A hybrid method for feature construction and selection to improve wind-damage prediction in the forestry sector
العنوان: | A hybrid method for feature construction and selection to improve wind-damage prediction in the forestry sector |
---|---|
المؤلفون: | Hart, Emma, Sim, Kevin, Gardiner, Barry, Kamimura, Kana |
بيانات النشر: | Association for Computing Machinery (ACM) |
سنة النشر: | 2017 |
المجموعة: | Edinburgh Napier Repository (Napier University Edinburgh) |
مصطلحات موضوعية: | Computing methodologies, search methodologies, genetic programming, KEYWORDS Feature-construction, Machine-Learning, Forestry, 004 Data processing & computer science, QA75 Electronic computers. Computer science |
الوصف: | Catastrophic damage to forests resulting from major storms has resulted in serious timber and financial losses within the sector across Europe in the recent past. Developing risk assessment methods is thus one of the keys to finding forest management strategies to reduce future damage. Previous approaches to predicting damage to individual trees have used mechanistic models of wind-flow or logistical regression with mixed results. We propose a novel filter-based Genetic Programming method for constructing a large set of new features which are ranked using the Hellinger distance metric which is insensitive to skew in the data. A wrapper-based feature-selection method that uses a random forest classifier is then applied predict damage to individual trees. Using data collected from two forests within SouthWest France, we demonstrate significantly improved classification results using the new features, and in comparison to previously published results. The feature-selection method retains a small set of relevant variables consisting only of newly constructed features whose components provide insights that can inform forest management policies. |
نوع الوثيقة: | other/unknown material |
اللغة: | English |
ردمك: | 978-1-4503-4920-8 1-4503-4920-X |
العلاقة: | http://researchrepository.napier.ac.uk/Output/826213Test; https://napier-repository.worktribe.com/file/826213/1/A%20Hybrid%20Method%20for%20Feature%20Construction%20and%20Selection%20to%20Improve%20Wind-Damage%20Prediction%20in%20the%20Forestry%20SectorTest |
DOI: | 10.1145/3071178.3071217 |
الإتاحة: | https://doi.org/10.1145/3071178.3071217Test https://napier-repository.worktribe.com/file/826213/1/A%20Hybrid%20Method%20for%20Feature%20Construction%20and%20Selection%20to%20Improve%20Wind-Damage%20Prediction%20in%20the%20Forestry%20SectorTest http://researchrepository.napier.ac.uk/Output/826213Test |
حقوق: | openAccess |
رقم الانضمام: | edsbas.84A2A223 |
قاعدة البيانات: | BASE |
ردمك: | 9781450349208 145034920X |
---|---|
DOI: | 10.1145/3071178.3071217 |