Anglia Ruskin Research Online (ARRO)
Browse

File(s) under permanent embargo

Fusion of Artificial Intelligence in Neuro-Rehabilitation Video Games

journal contribution
posted on 2023-09-01, 14:30 authored by Shabnam Sadeghi Esfahlani, Hassan Shirvani, Javaid Butt
In this paper, an intuitive neuro-rehabilitation video game has been developed employing the fusion of artificial neural networks (ANNs), inverse kinematics (IK), and fuzzy logic (FL) algorithms. The embedded algorithms automatically adjust the game difficulty level based on the player’s interaction with the game. Moreover, it is manifested as an alternative approach for possible movements to improve incorrect positioning through real-time visual feedback on the screen; 52 participants volunteered to engage in the program. Motor assessment scale (MAS) was determined to assess the participants’ functional ability pre- and post-treatments. The system input is received via the Microsoft Kinect, a foot Pedal (Saitek), and the Thalmic Myo armband. The ANN classifier integrates the limb joints orientation, angular velocity, lower arms’ muscle activity, hand gestures, feet sole (plantar) pressure parameters, and the MAS scores to learn from data and predict the improvement following the intervention. The fuzzy input generates a crisp output and provides a personalized rehabilitation program with the potential to be integrated into clinical protocols. Experiments to obtain the input signals and desired outputs were conducted for the learning and validation of the network. The networks pattern recognition, self-organizing map, and non-linear auto-regression analysis performed using feed-forward and Levenberg–Marquardt backpropagation (LMBP) procedure. The results showed the effectiveness of the non-linear auto-regression using the optimized LMBP algorithm to classify and visualize the target categories. Furthermore, the state of the network demonstrates the prediction accuracy exceeding 94%. Clustering algorithm grouped the data based on the similarity. Self-organizing map trained the network to learn the topology of samples with high correlation, presented outputs with high achievement.

History

Refereed

  • Yes

Volume

7

Page range

102617

Number of pages

16

Publication title

IEEE Access

ISSN

2169-3536

Publisher

IEEE

File version

  • Accepted version

Language

  • eng

Legacy posted date

2019-07-01

Legacy creation date

2019-06-28

Legacy Faculty/School/Department

Faculty of Science & Engineering

Usage metrics

    ARU Outputs

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC