• No results found

Metrics and visualisation for crime analysis and genomics Laros, J.F.J.

N/A
N/A
Protected

Academic year: 2021

Share "Metrics and visualisation for crime analysis and genomics Laros, J.F.J."

Copied!
2
0
0

Bezig met laden.... (Bekijk nu de volledige tekst)

Hele tekst

(1)

Metrics and visualisation for crime analysis and genomics

Laros, J.F.J.

Citation

Laros, J. F. J. (2009, December 21). Metrics and visualisation for crime analysis and genomics. IPA Dissertation Series. Retrieved from

https://hdl.handle.net/1887/14533

Version: Corrected Publisher’s Version

License: Licence agreement concerning inclusion of doctoral thesis in the Institutional Repository of the University of Leiden

Downloaded from: https://hdl.handle.net/1887/14533

Note: To cite this publication please use the final published version (if

applicable).

(2)

Stellingen behorende bij het proefschrift

Metrics and Visualisation for

Crime Analysis and Genomics

Jeroen F. J. Laros

1. The push-only variant of the particle model combined with a closed surface will eliminate the need for scaling and should be investigated further. [this thesis, Chapter 2]

2. Temporal extrapolation using dimension reduction is only feasable if either the clustering is dynamic, or if a linear dimension reduction technique is used. [this thesis, Chapter 5]

3. Of all the closed surfaces, the torus is most suitable as an output surface of a dimension reduction technique. [this thesis, Chapter 3]

4. In the push and pull model, a better embedding can be obtained by adapting the push and pull forces to the input data. [this thesis, Chapter 2]

5. Non-metric visualisations should only be used if nothing else is available.

6. Data Mining is neither the only, nor the best solution for the extraction of information from an excessive amount of data.

7. Results from Data Mining should only be used by experts who understand the applied technique.

8. Randomised techniques are too frequently employed, even when exact solu- tions are at hand.

9. The complexity of biological systems would suggest that intelligent design is not an acceptable explanation, unless intelligent is to be interpreted as cumbersome.

10. The Dutch proverb “Schoenmaker, houd je bij je leest.” is highly applicable in interdisciplenary research areas.

11. In general, PhD students are useful for society because of their educative tasks, not so much for their thesis.

Referenties

GERELATEERDE DOCUMENTEN

The general algorithm for 2-dimensional visualisation tries to solve the following problem: We have a pairwise distance matrix as input and as output we desire a 2-dimensional

Normal clustering would result in a flat image where the points outside the torus region would have correct distances to the torus region, but with the correct inflation factor, the

In the latter case, parts of the constructed dimension reduction can be useless and thus visualisation of the error would gain insight in the quality of the picture.. If an error

In this chapter we will focus on a way to find similar careers and perhaps to automatically make a prediction of a future path of a criminal career by looking at the trends in

License: Licence agreement concerning inclusion of doctoral thesis in the Institutional Repository of the University of Leiden Downloaded from: https://hdl.handle.net/1887/14533.

The exact difference can be tuned by altering the function f , which specifies the distance between groups with a different number of marbles of the same colour.. When looking at

Since all sequences in this test set are of the same length, there is no difference between local and global alignment, there is also no difference between absolute and relative

We again extract all strings of length  from the genome and test them to the trie with the Distance Selection algorithm (instead of the strings that are in the subset (and in