Multimodal Reaching-Position Prediction for ADL Support Using Neural Networks

TL;DR

This paper presents a neural network-based multimodal prediction system for reaching positions to support daily activities of hemiplegic patients and the elderly, achieving high accuracy with limited sensor data.

Contribution

It introduces a novel multimodal motion feature-based deep learning model for predicting reaching positions in environments with minimal sensors.

Findings

Achieved 93% macro average accuracy in 9-class prediction.

F1-score of 0.69 at 35% of motion completion.

Demonstrated effective prediction with limited sensor setup.

Abstract

This study aimed to develop daily living support robots for patients with hemiplegia and the elderly. To support the daily living activities using robots in ordinary households without imposing physical and mental burdens on users, the system must detect the actions of the user and move appropriately according to their motions. We propose a reaching-position prediction scheme that targets the motion of lifting the upper arm, which is burdensome for patients with hemiplegia and the elderly in daily living activities. For this motion, it is difficult to obtain effective features to create a prediction model in environments where large-scale sensor system installation is not feasible and the motion time is short. We performed motion-collection experiments, revealed the features of the target motion and built a prediction model using the multimodal motion features and deep learning. The proposed model achieved an accuracy of 93 \% macro average and F1-score of 0.69 for a 9-class classification prediction at 35\% of the motion completion.