Lower limb wearable capacitive sensing and its applications to recognizing human gaits

Area of Science:

• Biomedical Engineering
• Wearable Technology
• Human Motion Analysis

Background:

• Accurate recognition of human locomotion modes is crucial for various applications, including rehabilitation and human-computer interaction.
• Existing methods like electromyography (EMG) and inertial measurement units (IMUs) have limitations in terms of comfort, cost, or placement.
• Capacitive sensing offers a potential alternative for non-invasive and comfortable human motion monitoring.

Purpose of the Study:

• To develop and validate a wearable capacitive sensing system for recognizing lower limb locomotion modes.
• To assess the system's accuracy, stability, and adaptability in real-world conditions.
• To compare the performance of capacitive sensing with established methods like EMG and IMUs.

Main Methods:

• A wearable sensing system comprising sensing bands, a signal processing circuit, and a gait event detection module was designed.
• Twelve able-bodied subjects participated in experiments involving eleven normal gait modes.
• An event-dependent linear discriminant analysis classifier with feature selection was employed, utilizing four time-domain features.

Main Results:

• The capacitive sensing system demonstrated high recognition accuracies for different phases of the gait cycle: 97.3% ± 0.5%, 97.0% ± 0.4%, 95.6% ± 0.9%, and 97.0% ± 0.4%.
• The system showed long-term working stability and adaptability to disturbances.
• Performance was found to be comparable to electromyography-based and inertial-based systems.

Conclusions:

• The proposed lower limb capacitive sensing approach is effective for recognizing human normal gaits.
• This technology offers a promising, accurate, and potentially more comfortable alternative for locomotion mode recognition.
• Further research can explore its application in clinical settings and advanced human-computer interaction.