Suraj Pattar

Robotics AI Research Engineer / Ph.D. in AI and Robotics / Data Scientist / 3D Printing Enthusiast

Unsupervised Learning in Evolving Environments

Keywords: Clustering, Anomaly Detection

Project Description

Draft Paper Slides Github

This work was done as a group project for the final semester at University of Genoa with another Masters student colleague, Zsolt Pazstori.

In this work, the goal was to detect the anomaly in streaming 2D data.

Data

There were two datasets used in this work.

Primary dataset was a artificial dataset generated for x and y position of vehicles at a traffic junction in Genoa.

Another dataset to test our method was the Real rainfall data from Bristol, UK, first two weeks of January, 2014 [7,14].

Software:

Matlab

Anomaly Detection in Fuzzy Clustering on Streaming Data