TY - GEN
T1 - Bayesian-based scenario generation method for human activities
AU - Sung, Yunsick
AU - Helal, Abdelsalam
AU - Lee, Jae Woong
AU - Cho, Kyungeun
PY - 2013
Y1 - 2013
N2 - Emerging smart space applications are increasingly relying on capabilities for recognizing human activities. Activity recognition research is however challenged and slowed by the lack of data necessary for testing and validation. Collecting data through live-in trials in real world deployments is often very expensive and complicated. Legitimate limitations on the use of human subjects also renders a much smaller dataset than desired to be collected. To address this challenge, we propose a scenario generation approach in which a small set of scenarios is used to generate new relevant and realistic scenarios, and hence increase the base of testing data needed for activity recognition validation. Unlike existing methods for generating scenarios, which usually focus on scenario structure and complexity, we propose a Bayesian-based approach that learns the stochastic characteristics of a small number of collected datasets to generate additional scenarios of similar characteristics. Our approach is prolific and can generate enormous datasets with high degree of realism at affordable cost. The proposed approach is validated using a Viterbi-based algorithm and a real dataset case study. The validation experiment confirms that the generated dataset has highly similar stochastic characteristics as that of the real dataset.
AB - Emerging smart space applications are increasingly relying on capabilities for recognizing human activities. Activity recognition research is however challenged and slowed by the lack of data necessary for testing and validation. Collecting data through live-in trials in real world deployments is often very expensive and complicated. Legitimate limitations on the use of human subjects also renders a much smaller dataset than desired to be collected. To address this challenge, we propose a scenario generation approach in which a small set of scenarios is used to generate new relevant and realistic scenarios, and hence increase the base of testing data needed for activity recognition validation. Unlike existing methods for generating scenarios, which usually focus on scenario structure and complexity, we propose a Bayesian-based approach that learns the stochastic characteristics of a small number of collected datasets to generate additional scenarios of similar characteristics. Our approach is prolific and can generate enormous datasets with high degree of realism at affordable cost. The proposed approach is validated using a Viterbi-based algorithm and a real dataset case study. The validation experiment confirms that the generated dataset has highly similar stochastic characteristics as that of the real dataset.
KW - activity recognition
KW - bayesian probability
KW - human activity
KW - scenario generation
UR - http://www.scopus.com/inward/record.url?scp=84878652697&partnerID=8YFLogxK
U2 - 10.1145/2486092.2486111
DO - 10.1145/2486092.2486111
M3 - Conference contribution
AN - SCOPUS:84878652697
SN - 9781450319201
T3 - SIGSIM-PADS 2013 - Proceedings of the 2013 ACM SIGSIM Principles of Advanced Discrete Simulation
SP - 147
EP - 157
BT - SIGSIM-PADS 2013 - Proceedings of the 2013 ACM SIGSIM Principles of Advanced Discrete Simulation
T2 - 2013 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, SIGSIM-PADS 2013
Y2 - 19 May 2013 through 22 May 2013
ER -