Classification Algorithms for Big Data with Applications to the Internet of Things (IoT) and Beyond
Supervisor:
Miguel Rodrigues
Submitted on: Saturday 14th February 2015
The Internet of Things (IoT) will provide pervasive connectivity to a large number of devices, systems and services to enable a range of breakthrough applications in domains such as the digital economy, business and commerce, manufacturing, and medicine and healthcare.
It is however estimated that by 2020 there will be circa 200 Billion of devices for 8 Billion people all capturing, generating and transmitting data. One is therefore confronted with one major challenge: it is widely acknowledged that without radical changes to the way one collects, analyzes and processes information the current information infrastructure will not be able to keep up with the current pace of data growth in view of fundamental limitations in transmission, storage and computation capability (cf. Kryder’s Law, Moore’s Law) or even other resources such as energy.
The goal of this research project is to develop new big data classification schemes and algorithms to enable energy- and bandwidth-efficient communication for the IoT and beyond. In particular, the project will develop novel classification approaches able to capture key attributes of data under energy-efficiency and bandwidth-efficiency constraints, as well as assess the efficacy of the new classification schemes and algorithms through a series of case studies.
The main elements of this research programme include:
1. Development of novel energy-efficient and bandwidth-efficient data classification schemes and algorithms for IoT applications;
2. Assessment of the energy-efficiency and bandwidth-efficiency of the new classification approaches via simulations;
3. Applications of the new classification approaches in various domains through a series of case studies in order to illustrate the gains in bandwidth efficiency and energy efficiency.
This project covers new research in the emerging fields of Big Data and the IoT, so high-level publications would be anticipated as a possible outcome of the research. This project is therefore ideal to pave the way to a successful career in industry or academia.
Additional Information:
This research work requires students with analytical and programming skills as well as some experience with system simulation in MATLAB. Potential students are encouraged to contact the proponents to discuss further details about the project.
This research project is complementary but independent of the related research project on “New sensing schemes and protocols for energy- and bandwidth-efficient communications with applications to the Internet of Things (IoT) and beyond”. This page has been automatically generated by the EE Project Submissions Facility Back to Projects index