Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Overview of studies that developed machine learning models utilizing EDA for point estimations of pain intensity.

More »

Table 1 Expand

Table 2.

The top 22 most informative features extracted from the EDA signal.

More »

Table 2 Expand

Table 3.

The neural network parameters are optimized through a search space hyperparameter tuning process.

More »

Table 3 Expand

Fig 1.

GA consists of selection, crossover, and mutation steps.

More »

Fig 1 Expand

Table 4.

GA and loss function (LossL) parameters are optimized using their search spaces through the hyperparameter tuning.

More »

Table 4 Expand

Table 5.

GD and soft loss function (LossS) parameters are optimized through the hyperparameter tuning process within their search spaces.

More »

Table 5 Expand

Fig 2.

Performance comparison of LossS by GD, LossL by GA, and bootstrap methods; LossS outperforms by yielding a narrower PIW across all PICP values.

More »

Fig 2 Expand

Fig 3.

(a) higher softening factor (s) value improves the PICP. (b) A higher Lagrangian multiplier (λ) value results in a slightly higher PICP.

More »

Fig 3 Expand

Table 6.

The generalized model results demonstrate how MPIW and NMPIW change as PICP varies.

More »

Table 6 Expand

Table 7.

The mean of the upper and lower bounds for each pain level in the generalized model as PICP varies.

More »

Table 7 Expand

Table 8.

Compared to the generalized model results, the PI widths of the personalized model are wider.

More »

Table 8 Expand

Table 9.

The mean upper and lower bounds for each pain level averaged across participants for various PICP values.

More »

Table 9 Expand

Table 10.

The hybrid model results include PICP, MPIW, and NMPIW.

More »

Table 10 Expand

Table 11.

The mean upper and lower bounds for each pain level averaged across clusters for PICP values of 50%, 75%, 85%, and 95%.

More »

Table 11 Expand

Fig 4.

The distribution of pairwise Euclidean distances for Clusters 1, 2, 3, and 4.

More »

Fig 4 Expand

Fig 5.

The hybrid approach, which utilizes a clustering technique, outperforms the other models and is considered a viable option for implementation in clinical settings.

More »

Fig 5 Expand