Online Decoding of Hidden Markov Models for Gait Event Detection Using Foot-Mounted Gyroscopes

• Published in: IEEE journal of biomedical and health informatics Vol. 18; no. 4; pp. 1122 - 1130
• Main Authors: Mannini, Andrea, Genovese, Vincenzo, Sabatin, Angelo Maria
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2014; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Decoding; Foot; Foot - physiology; Gait - physiology; Gait event detection; gyroscope; hidden Markov model (HMM); Hidden Markov models; human movement analysis; Humans; Internet; Legged locomotion; Markov Chains; Monitoring, Ambulatory - instrumentation; Monitoring, Ambulatory - methods; Sensors; short-time Viterbi (STV); Signal Processing, Computer-Assisted; Telemedicine; Vectors; Viterbi algorithm

In this paper, we present an approach to the online implementation of a gait event detector based on machine learning algorithms. Gait events were detected using a uniaxial gyro that measured the foot instep angular velocity in the sagittal plane to feed a four-state left-right hidden Markov model (...