Cognitive performance detection using entropy-based features and lead-specific approach

Sharma, Lakhan Dev; Saraswat, Ritesh Kumar; Sunkaria, Ramesh Kumar

doi:10.1007/s11760-021-01927-0

Cited by 16 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies show that EEG signals were broadly analyzed using two types of methodologies: 1) traditional techniques which required hand-crafting of features and 2) data-driven framework, deep learning. Sharma L. D. et al (2021) utilized 1D representation of entropy-based features and SVM to classify mental arithmetic tasks on a publicly available "EEG Mental Arithmetic Dataset" by Physionet PhysioBank (2000), Zyma et al (2019) and achieved an accuracy of 94%. To classify mental arithmetic vs. rest, the stacked long-short term memory (LSTM) was applied to raw 1D EEG signals, resulting in an accuracy of 93.59% in the study by Ganguly et al (2020).…”

Section: Introductionmentioning

confidence: 99%

An investigation of the multi-dimensional (1D vs. 2D vs. 3D) analyses of EEG signals using traditional methods and deep learning-based methods

Shah

Sinha

2022

Front. Signal Process.

View full text Add to dashboard Cite

Electroencephalographic (EEG) signals are electrical signals generated in the brain due to cognitive activities. They are non-invasive and are widely used to assess neurodegenerative conditions, mental load, and sleep patterns. In this work, we explore the utility of representing the inherently single dimensional time-series in different dimensions such as 1D-feature vector, 2D-feature maps, and 3D-videos. The proposed methodology is applied to four diverse datasets: 1) EEG baseline, 2) mental arithmetic, 3) Parkinson’s disease, and 4) emotion dataset. For a 1D analysis, popular 1D features hand-crafted from the time-series are utilized for classification. This performance is compared against the data-driven approach of using raw time-series as the input to the deep learning framework. To assess the efficacy of 2D representation, 2D feature maps that utilize a combination of the Feature Pyramid Network (FPN) and Atrous Spatial Pyramid Pooling (ASPP) is proposed. This is compared against an approach utilizing a composite feature set consisting of 2D feature maps and 1D features. However, these approaches do not exploit spatial, spectral, and temporal characteristics simultaneously. To address this, 3D EEG videos are created by stacking spectral feature maps obtained from each sub-band per time frame in a temporal domain. The EEG videos are the input to a combination of the Convolution Neural Network (CNN) and Long–Short Term Memory (LSTM) for classification. Performances obtained using the proposed methodologies have surpassed the state-of-the-art for three of the classification scenarios considered in this work, namely, EEG baselines, mental arithmetic, and Parkinson’s disease. The video analysis resulted in 92.5% and 98.81% peak mean accuracies for the EEG baseline and EEG mental arithmetic, respectively. On the other hand, for distinguishing Parkinson’s disease from controls, a peak mean accuracy of 88.51% is achieved using traditional methods on 1D feature vectors. This illustrates that 3D and 2D feature representations are effective for those EEG data where topographical changes in brain activation regions are observed. However, in scenarios where topographical changes are not consistent across subjects of the same class, these methodologies fail. On the other hand, the 1D analysis proves to be significantly effective in the case involving changes in the overall activation of the brain due to varying degrees of deterioration.

show abstract

Section: Introductionmentioning

confidence: 99%

An investigation of the multi-dimensional (1D vs. 2D vs. 3D) analyses of EEG signals using traditional methods and deep learning-based methods

Shah

Sinha

2022

Front. Signal Process.

View full text Add to dashboard Cite

show abstract

“…sample entropy and machine learning (ML). This model outperform the other methods based on non-linear features and ML based classification [4,30,31]. It has also been compared with other methods based on Time-Frequency (T-F) based features and ML models [7,32].…”

Section: Discussionmentioning

confidence: 98%

“…In this work, such variations in EEG signal under the exposure of stressful activities are detected and analyzed in order to classify the overall brain response into two relevant classes i.e. resting state and stressed or cognitive task performing state [4]. Literature suggests numerous EEG based classification approaches that make significant contribution in medical field [5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Mental arithmetic task load recognition using EEG signal and Bayesian optimized K-nearest neighbor

Sharma

Chhabra²,

Chauhan

et al. 2021

Int. j. inf. tecnol.

Self Cite

View full text Add to dashboard Cite

Cognitive load recognition during mental arithmetic activity facilitates to observe and identify the brain's response towards stress stimulus. As a result, an efficient mental load characterization approach using electroencephalogram (EEG) signal and Bayesian optimized K-Nearest Neighbor (BO-KNN) has been proposed in this work. The study has been conducted on a recorded EEG dataset of 30 healthy subjects who were exposed to an arithmetic questioner. To obtain artifacts free EEG signal, the Savitzky-Golay filtering approach has been utilized. Further, the decomposition of the extracted EEG signal has been carried out using stationary wavelength transform. In this work, the entropy based feature extraction has been performed followed by F-score based feature selection. Top 40 features having the highest precedence have been used for classification using BO-KNN. The rigorous experimental analysis has been performed to analyze the effectiveness of the proposed method over other state-ofthe-art methods and it shows that the classification accuracy is substantially improved.

show abstract

“…In recent years, many researchers have used EEG to automatically recognize human emotions and obtained high recognition accuracy ( Kurniawan et al, 2013 ; Luo et al, 2018 ; Qing et al, 2019 ; Torres et al, 2020 ; Gao et al, 2021 ; Huang, 2021 ; Liu et al, 2021 ; Sharma et al, 2021 ; Yedukondalu and Sharma, 2022 ). In Table 1 , the methods and accuracy rates of researchers using EEG to diagnose depression are shown.…”

Section: Introductionmentioning

confidence: 99%

EEG diagnosis of depression based on multi-channel data fusion and clipping augmentation and convolutional neural network

Wang

Kang²,

Huo³

et al. 2022

Front. Physiol.

View full text Add to dashboard Cite

Depression is an undetectable mental disease. Most of the patients with depressive symptoms do not know that they are suffering from depression. Since the novel Coronavirus pandemic 2019, the number of patients with depression has increased rapidly. There are two kinds of traditional depression diagnosis. One is that professional psychiatrists make diagnosis results for patients, but it is not conducive to large-scale depression detection. Another is to use electroencephalography (EEG) to record neuronal activity. Then, the features of the EEG are extracted using manual or traditional machine learning methods to diagnose the state and type of depression. Although this method achieves good results, it does not fully utilize the multi-channel information of EEG. Aiming at this problem, an EEG diagnosis method for depression based on multi-channel data fusion cropping enhancement and convolutional neural network is proposed. First, the multi-channel EEG data are transformed into 2D images after multi-channel fusion (MCF) and multi-scale clipping (MSC) augmentation. Second, it is trained by a multi-channel convolutional neural network (MCNN). Finally, the trained model is loaded into the detection device to classify the input EEG signals. The experimental results show that the combination of MCF and MSC can make full use of the information contained in the single sensor records, and significantly improve the classification accuracy and clustering effect of depression diagnosis. The method has the advantages of low complexity and good robustness in signal processing and feature extraction, which is beneficial to the wide application of detection systems.

show abstract

Cognitive performance detection using entropy-based features and lead-specific approach

Cited by 16 publications

References 32 publications

An investigation of the multi-dimensional (1D vs. 2D vs. 3D) analyses of EEG signals using traditional methods and deep learning-based methods

An investigation of the multi-dimensional (1D vs. 2D vs. 3D) analyses of EEG signals using traditional methods and deep learning-based methods

Mental arithmetic task load recognition using EEG signal and Bayesian optimized K-nearest neighbor

EEG diagnosis of depression based on multi-channel data fusion and clipping augmentation and convolutional neural network

Contact Info

Product

Resources

About