Abstract
By the inverse n th power gravitation in physics, a novel classifier for data classification, called the I-n-PG classifier, is introduced. In the I-n-PG model, training samples from each class are regarded as a system of particles and an I-n-PG field is defined for each class. A test sample belongs to the class whose particle system has the maximum I-n-PG to this test sample. Experiments on large numbers of real data show that the I-n-PG classifier can provide a good classification performance. Compared with the nearest neighbor classifier and SVM, performances of the I-n-PG classifier are always superior/close to the better one of them, and thus the I-n-PG classifier has also a wide range of adaptability to data sets.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Karampatziakis N. Static analysis of binary executables using structural SVMs. In: Advances in Neural Information Processing Systems 23, 2010. 1063–1071
Vapnik V N. The Nature of Statistical Learning Theory. Berlin: Springer Verlag, 1995
Ji S W, Xu W, Yang M, et al. 3D convolutional neural networks for human action recognition. In: The 27th International Conference on Machine Learning, 2010. 495–502
Chandrasekhar S. Newton’s Principia for the Common Reader. Oxford: Oxford University Press, 1995
Heintz W H. Runge-Lenz vector for non-relativistic Kepler motion modified by an inverse cube force. Am J Phys, 1976, 44: 687–694
Roseveare N T. Mercury’s Perihelion from Le Verrier to Einstein. Oxford: Oxford University Press, 1982
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xu, H., Wang, X., Zeng, Z. et al. Data classification from the inverse n th power gravitation. Sci. China Inf. Sci. 55, 184–190 (2012). https://doi.org/10.1007/s11432-011-4437-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-011-4437-y