• University of East Anglia Featured PhD Programmes
  • Aberdeen University Featured PhD Programmes
  • University of Birmingham Featured PhD Programmes
  • University of Cambridge Featured PhD Programmes
  • Castelldefels School of Social Sciences Featured PhD Programmes
  • University of Glasgow Featured PhD Programmes
Ludwig-Maximilians-Universität Munich Featured PhD Programmes
Coventry University Featured PhD Programmes
John Innes Centre Featured PhD Programmes
University of Bristol Featured PhD Programmes
University of Reading Featured PhD Programmes

Cloud-based Approaches to Streaming Data Analysis


Project Description

The use of sensors, both in conventional industrial settings and in the modern ‘internet of things’ settings, generates large quantities of data – so called Big Data. One of the major challenges in Big Data is to perform real-time analysis on multiple high-velocity data streams, examples of which include credit card fraud detection from large-scale business transactions and real-time anomaly detection on high-resolution weather sensor data.

Recent development in cloud computing makes it possible to develop scalable machine learning algorithms to infer appropriate models, which can predict the behaviour and discover novel patterns across multiple data streams.

In this project, we are going to explore how to develop efficient model learning algorithms in the cloud for better analysing streaming data, and we want to answer the following questions:

1. How to effectively capture and pre-process multiple data streams in the cloud environment.
2. How to develop model learning algorithms by making use of existing cloud computing techniques.
3. How to perform model selection given a set of candidate models.
4. Whether can we learn ab initio models from existing knowledge and data or learn models through composition of model fragments?

To achieve this we will investigate the development of evolutionary model learning approaches on the cloud. We will study the suitability of different cloud platforms for processing multiple streams. We will test our model learning algorithm by both synthetic and real world data.

The successful candidate should have, or expect to have, an Honours Degree at 2.1 or above (or equivalent) in Computing Science or related disciplines.

Knowledge of: Essential: machine learning basics; cloud computing basics; programming in Java, Python, Ruby, or Scala.

Desirable: evolutionary computing, experience in Hadoop; programming with MapReduce; Experience in Apache Spark.

Funding Notes

There is no funding attached to this project, it is for self-funded students only

References

APPLICATION PROCEDURE:
This project is advertised in relation to the research areas of the discipline of Computing Science. Formal applications can be completed online: http://www.abdn.ac.uk/postgraduate/apply. You should apply for PhD in Computing Science, to ensure that your application is passed to the correct College for processing. NOTE CLEARLY THE NAME OF THE SUPERVISOR and EXACT PROJECT TITLE ON THE APPLICATION FORM. Applicants are limited to applying for a maximum of 2 projects. Any further applications received will be automatically withdrawn.

Informal inquiries can be made to Prof G Coghill ([email protected]) with a copy of your curriculum vitae and cover letter. All general enquiries should be directed to the Graduate School Admissions Unit ([email protected]).

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully




Cookie Policy    X