# Freezing of Gait Prediction on FOG Prediction Subject-Dependent (test)

Source: [Freezing of Gait Prediction on FOG Prediction Subject-Dependent (test)](<https://www.sota2.com/research/sota/freezing-of-gait-prediction-on-fog-prediction-subject-dependent-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-05T07:47:35.353Z

Evaluation of models on predicting Freezing of Gait events using the subject-dependent test split of the FOG Prediction dataset, measured by the Mean Prediction Horizon.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Freezing of Gait Prediction |
| Dataset (including any stated split) | FOG Prediction Subject-Dependent (test) |
| Metric | Mean Prediction Horizon (s) |
| Unit | TIME |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Mean Prediction Horizon (s)](<https://www.sota2.com/research/sota/freezing-of-gait-prediction-on-fog-prediction-subject-dependent-test.md?metric=Mean%20Prediction%20Horizon%20(s)>): Higher is better; unit: TIME.

## Recorded results

| Method | Mean Prediction Horizon (s) | Result date | Report paper |
| --- | --- | --- | --- |
| DDQN+PER Agent | 3.98 | Not recorded | 69a90dee2d603e6de3e406ec |
| CNN-LSTM | 2.77 | Not recorded | 69a90dee2d603e6de3e406ec |
| CNN-LSTM | 1.15 | Not recorded | 69a90dee2d603e6de3e406ec |

### DDQN+PER Agent

Mean Prediction Horizon (s): 3.98. Result ID: 69a934a06dbb7075b9525419.

[Reporting paper](<https://www.sota2.com/research/paper/69a90dee2d603e6de3e406ec.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90dee2d603e6de3e406ec.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CNN-LSTM

Mean Prediction Horizon (s): 2.77. Result ID: 69a934a06dbb7075b9525418.

[Reporting paper](<https://www.sota2.com/research/paper/69a90dee2d603e6de3e406ec.md>)

Recorded evaluation configuration: {"Model Configuration":"Baseline with 6 parameters"}. This record does not assert independent reproduction.

### CNN-LSTM

Mean Prediction Horizon (s): 1.15. Result ID: 69a934a06dbb7075b9525417.

[Reporting paper](<https://www.sota2.com/research/paper/69a90dee2d603e6de3e406ec.md>)

Recorded evaluation configuration: {"Model Configuration":"Baseline without 6 parameters"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.