A hybrid method for feature construction and selection to improve wind-damage prediction in the forestry sector
- Submitting institution
-
Edinburgh Napier University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1110897
- Type
- E - Conference contribution
- DOI
-
10.1145/3071178.3071217
- Title of conference / published proceedings
- GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference
- First page
- 1121
- Volume
- 8
- Issue
- 17
- ISSN
- -
- Open access status
- -
- Month of publication
- July
- Year of publication
- 2017
- 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)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- An interdisciplinary collaboration with forestry researchers, the paper proposed a novel method to improve classification on a real dataset. The paper was awarded a Bronze Medal and prize of $1000 in the 2018 Humies (https://bit.ly/3fvJtjI) awards at ACM GECCO: this competition rewards work where evolutionary methods outperform best-known existing results. An extension describing the benefits of using AI in Forestry was later published in a leading Forestry journal Agricultural and Forest Meteorology where it has been well-cited (doi.org/10.1016/j.agrformet.2018.10.022). A subsequent invited article in The Conversation on using AI in Forestry has 4816 reads https://bit.ly/3qswu76
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -