Bringing objectivity to motor skill assessment in children.

The study purpose was to use Inertial Measurement Units (IMUs) to objectively assess children's motor competence in seven movement skills. Fourteen children aged from seven to 12 years (M = 9.64) participated. Children were asked to perform up to 10 trials of each skill. Children performed the skills, which were captured by XSENS MVN Awinda wireless motion capture, and video. Skills were assessed from video as per the criteria from the Test of Gross Motor Development 3. Initially, 17 IMU sensors were used for signal processing, but this was restricted to four sensors (wrists and ankles) to be more feasible for field assessment. Results of the signal testing against its modelled "Good" signal, showed the skip was classified correctly each time, as was the sidestep. Accuracy % rates for each skill were: kick (95.2), catch (95.0), throw (80.5), jump (78.9), and hop (76.9). Using signal processing-based methods via four sensors was a reliable and feasible way to assess seven motor skills in children. This approach means monitoring and assessment of children's skills can be objective, which will potentially reduce the time involved in motor skill assessment and analysis for research, clinical, sport and education purposes.

RGB-D ergonomic assessment system of adopted working postures.

Ensuring a healthier working environment is of utmost importance for companies and global health organizations. In manufacturing plants, the ergonomic assessment of adopted working postures is indispensable to avoid risk factors of work-related musculoskeletal disorders. This process receives high research interest and requires extracting plausible postural information as a preliminary step. This paper presents a semi-automated end-to-end ergonomic assessment system of adopted working postures. The proposed system analyzes the human posture holistically, does not rely on any attached markers, uses low cost depth technologies and leverages the state-of-the-art deep learning techniques. In particular, we train a deep convolutional neural network to analyze the articulated posture and predict body joint angles from a single depth image. The proposed method relies on learning from synthetic training images to allow simulating several physical tasks, different body shapes and rendering parameters and obtaining a highly generalizable model. The corresponding ground truth joint angles have been generated using a novel inverse kinematics modeling stage. We validated the proposed system in real environments and achieved a joint angle mean absolute error (MAE) of 3.19±1.57∘ and a rapid upper limb assessment (RULA) grand score prediction accuracy of 89% with Kappa index of 0.71 which means substantial agreement with reference scores. This work facilities evaluating several ergonomic assessment metrics as it provides direct access to necessary postural information overcoming the need for computationally expensive post-processing operations.