A novel mobile-cloud system for capturing and analyzing wheelchair maneuvering data: A pilot study.

Area of Science:

• Rehabilitation Engineering
• Human-Computer Interaction
• Wearable Technology

Background:

• Accurate assessment of wheelchair user activity levels is crucial for rehabilitation and health monitoring.
• Existing methods for collecting wheelchair maneuvering data can be cumbersome, requiring specialized sensors attached to the wheelchair.
• There is a need for more accessible and user-friendly methods to capture and analyze wheelchair mobility patterns.

Purpose of the Study:

• To introduce a novel mobile-cloud (MC) system for capturing and analyzing wheelchair maneuvering data.
• To evaluate the feasibility and accuracy of the MC system in real-world settings.
• To offer a simplified approach for assessing wheelchair user activity levels.

Main Methods:

• Development of a mobile-cloud system integrating smartphone sensors and cloud computing.
• Utilizing smartphone sensors to collect wheelchair maneuvering data.
• Implementation of a k-nearest neighbor (KNN) machine-learning algorithm for data analysis and noise reduction.
• Conducting 30 trials in indoor environments, with each trial comprising 10 bouts of continuous wheelchair movement.

Main Results:

• The MC system successfully identified all 300 wheelchair maneuvering bouts across the trials.
• The approach demonstrated comparable accuracy to existing methods in analyzing accumulated movement time and maximum continuous movement periods (p > 0.8).
• The system proved easier to use compared to traditional sensor-attachment methods.

Conclusions:

• The proposed mobile-cloud system offers a feasible and accurate solution for collecting and analyzing wheelchair maneuvering data.
• This approach simplifies the data collection process, enhancing the evaluation of wheelchair user activity levels.
• The MC system represents a significant advancement in leveraging mobile and cloud technologies for assistive device monitoring.