@INPROCEEDINGS{5470597,
  author = {Blanke, Ulf and Schiele, Bernt and Kreil, Matthias and Lukowicz,
	Paul and Sick, Bernhard and Gruber, Thiemo},
  title = {{All for one or one for all? Combining Heterogeneous Features for
	Activity Spotting}},
  booktitle = {Workshop Proceedings of the 8th International Conference on Pervasive
	Computing and Communications (PerCom Workshops)},
  year = {2010},
  pages = {18--24},
  month = mar#"--"#apr,
  location = {Mannheim, Germany},
  abstract = {Choosing the right feature for motion based activity spotting is not
	a trivial task. Often, features derived by intuition or that proved
	to work well in previous work are used. While feature selection algorithms
	allow automatic decision, definition of features remains a manual
	task. We conduct a comparative study of features with very different
	origin. To this end, we propose a new type of features based on polynomial
	approximation of signals. The new feature type is compared to features
	used routinely for motion based activity recognition as well as to
	recently proposed body-model based features. Experiments were performed
	on three different, large datasets allowing a thorough, in-depth
	analysis. They not only show the respective strengths of the different
	feature types but also their complementarity resulting in improved
	performance through combination. It shows that each feature type
	with its individual and complementary strengths and weaknesses can
	improve results by combination.},
  doi = {10.1109/PERCOMW.2010.5470597},
  keywords = {feature extraction;image motion analysis;image recognition;image sensors;polynomial
	approximation;wearable computers;body-model based features;feature
	selection;heterogeneous features;motion based activity recognition;motion
	based activity spotting;signal polynomial approximation;wearable
	computing;wearable sensor;Boosting;Computational intelligence;Computer
	science;Embedded computing;Embedded system;Frequency;Intelligent
	systems;Performance analysis;Polynomials;Wearable sensors;activity
	recognition;feature analysis;wearable computing},
}