Table 1.
FOG definitions in FOG detection and prediction studies.
Table 2.
Participant information and questionnaire outcomes.
Fig 1.
Image adapted from [54].
Fig 2.
Sensors systems used in data collection.
(A) FScan pressure sensing insole. (B) Shimmer3 IMU sensor. (C) Diagram of IMU placement. (D) Insole and IMU systems on body. Modified from [54].
Fig 3.
Diagram of windowing approach.
Windows W1-W3 contain only non-FOG data, W4-W8 contain both non-FOG and Pre-FOG data, W9-W13 contain only Pre-FOG data, W14-W18 contain both Pre-FOG and FOG data, and W19 contains only FOG data.
Fig 4.
Diagram of FOG episode identification using the FOG episode-based evaluation.
Three consecutive positive window classifications (W1-W3) result in a model trigger decision (MTD) at the end of the third window (MTD instant). To be correctly identified, a FOG episode requires the MTD instant to be within the MTD target zone. Identification delay is the time difference between FOG onset and the MTD.
Table 3.
Number of FOG episodes for each participant for different merging thresholds.
Table 4.
Window-based FOG detection model performance for various merging thresholds.
Table 5.
Window-based FOG prediction model performance for various merging thresholds.
Table 6.
Episode-based FOG detection model performance for various merging thresholds.
Table 7.
Episode-based FOG prediction model performance for various merging thresholds.
Table 8.
MTD precision for the FOG detection model.
Table 9.
MTD precision for the FOG prediction model.
Table 10.
MTD precision for FOG prediction and detection models using a 2.5 s no-cue interval between consecutive cues.
Fig 5.
Example session of walking data classification and freeze identification.
(A) Without no-cue interval. (B) With 2.5 s no-cue interval. TP MTD: true positive model trigger decision (MTD within MTD target zone), FP MTD: false positive model trigger decision (MTD outside MTD target zone).