Detection and Classification of Postural Transitions in Real-World Conditions

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 20; no. 5; pp. 688 - 696
• Main Authors: Ganea, Raluca, Paraschiv-lonescu, Anisoara, Aminian, Kamiar
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2012; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acceleration; Actigraphy - instrumentation; Actigraphy - methods; Ambulatory monitoring; Chronic Pain - diagnosis; Chronic Pain - physiopathology; Classification algorithms; dynamic time warping; Equipment Design; Female; Frailty; functional assessment; Humans; inertial sensors; Legged locomotion; Male; Middle Aged; Monitoring; Monitoring systems; Monitoring, Ambulatory - instrumentation; Monitoring, Ambulatory - methods; Movement - physiology; Pain; Pain management; pattern matching; Pattern Recognition, Automated - methods; postural transitions; Posture - physiology; Reproducibility of Results; Senior citizens; Sensitivity and Specificity; Studies; Training

This study proposes a new robust classifier for sit-to-stand (SiSt) and stand-to-sit (StSt) detection in daily activity. The monitoring system consists of a single inertial sensor placed on the trunk. By using dynamic time warping, the trunk acceleration patterns of SiSt and StSi are classified base...