A PIR sensor-based WSN was developed by our group to
help mitigate human-wildlife conflicts occurring at the edge
of a forest [1]. This can potentially serve as an earlywarning
system which can aid forest officials to manage these
conflicts. The PIR sensor was the preferred sensing modality
due to its passive nature, relatively low cost, wide commercial
availability and the ability to operate in the absence of visible
light. At the heart of the WSN is a PIR sensor-based STP
(see Fig. 1) along with a supervised machine learning based
classification algorithm which enables discrimination between
signals generated by human, animal and wind-blown vegetation
motion (signals generated by vegetative motion are termed as
clutter) [1]. Only a small subclass of animals are considered
here, those comparable in size and shape to a dog or a tiger.