Machine learning for lumbar and pelvis kinematics clustering
Higgins, S. M.; Dutta, S.; Kakar, R. S.
Show abstract
Clustering algorithms such as k-means and agglomerative hierarchical clustering (HCA) may provide a unique opportunity to analyze time-series kinematic data. Here we present an approach for determining number of clusters and which clustering algorithm to use on time-series lumbar and pelvis kinematic data. Cluster evaluation measures such as silhouette coefficient, elbow method, Dunn Index, and gap statistic were used to evaluate the quality of decision making. The result show that multiple clustering evaluation methods should be used to determine the ideal number of clusters and algorithm suitable for clustering time-series data for each dataset being analyzed.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Normal feeding movements expressed by dimensionality reduction of whole-body joint motions using principal component analysis 91%
- Comparable behaviour of ring and little fingers due to an artificial reduction in thumb contribution to hold objects 91%
- Geometric variation of the human tibia-fibula: A public dataset of tibia-fibula surface meshes and statistical shape model 90%
Similar papers in this journal
- Automated Optimization of Residual Reduction Algorithm Parameters in OpenSim 93%
- Firefighter Helmets and Cervical Intervertebral Kinematics: An OpenSim-Based Biomechanical Study 93%
- Comparing the advantages and disadvantages of physics-based and neural network-based modelling for predicting cycling power 93%
Similar papers in this journal
- Effect of sampling frequency on fractal fluctuations during treadmill walking 93%
- Increase trajectories of tendon micro vibration intensity during ankle plantar flexion: A longitudinal data analysis using latent curve models 93%
- Analyzing Human Movements - Introducing A Framework To Extract And Evaluate Biomechanical Data 92%
Similar papers in this journal
- Effective Assessments of a Short-duration Poor Posture on Upper Limb Muscle Fatigue before Physical Exercise 92%
- Comparing algorithms for assessing upper limb use with inertial measurement units 91%
- Physical fitness and motor competence performance characteristics of elite Chinese youth athletes from four track and field throwing disciplines - a cross sectional study 89%
Similar papers in this journal
- A single decreasing ramp friction sprint for torque-cadence relationship assessment during cycling 92%
- RACLET: the Ramp Above Critical Level Endurance Test to evaluate critical power in cycling. 91%
- RACLET: the Ramp Above Critical Level Endurance Test to evaluate critical force in isometric task. 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.