Wiersma, Alida (2019) Statistical learning methods for environmental DNA. Master's Internship Report, Applied Mathematics.
|
Text
mAppM_2019_WiersmaAG.pdf Download (6MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (120kB) |
Abstract
In this report, the results of my internship about the data analysis of environmental DNA are presented. Environmental DNA is a new technique that gives a better insight which factors determine the water quality of lakes. This technique is being developed by Witteveen+Bos and Datura. Cluster analysis was used to check if the environmental DNA profiles of the lakes could be used to categorize the lakes. There were several methods considered. Namely, the dissimilarity coefficients: Euclidean, Correlation, Bray-Curtis and Jaccard were used in conjunction with the linkage methods: Single, Complete, Average, Weighted and Ward. In order to find the best method for this type of dataset the clustering results of the methods with several filters on the dataset were being compared. This was done to check for the robustness of the methods. Principal component analysis was used in order to visualize the clustering results and to see if there were there were factors that are characteristic for a cluster.
| Item Type: | Thesis (Master's Internship Report) |
|---|---|
| Supervisor name: | Schaft, A.J. van der |
| Degree programme: | Applied Mathematics |
| Thesis type: | Master's Internship Report |
| Language: | English |
| Date Deposited: | 28 Jun 2019 |
| Last Modified: | 08 Jul 2019 09:13 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/19753 |
Actions (login required)
 |
View Item |