Machine Learning
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Using Gravity to Estimate Accelerometer Orientation
ISWC '03 Proceedings of the 7th IEEE International Symposium on Wearable Computers
Shakra: tracking and sharing daily activity levels with unaugmented mobile phones
Mobile Networks and Applications
Activity sensing in the wild: a field trial of ubifit garden
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Gesture Recognition with a 3-D Accelerometer
UIC '09 Proceedings of the 6th International Conference on Ubiquitous Intelligence and Computing
Activity Recognition for Everyday Life on Mobile Phones
UAHCI '09 Proceedings of the 5th International on ConferenceUniversal Access in Human-Computer Interaction. Part II: Intelligent and Ubiquitous Interaction Environments
Activity recognition from accelerometer data
IAAI'05 Proceedings of the 17th conference on Innovative applications of artificial intelligence - Volume 3
IMCE '09 Proceedings of the 1st international workshop on Interactive multimedia for consumer electronics
The WEKA data mining software: an update
ACM SIGKDD Explorations Newsletter
UIC'10 Proceedings of the 7th international conference on Ubiquitous intelligence and computing
Activity recognition using cell phone accelerometers
ACM SIGKDD Explorations Newsletter
Estimating continuous distributions in Bayesian classifiers
UAI'95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence
A practical approach to recognizing physical activities
PERVASIVE'06 Proceedings of the 4th international conference on Pervasive Computing
Fish'n'Steps: encouraging physical activity with an interactive computer game
UbiComp'06 Proceedings of the 8th international conference on Ubiquitous Computing
Hi-index | 0.00 |
The rich sensing ability of smart mobile phones brings an unique opportunity to detect and long-term monitor people's physical activities. However, with mobile phone the application has to comply with people's usage habit of it and thus capture the right moment to recognize activities, which will potentially cause great in-class variances. As a result, the model potentially becomes complex and costs much computing resources in mobile phone. This paper recognize people's physical activities when they place the mobile phone in the pockets near the pelvic region. Experiment results show that the accuracy could reach 97.7%. To reduce the model size, evaluation of each feature attribution contribution for the accuracy is performed. And the result shows that we can cut the feature dimension from 22 to 8 while obtaining the smallest model.