An Efficient Approach for Preprocessing Data from a Large-Scale Chemical Sensor Array
- Submitting institution
-
University of Central Lancashire
- Unit of assessment
- 12 - Engineering
- Output identifier
- 18112
- Type
- D - Journal article
- DOI
-
10.3390/s140917786
- Title of journal
- Sensors
- Article number
- -
- First page
- 17786
- Volume
- 14
- Issue
- 9
- ISSN
- 1424-8220
- Open access status
- Out of scope for open access requirements
- Month of publication
- September
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
3
- Research group(s)
-
H - Computer Vision and Machine Learning Group
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper introduced a novel way to process very large amounts of sensor data, coupling the concept of EigenOdour with linear discriminant analysis and multi-class support vector machines to automatically assess input samples. It was faster than existing methods and showed superior classification capability. The study strengthened the partnership between the collaborating research groups in Manchester and Bari. The processes was also evaluated in the SNIFFER (FP7/2007-2013) project, and helped to secure funding for project “C-BORD” (Horizon 2020). Additionally, the method will be evaluated in a PhD project at UCLan, where it will be applied to online lubricant degradation monitoring.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
