Accuracy of Hidden Markov Models in Identifying Alterations in Movement Patterns during Biceps-Curl Weight-Lifting Exercise
Authors:
- André B. PeresAPAndré B. Peres
- Mário C. EspadaMário C. Espada
- Fernando J. SantosFernando J. Santos
- Ricardo A. M. RobaloRRRicardo A. M. Robalo
- Amândio A. P. DiasADAmândio A. P. Dias
- Jesús Muñoz-JiménezJMJesús Muñoz-Jiménez
- Andrei SancassaniASAndrei Sancassani
- Danilo A. MassiniDanilo A. Massini
- Dalton M. Pessôa FilhoDalton M. Pessôa Filho
Open Access
- 31 December 2022
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 13 (1) , 573
Abstract
This paper presents a comparison of mathematical and cinematic motion analysis regarding the accuracy of the detection of alterations in the patterns of positional sequence during biceps-curl lifting exercise. Two different methods, one with and one without metric data from the environment, were used to identify the changes. Ten volunteers performed a standing biceps-curl exercise with additional loads. A smartphone recorded their movements in the sagittal plane, providing information on joints and barbell sequential position changes during each lift attempt. An analysis of variance revealed significant differences in joint position (p < 0.05) among executions with three different loads. Hidden Markov models were trained with data from the bi-dimensional coordinates of the joint positional sequence to identify meaningful alteration with load increment. Tests of agreement tests between the results provided by the models with the environmental measurements, as well as those from image coordinates, were performed. The results demonstrated that it is possible to efficiently detect changes in the patterns of positional sequence with and without the necessity of measurement and/or environmental control, reaching an agreement of 86% between each other, and 100% and 86% for each respective method to the results of ANOVA. The method developed in this study illustrates the viability of smartphone camera use for identifying positional adjustments due to the inability to control limbs in an adequate range of motion with increasing load during a lifting task.Keywords
Funding Information
- São Paulo Research Foundation—FAPESP (PROCESS 2016/04544-3, APES-Finance Code 001, UIDB/04748/2020)
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brazil (PROCESS 2016/04544-3, APES-Finance Code 001, UIDB/04748/2020)
- Fundação para a Ciência e a Tecnologia (PROCESS 2016/04544-3, APES-Finance Code 001, UIDB/04748/2020)
- Instituto Politécnico de Setúbal (PROCESS 2016/04544-3, APES-Finance Code 001, UIDB/04748/2020)
This publication has 58 references indexed in Scilit:
- Modeling and prediction of driver behavior by foot gesture analysisComputer Vision and Image Understanding, 2012
- Three dimensional musculoskeletal modelling of the seated biceps curl resistance training exerciseSports Biomechanics, 2011
- Real-time lip reading system for isolated Korean word recognitionPattern Recognition, 2011
- Quantifying the Movement and the Influence of Load in the Back Squat ExerciseJournal of Strength & Conditioning Research, 2010
- Influence of Supervision Ratio on Muscle Adaptations to Resistance Training in Nontrained SubjectsJournal of Strength & Conditioning Research, 2010
- Resistance training among young athletes: safety, efficacy and injury prevention effectsBritish Journal of Sports Medicine, 2009
- Extraction of 2D motion trajectories and its application to hand gesture recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Recognition of human gestures and behaviour based on motion trajectoriesImage and Vision Computing, 2002
- Hidden Markov Models for Speech RecognitionTechnometrics, 1991
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989