Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses—A Machine Learning Approach
Speed is an essential parameter in biomechanical analysis and general locomotion research. It is possible to estimate the speed using global positioning systems (GPS) or inertial measurement units (IMUs). However, GPS requires a consistent signal connection to satellites, and errors accumulate durin...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/3/798 |
| _version_ | 1797407419801796608 |
|---|---|
| author | Hamed Darbandi Filipe Serra Bragança Berend Jan van der Zwaag John Voskamp Annik Imogen Gmel Eyrún Halla Haraldsdóttir Paul Havinga |
| author_facet | Hamed Darbandi Filipe Serra Bragança Berend Jan van der Zwaag John Voskamp Annik Imogen Gmel Eyrún Halla Haraldsdóttir Paul Havinga |
| author_sort | Hamed Darbandi |
| collection | DOAJ |
| description | Speed is an essential parameter in biomechanical analysis and general locomotion research. It is possible to estimate the speed using global positioning systems (GPS) or inertial measurement units (IMUs). However, GPS requires a consistent signal connection to satellites, and errors accumulate during IMU signals integration. In an attempt to overcome these issues, we have investigated the possibility of estimating the horse speed by developing machine learning (ML) models using the signals from seven body-mounted IMUs. Since motion patterns extracted from IMU signals are different between breeds and gaits, we trained the models based on data from 40 Icelandic and Franches-Montagnes horses during walk, trot, tölt, pace, and canter. In addition, we studied the estimation accuracy between IMU locations on the body (sacrum, withers, head, and limbs). The models were evaluated per gait and were compared between ML algorithms and IMU location. The model yielded the highest estimation accuracy of speed (RMSE = 0.25 m/s) within equine and most of human speed estimation literature. In conclusion, highly accurate horse speed estimation models, independent of IMU(s) location on-body and gait, were developed using ML. |
| first_indexed | 2024-03-09T03:41:14Z |
| format | Article |
| id | doaj.art-22453daddd714fc28ae029660280e3a9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T03:41:14Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-22453daddd714fc28ae029660280e3a92023-12-03T14:40:31ZengMDPI AGSensors1424-82202021-01-0121379810.3390/s21030798Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses—A Machine Learning ApproachHamed Darbandi0Filipe Serra Bragança1Berend Jan van der Zwaag2John Voskamp3Annik Imogen Gmel4Eyrún Halla Haraldsdóttir5Paul Havinga6Pervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB Enschede, The NetherlandsDepartment of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584 CM Utrecht, The NetherlandsPervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB Enschede, The NetherlandsRosmark Consultancy, 6733 AA Wekerom, The NetherlandsEquine Department, Vetsuisse Faculty, University of Zurich, 8057 Zurich, SwitzerlandEquine Department, Vetsuisse Faculty, University of Zurich, 8057 Zurich, SwitzerlandPervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB Enschede, The NetherlandsSpeed is an essential parameter in biomechanical analysis and general locomotion research. It is possible to estimate the speed using global positioning systems (GPS) or inertial measurement units (IMUs). However, GPS requires a consistent signal connection to satellites, and errors accumulate during IMU signals integration. In an attempt to overcome these issues, we have investigated the possibility of estimating the horse speed by developing machine learning (ML) models using the signals from seven body-mounted IMUs. Since motion patterns extracted from IMU signals are different between breeds and gaits, we trained the models based on data from 40 Icelandic and Franches-Montagnes horses during walk, trot, tölt, pace, and canter. In addition, we studied the estimation accuracy between IMU locations on the body (sacrum, withers, head, and limbs). The models were evaluated per gait and were compared between ML algorithms and IMU location. The model yielded the highest estimation accuracy of speed (RMSE = 0.25 m/s) within equine and most of human speed estimation literature. In conclusion, highly accurate horse speed estimation models, independent of IMU(s) location on-body and gait, were developed using ML.https://www.mdpi.com/1424-8220/21/3/798inertial measurement unitmachine learningbreedgaitfeature extraction |
| spellingShingle | Hamed Darbandi Filipe Serra Bragança Berend Jan van der Zwaag John Voskamp Annik Imogen Gmel Eyrún Halla Haraldsdóttir Paul Havinga Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses—A Machine Learning Approach Sensors inertial measurement unit machine learning breed gait feature extraction |
| title | Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses—A Machine Learning Approach |
| title_full | Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses—A Machine Learning Approach |
| title_fullStr | Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses—A Machine Learning Approach |
| title_full_unstemmed | Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses—A Machine Learning Approach |
| title_short | Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses—A Machine Learning Approach |
| title_sort | using different combinations of body mounted imu sensors to estimate speed of horses a machine learning approach |
| topic | inertial measurement unit machine learning breed gait feature extraction |
| url | https://www.mdpi.com/1424-8220/21/3/798 |
| work_keys_str_mv | AT hameddarbandi usingdifferentcombinationsofbodymountedimusensorstoestimatespeedofhorsesamachinelearningapproach AT filipeserrabraganca usingdifferentcombinationsofbodymountedimusensorstoestimatespeedofhorsesamachinelearningapproach AT berendjanvanderzwaag usingdifferentcombinationsofbodymountedimusensorstoestimatespeedofhorsesamachinelearningapproach AT johnvoskamp usingdifferentcombinationsofbodymountedimusensorstoestimatespeedofhorsesamachinelearningapproach AT annikimogengmel usingdifferentcombinationsofbodymountedimusensorstoestimatespeedofhorsesamachinelearningapproach AT eyrunhallaharaldsdottir usingdifferentcombinationsofbodymountedimusensorstoestimatespeedofhorsesamachinelearningapproach AT paulhavinga usingdifferentcombinationsofbodymountedimusensorstoestimatespeedofhorsesamachinelearningapproach |