User-Independent Recognition of Sports Activities From a Single Wrist-Worn Accelerometer: A Template-Matching-Based Approach. Margarito, J., Helaoui, R., Bianchi, A., M., Sartor, F., & Bonomi, A., G. IEEE Transactions on Biomedical Engineering, 63(4):788-796, IEEE, 4, 2016. ![User-Independent Recognition of Sports Activities From a Single Wrist-Worn Accelerometer: A Template-Matching-Based Approach [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website abstract bibtex Goal: To investigate the accuracy of template matching for classifying sports activities using the acceleration signal recorded with a wearable sensor. Methods: A population of 29 normal weight and 19 overweight subjects was recruited to perform eight common sports activities, while body movement was measured using a triaxial accelerometer placed at the wrist. User- and axis-independent acceleration signal templates were automatically extracted to represent each activity category and recognize activity types. Five different similarity measures between example signals and templates were compared: Euclidean distance, dynamic time warping (DTW), derivative DTW, correlation and an innovative index, and combining distance and correlation metrics (Rce). Template-based activity recognition was compared to statistical-learning classifiers, such as Naive Bayes, decision tree, logistic regression (LR), and artificial neural network (ANN) trained using time- and frequency-domain signal features. Each algorithm was tested on data from a holdout group of 15 normal weight and 19 overweight subjects. Results: The Rce index outperformed other template-matching metrics by achieving recognition rate above 80% for the majority of the activities. Template matching showed robust classification accuracy when tested on unseen data and in case of limited training examples. LR and ANN achieved the highest overall recognition accuracy ~85% but showed to be more vulnerable to misclassification error than template matching on overweight subjects' data. Conclusion: Template matching can be used to classify sports activities using the wrist acceleration signal. Significance: Automatically extracted template prototypes from the acceleration signal may be used to enhance accuracy and generalization properties of statistical-learning classifiers.
@article{
title = {User-Independent Recognition of Sports Activities From a Single Wrist-Worn Accelerometer: A Template-Matching-Based Approach},
type = {article},
year = {2016},
identifiers = {[object Object]},
keywords = {accelerometer,activity-recognition,machine-learning,wrist},
pages = {788-796},
volume = {63},
websites = {http://dx.doi.org/10.1109/tbme.2015.2471094},
month = {4},
publisher = {IEEE},
id = {bc7fba0a-a312-3350-b1cf-630db24fae81},
created = {2018-07-12T21:31:46.803Z},
file_attached = {false},
profile_id = {f954d000-ce94-3da6-bd26-b983145a920f},
group_id = {b0b145a3-980e-3ad7-a16f-c93918c606ed},
last_modified = {2018-07-12T21:31:46.803Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {margarito:recognition},
source_type = {article},
private_publication = {false},
abstract = {Goal: To investigate the accuracy of template matching for classifying sports activities using the acceleration signal recorded with a wearable sensor. Methods: A population of 29 normal weight and 19 overweight subjects was recruited to perform eight common sports activities, while body movement was measured using a triaxial accelerometer placed at the wrist. User- and axis-independent acceleration signal templates were automatically extracted to represent each activity category and recognize activity types. Five different similarity measures between example signals and templates were compared: Euclidean distance, dynamic time warping (DTW), derivative DTW, correlation and an innovative index, and combining distance and correlation metrics (Rce). Template-based activity recognition was compared to statistical-learning classifiers, such as Naive Bayes, decision tree, logistic regression (LR), and artificial neural network (ANN) trained using time- and frequency-domain signal features. Each algorithm was tested on data from a holdout group of 15 normal weight and 19 overweight subjects. Results: The Rce index outperformed other template-matching metrics by achieving recognition rate above 80% for the majority of the activities. Template matching showed robust classification accuracy when tested on unseen data and in case of limited training examples. LR and ANN achieved the highest overall recognition accuracy ~85% but showed to be more vulnerable to misclassification error than template matching on overweight subjects' data. Conclusion: Template matching can be used to classify sports activities using the wrist acceleration signal. Significance: Automatically extracted template prototypes from the acceleration signal may be used to enhance accuracy and generalization properties of statistical-learning classifiers.},
bibtype = {article},
author = {Margarito, Jenny and Helaoui, Rim and Bianchi, Anna M and Sartor, Francesco and Bonomi, Alberto G},
journal = {IEEE Transactions on Biomedical Engineering},
number = {4}
}
Downloads: 0
{"_id":"npYzpyRsPQiGYGjNx","bibbaseid":"margarito-helaoui-bianchi-sartor-bonomi-userindependentrecognitionofsportsactivitiesfromasinglewristwornaccelerometeratemplatematchingbasedapproach-2016","downloads":0,"creationDate":"2019-02-15T15:14:59.903Z","title":"User-Independent Recognition of Sports Activities From a Single Wrist-Worn Accelerometer: A Template-Matching-Based Approach","author_short":["Margarito, J.","Helaoui, R.","Bianchi, A., M.","Sartor, F.","Bonomi, A., G."],"year":2016,"bibtype":"article","biburl":null,"bibdata":{"title":"User-Independent Recognition of Sports Activities From a Single Wrist-Worn Accelerometer: A Template-Matching-Based Approach","type":"article","year":"2016","identifiers":"[object Object]","keywords":"accelerometer,activity-recognition,machine-learning,wrist","pages":"788-796","volume":"63","websites":"http://dx.doi.org/10.1109/tbme.2015.2471094","month":"4","publisher":"IEEE","id":"bc7fba0a-a312-3350-b1cf-630db24fae81","created":"2018-07-12T21:31:46.803Z","file_attached":false,"profile_id":"f954d000-ce94-3da6-bd26-b983145a920f","group_id":"b0b145a3-980e-3ad7-a16f-c93918c606ed","last_modified":"2018-07-12T21:31:46.803Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"margarito:recognition","source_type":"article","private_publication":false,"abstract":"Goal: To investigate the accuracy of template matching for classifying sports activities using the acceleration signal recorded with a wearable sensor. Methods: A population of 29 normal weight and 19 overweight subjects was recruited to perform eight common sports activities, while body movement was measured using a triaxial accelerometer placed at the wrist. User- and axis-independent acceleration signal templates were automatically extracted to represent each activity category and recognize activity types. Five different similarity measures between example signals and templates were compared: Euclidean distance, dynamic time warping (DTW), derivative DTW, correlation and an innovative index, and combining distance and correlation metrics (Rce). Template-based activity recognition was compared to statistical-learning classifiers, such as Naive Bayes, decision tree, logistic regression (LR), and artificial neural network (ANN) trained using time- and frequency-domain signal features. Each algorithm was tested on data from a holdout group of 15 normal weight and 19 overweight subjects. Results: The Rce index outperformed other template-matching metrics by achieving recognition rate above 80% for the majority of the activities. Template matching showed robust classification accuracy when tested on unseen data and in case of limited training examples. LR and ANN achieved the highest overall recognition accuracy ~85% but showed to be more vulnerable to misclassification error than template matching on overweight subjects' data. Conclusion: Template matching can be used to classify sports activities using the wrist acceleration signal. Significance: Automatically extracted template prototypes from the acceleration signal may be used to enhance accuracy and generalization properties of statistical-learning classifiers.","bibtype":"article","author":"Margarito, Jenny and Helaoui, Rim and Bianchi, Anna M and Sartor, Francesco and Bonomi, Alberto G","journal":"IEEE Transactions on Biomedical Engineering","number":"4","bibtex":"@article{\n title = {User-Independent Recognition of Sports Activities From a Single Wrist-Worn Accelerometer: A Template-Matching-Based Approach},\n type = {article},\n year = {2016},\n identifiers = {[object Object]},\n keywords = {accelerometer,activity-recognition,machine-learning,wrist},\n pages = {788-796},\n volume = {63},\n websites = {http://dx.doi.org/10.1109/tbme.2015.2471094},\n month = {4},\n publisher = {IEEE},\n id = {bc7fba0a-a312-3350-b1cf-630db24fae81},\n created = {2018-07-12T21:31:46.803Z},\n file_attached = {false},\n profile_id = {f954d000-ce94-3da6-bd26-b983145a920f},\n group_id = {b0b145a3-980e-3ad7-a16f-c93918c606ed},\n last_modified = {2018-07-12T21:31:46.803Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {margarito:recognition},\n source_type = {article},\n private_publication = {false},\n abstract = {Goal: To investigate the accuracy of template matching for classifying sports activities using the acceleration signal recorded with a wearable sensor. Methods: A population of 29 normal weight and 19 overweight subjects was recruited to perform eight common sports activities, while body movement was measured using a triaxial accelerometer placed at the wrist. User- and axis-independent acceleration signal templates were automatically extracted to represent each activity category and recognize activity types. Five different similarity measures between example signals and templates were compared: Euclidean distance, dynamic time warping (DTW), derivative DTW, correlation and an innovative index, and combining distance and correlation metrics (Rce). Template-based activity recognition was compared to statistical-learning classifiers, such as Naive Bayes, decision tree, logistic regression (LR), and artificial neural network (ANN) trained using time- and frequency-domain signal features. Each algorithm was tested on data from a holdout group of 15 normal weight and 19 overweight subjects. Results: The Rce index outperformed other template-matching metrics by achieving recognition rate above 80% for the majority of the activities. Template matching showed robust classification accuracy when tested on unseen data and in case of limited training examples. LR and ANN achieved the highest overall recognition accuracy ~85% but showed to be more vulnerable to misclassification error than template matching on overweight subjects' data. Conclusion: Template matching can be used to classify sports activities using the wrist acceleration signal. Significance: Automatically extracted template prototypes from the acceleration signal may be used to enhance accuracy and generalization properties of statistical-learning classifiers.},\n bibtype = {article},\n author = {Margarito, Jenny and Helaoui, Rim and Bianchi, Anna M and Sartor, Francesco and Bonomi, Alberto G},\n journal = {IEEE Transactions on Biomedical Engineering},\n number = {4}\n}","author_short":["Margarito, J.","Helaoui, R.","Bianchi, A., M.","Sartor, F.","Bonomi, A., G."],"urls":{"Website":"http://dx.doi.org/10.1109/tbme.2015.2471094"},"bibbaseid":"margarito-helaoui-bianchi-sartor-bonomi-userindependentrecognitionofsportsactivitiesfromasinglewristwornaccelerometeratemplatematchingbasedapproach-2016","role":"author","keyword":["accelerometer","activity-recognition","machine-learning","wrist"],"downloads":0},"search_terms":["user","independent","recognition","sports","activities","single","wrist","worn","accelerometer","template","matching","based","approach","margarito","helaoui","bianchi","sartor","bonomi"],"keywords":["accelerometer","activity-recognition","machine-learning","wrist"],"authorIDs":[]}