Sensors are nice, but useless without proper analytics
Sensing is not about collecting data. It is about sense making. About sensing clues!
To gain a deeper understanding of poaching patterns, the effect of patrolling, the relations between poachers, facilitators, and incidents, the identification of black spots, etc. we made a Wildlife Deal with the NSCR to develop a Wildlife Crime Analyst Toolbox (WildCAT). The toolbox does three things:
- rule-based evaluation of real-time sensor-data,
- interactive exploratory analysis of available data,
- hybrid real-time analytics.
Rule-based evaluation of real-time sensor-data
All sensor-data is analysed at real-time. Singular measurements (observations) can be combined with that of other sensors, thus gaining sight on time-spatial patterns that may signal poaching behaviour. If such is the case, an alarm is generated and pushed to the Cluey-app.
Knowledge rules are typically uncovered with the SCUM-method. The rules are implemented by Sensing Clues. Facilities to self-create knowledge rules are foreseen.
Interactive exploratory analysis
Catching poachers, illegal loggers, and other law offenders red-handedly demands a sound intelligence position. Having the information is one thing. Making it readily available for interactive analysis by laymen (from an analytics perspective) is yet another challenge. WildCAT is designed to facilitate just that. By simply selecting objects and creating relations, one may browse intuitively through all available data. Snippets of valuable information, such as related incidents, names, phone numbers, etc., can be noted and through the Cluey-app shared in real-time with rangers in the field, or other partners.
Hybrid real-time analytics
Interactive exploratory analysis can be combined with rule-based evaluation of real-time sensor-data. By activating the notification function, the analyst is notified every time new sensor-data comes available. Where handy, the analyst can join the Cluey-chat-session of the fast-responders and convey his insights or suggestions.
To make the most of WIldCAT, Sensing Clues helps its partners to make their databases and sensor-data available in WildCAT.
The technologies behind WildCAT
WildCAT is powered by MarkLogic, the only Enterprise NoSQL database. It is a new generation database that is built with a flexible data model to store, manage, and search today’s data, without sacrificing any of the data resiliency and consistency features of last-generation relational databases. With these capabilities, MarkLogic is ideally suited for making heterogeneous data integration simpler and faster and for doing dynamic content delivery at massive scale.
WildCAT’s analytical functions are supported by RStudio and Shiny. For your convenience, we have setup a secure cloud-based platform where you can create your own scripts (with RStudio) and serve them to end-users (through Shiny).
Can’t wait? Just contact us to discuss how to proceed.