TY - GEN
T1 - Personalization without user interruption
T2 - 8th ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS 2017
AU - Fallahzadeh, Ramin
AU - Ghasemzadeh, Hassan
N1 - Funding Information:
The authors would like to thank the anonymous referees for their valuable comments and helpful suggestions. This work was supported in part by the National Science Foundation under Grant No.: 1566359. Any opinions, findings, conclusions, or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of the funding organizations.
Publisher Copyright:
© 2017 ACM.
PY - 2017/4/18
Y1 - 2017/4/18
N2 - Activity recognition systems are widely used in monitoring physical and physiological conditions as well as observing the short/long term behavioral patterns for the purpose of improving the health and wellbeing of the users. The major obstacle in widespread use of these systems is the need for collecting labeled data to train the activity recognition model. While a personalized model outperforms a user-independent model, collecting labels from every single user is burdensome and in some cases impractical. In this paper, we propose an uninformed cross-subject transfer learning algorithm that leverages the cross-user similarities by constructing a networkbased feature-level representation of the data in source and target users and perform a best effort community detection to extract the core observations in target data. Our algorithm uses a heuristic classifier-based mapping to assign activity labels to the core observations. Finally, the output of labeling is conditionally fused with the prediction of the source-model to develop a boosted and personalized activity recognition algorithm. Our analysis on real-world data demonstrates the superiority of our approach. Our algorithm achieves over 87% accuracy on average which is 7% higher than the state-of-the art approach.
AB - Activity recognition systems are widely used in monitoring physical and physiological conditions as well as observing the short/long term behavioral patterns for the purpose of improving the health and wellbeing of the users. The major obstacle in widespread use of these systems is the need for collecting labeled data to train the activity recognition model. While a personalized model outperforms a user-independent model, collecting labels from every single user is burdensome and in some cases impractical. In this paper, we propose an uninformed cross-subject transfer learning algorithm that leverages the cross-user similarities by constructing a networkbased feature-level representation of the data in source and target users and perform a best effort community detection to extract the core observations in target data. Our algorithm uses a heuristic classifier-based mapping to assign activity labels to the core observations. Finally, the output of labeling is conditionally fused with the prediction of the source-model to develop a boosted and personalized activity recognition algorithm. Our analysis on real-world data demonstrates the superiority of our approach. Our algorithm achieves over 87% accuracy on average which is 7% higher than the state-of-the art approach.
KW - Activity recognition
KW - Cross-subject boosting
KW - Uninformed transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85019028990&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85019028990&partnerID=8YFLogxK
U2 - 10.1145/3055004.3055015
DO - 10.1145/3055004.3055015
M3 - Conference contribution
AN - SCOPUS:85019028990
T3 - Proceedings - 2017 ACM/IEEE 8th International Conference on Cyber-Physical Systems, ICCPS 2017 (part of CPS Week)
SP - 293
EP - 302
BT - Proceedings - 2017 ACM/IEEE 8th International Conference on Cyber-Physical Systems, ICCPS 2017 (part of CPS Week)
PB - Association for Computing Machinery, Inc
Y2 - 18 April 2017 through 20 April 2017
ER -