Table 1.
Existing research and its limitations.
Table 2.
Definitions of mathematical notation used in this paper.
Fig 1.
PhysioFormer model architecture consists of three submodules: the Feature Embedding Module, Affective Representation Module, and Prediction Module.
The Feature Embedding Module encodes physiological data, the Affective Representation Module builds on these encoded features, and the Prediction Module forecasts the individual’s current affective state. The Explanation model analyzes data within the trained model, generating feature importance scores and selecting key features, followed by symbolic regression to derive formulas that explain and quantify the influence of physiological indicators on affective states.
Fig 2.
Example of time window segmentation in the dataset.
This figure illustrates the time window segmentation process for the physiological signal dataset. The monitoring data is divided into multiple consecutive time windows, with each window being independent and having no overlapping parts.
Fig 3.
The figure shows the process of Explanation model.
First, the input data undergoes feature extraction and affective state representation through the Feature Embedding and Affective Representation modules. The processed features and state information are used to symbolic distillation, where feature importance scores generated by the PhysioFormer model are used to select key features. Next, symbolic regression is employed to generate the predicted value , which is compared with the model’s predicted value e thereby extracting and generating symbolic laws for the physiological indicators.
Table 3.
The performance comparation beween the proposed PhysioFormer Model and the state-of-the-art (SOTA) methods in terms of AUC (%), F1-Socre and MSE on WESAD dataset. The performance results reported in the table correspond to the best accuracy achieved for each model under its optimal hyperparameter settings.
Fig 4.
Convergence trends of the PhysioFormer model across datasets by splitting the WESAD dataset through windows of different sizes.
Although convergence trends are shown on all datasets, there are differences in the speed of convergence and the magnitude of losses.
Table 4.
The performance comparation of the proposed PhysioFormer model on different datasets divided by different window sizes in terms of AUC (%), F1-Socre and MSE.
Table 5.
The performance comparison of the proposed PhysioFormer model on the Wrist dataset with different numbers of hidden layer neurons in the ContribNet and AffectNet models in terms of AUC (%).
Table 6.
The performance comparison of the proposed PhysioFormer model on the Wrist dataset with different numbers of hidden layer neurons in the ContribNet and AffectNet models in terms of AUC (%).
Fig 5.
The role of feature embedding in affective computation tasks on both datasets, with the results presented in terms of ACC.
represents the performance of the PhysioFormer model without using the feature embedding module, while
indicates the performance of the PhysioFormer model after applying the feature embedding module.
Fig 6.
The role of individual attributes features in affective computation tasks on both datasets, with the results presented in terms of ACC.
represents the performance of the PhysioFormer model without combining individual attributes features, while
indicates the performance of the PhysioFormer model after combining individual attributes features.
Fig 7.
Distribution map of the number of features.
The figure shows the distribution of the number of features calculated from various physiological indicators in the Wrist dataset and the Chest dataset, respectively.
Fig 8.
The visualization of the importance scores for all features in the Wrist dataset, with darker colors indicating higher importance scores.
In the subsequent symbolic distillation task, the top ten features with the highest importance scores will be selected for further analysis and modeling.
Fig 9.
The visualization of the importance scores for all features in the Chest dataset, with darker colors indicating higher importance scores.
In the subsequent symbolic distillation task, the top ten features with the highest importance scores will be selected for further analysis and modeling.
Fig 10.
Complexity-Loss curve in Wrist dataset.
The red dot indicate the selected formula, and the corresponding formula are shown below the charts.
Fig 11.
Complexity-Loss curve in Chest dataset.
The red dot indicate the selected formula, and the corresponding formula are shown below the charts.
Fig 12.
The comparison of the fitted curves for affective indicators based on the selected formulas for four randomly chosen individuals.
Using the selected formulas and the output from the PhysioFormer model, the fitting curves for each affective indicator in the Wrist dataset were plotted. In the figure, the blue curve represents the model’s output, while the red curve represents the results calculated from the formulas.
Fig 13.
The comparison of the fitted curves for affective indicators based on the selected formulas for four randomly chosen individuals.
Using the selected formulas and the output from the PhysioFormer model, the fitting curves for each affective indicator in the Chest dataset were plotted. In the figure, the blue curve represents the model’s output, while the red curve represents the results calculated from the formulas.
Table 7.
The table presents the evaluation results of the selected formulas using the R2 metric, which measures the goodness of fit between the predicted values and the actual values. The R2 values for all the selected formulas are listed, providing a clear view of the fitting performance of each formula.