Javascript must be enabled for the correct page display

Extreme learning machine using filters for artificial lateral line source localisation

Egbers, Jelle (2018) Extreme learning machine using filters for artificial lateral line source localisation. Bachelor's Thesis, Artificial Intelligence.

[img]
Preview
Text
bAI_2018_EgbersJT.pdf

Download (1MB) | Preview
[img] Text
Toestemming.pdf
Restricted to Registered users only

Download (73kB)

Abstract

Data of an artificial lateral line, an array of sensors which are able to sense the differences in water flow, can be used for source localisation and angle prediction. In this research, possibilities to improve an extreme learning machine used for this purpose are explored. This is tried with filters, by changing the input representation, and by changing the activation function. Changing the input representation to a square matrix improves the accuracy of the algorithm, with the mean square error reaching an asymptotic line as increasingly more filters are added. An algorithm with both the ReLu and tanh activation functions also turned out to work well, because of the fact that one function was good at predicting the location and the other function was good at predicting the angle.

Item Type: Thesis (Bachelor's Thesis)
Supervisor:
Supervisor nameSupervisor E mail
Netten, S.M. vanS.M.van.Netten@rug.nl
Wolf, B.J.B.J.Wolf@rug.nl
Supervisor (outside RUG):
Supervisor outside RUG nameSupervisor outside RUG E mail
Pirih, PrimozUNSPECIFIED
Degree programme: Artificial Intelligence
Thesis type: Bachelor's Thesis
Language: English
Date Deposited: 30 Jun 2018
Last Modified: 03 Jul 2018 14:14
URI: http://fse.studenttheses.ub.rug.nl/id/eprint/17527

Actions (login required)

View Item View Item