Prediction of Cognitive Load from Electroencephalography Signals Using Long Short-Term Memory Network

Yoo, Gilsang; Kim, Hyeoncheol; Hong, Sungdae

doi:10.3390/bioengineering10030361

Cited by 14 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Likewise, exploiting such intrinsic patterns should be based on neural architectures that are equipped with such capacities. These complex neural network architectures (CNN, RNN, transformers [ 31 , 33 , 34 ]) could be used combinatorically to achieve such purposes, which, however, would require a much larger number of data samples.…”

Section: Discussionmentioning

confidence: 99%

Exploiting Information in Event-Related Brain Potentials from Average Temporal Waveform, Time–Frequency Representation, and Phase Dynamics

Ouyang,

Zhou

2023

Bioengineering

View full text Add to dashboard Cite

Characterizing the brain’s dynamic pattern of response to an input in electroencephalography (EEG) is not a trivial task due to the entanglement of the complex spontaneous brain activity. In this context, the brain’s response can be defined as (1) the additional neural activity components generated after the input or (2) the changes in the ongoing spontaneous activities induced by the input. Moreover, the response can be manifested in multiple features. Three commonly studied examples of features are (1) transient temporal waveform, (2) time–frequency representation, and (3) phase dynamics. The most extensively used method of average event-related potentials (ERPs) captures the first one, while the latter two and other more complex features are attracting increasing attention. However, there has not been much work providing a systematic illustration and guidance for how to effectively exploit multifaceted features in neural cognitive research. Based on a visual oddball ERPs dataset with 200 participants, this work demonstrates how the information from the above-mentioned features are complementary to each other and how they can be integrated based on stereotypical neural-network-based machine learning approaches to better exploit neural dynamic information in basic and applied cognitive research.

show abstract

Section: Discussionmentioning

confidence: 99%

Exploiting Information in Event-Related Brain Potentials from Average Temporal Waveform, Time–Frequency Representation, and Phase Dynamics

Ouyang,

Zhou

2023

Bioengineering

View full text Add to dashboard Cite

show abstract

“…7). To qualitatively identify patterns, encompassing both local and global aspects, and to isolate local patterns within the branch layers of reflectance and transmittance, a high-pass filter was employed in this study [43,44]. The high-pass filter adopts a fast Fourier transform that can enhance the minor contribution or local aspect by capturing the high frequency in the feature importance [35].…”

Section: Spectral Importance To Tfcc Retrieval Using Y-netmentioning

confidence: 99%

Spectroscopic assessment of flavor-related chemical compounds in fresh tea shoots using deep learning

Denaro,

Lin,

Huang

2024

Preprint

View full text Add to dashboard Cite

This study employs a deep-learning method, Y-Net, to estimate 10 tea flavor-related chemical compounds (TFCC), including gallic acid, caffeine and eight catechin isomers, using fresh tea shoot reflectance and transmittance. The unique aspect of Y-Net lies in its utilization of dual inputs, reflectance and transmittance, which are seamlessly integrated within the Y-Net architecture. This architecture harnesses the power of a convolutional neural network-based residual network to fuse tea shoot spectra effectively. This strategic combination enhances the capacity of the model to discern intricate patterns in the optical characteristics of fresh tea shoots, providing a comprehensive framework for TFCC estimation. In this study, we destructively sampled tea shoots from tea farms in Alishan (Ali-Mountain) in Central Taiwan within the elevation range of 879-1552 m a.s.l. Tea shoot reflectance and transmittance data (n = 2032) within the optical region (400-2500 nm) were measured using a portable spectroradiometer and pre-processed using an algorithm; corresponding TFCC were qualified using the high-performance liquid chromatography analysis. To enhance the robustness and performance of Y-Net, we employed data augmentation techniques for model training. We compared the performances of Y-Net and seven other commonly utilized statistical, machine-/deep-learning models (partial least squared regression, Gaussian process, cubist, random forests and three feedforward neural networks) using root-mean-square error (RMSE). Furthermore, we assessed the prediction accuracies of Y-Net and Y-Net using spectra within the visible and near-infrared (VNIR) regions (for higher energy throughput and low-cost instruments) and reflectance only (for airborne and spaceborne remote sensing applications). The results showed that overall Y-Net (mean RMSE +/- standard deviation [SD] = 2.51 +/- 2.20 mg g-1) outperformed the other statistical, machine- and deep-learning models (>= 2.59 +/- 2.64 mg g-1), demonstrating its superiority in predicting TFCC. In addition, this original Y-Net also yielded slightly lower mean RMSE (+/- SD) compared with VNIR (2.76 +/- 2.41 mg g-1) and reflectance-only (2.68 +/- 2.74 mg g-1) Y-Nets using validation data. This study highlights the feasibility of using spectroscopy and Y-Net to assess minor biochemical components in fresh tea shoots and sheds light on the potential of the proposed approach for effective regional monitoring of tea shoot quality.

show abstract

“…The integration of EEG with advanced machine learning techniques, especially deep learning approaches, has demonstrated considerable promise in this realm. A study of particular note employed a long short-term memory (LSTM) network-a variant of recurrent neural networks-to analyze EEG signals for predicting cognitive load [165]. This methodology surpassed the performance of other machine learning models such as random forest, AdaBoost, support vector machine, and extreme gradient boosting, attaining a remarkable accuracy of 87.1% in cognitive load recognition.…”

Section: Machine Learning and Aimentioning

confidence: 99%

Examining the Landscape of Cognitive Fatigue Detection: A Comprehensive Survey

Karim,

Pavel,

Nikanfar

et al. 2024

Technologies

View full text Add to dashboard Cite

Cognitive fatigue, a state of reduced mental capacity arising from prolonged cognitive activity, poses significant challenges in various domains, from road safety to workplace productivity. Accurately detecting and mitigating cognitive fatigue is crucial for ensuring optimal performance and minimizing potential risks. This paper presents a comprehensive survey of the current landscape in cognitive fatigue detection. We systematically review various approaches, encompassing physiological, behavioral, and performance-based measures, for robust and objective fatigue detection. The paper further analyzes different challenges, including the lack of standardized ground truth and the need for context-aware fatigue assessment. This survey aims to serve as a valuable resource for researchers and practitioners seeking to understand and address the multifaceted challenge of cognitive fatigue detection.

show abstract

Prediction of Cognitive Load from Electroencephalography Signals Using Long Short-Term Memory Network

Cited by 14 publications

References 31 publications

Exploiting Information in Event-Related Brain Potentials from Average Temporal Waveform, Time–Frequency Representation, and Phase Dynamics

Exploiting Information in Event-Related Brain Potentials from Average Temporal Waveform, Time–Frequency Representation, and Phase Dynamics

Spectroscopic assessment of flavor-related chemical compounds in fresh tea shoots using deep learning

Examining the Landscape of Cognitive Fatigue Detection: A Comprehensive Survey

Contact Info

Product

Resources

About