Combining Smartphone Inertial Sensors and Machine Learning Algorithms to Estimate Power Variables in Standing Long Jump
Standing long jump (SLJ) power is recognized as informative of the ability of lower limbs to exert power. The study aims to provide athletes/coaches with a simple and low-cost estimate of selected SLJ power features. A group of 150 trained young participants was recruited and performed a SLJ task wh...
| Autores principales: | , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | English |
| Publicado: |
MDPI AG
2025-01-01
|
| Colección: | Computers |
| Materias: | |
| Acceso en línea: | https://www.mdpi.com/2073-431X/14/2/31 |
| _version_ | 1826582776751587328 |
|---|---|
| author | Beatrice De Lazzari Giuseppe Vannozzi Valentina Camomilla |
| author_facet | Beatrice De Lazzari Giuseppe Vannozzi Valentina Camomilla |
| author_sort | Beatrice De Lazzari |
| collection | DOAJ |
| description | Standing long jump (SLJ) power is recognized as informative of the ability of lower limbs to exert power. The study aims to provide athletes/coaches with a simple and low-cost estimate of selected SLJ power features. A group of 150 trained young participants was recruited and performed a SLJ task while holding a smartphone, whose inertial sensors were used to collect data. Considering the state-of-the-art in SLJ biomechanics, a set of features was extracted and then selected by Lasso regression and used as inputs to several different optimized machine learning architectures to estimate the SLJ power variables. A Multi-Layer Perceptron Regressor was selected as the best-performing model to estimate total and concentric antero-posterior mean power, with an RMSE of 0.37 W/kg, R<sup>2</sup> > 0.70, and test phase homoscedasticity (Kendall’s τ < 0.1) in both cases. Model performance was dependent on the dataset size rather than the participants’ sex. A Multi-Layer Perceptron Regressor was able to also estimate the antero-posterior peak power (RMSE = 2.34 W/kg; R<sup>2</sup> = 0.67), although affected by heteroscedasticity. This study proved the feasibility of combining low-cost smartphone sensors and machine learning to automatically and objectively estimate SLJ power variables in ecological settings. |
| first_indexed | 2025-03-14T15:11:20Z |
| format | Article |
| id | doaj.art-0befa1a616604d1b92bce0bae6334bf1 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2025-03-14T15:11:20Z |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-0befa1a616604d1b92bce0bae6334bf12025-02-25T13:21:47ZengMDPI AGComputers2073-431X2025-01-011423110.3390/computers14020031Combining Smartphone Inertial Sensors and Machine Learning Algorithms to Estimate Power Variables in Standing Long JumpBeatrice De Lazzari0Giuseppe Vannozzi1Valentina Camomilla2Department of Movement, Human and Health Science, University of Rome “Foro Italico”, Piazza Lauro de Bosis 6, 00135 Roma, LZ, ItalyDepartment of Movement, Human and Health Science, University of Rome “Foro Italico”, Piazza Lauro de Bosis 6, 00135 Roma, LZ, ItalyDepartment of Movement, Human and Health Science, University of Rome “Foro Italico”, Piazza Lauro de Bosis 6, 00135 Roma, LZ, ItalyStanding long jump (SLJ) power is recognized as informative of the ability of lower limbs to exert power. The study aims to provide athletes/coaches with a simple and low-cost estimate of selected SLJ power features. A group of 150 trained young participants was recruited and performed a SLJ task while holding a smartphone, whose inertial sensors were used to collect data. Considering the state-of-the-art in SLJ biomechanics, a set of features was extracted and then selected by Lasso regression and used as inputs to several different optimized machine learning architectures to estimate the SLJ power variables. A Multi-Layer Perceptron Regressor was selected as the best-performing model to estimate total and concentric antero-posterior mean power, with an RMSE of 0.37 W/kg, R<sup>2</sup> > 0.70, and test phase homoscedasticity (Kendall’s τ < 0.1) in both cases. Model performance was dependent on the dataset size rather than the participants’ sex. A Multi-Layer Perceptron Regressor was able to also estimate the antero-posterior peak power (RMSE = 2.34 W/kg; R<sup>2</sup> = 0.67), although affected by heteroscedasticity. This study proved the feasibility of combining low-cost smartphone sensors and machine learning to automatically and objectively estimate SLJ power variables in ecological settings.https://www.mdpi.com/2073-431X/14/2/31SLJIMUaccelerometerpredictionin-field testML |
| spellingShingle | Beatrice De Lazzari Giuseppe Vannozzi Valentina Camomilla Combining Smartphone Inertial Sensors and Machine Learning Algorithms to Estimate Power Variables in Standing Long Jump Computers SLJ IMU accelerometer prediction in-field test ML |
| title | Combining Smartphone Inertial Sensors and Machine Learning Algorithms to Estimate Power Variables in Standing Long Jump |
| title_full | Combining Smartphone Inertial Sensors and Machine Learning Algorithms to Estimate Power Variables in Standing Long Jump |
| title_fullStr | Combining Smartphone Inertial Sensors and Machine Learning Algorithms to Estimate Power Variables in Standing Long Jump |
| title_full_unstemmed | Combining Smartphone Inertial Sensors and Machine Learning Algorithms to Estimate Power Variables in Standing Long Jump |
| title_short | Combining Smartphone Inertial Sensors and Machine Learning Algorithms to Estimate Power Variables in Standing Long Jump |
| title_sort | combining smartphone inertial sensors and machine learning algorithms to estimate power variables in standing long jump |
| topic | SLJ IMU accelerometer prediction in-field test ML |
| url | https://www.mdpi.com/2073-431X/14/2/31 |
| work_keys_str_mv | AT beatricedelazzari combiningsmartphoneinertialsensorsandmachinelearningalgorithmstoestimatepowervariablesinstandinglongjump AT giuseppevannozzi combiningsmartphoneinertialsensorsandmachinelearningalgorithmstoestimatepowervariablesinstandinglongjump AT valentinacamomilla combiningsmartphoneinertialsensorsandmachinelearningalgorithmstoestimatepowervariablesinstandinglongjump |