High-Performance and Scalable processing of DirectLife Physical Activity Data

From Master Projects
Jump to: navigation, search

About High-Performance and Scalable processing of DirectLife Physical Activity Data

  • This project has not yet been fulfilled.
  • This project fits in the following Bachelor programs: {{#arraymap:|, |xXx|bachelorproject within::xXx|,}}
  • This project fits in the following masterareas: {{#arraymap:High Performance Distributed Computing, Parallel and Distributed Computer Systems|, |xXx|project within::xXx|,}}


Most people are not aware of their daily amount of physical activity and associated energy expenditure. A persons’ energy expenditure can be measured with a relatively simple tri-axial accelerometer embedded inside an activity monitor. Algorithms for calculating energy expenditure from tri-axial accelerometer data have been developed and an increasing amount of services are now offered to consumers that want to increase awareness of their physical activity. Most of these services, e.g. MiLife, HealthMedia and DirectLife, use a website to give consumers feedback. Users are required to regularly upload data to the website.

However, with the growing number of people that use physical activity self-monitoring services, it becomes important to process activity data in a scalable and highly available way. In addition, as new data processing algorithms become available, a multi-dimensional parallel analysis of accelerometer data is needed.

A high-performance distributed computing solution is expected to give this flexibility, while meeting performance, scalability and availability requirements

The objective of this assignment is to design, implement and evaluate a high-performance distributed computing solution for scalable processing of physical activity data. Design alternatives should be evaluated against responsiveness, availability and scalability properties. The Philips DirectLife service (http://www.directlife.philips.com) will be the use-case for this assignment.