Publications:Gait Event Detection in the Real World
Do not edit this section
"Wickström, Nicholas (nicholas), Associate Professor (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), ;;CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650))Rögnvaldsson, Thorsteinn (denni), Professor (Högskolan i Halmstad (2804), Akademin för informationsteknologi (16904), Halmstad Embedded and Intelligent Systems Research (EIS) (3938), ;;CAISR Centrum för tillämpade intelligenta system (IS-lab) (13650))" cannot be used as a page name in this wiki.
Keep all hand-made modifications below
|Title||Gait Event Detection in the Real World|
|Abstract||Healthy gait requires a balance between various neuro-physiological systems and is considered an important indicator of a subject's physical and cognitive health status. As such, health-related applications would immensely benefit by performing long-term or continuous monitoring of subjects' gait in their natural environment and everyday lives. In contrast to stationary sensors such as motion capture systems and force plates, inertial sensors provide a good alternative for such gait analysis applications as they are miniature, cheap, mobile and can be easily integrated into wearable systems.This thesis focuses on improving overall gait analysis using inertial sensors by providing a methodology for detecting gait events in real-world settings. Although the experimental protocols for such analysis have been restricted to only highly-controlled lab-like indoor settings; this thesis presents a new gait database that consists of data from gait activities carried out in both, indoor and outdoor environments. The thesis shows how domain knowledge about gait could be formulated and utilized to develop methods that are robust and can tackle real-world challenges. It also shows how the proposed approach can be generalized to estimate gait events from multiple body locations. Another aspect of this thesis is to demonstrate that the traditionally used temporal error metrics are not enough for presenting the overall performance of gait event detection methods. The thesis introduces how non-parametric tests can be used to complement them and provide a better overview.The results of comparing the proposed methodology to state-of-the-art methods showed that the approach of incorporating domain knowledge into the time-frequency analysis of the signal was robust across different real-world scenarios and outperformed other methods, especially for the scenario involving variable gait speeds in outdoor settings. The methodology was also benchmarked on publicly available gait databases yielding good performance for estimating events from different body locations. To conclude, this thesis presents a road map for the development of gait analysis systems in real-world settings.|