No abstract

BackgroundRecently, much attention has been given to the use of inertial sensors for remote monitoring of individuals with limited mobility. However, the focus has been mostly on the detection of symptoms, not specific activities. The objective of the present study was to develop an automated recognition and segmentation algorithm based on inertial sensor data to identify common gross motor patterns during activity of daily living.MethodA modified Time-Up-And-Go (TUG) task was used since it is comprised of four common daily living activities; Standing, Walking, Turning, and Sitting, all performed in a continuous fashion resulting in six different segments during the task. Sixteen healthy older adults performed two trials of a 5 and 10 meter TUG task. They were outfitted with 17 inertial motion sensors covering each body segment. Data from the 10 meter TUG were used to identify pertinent sensors on the trunk, head, hip, knee, and thigh that provided suitable data for detecting and segmenting activities associated with the TUG. Raw data from sensors were detrended to remove sensor drift, normalized, and band pass filtered with optimal frequencies to reveal kinematic peaks that corresponded to different activities. Segmentation was accomplished by identifying the time stamps of the first minimum or maximum to the right and the left of these peaks. Segmentation time stamps were compared to results from two examiners visually segmenting the activities of the TUG.ResultsWe were able to detect these activities in a TUG with 100% sensitivity and specificity (n = 192) during the 10 meter TUG. The rate of success was subsequently confirmed in the 5 meter TUG (n = 192) without altering the parameters of the algorithm. When applying the segmentation algorithms to the 10 meter TUG, we were able to parse 100% of the transition points (n = 224) between different segments that were as reliable and less variable than visual segmentation performed by two independent examiners.ConclusionsThe present study lays the foundation for the development of a comprehensive algorithm to detect and segment naturalistic activities using inertial sensors, in hope of evaluating automatically motor performance within the detected tasks.

No abstract

In this work, we propose to classify, by simulation, the shape variability (or non-Gaussianity) of the surface electromyogram (sEMG) amplitude probability density function (PDF), according to contraction level, using high-order statistics (HOS) and a recent functional formalism, the core shape modeling (CSM). According to recent studies, based on simulated and/or experimental conditions, the sEMG PDF shape seems to be modified by many factors as: contraction level, fatigue state, muscle anatomy, used instrumentation, and also motor control parameters. For sensitivity evaluation against these several sources (physiological, instrumental, and neural control) of variability, a large-scale simulation (25 muscle anatomies, ten parameter configurations, three electrode arrangements) is performed, by using a recent sEMG-force model and parallel computing, to classify sEMG data from three contraction levels (20, 50, and 80% MVC). A shape clustering algorithm is then launched using five combinations of HOS parameters, the CSM method and compared to amplitude clustering with classical indicators [average rectified value (ARV) and root mean square (RMS)]. From the results screening, it appears that the CSM method obtains, using Laplacian electrode arrangement, the highest classification scores, after ARV and RMS approaches, and followed by one HOS combination. However, when some critical confounding parameters are changed, these scores decrease. These simulation results demonstrate that the shape screening of the sEMG amplitude PDF is a complex task which needs both efficient shape analysis methods and specific signal recording protocol to be properly used for tracking neural drive and muscle activation strategies with varying force contraction in complement to classical amplitude estimators.