The following navigation utilizes arrow, enter, escape, and space bar key commands. Left and right arrows move through main tier links and expand / close menus in sub tiers. Up and Down arrows will open main tier menus and toggle through sub tier links. Enter and space open menus and escape closes them as well. Tab will move on to the next part of the site rather than go through menu items.
Ethan Chatfield, Yinying Liang, Dr. Wan Bae, Department of Computer Science, Seattle University 901 12th Ave Seattle, WA 98122
To improve people and carnivores coexistence in Greater Seattle, this project focuses on seasonal and locational analysis of carnivore data through explanatory data analysis and cluster evaluation. By doing this, we can help protect species and live in harmony with them, as the current trends of this due to industrial expansion are negative. The goal of this project is to accomplish both scientific and ethical merits. The scientific merit is to develop visualization tools and computational methods for finding spatial and temporal interactions between people and carnivores in urban areas. The ethical merit is to apply this increased understanding to the way in which humans live in proximity to these carnivores as an attempt to create a more harmonious relationship with a higher degree of safety between the two. In this project, we used the data obtained by Urban Carnivore Project (https://www.zoo.org/seattlecarnivores): (1) Carnivore spotter data and (2) Camera trap data. We first conducted explanatory data analysis using data visualization. Secondly, we applied popular clustering algorithms to analyze the locations of carnivore living and traveling. The algorithms were used in the project are K-means, Mean shift, DBSCAN, and Hierarchical clustering. The time analysis results show the most active time and season of each carnivore species. The results also show that the carnivores tended to be spotted near the city, and that the number of carnivores being spotted changed quite drastically depending on the season. Given these results, some interesting future work strongly suggest itself. Geographical barriers and constraints can be used to identify each carnivore’s home ranges, and changes in its size or movement direction. It would be also worthwhile to attempt to implement a more accessible and user-friendly interface for promoting this project.
Presenters: Yinying Liang, Ethan Chatfield
Institution: Seattle University
Type: Poster
Subject: Computer Science
Status: Approved
