Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Using Causal Trees to Estimate Personalized Task Difficulty in Post-Stroke Individuals

Nathaniel Dennler, Stefanos Nikolaidis, Maja Matarić

TL;DR

This work proposes a method that automatically generates regions of different task difficulty levels based on an individual's performance and shows that this technique explains the variance in user performance for a reaching task better than previous approaches to estimating task difficulty.

Abstract

Adaptive training programs are crucial for recovery post stroke. However, developing programs that automatically adapt depends on quantifying how difficult a task is for a specific individual at a particular stage of their recovery. In this work, we propose a method that automatically generates regions of different task difficulty levels based on an individual's performance. We show that this technique explains the variance in user performance for a reaching task better than previous approaches to estimating task difficulty.

Using Causal Trees to Estimate Personalized Task Difficulty in Post-Stroke Individuals

TL;DR

This work proposes a method that automatically generates regions of different task difficulty levels based on an individual's performance and shows that this technique explains the variance in user performance for a reaching task better than previous approaches to estimating task difficulty.

Abstract

Adaptive training programs are crucial for recovery post stroke. However, developing programs that automatically adapt depends on quantifying how difficult a task is for a specific individual at a particular stage of their recovery. In this work, we propose a method that automatically generates regions of different task difficulty levels based on an individual's performance. We show that this technique explains the variance in user performance for a reaching task better than previous approaches to estimating task difficulty.
Paper Structure (8 sections, 2 equations, 1 figure, 1 table)

This paper contains 8 sections, 2 equations, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Statement
  4. Dataset for Evaluating Approach
  5. Preliminary Results
  6. Estimating Personalized Difficulty
  7. Visualizing Personalized Difficulty
  8. Discussion and Conclusions

Figures (1)

  • Figure 1: Maps of difficulties for two different participants. PID 25 was left-affected and had lower overall Fugyl-Meyer score (47 out of 65). PID 25 exhibited more difficulty reaching far in front. PID 27 is right-affected and had a higher Fugyl-Meyer Score (62 out of 65). PID 27 exhibited more difficulty reaching higher points on their right side.