Classification of the <scp>four‐class</scp> motor imagery signals using continuous wavelet transform filter bank‐based two‐dimensional images

Mahamune, Rupesh; Laskar, Shahedul Haque

doi:10.1002/ima.22593

Cited by 21 publications

(22 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As channel selection may enable lower generalization errors in DL [67], we compute the topoplot representation from the whole set of EEG channels to visualize the spectral power variations on the scalp averaged over each MI interval. The topoplots extracted by FBCSP and CWT algorithms are inputs to a Convolutional Neural Network with a Deep and Wide architecture that is more generic for decoding EEG signals, delivering a competitive classification accuracy [68]. The feature extraction procedures require several parameters to fix, affecting the CNN learning properties like discriminability and interpretability.…”

Section: Discussion and Concluding Remarksmentioning

confidence: 99%

Image-Based Learning Using Gradient Class Activation Maps for Enhanced Physiological Interpretability of Motor Imagery Skills

Collazos-Huertas

Álvarez-Meza

Castellanos-Domínguez

2022

Applied Sciences

View full text Add to dashboard Cite

Brain activity stimulated by the motor imagery paradigm (MI) is measured by Electroencephalography (EEG), which has several advantages to be implemented with the widely used Brain–Computer Interfaces (BCIs) technology. However, the substantial inter/intra variability of recorded data significantly influences individual skills on the achieved performance. This study explores the ability to distinguish between MI tasks and the interpretability of the brain’s ability to produce elicited mental responses with improved accuracy. We develop a Deep and Wide Convolutional Neuronal Network fed by a set of topoplots extracted from the multichannel EEG data. Further, we perform a visualization technique based on gradient-based class activation maps (namely, GradCam++) at different intervals along the MI paradigm timeline to account for intra-subject variability in neural responses over time. We also cluster the dynamic spatial representation of the extracted maps across the subject set to come to a deeper understanding of MI-BCI coordination skills. According to the results obtained from the evaluated GigaScience Database of motor-evoked potentials, the developed approach enhances the physiological explanation of motor imagery in aspects such as neural synchronization between rhythms, brain lateralization, and the ability to predict the MI onset responses and their evolution during training sessions.

show abstract

Section: Discussion and Concluding Remarksmentioning

confidence: 99%

Image-Based Learning Using Gradient Class Activation Maps for Enhanced Physiological Interpretability of Motor Imagery Skills

Collazos-Huertas

Álvarez-Meza

Castellanos-Domínguez

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…where a denotes the scale or dilation parameter, and b is the shifting parameter, which denotes the time information in the transform [34].…”

Section: Figure 1 Arousal-valence Emotion Modelmentioning

confidence: 99%

“…The analytic Morse wavelet is utilized for CWT because it has greater time-frequency localization [34]. The symmetry parameter (gamma) and time bandwidth product for Morse wavelets were preserved at 3 and 60, respectively.…”

Section: Figure 1 Arousal-valence Emotion Modelmentioning

confidence: 99%

Wavelet ELM-AE Based Data Augmentation and Deep Learning for Efficient Emotion Recognition Using EEG Recordings

et al. 2022

View full text Add to dashboard Cite

Emotion perception is critical for behavior prediction. There are many ways to capture emotional states by observing the body and copying actions. Physiological markers such as electroencephalography (EEG) have gained popularity, as facial emotions may not always adequately convey true emotion. This study has two main aims. The first is to measure four emotion categories using deep learning architectures and EEG data. The second purpose is to increase the number of samples in the dataset. To this end, a novel data augmentation approach namely the Extreme Learning Machine Wavelet Auto Encoder (ELM-W-AE) is proposed for data augmentation. The proposed data augmentation approach is both simple and faster than the other synthetic data augmentation approaches. For deep architectures, large datasets are important for performance. For this reason, data multiplexing approaches with classical and synthetic methods have become popular recently. The proposed synthetic data augmentation is the ELM-W-AE because of its efficiency and detail reproduction. The ELM-AE structure uses wavelet activation functions such as Gaussian, GgW, Mexican, Meyer, Morlet, and Shannon. Deep convolutional architectures classify EEG signals as images. EEG waves are scalogram using Continuous Wavelet Transform (CWT). The ResNet18 architecture recognizes emotions. The proposed technique uses GAMEMO data collected during gameplay. Each of these states is represented in the GAMEMO data collection. The visual data set created from the signal was divided into two groups as 70% training and 30% testing. ResNet18 has been fine-tuned with augmented photos, training images only. It achieved 99.6% classification accuracy in tests. The proposed method is compared with the other approaches on the same dataset, and an approximately 22% performance improvement is achieved.

show abstract

“…For generating visual evoked potentials, the subject needs repetitive external stimuli which can be tiring and uncomfortable for them. MI 2 is limited by its degree of freedom and slow cortical potentials need more time for training. Speech imagery (SI) is a relatively new and more natural paradigm for BCI to provide a means for speech prosthesis for patients having medical conditions such as advanced amyotrophic lateral sclerosis (ALS), traumatic brain injury, and pseudo‐coma in which the patients cannot speak but are mentally active.…”

Section: Introductionmentioning

confidence: 99%

Electroencephalography based imagined alphabets classification using spatial and time‐domain features

Agarwal

Kumar

2021

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Imagined speech is a neuro-paradigm that can provide an alternative communication channel for patients in a locked-in syndrome state. We have performed an experiment in which a 32 channel industry-standard electroencephalography (EEG) device was used to record 26 imagined English alphabets from 13 subjects. We denoised the imagined signals by discrete wavelet transform and extracted the spatial filters by common spatial pattern method, and time-domain features. Spatial features when classified with linear support vector machine, and time-domain features classified by random forest gave the best results. Alpha, beta, and theta bands could classify imagined alphabets better than other bands and had average classification accuracies of 88.59%, 87.39%, and 88.97%, respectively by using spatial features and 81.88%, 76.72%, and 79.25%, respectively, by time-domain features. The grand average accuracies of all the 26 alphabets in six EEG frequency bands was found to be 77.97% in a subject independent binary classification framework.

show abstract

Classification of the four‐class motor imagery signals using continuous wavelet transform filter bank‐based two‐dimensional images

Cited by 21 publications

References 54 publications

Image-Based Learning Using Gradient Class Activation Maps for Enhanced Physiological Interpretability of Motor Imagery Skills

Image-Based Learning Using Gradient Class Activation Maps for Enhanced Physiological Interpretability of Motor Imagery Skills

Wavelet ELM-AE Based Data Augmentation and Deep Learning for Efficient Emotion Recognition Using EEG Recordings

Electroencephalography based imagined alphabets classification using spatial and time‐domain features

Contact Info

Product

Resources

About