Development of an automated physical activity classification application for mobile phones.
| dc.contributor.author | Xia, Ying | |
| dc.contributor.author | Cheung, Vivian | |
| dc.contributor.author | Garcia, Elsa | |
| dc.contributor.author | Ding, Hang | |
| dc.contributor.author | Karunaithi, Mohan | |
| dc.date.accessioned | 2020-02-06T15:42:37Z | |
| dc.date.available | 2020-02-06T15:42:37Z | |
| dc.date.issued | 2011-09-06 | |
| dc.description.abstract | BACKGROUND Physical activity classification is an objective approach to assess levels of physical activity and indicates an individual s degree of functional ability It is significant for a number of the disciplines such as behavioural sciences physiotherapy etc Accelerometry is found to be a practical and low cost method for activity classification that could provide an objective and efficient measurement of people s daily activities METHODS This paper utilises a mobile phone with a built in tri axial accelerometer sensor to automatically classify normal physical activities A rule based activity classification model which can recognise 4 common daily activities lying walking sitting and standing and 6 transitions between postural orientations is introduced here In this model three types of statuses walking transition lying and sitting standing are first classified based on the kinetic energy and upright angle Transitions are then separated from walking and assigned to the corresponding type using upright angle algorithm To evaluate the performance of this developed application a trial is designed with 8 healthy adult subjects who are required to perform a 6 minute activity routine with an iPhone fixed at the waist position RESULTS Based on the evaluation result our application measures the length of time of each activity accurately and the achieved sensitivity of each activity classification exceeds 90 while the achieved specificity exceeds 96 Meanwhile regarding the transition identification the sensitivities are high in stand to sit 80 and low in sit to stand 56 | |
| dc.identifier.uri | http://dx.doi.org/Not available | |
| dc.identifier.uri | https://lib.digitalsquare.io/xmlui/handle/123456789/72 | |
| dc.relation.uri | Studies in health technology and informatics | |
| dc.subject | Facility-based health worker | |
| dc.subject | Access to information or data | |
| dc.subject | Prototype | |
| dc.subject | Functionality | |
| dc.subject | Non-communicable diseases | |
| dc.subject | Unintentional injury | |
| dc.subject | Data collection and reporting | |
| dc.subject | Accelerometers / Motion sensors | |
| dc.subject | Raw data | |
| dc.subject | Installed application | |
| dc.title | Development of an automated physical activity classification application for mobile phones. | en |
| dcterms.abstract | BACKGROUND Physical activity classification is an objective approach to assess levels of physical activity and indicates an individual s degree of functional ability It is significant for a number of the disciplines such as behavioural sciences physiotherapy etc Accelerometry is found to be a practical and low cost method for activity classification that could provide an objective and efficient measurement of people s daily activities METHODS This paper utilises a mobile phone with a built in tri axial accelerometer sensor to automatically classify normal physical activities A rule based activity classification model which can recognise 4 common daily activities lying walking sitting and standing and 6 transitions between postural orientations is introduced here In this model three types of statuses walking transition lying and sitting standing are first classified based on the kinetic energy and upright angle Transitions are then separated from walking and assigned to the corresponding type using upright angle algorithm To evaluate the performance of this developed application a trial is designed with 8 healthy adult subjects who are required to perform a 6 minute activity routine with an iPhone fixed at the waist position RESULTS Based on the evaluation result our application measures the length of time of each activity accurately and the achieved sensitivity of each activity classification exceeds 90 while the achieved specificity exceeds 96 Meanwhile regarding the transition identification the sensitivities are high in stand to sit 80 and low in sit to stand 56 | |
| dcterms.contributor | Xia, Ying | |
| dcterms.contributor | Cheung, Vivian | |
| dcterms.contributor | Garcia, Elsa | |
| dcterms.contributor | Ding, Hang | |
| dcterms.contributor | Karunaithi, Mohan | |
| dcterms.identifier | http://dx.doi.org/Not available | |
| dcterms.relation | Studies in health technology and informatics | |
| dcterms.subject | Facility-based health worker | |
| dcterms.subject | Access to information or data | |
| dcterms.subject | Prototype | |
| dcterms.subject | Functionality | |
| dcterms.subject | Non-communicable diseases | |
| dcterms.subject | Unintentional injury | |
| dcterms.subject | Data collection and reporting | |
| dcterms.subject | Accelerometers / Motion sensors | |
| dcterms.subject | Raw data | |
| dcterms.subject | Installed application | |
| dcterms.title | Development of an automated physical activity classification application for mobile phones. | en |