What is it about?
The paper looks at how to analyze millions of fish trajectories to estimate speed versus water temperature, for one species of coral reef fish, and shows that the average fish speed increases. The paper shows that the same conclusion can be reached from both the raw and partially cleaned dataset.
Featured Image
Why is it important?
1) Real datasets are noisy and the paper introduces methods to still extract interesting conclusions. 2) Cleaning a dataset is good, but risks damaging the dataset by also removing good data. We show that our approach did not damage the dataset.
Perspectives
It shows that you can still extract meaningful information from very noisy data if you have enough - a big data perspective.
Robert Fisher
University of Edinburgh
Read the Original
This page is a summary of: Extracting Statistically Significant Behaviour from Fish Tracking Data With and Without Large Dataset Cleaning , IET Computer Vision, November 2017, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-cvi.2016.0462.
You can read the full text:
Contributors
The following have contributed to this page
