A “one-size-fits-most” walking recognition method for smartphones, smartwatches, and wearable accelerometers
Abstract The ubiquity of personal digital devices offers unprecedented opportunities to study human behavior. Current state-of-the-art methods quantify physical activity using “activity counts,” a measure which overlooks specific types of physical activities. We propose a walking recognition method...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-02-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-022-00745-z |
| _version_ | 1797426728488927232 |
|---|---|
| author | Marcin Straczkiewicz Emily J. Huang Jukka-Pekka Onnela |
| author_facet | Marcin Straczkiewicz Emily J. Huang Jukka-Pekka Onnela |
| author_sort | Marcin Straczkiewicz |
| collection | DOAJ |
| description | Abstract The ubiquity of personal digital devices offers unprecedented opportunities to study human behavior. Current state-of-the-art methods quantify physical activity using “activity counts,” a measure which overlooks specific types of physical activities. We propose a walking recognition method for sub-second tri-axial accelerometer data, in which activity classification is based on the inherent features of walking: intensity, periodicity, and duration. We validate our method against 20 publicly available, annotated datasets on walking activity data collected at various body locations (thigh, waist, chest, arm, wrist). We demonstrate that our method can estimate walking periods with high sensitivity and specificity: average sensitivity ranged between 0.92 and 0.97 across various body locations, and average specificity for common daily activities was typically above 0.95. We also assess the method’s algorithmic fairness to demographic and anthropometric variables and measurement contexts (body location, environment). Finally, we release our method as open-source software in Python and MATLAB. |
| first_indexed | 2024-03-09T08:34:05Z |
| format | Article |
| id | doaj.art-826f481d70114b2a8df3130eca7075b7 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T08:34:05Z |
| publishDate | 2023-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-826f481d70114b2a8df3130eca7075b72023-12-02T18:44:53ZengNature Portfolionpj Digital Medicine2398-63522023-02-016111610.1038/s41746-022-00745-zA “one-size-fits-most” walking recognition method for smartphones, smartwatches, and wearable accelerometersMarcin Straczkiewicz0Emily J. Huang1Jukka-Pekka Onnela2Department of Biostatistics, Harvard UniversityDepartment of Statistical Sciences, Wake Forest UniversityDepartment of Biostatistics, Harvard UniversityAbstract The ubiquity of personal digital devices offers unprecedented opportunities to study human behavior. Current state-of-the-art methods quantify physical activity using “activity counts,” a measure which overlooks specific types of physical activities. We propose a walking recognition method for sub-second tri-axial accelerometer data, in which activity classification is based on the inherent features of walking: intensity, periodicity, and duration. We validate our method against 20 publicly available, annotated datasets on walking activity data collected at various body locations (thigh, waist, chest, arm, wrist). We demonstrate that our method can estimate walking periods with high sensitivity and specificity: average sensitivity ranged between 0.92 and 0.97 across various body locations, and average specificity for common daily activities was typically above 0.95. We also assess the method’s algorithmic fairness to demographic and anthropometric variables and measurement contexts (body location, environment). Finally, we release our method as open-source software in Python and MATLAB.https://doi.org/10.1038/s41746-022-00745-z |
| spellingShingle | Marcin Straczkiewicz Emily J. Huang Jukka-Pekka Onnela A “one-size-fits-most” walking recognition method for smartphones, smartwatches, and wearable accelerometers npj Digital Medicine |
| title | A “one-size-fits-most” walking recognition method for smartphones, smartwatches, and wearable accelerometers |
| title_full | A “one-size-fits-most” walking recognition method for smartphones, smartwatches, and wearable accelerometers |
| title_fullStr | A “one-size-fits-most” walking recognition method for smartphones, smartwatches, and wearable accelerometers |
| title_full_unstemmed | A “one-size-fits-most” walking recognition method for smartphones, smartwatches, and wearable accelerometers |
| title_short | A “one-size-fits-most” walking recognition method for smartphones, smartwatches, and wearable accelerometers |
| title_sort | one size fits most walking recognition method for smartphones smartwatches and wearable accelerometers |
| url | https://doi.org/10.1038/s41746-022-00745-z |
| work_keys_str_mv | AT marcinstraczkiewicz aonesizefitsmostwalkingrecognitionmethodforsmartphonessmartwatchesandwearableaccelerometers AT emilyjhuang aonesizefitsmostwalkingrecognitionmethodforsmartphonessmartwatchesandwearableaccelerometers AT jukkapekkaonnela aonesizefitsmostwalkingrecognitionmethodforsmartphonessmartwatchesandwearableaccelerometers AT marcinstraczkiewicz onesizefitsmostwalkingrecognitionmethodforsmartphonessmartwatchesandwearableaccelerometers AT emilyjhuang onesizefitsmostwalkingrecognitionmethodforsmartphonessmartwatchesandwearableaccelerometers AT jukkapekkaonnela onesizefitsmostwalkingrecognitionmethodforsmartphonessmartwatchesandwearableaccelerometers |