In clinical gait analysis the correct identification of beginning and ending of steps allow estimation of gait parameters, such as cadence, duration, symmetry, step-by-step variability. Many of these parameters are related to neurological disease status, and as such can be used for diagnostic purposes or tracking disease progression. Current research focuses on identification of the initial contact of the foot with the floor based on the signal recorded with a single inertial measurement unit (IMU) at the lower back. However, the signal pattern is highly affected by environmental factors, movement artifacts, and abnormal gait present in neurological diseases.

The aim of this project is therefore to develop and implement an algorithm for real-time initial contact detection based on IMU data as recorded with an IMU located on the lower back in a heterogeneous population of participants with Parkinson’s disease, participants who suffered a stroke, and older adults. Results will be compared to reference values obtained with a “silver standard”, that was obtained with IMUs located bilaterally on the shanks.