This report aims to solve a problem for the waxers in the Swedish National Cross-country Ski Team, which hereafter will be referred to as the national team. The problem in hand is that currently, the national team lacks a system for book-keeping of ski pairs and ski tests. Also, the project intends to provide a tool for predicting the best ski pairs in given conditions. The report describes cross-country skis and factors that affect the performance of these skis. Moreover, this report presents the testing procedure of the national team. The project provides a solution to the problem in hand by developing a web service based on Django and Django REST Framework and an iOS application to handle the user interaction. The app was tested and approved by the waxers of the national team. To predict the best performing skis in given conditions, the three Machine Learning algorithms Support Vector Machine (SVM), Decision Tree, and Artificial Neural Network (ANN) is implemented and evaluated. Experimental results indicate that the ANN algorithm has better accuracy than the Decision Tree, and that the SVM algorithms and that the SVM was performing slightly worse than the other two, when applied on test data which is artificially generated based on the experience of the national team. All three Machine Learning algorithms perform better in terms of mean accuracy which is significantly higher compared to the accuracy of a baseline algorithm. The report suggests that the accuracy of the ANN algorithm is high enough to be useful for the national team.
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:miun-37949 |
Date | January 2018 |
Creators | Nelson, Lars |
Publisher | Mittuniversitetet, Institutionen för data- och systemvetenskap |
Source Sets | DiVA Archive at Upsalla University |
Language | English |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0022 seconds