TY - GEN
T1 - Towards population scale activity recognition
T2 - 26th AAAI Conference on Artificial Intelligence and the 24th Innovative Applications of Artificial Intelligence Conference, AAAI-12 / IAAI-12
AU - Abdullah, Saeed
AU - Lane, Nicholas D.
AU - Choudhury, Tanzeem
PY - 2012
Y1 - 2012
N2 - The rising popularity of the sensor-equipped smartphone is changing the possible scale and scope of human activity inference. The diversity in user population seen in large user bases can overwhelm conventional one-size-fits-all classication approaches. Although personalized models are better able to handle population diversity, they often require increased effort from the end user during training and are computationally expensive. In this paper, we propose an activity classification framework that is scalable and can tractably handle an increasing number of users. Scalability is achieved by maintaining distinct groups of similar users during the training process, which makes it possible to account for the differences between users without resorting to training individualized classifiers. The proposed framework keeps user burden low by leveraging crowd-sourced data labels, where simple natural language processing techniques in combination with multiinstance learning are used to handle labeling errors introduced by low-commitment everyday users. Experiment results on a large public dataset demonstrate that the framework can cope with population diversity irrespective of population size.
AB - The rising popularity of the sensor-equipped smartphone is changing the possible scale and scope of human activity inference. The diversity in user population seen in large user bases can overwhelm conventional one-size-fits-all classication approaches. Although personalized models are better able to handle population diversity, they often require increased effort from the end user during training and are computationally expensive. In this paper, we propose an activity classification framework that is scalable and can tractably handle an increasing number of users. Scalability is achieved by maintaining distinct groups of similar users during the training process, which makes it possible to account for the differences between users without resorting to training individualized classifiers. The proposed framework keeps user burden low by leveraging crowd-sourced data labels, where simple natural language processing techniques in combination with multiinstance learning are used to handle labeling errors introduced by low-commitment everyday users. Experiment results on a large public dataset demonstrate that the framework can cope with population diversity irrespective of population size.
UR - http://www.scopus.com/inward/record.url?scp=84868279929&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84868279929&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84868279929
SN - 9781577355687
T3 - Proceedings of the National Conference on Artificial Intelligence
SP - 851
EP - 857
BT - AAAI-12 / IAAI-12 - Proceedings of the 26th AAAI Conference on Artificial Intelligence and the 24th Innovative Applications of Artificial Intelligence Conference
Y2 - 22 July 2012 through 26 July 2012
ER -