Fast k-nearest-neighbours searching through extended versions of the approximating and eliminating search algorithm (AESA)

• Published in: Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170) Vol. 1; pp. 828 - 830 vol.1
• Main Authors: Juan, A., Vidal, E., Aibar, P.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 1998
• Subjects: Computational efficiency; Electrical capacitance tomography; Extraterrestrial measurements; Neural networks; Pattern recognition; Performance evaluation; Prototypes; Testing; Upper bound
• ISBN: 0818685123; 9780818685125
• ISSN: 1051-4651; 2831-7475
• DOI: 10.1109/ICPR.1998.711277

The approximating and eliminating search algorithm (AESA) is probably the technique requiring the fewest distance computations for nearest-neighbour searching in general metric spaces. In this paper we propose direct and refined extensions to the AESA for finding k-nearest-neighbours. Results of a number of experiments involving synthetic data are reported, showing that both extensions, and especially the last one, lead to computational savings similar to that of the original (1-NN) AESA.