Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor Data
The validity of results in race walking is often questioned due to subjective decisions in the detection of faults. This study aims to compare machine-learning algorithms fed with data gathered from inertial sensors placed on lower-limb segments to define the best-performing classifiers for the auto...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/6/1461 |
| _version_ | 1811262829077987328 |
|---|---|
| author | Juri Taborri Eduardo Palermo Stefano Rossi |
| author_facet | Juri Taborri Eduardo Palermo Stefano Rossi |
| author_sort | Juri Taborri |
| collection | DOAJ |
| description | The validity of results in race walking is often questioned due to subjective decisions in the detection of faults. This study aims to compare machine-learning algorithms fed with data gathered from inertial sensors placed on lower-limb segments to define the best-performing classifiers for the automatic detection of illegal steps. Eight race walkers were enrolled and linear accelerations and angular velocities related to pelvis, thighs, shanks, and feet were acquired by seven inertial sensors. The experimental protocol consisted of two repetitions of three laps of 250 m, one performed with regular race walking, one with loss-of-contact faults, and one with knee-bent faults. The performance of 108 classifiers was evaluated in terms of accuracy, recall, precision, F1-score, and goodness index. Generally, linear accelerations revealed themselves as more characteristic with respect to the angular velocities. Among classifiers, those based on the support vector machine (SVM) were the most accurate. In particular, the quadratic SVM fed with shank linear accelerations was the best-performing classifier, with an F1-score and a goodness index equal to 0.89 and 0.11, respectively. The results open the possibility of using a wearable device for automatic detection of faults in race walking competition. |
| first_indexed | 2024-04-12T19:33:45Z |
| format | Article |
| id | doaj.art-1760ea01ba0e483597ded4fb23fb2405 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-12T19:33:45Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1760ea01ba0e483597ded4fb23fb24052022-12-22T03:19:16ZengMDPI AGSensors1424-82202019-03-01196146110.3390/s19061461s19061461Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor DataJuri Taborri0Eduardo Palermo1Stefano Rossi2Department of Economics, Engineering, Society and Business Organization (DEIM), University of Tuscia, 01100 Viterbo, ItalyDepartment of Mechanical and Aerospace Engineering, Sapienza University of Rome, 00184 Rome, ItalyDepartment of Economics, Engineering, Society and Business Organization (DEIM), University of Tuscia, 01100 Viterbo, ItalyThe validity of results in race walking is often questioned due to subjective decisions in the detection of faults. This study aims to compare machine-learning algorithms fed with data gathered from inertial sensors placed on lower-limb segments to define the best-performing classifiers for the automatic detection of illegal steps. Eight race walkers were enrolled and linear accelerations and angular velocities related to pelvis, thighs, shanks, and feet were acquired by seven inertial sensors. The experimental protocol consisted of two repetitions of three laps of 250 m, one performed with regular race walking, one with loss-of-contact faults, and one with knee-bent faults. The performance of 108 classifiers was evaluated in terms of accuracy, recall, precision, F1-score, and goodness index. Generally, linear accelerations revealed themselves as more characteristic with respect to the angular velocities. Among classifiers, those based on the support vector machine (SVM) were the most accurate. In particular, the quadratic SVM fed with shank linear accelerations was the best-performing classifier, with an F1-score and a goodness index equal to 0.89 and 0.11, respectively. The results open the possibility of using a wearable device for automatic detection of faults in race walking competition.https://www.mdpi.com/1424-8220/19/6/1461race walkingillegal stepsmachine-learning algorithmsinertial sensorsactivity recognition |
| spellingShingle | Juri Taborri Eduardo Palermo Stefano Rossi Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor Data Sensors race walking illegal steps machine-learning algorithms inertial sensors activity recognition |
| title | Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor Data |
| title_full | Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor Data |
| title_fullStr | Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor Data |
| title_full_unstemmed | Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor Data |
| title_short | Automatic Detection of Faults in Race Walking: A Comparative Analysis of Machine-Learning Algorithms Fed with Inertial Sensor Data |
| title_sort | automatic detection of faults in race walking a comparative analysis of machine learning algorithms fed with inertial sensor data |
| topic | race walking illegal steps machine-learning algorithms inertial sensors activity recognition |
| url | https://www.mdpi.com/1424-8220/19/6/1461 |
| work_keys_str_mv | AT juritaborri automaticdetectionoffaultsinracewalkingacomparativeanalysisofmachinelearningalgorithmsfedwithinertialsensordata AT eduardopalermo automaticdetectionoffaultsinracewalkingacomparativeanalysisofmachinelearningalgorithmsfedwithinertialsensordata AT stefanorossi automaticdetectionoffaultsinracewalkingacomparativeanalysisofmachinelearningalgorithmsfedwithinertialsensordata |