Ankle bracelets (anklets) imposed by law to track convicted individuals are being used in many countries as an alternative to overloaded prisons. There are many different systems for monitoring individuals wearing such devices, and these electronic anklet monitoring systems commonly detect violations of circulation areas permitted to holders. In spite of being able to monitor individual localization, such systems do not identify grouping activities of the monitored individuals, although this kind of event could represent a real risk of further offenses planned by those individuals. In order to address such a problem and to help monitoring systems to be able to have a proactive approach, this paper proposes sensor data fusion algorithms that are able to identify such groups based on data provided by anklet positioning devices. The results from the proposed algorithms can be applied to support risk assessment in the context of monitoring systems. The processing is performed using geographic points collected by a monitoring center, and as result, it produces a history of groups with their members, timestamps, locations and frequency of meetings. The proposed algorithms are validated in various serial and parallel computing scenarios, and the correspondent results are presented and discussed. The information produced by the proposed algorithms yields to a better characterization of the monitored individuals and can be adapted to support decision-making systems used by authorities that are responsible for planning decisions regarding actions affecting public security.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited