Dwell times showcase how goal structure informs preschoolers’ analysis of unfolding motion patterns

Speed is an essential parameter in biomechanical analysis and general locomotion research. It is possible to estimate the speed using global positioning systems (GPS) or inertial measurement units (IMUs). However, GPS requires a consistent signal connection to satellites, and errors accumulate during IMU signals integration. In an attempt to overcome these issues, we have investigated the possibility of estimating the horse speed by developing machine learning (ML) models using the signals from seven body-mounted IMUs. Since motion patterns extracted from IMU signals are different between breeds and gaits, we trained the models based on data from 40 Icelandic and Franches-Montagnes horses during walk, trot, tölt, pace, and canter. In addition, we studied the estimation accuracy between IMU locations on the body (sacrum, withers, head, and limbs). The models were evaluated per gait and were compared between ML algorithms and IMU location. The model yielded the highest estimation accuracy of speed (RMSE = 0.25 m/s) within equine and most of human speed estimation literature. In conclusion, highly accurate horse speed estimation models, independent of IMU(s) location on-body and gait, were developed using ML.

Download Full-text

Automatic Discovery of Motion Patterns that Improve Learning Rate in Communication-Limited Multi-Robot Systems

2020 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) ◽

10.1109/mfi49285.2020.9235218 ◽

2020 ◽

Author(s):

Taeyeong Choi ◽

Theodore P. Pavlic

Keyword(s):

Learning Rate ◽

Motion Patterns ◽

Automatic Discovery ◽

Robot Systems ◽

Multi Robot

Download Full-text

Effect of post-stroke spasticity on voluntary movement of the upper limb

Journal of NeuroEngineering and Rehabilitation ◽

10.1186/s12984-021-00876-6 ◽

2021 ◽

Vol 18 (1) ◽

Author(s):

Hadar Lackritz ◽

Yisrael Parmet ◽

Silvi Frenkel-Toledo ◽

Melanie C. Baniña ◽

Nachum Soroker ◽

...

Keyword(s):

Upper Limb ◽

Target Location ◽

Distance Measure ◽

Movement Time ◽

Motor Impairment ◽

Reach To Grasp ◽

Motion Patterns ◽

Post Stroke ◽

The Impact ◽

Elbow Motion

Abstract Background Hemiparesis following stroke is often accompanied by spasticity. Spasticity is one factor among the multiple components of the upper motor neuron syndrome that contributes to movement impairment. However, the specific contribution of spasticity is difficult to isolate and quantify. We propose a new method of quantification and evaluation of the impact of spasticity on the quality of movement following stroke. Methods Spasticity was assessed using the Tonic Stretch Reflex Threshold (TSRT). TSRT was analyzed in relation to stochastic models of motion to quantify the deviation of the hemiparetic upper limb motion from the normal motion patterns during a reaching task. Specifically, we assessed the impact of spasticity in the elbow flexors on reaching motion patterns using two distinct measures of the ‘distance’ between pathological and normal movement, (a) the bidirectional Kullback–Liebler divergence (BKLD) and (b) Hellinger’s distance (HD). These measures differ in their sensitivity to different confounding variables. Motor impairment was assessed clinically by the Fugl-Meyer assessment scale for the upper extremity (FMA-UE). Forty-two first-event stroke patients in the subacute phase and 13 healthy controls of similar age participated in the study. Elbow motion was analyzed in the context of repeated reach-to-grasp movements towards four differently located targets. Log-BKLD and HD along with movement time, final elbow extension angle, mean elbow velocity, peak elbow velocity, and the number of velocity peaks of the elbow motion were computed. Results Upper limb kinematics in patients with lower FMA-UE scores (greater impairment) showed greater deviation from normality when the distance between impaired and normal elbow motion was analyzed either with the BKLD or HD measures. The severity of spasticity, reflected by the TSRT, was related to the distance between impaired and normal elbow motion analyzed with either distance measure. Mean elbow velocity differed between targets, however HD was not sensitive to target location. This may point at effects of spasticity on motion quality that go beyond effects on velocity. Conclusions The two methods for analyzing pathological movement post-stroke provide new options for studying the relationship between spasticity and movement quality under different spatiotemporal constraints.

Download Full-text