Machine Learning and Optimisation

In crisis, such as natural disasters, communication channels are destroyed and families and friends are separated. Many flee to relief camps, where there may be more than a million people. In camps of this size, it’s almost impossible to find loved ones. So, aid organisations provide services to help people find those they’ve lost.

Typically the process of obtaining and recording information is time-consuming, with aid workers interviewing those who are looking for loved ones and asking for their personal details, the details of those they have lost and how they were separated, all recorded onto paper. By manually searching these paper records, aid workers try to reunite people as fast as possible. However, there may be few aid workers with the language skills required to conduct interviews and paper records are difficult to search and may contain errors.

Working with Tearfund, a team from the Machine Learning and Optimisation Group developed the REUNITE system, which provides an alternative to this time-consuming process. REUNITE allows aid workers to record information from missing people’s relatives on Smartphones rather than paper and upload it to a central server, where it can be quickly transcribed, validated and analysed by trusted individuals. Colleagues away from the scene can then collate the data with further details gathered using social network-style techniques and pattern matching technology can then be used to match up individuals so that aid workers can be notified of matches between people in their care.

The benefits:

• With REUNITE, reuniting families becomes quicker, easier and more secure.
• Its 'crowd-sourcing' techniques make missing person details available securely to an unlimited number of users online, considerably increasing the available workforce.
• Machine learning techniques identify and champion the most capable users, and improve the reliability of tasks carried out by 'the crowd'.