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

Fig 1.

A systematic methodology approach from raw IMU signals to DL models evaluation.

More »

Fig 1 Expand

Fig 2.

Visualization of TUG test, a data acquisition in FRAILPOL using five IMU sensors mounted on participant’s body limbs.

More »

Fig 2 Expand

Table 1.

Overview of GSTRIDE and FRAILPOL datasets.

More »

Table 1 Expand

Fig 3.

IMU data partitioning for GSTRIDE and FRAILPOL datasets using the Sliding Window Technique and Participant-based splitting.

More »

Fig 3 Expand

Table 2.

Hyperparameters of CNN algorithm for both GSTRIDE & FRAILPOL datasets.

More »

Table 2 Expand

Table 3.

Hyperparameters of DeepConvLSTM algorithm for both GSTRIDE & FRAILPOL datasets.

More »

Table 3 Expand

Table 4.

Hyperparameters of InceptionTime algorithm for both GSTRIDE & FRAILPOL datasets.

More »

Table 4 Expand

Fig 4.

Training and validation losses of DL algorithms on FRAILPOL dataset: (a) CNN, (b) DeepConvLSTM, (c) InceptionTime; and on GSTRIDE dataset: (d) CNN, (e) DeepConvLSTM, (f) InceptionTime.

More »

Fig 4 Expand

Table 5.

Overall classification results of DL algorithms on both GSTRIDE & FRAILPOL datasets across three independent runs (Mean ± Standard Deviation).

More »

Table 5 Expand

Fig 5.

Window-level confusion matrices for (a) (d) CNN (b) (e) DeepConvLSTM, and (c) (f) InceptionTime models evaluated on both datasets: FRAILPOL and GSTRIDE.

More »

Fig 5 Expand