Multi-task artificial neural networks and their extrapolation capabilities to predict full-body 3D human posture during one- and two-handed load-handling activities

• Published in: Journal of biomechanics Vol. 162; p. 111884
• Main Authors: Mohseni, Mahdi, Zargarzadeh, Sadra, Arjmand, Navid
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2024; Elsevier Limited
• Subjects: Algorithms; Artificial neural networks; Back pain; Biomechanics; Body mass index; Body weight; Datasets; Ergonomics; Errors; Extrapolation; Extrapolation capability; Hand; Handedness; Humans; Kinematics; Lifting techniques; Machine learning; Motion analysis; Motion capture; Musculoskeletal diseases; Neural networks; Neural Networks, Computer; Obesity; Overweight; Posture; Posture prediction; Predictions; Robustness; Skin; Thinness; Underweight; Body mass index; Lifting techniques; Posture prediction; Motion analysis; Machine learning; Extrapolation capability

Machine-learning based human posture-prediction tools can potentially be robust alternatives to motion capture measurements. Existing posture-prediction approaches are confined to two-handed load-handling activities performed at heights below 120 cm from the floor and to predicting a limited number...