Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Freezing of Gait Prediction using Proactive Agent that Learns from Selected Experience and DDQN Algorithm

Septian Enggar Sukmana, Sang Won Bae, Tomohiro Shibata

TL;DR

A reinforcement learning-based framework designed to identify optimal pre-FOG onset points, thereby extending the prediction horizon for anticipatory cueing systems, and demonstrated robust performance in both subject-dependent and subject-independent evaluations.

Abstract

Freezing of Gait (FOG) is a debilitating motor symptom commonly experienced by individuals with Parkinson's Disease (PD) which often leads to falls and reduced mobility. Timely and accurate prediction of FOG episodes is essential for enabling proactive interventions through assistive technologies. This study presents a reinforcement learning-based framework designed to identify optimal pre-FOG onset points, thereby extending the prediction horizon for anticipatory cueing systems. The model implements a Double Deep Q-Network (DDQN) architecture enhanced with Prioritized Experience Replay (PER) allowing the agent to focus learning on high-impact experiences and refine its policy. Trained over 9000 episodes with a reward shaping strategy that promotes cautious decision-making, the agent demonstrated robust performance in both subject-dependent and subject-independent evaluations. The model achieved a prediction horizon of up to 8.72 seconds prior to FOG onset in subject-independent scenarios and 7.89 seconds in subject-dependent settings. These results highlight the model's potential for integration into wearable assistive devices, offering timely and personalized interventions to mitigate FOG in PD patients.

Freezing of Gait Prediction using Proactive Agent that Learns from Selected Experience and DDQN Algorithm

TL;DR

A reinforcement learning-based framework designed to identify optimal pre-FOG onset points, thereby extending the prediction horizon for anticipatory cueing systems, and demonstrated robust performance in both subject-dependent and subject-independent evaluations.

Abstract

Freezing of Gait (FOG) is a debilitating motor symptom commonly experienced by individuals with Parkinson's Disease (PD) which often leads to falls and reduced mobility. Timely and accurate prediction of FOG episodes is essential for enabling proactive interventions through assistive technologies. This study presents a reinforcement learning-based framework designed to identify optimal pre-FOG onset points, thereby extending the prediction horizon for anticipatory cueing systems. The model implements a Double Deep Q-Network (DDQN) architecture enhanced with Prioritized Experience Replay (PER) allowing the agent to focus learning on high-impact experiences and refine its policy. Trained over 9000 episodes with a reward shaping strategy that promotes cautious decision-making, the agent demonstrated robust performance in both subject-dependent and subject-independent evaluations. The model achieved a prediction horizon of up to 8.72 seconds prior to FOG onset in subject-independent scenarios and 7.89 seconds in subject-dependent settings. These results highlight the model's potential for integration into wearable assistive devices, offering timely and personalized interventions to mitigate FOG in PD patients.
Paper Structure (12 sections, 6 equations, 8 figures, 5 tables, 1 algorithm)

This paper contains 12 sections, 6 equations, 8 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related literature
  3. Dataset
  4. Method
  5. Parameter and Setting
  6. Proactive Agent
  7. Internal Baseline (CNN-LSTM)
  8. Evaluation
  9. Result and Discussion
  10. Conclusion
  11. Pseudocode
  12. RL Baseline Results

Figures (8)

  • Figure 1: Illustration of FOG prediction techniques: (a)fixed-window Naghavi2019Kleanthous2020Pardoel2022Li2023Pardoel2024; (b) threshold by machine learningFu2025; (c) proactive using RL agent
  • Figure 2: Time-Based Reward Shaping for FOG Prediction
  • Figure 3: Proactive agent action to predict FOG
  • Figure 4: Example FOG prediction point on: (a) Subject 5; (b) Subject 7
  • Figure 5: Illustration of trained prediction points by replay scheme
  • ...and 3 more figures