Detecting Falls with Wearable Sensors Using Machine Learning Techniques

• Published in: Sensors (Basel, Switzerland) Vol. 14; no. 6; pp. 10691 - 10708
• Main Authors: Özdemir, Ahmet, Barshan, Billur
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 18.06.2014; MDPI
• Subjects: Accelerometry - instrumentation; Accelerometry - methods; Accidental Falls - prevention & control; Activities of daily living; Adult; Algorithms; Artificial Intelligence; Automation; Classifiers; Complexity; Computation; fall detection; Falls; feature extraction and reduction; Humans; Machine learning; Magnetometry - instrumentation; Male; Monitoring, Ambulatory - instrumentation; Monitoring, Ambulatory - methods; Orthopedics; pattern classification; Pattern Recognition, Automated - methods; Public health; Reproducibility of Results; Risk Assessment - methods; Sensitivity and Specificity; Sensors; Support vector machines; Training; Wearable; wearable motion sensors; Young Adult; Turkey

Falls are a serious public health problem and possibly life threatening for people in fall risk groups. We develop an automated fall detection system with wearable motion sensor units fitted to the subjects’ body at six different positions. Each unit comprises three tri-axial devices (accelerometer,...