Cognitive Analysis of Working Memory Load from Eeg, by a Deep Recurrent Neural Network

Highlights • Data augmentation (DA) is increasingly used with deep learning (DL) on EEG • It enhances decoding accuracy left unexplained by 29% on average on the datasets we review • We analyze which specific DA techniques appear to work best for which EEG tasks • We tested various DA techniques on an open motor-imagery task and compared the accuracy gains to demonstrate the usefulness of DA for DL-based EEG analysis • We propose guidelines for reporting parameters for different DA techniques Abstract-Background Data augmentation (DA) has recently been demonstrated to achieve considerable performance gains for deep learning (DL)-increased accuracy and stability and reduced overfitting. Some electroencephalography (EEG) tasks suffer from low samples-to-features ratio, severely reducing DL effectiveness. DA with DL thus holds transformative promise for EEG processing, possibly like DL revolutionized computer vision, etc.-New method We review trends and approaches to DA for DL in EEG to address: Which DA approaches exist and are common for which EEG tasks? What input features are used? And, what kind of accuracy gain can be expected?-Results DA for DL on EEG begun 5 years ago and is steadily used more. We grouped DA techniques (noise addition, generative adversarial networks, sliding windows, sampling, Fourier transform, recombination of segmentation, and others) and EEG tasks (into seizure detection, sleep stages, motor imagery, mental workload, emotion recognition, motor tasks, and visual tasks). DA efficacy across techniques varied considerably. Noise addition and sliding windows provided the highest accuracy boost; mental workload most benefitted from DA. Sliding window, noise addition, and sampling methods most common for seizure detection, mental workload, and sleep stages, respectively.-Comparing with existing methods Percent of decoding accuracy explained by DA beyond unaugmented accuracy varied between 8% for recombination of segmentation and 36% for noise addition and from 14% for motor imagery to 56% for mental workload-29% on average.-Conclusions DA increasingly used and considerably improved DL decoding accuracy on EEG. Additional publications-if adhering to our reporting guidelines-will facilitate more detailed analysis.

show abstract

“…Research into mental workload has applications in BCI performance monitoring and in cognitive stress monitoring (e.g. [47]).…”

Section: Mental Workload Tasksmentioning

confidence: 99%

Data augmentation for deep-learning-based electroencephalography

Lashgari

Liang

Maoz

2020

Journal of Neuroscience Methods

256

140

View full text Add to dashboard Cite

show abstract

“…Here, the bi-directional-residual recurrent layers statistically signify the increment of performance in predictive accuracy. Kuanar et al [14] designed an EEG-based multispectral time-series imaging technique with a recurrent neural network algorithm to do the cognitive analysis of working memory load. However, these deep networks usually need huge amounts of data for training purposes.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Feature Pool-Based Emotional Stress State Detection Algorithm Using EEG Signals

Hasan

Kim

2019

Brain Sciences

View full text Add to dashboard Cite

Human stress analysis using electroencephalogram (EEG) signals requires a detailed and domain-specific information pool to develop an effective machine learning model. In this study, a multi-domain hybrid feature pool is designed to identify most of the important information from the signal. The hybrid feature pool contains features from two types of analysis: (a) statistical parametric analysis from the time domain, and (b) wavelet-based bandwidth specific feature analysis from the time-frequency domain. Then, a wrapper-based feature selector, Boruta, is applied for ranking all the relevant features from that feature pool instead of considering only the non-redundant features. Finally, the k-nearest neighbor (k-NN) algorithm is used for final classification. The proposed model yields an overall accuracy of 73.38% for the total considered dataset. To validate the performance of the proposed model and highlight the necessity of designing a hybrid feature pool, the model was compared to non-linear dimensionality reduction techniques, as well as those without feature ranking.

show abstract

“…Quantitative Results: We compare with several baselines on the ZuCo 2.0 dataset and report the average values of F1 score and the accuracy, respectively, in Table 1. Unimodal baselines include methods that process EEG and EM independently, either using recurrent neural networks such as LSTMs [16] or graph convolutional networks (GCNs) similar to [21]. In contrast, multimodal baselines perform late fusion to process both EEG as well as EM signals.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Dynamic Graph Modeling Of Simultaneous EEG And Eye-Tracking Data For Reading Task Identification

Mathur

Mittal

Manocha

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We present a new approach, that we call AdaGTCN, for identifying human reader intent from Electroencephalogram (EEG) and Eye movement (EM) data in order to help differentiate between normal reading and task-oriented reading. Understanding the physiological aspects of the reading process (the cognitive load and the reading intent) can help improve the quality of crowd-sourced annotated data. Our method, Adaptive Graph Temporal Convolution Network (AdaGTCN), uses an Adaptive Graph Learning Layer and Deep Neighborhood Graph Convolution Layer for identifying the reading activities using time-locked EEG sequences recorded during word-level eye-movement fixations. Adaptive Graph Learning Layer dynamically learns the spatial correlations between the EEG electrode signals while the Deep Neighborhood Graph Convolution Layer exploits temporal features from a dense graph neighborhood to establish the state of the art in reading task identification over other contemporary approaches. We compare our approach with several baselines to report an improvement of 6.29% on the ZuCo 2.0 dataset, along with extensive ablation experiments.

show abstract

Cognitive Analysis of Working Memory Load from Eeg, by a Deep Recurrent Neural Network

Cited by 90 publications

References 10 publications

Data augmentation for deep-learning-based electroencephalography

Data augmentation for deep-learning-based electroencephalography

A Hybrid Feature Pool-Based Emotional Stress State Detection Algorithm Using EEG Signals

Dynamic Graph Modeling Of Simultaneous EEG And Eye-Tracking Data For Reading Task Identification

Contact Info

Product

Resources

About