TY - GEN
T1 - Determining the single best axis for exercise repetition recognition and counting on smartwatches
AU - Mortazavi, Bobak Jack
AU - Pourhomayoun, Mohammad
AU - Alsheikh, Gabriel
AU - Alshurafa, Nabil
AU - Lee, Sunghoon Ivan
AU - Sarrafzadeh, Majid
PY - 2014
Y1 - 2014
N2 - Due to the exploding costs of chronic diseasesstemming from physical inactivity, wearable sensor systems toenable remote, continuous monitoring of individuals has increasedin popularity. Many research and commercial systems exist inorder to track the activity levels of users from general dailymotion to detailed movements. This work examines this problemfrom the space of smartwatches, using the Samsung GalaxyGear, a commercial device containing an accelerometer and agyroscope, to be used in recognizing physical activity. This workalso shows the sensors and features necessary to enable suchsmartwatches to accurately count, in real-time, the repetitions offree-weight and body-weight exercises. The goal of this work isto try and select only the best single axis for each activity byextracting only the most informative activity-specific features, inorder to minimize computational load and power consumptionin repetition counting. The five activities are incorporated in aworkout routine, and knowing this information, a random forestclassifier is built with average area under the curve (AUC) of: 974, with average accuracy of 93%, in cross validation to identify eachrepetition of a given exercise using all available sensors and AUCof: 950 with accuracy of 89:9% using the single best axis foreach activity alone. Adding a gyroscope with the accelerometerincreased the average AUC from: 968 to: 974, increasing theaccuracy of specific movements as much as 2%. Results show that, while a combination of accelerometer and gyroscope provide thestrongest classification results, often times features extracted froma single, best axis are enough to accurately identify movementsfor a personal training routine, where that axis is often, but notalways, an accelerometer axis.
AB - Due to the exploding costs of chronic diseasesstemming from physical inactivity, wearable sensor systems toenable remote, continuous monitoring of individuals has increasedin popularity. Many research and commercial systems exist inorder to track the activity levels of users from general dailymotion to detailed movements. This work examines this problemfrom the space of smartwatches, using the Samsung GalaxyGear, a commercial device containing an accelerometer and agyroscope, to be used in recognizing physical activity. This workalso shows the sensors and features necessary to enable suchsmartwatches to accurately count, in real-time, the repetitions offree-weight and body-weight exercises. The goal of this work isto try and select only the best single axis for each activity byextracting only the most informative activity-specific features, inorder to minimize computational load and power consumptionin repetition counting. The five activities are incorporated in aworkout routine, and knowing this information, a random forestclassifier is built with average area under the curve (AUC) of: 974, with average accuracy of 93%, in cross validation to identify eachrepetition of a given exercise using all available sensors and AUCof: 950 with accuracy of 89:9% using the single best axis foreach activity alone. Adding a gyroscope with the accelerometerincreased the average AUC from: 968 to: 974, increasing theaccuracy of specific movements as much as 2%. Results show that, while a combination of accelerometer and gyroscope provide thestrongest classification results, often times features extracted froma single, best axis are enough to accurately identify movementsfor a personal training routine, where that axis is often, but notalways, an accelerometer axis.
KW - Activity Recognition
KW - Exercise Recognition
KW - Repetition Counting
KW - SmartWatch
KW - Wireless Health
UR - http://www.scopus.com/inward/record.url?scp=84905992005&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84905992005&partnerID=8YFLogxK
U2 - 10.1109/BSN.2014.21
DO - 10.1109/BSN.2014.21
M3 - Conference contribution
AN - SCOPUS:84905992005
SN - 9781479949328
T3 - Proceedings - 11th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2014
SP - 33
EP - 38
BT - Proceedings - 11th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2014
PB - IEEE Computer Society
T2 - 11th International Conference on Wearable and Implantable Body Sensor Networks, BSN 2014
Y2 - 16 June 2014 through 19 June 2014
ER -