Paper Info
Title
Activity recognition through goal-based segmentation
Abstract
A major issue in activity recognition in a sensor network is how to automatically segment the low-level signal sequences in order to optimize the probabilistic recognition models for goals and activities. Past efforts have relied on segmenting the signal sequences by hand, which is both time-consuming and error-prone. In our view, segments should correspond to atomic human activities that enable a goal-recognizer to operate optimally; the two are intimately related. In this paper, we present a novel method for building probabilistic activity models at the same time as we segment signal sequences into motion patterns. We model each motion pattern as a linear dynamic model and the transitions between motion patterns as a Markov process conditioned on goals. Our EM learning algorithm simultaneously learns the motion-pattern boundaries and probabilistic models for goals and activities, which in turn can be used to accurately recognize activities in an online phase. A major advantage of our algorithm is that it can reduce the human effort in segmenting and labeling signal sequences. We demonstrate the effectiveness of our algorithm using the data collected in a real wireless environment.
Year
Venue
Keywords
2005
AAAI
signal sequence,probabilistic model,segment signal sequence,goal-based segmentation,probabilistic activity model,motion pattern,probabilistic recognition model,atomic human activity,activity recognition,low-level signal sequence,human effort,data collection,sensor network,markov process
Field
DocType
ISBN
Wireless,Activity recognition,Market segmentation,Markov process,Computer science,Segmentation,Artificial intelligence,Probabilistic logic,Wireless sensor network,Machine learning
Conference
1-57735-236-x
Citations 
PageRank 
References 
9
0.59
14
Authors
4
Name
Order
Citations
PageRank
Jie Yin1134087.67
Dou Shen2122459.46
Qiang Yang317039875.69
Ze-Nian Li477381.06