TY - JOUR
T1 - Recognition of hand movements using wearable accelerometers
AU - Krishnan, Narayanan C.
AU - Juillard, Colin
AU - Colbry, Dirk
AU - Panchanathan, Sethuraman
PY - 2009
Y1 - 2009
N2 - Accelerometer based activity recognition systems have typically focused on recognizing simple ambulatory activities of daily life, such as walking, sitting, standing, climbing stairs, etc. In this work, we developed and evaluated algorithms for detecting and recognizing short duration hand movements (lift to mouth, scoop, stir, pour, unscrew cap). These actions are a part of the larger and complex Instrumental Activities of Daily Life (IADL) making a drink and drinking. We collected data using small wireless tri-axial accelerometers worn simultaneously on different parts of the hand. Acceleration data for training was collected from 5 subjects, who also performed the two IADLs without being given specific instructions on how to complete them. Feature vectors (mean, variance, correlation, spectral entropy and spectral energy) were calculated and tested on three classifiers (AdaBoost, HMM, k-NN). AdaBoost showed the best performance, with an overall accuracy of 86% for detecting each of these hand actions. The results show that although some actions are recognized well with the generalized classifer trained on the subject-independent data, other actions require some amount of subject-specific training. We also observed an improvement in the performance of the system when multiple accelerometers placed on the right hand were used.
AB - Accelerometer based activity recognition systems have typically focused on recognizing simple ambulatory activities of daily life, such as walking, sitting, standing, climbing stairs, etc. In this work, we developed and evaluated algorithms for detecting and recognizing short duration hand movements (lift to mouth, scoop, stir, pour, unscrew cap). These actions are a part of the larger and complex Instrumental Activities of Daily Life (IADL) making a drink and drinking. We collected data using small wireless tri-axial accelerometers worn simultaneously on different parts of the hand. Acceleration data for training was collected from 5 subjects, who also performed the two IADLs without being given specific instructions on how to complete them. Feature vectors (mean, variance, correlation, spectral entropy and spectral energy) were calculated and tested on three classifiers (AdaBoost, HMM, k-NN). AdaBoost showed the best performance, with an overall accuracy of 86% for detecting each of these hand actions. The results show that although some actions are recognized well with the generalized classifer trained on the subject-independent data, other actions require some amount of subject-specific training. We also observed an improvement in the performance of the system when multiple accelerometers placed on the right hand were used.
KW - Accelerometers
KW - Adaboost
KW - Classification
KW - Hand movements
UR - http://www.scopus.com/inward/record.url?scp=78651574474&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78651574474&partnerID=8YFLogxK
U2 - 10.3233/AIS-2009-0019
DO - 10.3233/AIS-2009-0019
M3 - Article
AN - SCOPUS:78651574474
SN - 1876-1364
VL - 1
SP - 143
EP - 155
JO - Journal of Ambient Intelligence and Smart Environments
JF - Journal of Ambient Intelligence and Smart Environments
IS - 2
ER -