Scanning environments with swarms of learning birds: A computational intelligence approach for managing disasters

Much work is underway within the broad next generation technologies community on issues associated with the development of services to foster collaboration via the integration of distributed and heterogeneous data systems and technologies. In previous works, we have discussed how these could help coin and prompt future direction of their usage (integration) in various real-world scenarios such as in disaster management. This paper builds upon on our previous works and addresses the use of learning agents called learning birds in modelling the process of data collection using wireless sensor networks, Specifically, learning birds are some sort of nature-inspired learning agents collaborating to create collective behaviours. As an artificial bird flock, the swarm members collaborate in positioning while moving within a particular environment. In order to improve the diversity of the flock, each individual needs learning the how to position relatively to its neighbours. Q learning is a very famous reinforcement learning algorithm, which offers a very efficient and straightforward learning approach based-on gained experiences. Therefore, a swarm of birds collaborating and learning while exchanging information to position offers a very useful modelling approach to develop ad hoc based mobile data collection tools. To achieve this, we use a disaster management scenario.