Human Behavior Recognition with Generic Exponential Family Duration Modeling in the Hidden Semi-Markov Model
MetadataShow full item record
The ability to learn and recognize human activities of daily living (ADLs) is important in building pervasive and smart environments. In this paper, we tackle this problem using the hidden semi-Markov model. We discuss the state-of-the-art duration modeling choices and then address a large class of exponential family distributions to model state durations. Inference and learning are efficiently addressed by providing a graphical representation for the model in terms of a dynamic Bayesian network (DBN). We investigate both discrete and continuous distributions from the exponential family (Poisson and inverse Gaussian respectively) for the problem of learning and recognizing ADLs. A full comparison between the exponential family duration models and other existing models including the traditional multinomial and the new Coxian are also presented. Our work thus completes a thorough investigation into the aspect of duration modeling and its application to human activities recognition in a real-world smart home surveillance scenario.
Showing items related by title, author, creator and subject.
Duong, Thi; Phung, Dinh; Bui, Hung H.; Venkatesh, Svetha (2009)A challenge in building pervasive and smart spaces is to learn and recognize human activities of daily living (ADLs). In this paper, we address this problem and argue that in dealing with ADLs, it is beneficial to exploit ...
Inoue, Madoka (2012)This thesis examines infant feeding practices, including knowledge and attitudes towards breastfeeding, factors that influence the duration of breastfeeding, and breastfeeding outcomes in relation to postpartum women’s ...
Mahadik, M.; Bahrami, Hassan; Hossain, Mofazzal; Tsar Mitchel, P. (2012)Exponential decline curve analysis is widely used to estimate recoverable reserves due to its simplicity. In most cases, however, an exponential model cannot provide a satisfactory match of overall production history. The ...