An optimised algorithm for accurate steps counting from smart-phone accelerometry
Step counting from smart-phones allows a wide range of applications related to fitness and health. Estimating steps from phones' accelerometers is challenging because of the multitude of ways a smart-phone can be carried. We focus our work on the windowed peak detection algorithm, which has pre...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Published: |
IEEE
2018
|
| _version_ | 1797089383395885056 |
|---|---|
| author | Salvi, D Velardo, C Brynes, J Tarassenko, L |
| author_facet | Salvi, D Velardo, C Brynes, J Tarassenko, L |
| author_sort | Salvi, D |
| collection | OXFORD |
| description | Step counting from smart-phones allows a wide range of applications related to fitness and health. Estimating steps from phones' accelerometers is challenging because of the multitude of ways a smart-phone can be carried. We focus our work on the windowed peak detection algorithm, which has previously been shown to be accurate and efficient and thus suitable for mobile devices. We explore and optimise further the algorithm and its parameters making use of data collected by three volunteers holding the phone in six different positions. In order to simplify the analysis of the data, we also built a novel device for the detection of the ground truth steps. Over the collected data set, the algorithm reaches 95% average accuracy. We implemented the algorithm for the Android OS and released it as an open source project. A separate dataset was collected with the algorithm running on the smart-phone for further validation. The validation confirms the accuracy of the algorithm in real-time conditions. |
| first_indexed | 2024-03-07T03:03:22Z |
| format | Conference item |
| id | oxford-uuid:b1b3cf44-8fa6-4866-9408-bb65129340a8 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T03:03:22Z |
| publishDate | 2018 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:b1b3cf44-8fa6-4866-9408-bb65129340a82022-03-27T04:05:59ZAn optimised algorithm for accurate steps counting from smart-phone accelerometryConference itemhttp://purl.org/coar/resource_type/c_5794uuid:b1b3cf44-8fa6-4866-9408-bb65129340a8Symplectic Elements at OxfordIEEE2018Salvi, DVelardo, CBrynes, JTarassenko, LStep counting from smart-phones allows a wide range of applications related to fitness and health. Estimating steps from phones' accelerometers is challenging because of the multitude of ways a smart-phone can be carried. We focus our work on the windowed peak detection algorithm, which has previously been shown to be accurate and efficient and thus suitable for mobile devices. We explore and optimise further the algorithm and its parameters making use of data collected by three volunteers holding the phone in six different positions. In order to simplify the analysis of the data, we also built a novel device for the detection of the ground truth steps. Over the collected data set, the algorithm reaches 95% average accuracy. We implemented the algorithm for the Android OS and released it as an open source project. A separate dataset was collected with the algorithm running on the smart-phone for further validation. The validation confirms the accuracy of the algorithm in real-time conditions. |
| spellingShingle | Salvi, D Velardo, C Brynes, J Tarassenko, L An optimised algorithm for accurate steps counting from smart-phone accelerometry |
| title | An optimised algorithm for accurate steps counting from smart-phone accelerometry |
| title_full | An optimised algorithm for accurate steps counting from smart-phone accelerometry |
| title_fullStr | An optimised algorithm for accurate steps counting from smart-phone accelerometry |
| title_full_unstemmed | An optimised algorithm for accurate steps counting from smart-phone accelerometry |
| title_short | An optimised algorithm for accurate steps counting from smart-phone accelerometry |
| title_sort | optimised algorithm for accurate steps counting from smart phone accelerometry |
| work_keys_str_mv | AT salvid anoptimisedalgorithmforaccuratestepscountingfromsmartphoneaccelerometry AT velardoc anoptimisedalgorithmforaccuratestepscountingfromsmartphoneaccelerometry AT brynesj anoptimisedalgorithmforaccuratestepscountingfromsmartphoneaccelerometry AT tarassenkol anoptimisedalgorithmforaccuratestepscountingfromsmartphoneaccelerometry AT salvid optimisedalgorithmforaccuratestepscountingfromsmartphoneaccelerometry AT velardoc optimisedalgorithmforaccuratestepscountingfromsmartphoneaccelerometry AT brynesj optimisedalgorithmforaccuratestepscountingfromsmartphoneaccelerometry AT tarassenkol optimisedalgorithmforaccuratestepscountingfromsmartphoneaccelerometry |