missing part of the signal with the normalized weighted sum of other channels. The weighting process is based on inter-channel correlation of the non-missing preceding and proceeding temporal windows. The algorithm was designed to be computationally efficient. Experimental data from patients (N = 20) undergoing general anesthesia due to elective surgery were used for the validation of the algorithm. The data were recorded using a portable EEG device with ten channels and a self-adhesive frontal electrode during induction of anesthesia with propofol from waking state until burst suppression level, containing lots of variation in both amplitude and frequency properties. The proposed imputation technique was compared with another simple-structure technique. Distance correlation (DC) was used as a measure of comparison evaluation. Main results.:The proposed method with average distance correlation of 82.48±10.01 (µ ± σ)% outperformed its competitor with average distance correlation of 67.89±14.12 (µ ± σ)% . This algorithm also showed better performance for an increasing number of missing channels. Significance. the proposed technique provides an easy-to-implement and computationally efficient approach for the reliable reconstruction of missing or contaminated EEG segments.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Reconstruction of missing channel in electroencephalogram using spatiotemporal correlation-based averaging

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although GAN was successfully adopted in an unsupervised manner and attained accepted results in each task [ 18 , 57 , 63 , 68 , 74 ], further investigations of GAN for unsupervised algorithms are still required to enhance the performance and achieve these results that compete with the supervised processes. Finally, the training process of GAN is not considered an easy task and generally takes a lot of time, which might require recording longer initial datasets to start with [ 86 , 103 ]. Moreover, GANs could be more complex than other data augmentation techniques because of their adversarial nature.…”

Section: Discussionmentioning

confidence: 99%

Generative adversarial networks in EEG analysis: an overview

Habashi

Azab

Eldawlatly

et al. 2023

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

Electroencephalogram (EEG) signals have been utilized in a variety of medical as well as engineering applications. However, one of the challenges associated with recording EEG data is the difficulty of recording large amounts of data. Consequently, data augmentation is a potential solution to overcome this challenge in which the objective is to increase the amount of data. Inspired by the success of Generative Adversarial Networks (GANs) in image processing applications, generating artificial EEG data from the limited recorded data using GANs has seen recent success. This article provides an overview of various techniques and approaches of GANs for augmenting EEG signals. We focus on the utility of GANs in different applications including Brain-Computer Interface (BCI) paradigms such as motor imagery and P300-based systems, in addition to emotion recognition, epileptic seizures detection and prediction, and various other applications. We address in this article how GANs have been used in each study, the impact of using GANs on the model performance, the limitations of each algorithm, and future possibilities for developing new algorithms. We emphasize the utility of GANs in augmenting the limited EEG data typically available in the studied applications.

show abstract

Deep learning-based classification of multichannel bio-signals using directedness transfer learning

Bahador

Kortelainen

2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Morphology-preserving reconstruction of times series with missing data for enhancing deep learning-based classification

Cited by 3 publications

References 30 publications

Reconstruction of missing channel in electroencephalogram using spatiotemporal correlation-based averaging

Reconstruction of missing channel in electroencephalogram using spatiotemporal correlation-based averaging

Generative adversarial networks in EEG analysis: an overview

Deep learning-based classification of multichannel bio-signals using directedness transfer learning

Contact Info

Product

Resources

About