Activity detection with dendrite threshold model

Daniyar Bakirov, Anuar Dorzhigulov, Swathikiran Sudhakaran, Alex Pappachen James, Alex Pappachen James

2015

Closed access Metadata (CSL-JSON)
DOI 10.1109/icacci.2015.7275962
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This paper presents an activity detection system using dendrite threshold logic neuron models. This method generates a dendrite weight matrix from the background image and detect the changes in the subsequent images through the trained neuron outputs. Using only one layer of dendrite neuron cells with simplistic threshold logic cells, an accuracy of 98% is reported in realistic imaging conditions. The real-time implementation of the system is done using OpenCV libraries to be deployed in raspberry pi platform.