# A Sensor-Based Classification for Neuromotor Robot-Assisted Rehabilitation

## TL;DR

This paper proposes a sensor classification and framework to improve personalized robot-assisted rehabilitation for patients with motor deficits.

## Contribution

A novel sensor classification and framework for patient-centered neuromotor rehabilitation using collective sensor data.

## Key findings

- A comprehensive sensor classification was developed based on specific and non-specific parameters.
- A framework was proposed to collect and use sensor data for efficient, personalized rehabilitation.
- The classification identifies key variables for dynamic, patient-centered rehabilitation frameworks.

## Abstract

Neurological diseases leading to motor deficits constitute significant challenges to healthcare systems. Despite technological advancements in data acquisition, sensor development, data processing, and virtual reality (VR), a suitable framework for patient-centered neuromotor robot-assisted rehabilitation using collective sensor information does not exist. An extensive literature review was achieved based on 124 scientific publications regarding different types of sensors and the usage of the bio-signals they measure for neuromotor robot-assisted rehabilitation. A comprehensive classification of sensors was proposed, distinguishing between specific and non-specific parameters. The classification criteria address essential factors such as the type of sensors, the data they measure, their usability, ergonomics, and their overall impact on personalized treatment. In addition, a framework designed to collect and utilize relevant data for the optimal rehabilitation process efficiently is proposed. The proposed classifications aim to identify a set of key variables that can be used as a building block for a dynamic framework tailored for personalized treatments, thereby enhancing the effectiveness of patient-centered procedures in rehabilitation.