Data Science for the Internet of Things

Şefki Kolozal

Tutorial Title:
Data Science for the Internet of Things

The aim of this tutorial is to provide an introduction to pre-processing and state space models. The course will introduce downsampling techniques to learn how to reduce the size of large amount of time series data, such as Discrete Wavelet Transform and Symbolic Aggregate Approximation, and then introduce Hidden Markov Models, Linear Dynamic Systems and show how they can help us to solve complex classification problems.

Course objectives:

  • Familiarise with preprocessing techniques for time series data
  • Understand how to use state-space models to solve complex problems

Course Requirements:  This course will show the use of python in data science approaches for the Internet of Things but students will have an option to code themselves.

•  python 3 •  numpy • ipython3 for python3 •  python3-scikits-learn • python3-pandas •  python3-pydot

Background Requirements: A background in computer science, maths, business and social science with some mathematical skills would be useful. This course requires high-school level maths.

Biography: I am a Postdoctoral Research Fellow at the Institute of Analytics and Data Science, University of Essex. I am interested in the field of Internet of Things. Previously, I worked as a Research Associate in Applied Big Data Analysis at the MRC-PHE Centre for Environment and Health, King’s College London. I worked on exploring links between the environment and human health through the analysis of very large time series datasets. I was part of the COPE study team, which aims to reduce the frequency of hospital and GP visits by patients with respiratory disease. I also worked as a Research Fellow in large-scale data analytics for the Internet of Things at the 5G innovation centre, University of Surrey, where I was a work package leader in large scale data analysis and seamless integration of data sources in the CityPulse project. I received a B.Sc. degree in Computer Engineering from Near East University, Nicosia, Turkish Republic of Northern Cyprus, in 2005. I received an M.Sc. degree from the University of Essex and a PhD degree from Queen Mary University of London. My thesis was titled Automatic Ontology Generation Based on Semantic Audio Analysis.