Feature selection for activity recognition in multi-robot domains

In multi-robot settings, activity recognition allows a robot to respond intelligently to the other robots in its environment. Conditional random fields are temporal models that are well suited for activity recognition because they can robustly incorporate rich, non-independent features computed from sensory data. In this work, we explore feature selection in conditional random fields for activity recognition to choose which features should be included in the final model. We compare two feature selection methods, grafting, a greedy forward-selection strategy, and l1 regularization, which simultaneously smoothes the model and selects a subset of the features. We use robot data recorded during four games of the Small Size League of the RoboCup'07 robot soccer world championship to empirically compare the performance of the two feature selection algorithms in terms of accuracy of the final model, the number of features selected in the final model, and the time required to train the final model.

[1]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[2]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[3]  Manuela M. Veloso,et al.  CMDragons: Dynamic passing and strategy on a champion robot soccer team , 2008, 2008 IEEE International Conference on Robotics and Automation.

[4]  北野 宏明,et al.  RoboCup-97 : robot soccer World Cup I , 1998 .

[5]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[6]  Manuela M. Veloso,et al.  Conditional random fields for activity recognition , 2007, AAMAS '07.

[7]  Michael I. Jordan,et al.  On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes , 2001, NIPS.

[8]  Stephen P. Boyd,et al.  An Interior-Point Method for Large-Scale l1-Regularized Logistic Regression , 2007, J. Mach. Learn. Res..

[9]  James Theiler,et al.  Grafting: Fast, Incremental Feature Selection by Gradient Descent in Function Space , 2003, J. Mach. Learn. Res..

[10]  Henry A. Kautz,et al.  Training Conditional Random Fields Using Virtual Evidence Boosting , 2007, IJCAI.

[11]  Jianfeng Gao,et al.  Scalable training of L1-regularized log-linear models , 2007, ICML '07.

[12]  Andrew McCallum,et al.  Efficiently Inducing Features of Conditional Random Fields , 2002, UAI.

[13]  Manuela Veloso,et al.  Automated Robot Behavior Recognition Applied to Robotic Soccer , 1999 .

[14]  Manuela M. Veloso,et al.  Feature selection in conditional random fields for activity recognition , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[16]  Andrew McCallum,et al.  Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data , 2004, J. Mach. Learn. Res..

[17]  Michael I. Jordan,et al.  Loopy Belief Propagation for Approximate Inference: An Empirical Study , 1999, UAI.

[18]  Andrew McCallum,et al.  An Introduction to Conditional Random Fields for Relational Learning , 2007 .