Identification of Gait Motion Patterns Using Wearable Inertial Sensor Network.

Area of Science:

• Biomechanics
• Wearable Technology
• Biomedical Engineering

Background:

• Gait analysis is crucial for assessing an individual's health status, as deviations can indicate abnormalities.
• Existing gait monitoring systems often require controlled laboratory environments, limiting real-world applicability.

Purpose of the Study:

• To develop a wireless gait sensor network system for monitoring the gait cycle.
• To enable gait data collection in diverse, non-laboratory settings.
• To introduce a novel gait pattern classification method for detecting abnormalities.

Main Methods:

• Utilized a pair of wireless inertial measurement unit (IMU) sensors placed on a single leg.
• Extracted three-dimensional angular motions of hip and knee joints during walking.
• Developed mathematical models to decompose sensor data into individual and relative joint motions.
• Implemented a new classification approach based on phase difference angles between hip and knee joints.

Main Results:

• Successfully extracted detailed hip and knee joint angular motions from wearable IMU sensors.
• Demonstrated a novel gait pattern classification method using phase difference angles.
• Experimental results indicate the potential for smart detection of abnormal gait patterns.

Conclusions:

• The developed wireless IMU sensor system facilitates gait analysis outside laboratory settings.
• The proposed phase difference angle classification method shows promise for identifying abnormal gaits.
• This technology has potential applications in remote health monitoring and early detection of gait-related conditions.