DocumentCode :
2229831
Title :
Structural Learning of Activities from Sparse Datasets
Author :
Albinali, Fahd ; Davies, Nigel ; Friday, Adrian
Author_Institution :
Dept. of Comput. Sci., Arizona Univ., Tucson, AZ
fYear :
2007
fDate :
19-23 March 2007
Firstpage :
221
Lastpage :
228
Abstract :
A major challenge in pervasive computing is to develop systems that can reliably recognize human activity patterns, such as bathing from sensor data. Typical sensor deployments generate sparse datasets with thousands of sensor readings and few instances of activities. The imbalance between the number of features (i.e. sensors firing) and the classification targets (i.e. activities) complicates the learning process. In this paper, we propose a novel framework for discovering relationships between sensor signals and observed human activities from sparse datasets. The framework builds on the use of Bayesian networks for modeling activities by representing statistical dependencies between sensors. This allows us to solve two key problems: firstly, how to automatically determine an effective structure for a Bayesian network that recognizes a particular activity without human intervention; and, secondly, we address the pragmatic problem of sparse training data, where the data available to train the activity recognizers is limited. In our approach, we `learn´ the structure of the Bayesian networks automatically from the sensor data. We optimize this process in 3 ways: firstly, we perform multicollinearity analysis to focus on orthogonal sensor data with minimal redundancy. Secondly, we propose Efron´s bootstrapping to generate large training sets that capture important features of an activity. Finally, we find the best Bayesian network that explains our data using a heuristic search that is unbiased to the ordering between consecutive variables. We evaluate our approach using a data set gathered from MIT´s PlaceLab. The inferred networks correctly identify activities for 85% of the time
Keywords :
belief networks; ubiquitous computing; Bayesian networks; heuristic search; human activity patterns; learning process; multicollinearity analysis; orthogonal sensor data; pervasive computing; sparse datasets; sparse training data; structural learning; Bayesian methods; Computer science; Humans; Pattern recognition; Performance analysis; Pervasive computing; Redundancy; Sensor phenomena and characterization; Sensor systems; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pervasive Computing and Communications, 2007. PerCom '07. Fifth Annual IEEE International Conference on
Conference_Location :
White Plains, NY
Print_ISBN :
0-7695-2787-6
Type :
conf
DOI :
10.1109/PERCOM.2007.33
Filename :
4144767
Link To Document :
بازگشت