Cross-Task Cognitive Load Classification with Identity Mapping-Based Distributed CNN and Attention-Based RNN Using Gabor Decomposed Data Images

Cross-task-oriented EEG signal analysis methods: Our opinion

“…(2) Research from the perspectives of both feature extraction and feature classification. At present, most cross-task researches were carried out independently from the perspective of feature extraction or feature classification, and it is a valuable practice to find common ground from these two perspectives simultaneously in the future, such as multi-source domain adaptation (Zhou et al, 2022 ) and multi-scale and multi-directional filter (Taori et al, 2022 ) used for the study of single cross-task EEG signals.…”

“…From the perspective of feature classification, although the differences between tasks corresponding to different EEG signals limit the cross-task versatility of existing classification models (Zhou et al, 2022 ), researchers are still committed to finding or constructing some relatively general cross-task feature classification models (Kamrud et al, 2021 ; Mota et al, 2021 ; Taori et al, 2022 ).…”

“…In the same year, Wang et al proposed a cascade structure (R3DCNN) of a deep recurrent and three-dimensional convolutional neural network (3DCNN) (Zhang et al, 2019 ), and the results showed that 3DCNN could be used to learn the spatial and spectral features of EEG signals, and the use of RNN layers that can obtain temporal representations improved the performance. Taori et al proposed a structural model built on RNN and attention mechanisms (Taori et al, 2022 ), and the results showed that the model could extract effective cross-task features from the space-time domain.…”

“…At the same time, some researchers have explored the classifiers which are more friendly to the differences between different tasks by comparing with the traditional feature classification methods, including multi-layer perceptron neural network (MLPNN) (Kamrud et al, 2021 ), domain adaptive methods (Zhou et al, 2022 ), sliding-window support vector machine (SVM) (Boring et al, 2020 ), etc. On the other hand, some new cross-task models based on deep learning models were proposed to narrow the differences between tasks, such as convolutional neural networks (CNNs) (Mota et al, 2021 ), recurrent neural networks (RNNs) (Gupta et al, 2021 ), metric-based methods (Jia et al, 2023 ), combinations of CNNs and RNNs (Zhang et al, 2019 ; Zhou et al, 2019 ; Taori et al, 2022 ), etc. However, there are still many unexplored areas in the field of cross-task EEG signal analysis methods, such as: task segmentation and complexity design (Kamrud et al, 2021 ), multi-source domain adaptive application (Zhou et al, 2022 ), multi-scale and multi-directional filter research (Taori et al, 2022 ), considering both feature extraction and feature classification, and increasing the amount of data.…”

“…On the other hand, some new cross-task models based on deep learning models were proposed to narrow the differences between tasks, such as convolutional neural networks (CNNs) (Mota et al, 2021 ), recurrent neural networks (RNNs) (Gupta et al, 2021 ), metric-based methods (Jia et al, 2023 ), combinations of CNNs and RNNs (Zhang et al, 2019 ; Zhou et al, 2019 ; Taori et al, 2022 ), etc. However, there are still many unexplored areas in the field of cross-task EEG signal analysis methods, such as: task segmentation and complexity design (Kamrud et al, 2021 ), multi-source domain adaptive application (Zhou et al, 2022 ), multi-scale and multi-directional filter research (Taori et al, 2022 ), considering both feature extraction and feature classification, and increasing the amount of data. Furthermore, there are also some interconnections between cross-task analysis and relatively common cross-subject studies.…”