An optimal traffic data archive scheme
Zheng, P. and McDonald, M. (2007) An optimal traffic data archive scheme. Institution of Engineering & Technology, Intelligent Transport Systems, 1, (2), 144-149. (doi:10.1049/iet-its:20060082).
Download
Full text not available from this repository.
Description/Abstract
An optimal traffic data archive scheme where the maximum information of the original data can be preserved using less storage space has been described. Compared with traditional equal-width methods where compact data are obtained by aggregating source data at fixed intervals, the optimal scheme uses varying intervals to aggregate data at different levels based on the variations within the source data. The resultant scheme is optimal in terms of information conservation, that is, the errors between the source data and the optimal compact data are the smallest. Operational traffic data have been used to test three proposed optimisation schemes: single-variable, multi-variable and heuristic schemes. It was found that, compared with traditional equal-width schemes, the size of the archived data can be reduced by six times if the single-variable optimisation scheme, or by three times if the multi-variable optimisation scheme is employed. The heuristic scheme using a combination of single-variable and multi-variable optimisations can then reduce storage space by three to six times
| Item Type: | Article |
|---|---|
| ISSNs: | 1751-9578 (print) |
| Related URLs: | |
| Subjects: | T Technology > TE Highway engineering. Roads and pavements H Social Sciences > HE Transportation and Communications T Technology > TA Engineering (General). Civil engineering (General) |
| Divisions: | University Structure - Pre August 2011 > School of Civil Engineering and the Environment |
| Item ID: | 53290 |
| Date Deposited: | 29 Jul 2008 |
| Last Modified: | 01 Jun 2011 14:39 |
| Contributors: | Zheng, P. (Author) McDonald, M. (Author) |
| Date: | June 2007 |
| Status: | Published |
| URI: | http://eprints.soton.ac.uk/id/eprint/53290 |
Actions (login required)
 |
View Item |
