Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

BagStacking: An Integrated Ensemble Learning Approach for Freezing of Gait Detection in Parkinson's Disease

Seffi Cohen, Lior Rokach

TL;DR

The paper tackles the challenge of detecting Freezing of Gait (FOG) in Parkinson's disease from lower-back accelerometer data, addressing inherent data variability with an integrated ensemble called BagStacking. BagStacking combines bootstrap-based base-model training with a meta-learner to blend predictions, aiming to achieve both variance reduction and sophisticated model blending. Empirical results on a real-world FOG dataset show BagStacking delivers a MAP of 0.306, outperforming LightGBM and regular stacking, with substantially improved runtime over traditional stacking. The work demonstrates a robust, scalable approach with potential to improve PD monitoring and patient care in clinical and at-home settings.

Abstract

This paper introduces BagStacking, a novel ensemble learning method designed to enhance the detection of Freezing of Gait (FOG) in Parkinson's Disease (PD) by using a lower-back sensor to track acceleration. Building on the principles of bagging and stacking, BagStacking aims to achieve the variance reduction benefit of bagging's bootstrap sampling while also learning sophisticated blending through stacking. The method involves training a set of base models on bootstrap samples from the training data, followed by a meta-learner trained on the base model outputs and true labels to find an optimal aggregation scheme. The experimental evaluation demonstrates significant improvements over other state-of-the-art machine learning methods on the validation set. Specifically, BagStacking achieved a MAP score of 0.306, outperforming LightGBM (0.234) and classic Stacking (0.286). Additionally, the run-time of BagStacking was measured at 3828 seconds, illustrating an efficient approach compared to Regular Stacking's 8350 seconds. BagStacking presents a promising direction for handling the inherent variability in FOG detection data, offering a robust and scalable solution to improve patient care in PD.

BagStacking: An Integrated Ensemble Learning Approach for Freezing of Gait Detection in Parkinson's Disease

TL;DR

The paper tackles the challenge of detecting Freezing of Gait (FOG) in Parkinson's disease from lower-back accelerometer data, addressing inherent data variability with an integrated ensemble called BagStacking. BagStacking combines bootstrap-based base-model training with a meta-learner to blend predictions, aiming to achieve both variance reduction and sophisticated model blending. Empirical results on a real-world FOG dataset show BagStacking delivers a MAP of 0.306, outperforming LightGBM and regular stacking, with substantially improved runtime over traditional stacking. The work demonstrates a robust, scalable approach with potential to improve PD monitoring and patient care in clinical and at-home settings.

Abstract

This paper introduces BagStacking, a novel ensemble learning method designed to enhance the detection of Freezing of Gait (FOG) in Parkinson's Disease (PD) by using a lower-back sensor to track acceleration. Building on the principles of bagging and stacking, BagStacking aims to achieve the variance reduction benefit of bagging's bootstrap sampling while also learning sophisticated blending through stacking. The method involves training a set of base models on bootstrap samples from the training data, followed by a meta-learner trained on the base model outputs and true labels to find an optimal aggregation scheme. The experimental evaluation demonstrates significant improvements over other state-of-the-art machine learning methods on the validation set. Specifically, BagStacking achieved a MAP score of 0.306, outperforming LightGBM (0.234) and classic Stacking (0.286). Additionally, the run-time of BagStacking was measured at 3828 seconds, illustrating an efficient approach compared to Regular Stacking's 8350 seconds. BagStacking presents a promising direction for handling the inherent variability in FOG detection data, offering a robust and scalable solution to improve patient care in PD.
Paper Structure (16 sections, 1 theorem, 6 equations, 1 figure, 1 table)

This paper contains 16 sections, 1 theorem, 6 equations, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Proposed BagStacking Method
  4. BagStacking Theoretical Foundation
  5. Assumptions
  6. Step 1: Bagging's Variance Reduction
  7. Step 2: Stacking's Model Diversity
  8. Step 3: BagStacking's Combined Strengths
  9. Step 4: Expected Generalization Performance
  10. Experiments
  11. Dataset
  12. Preprocessing
  13. Experimental Setup
  14. Evaluation Metric
  15. Results
  16. ...and 1 more sections

Key Result

Theorem 3.1

Let $\mathcal{H}$ be a hypothesis space of base models, and let $M'$ be a hypothesis space for meta-learners. Given a loss function $\mathcal{L}$, and a labeled training set $S = \{(x_1, y_1), \ldots, (x_N, y_N)\}$, the BagStacking method is expected to produce equal or better generalization perform

Figures (1)

  • Figure 1: BagStacking method overview: D - Bootstrap sampling the training set S, M - Training the base models, P - Apply the base models on the original training set, M' - Train the meta learner on the base models predictions, $\hat{y}_{bagstacking}$ - Apply base models to new instance, feed outputs to meta-learner for final prediction.

Theorems & Definitions (1)

  • Theorem 3.1