Cognitive Modeling of the Natural Behavior of the Varroa destructor Mite on Video

The present work offers an innovative and automatic approach for detecting, tracking, analyzing, and reporting the natural behavior of the Varroa destructor mite and its activity from videos provided by the Tropical Apicultural Research Center (CINAT) in Costa Rica. These videos correspond to the pr...

Full description

Saved in:
Bibliographic Details
Published in:Cognitive computation 2017-08, Vol.9 (4), p.482-493
Main Authors: Ramírez-Bogantes, Melvin, Prendas-Rojas, Juan P., Figueroa-Mata, Geovanni, Calderon, Rafael A., Salas-Huertas, Oscar, Travieso, Carlos M.
Format: Article
Language:English
Subjects:
Artificial Intelligence
Bees
Biomedical and Life Sciences
Biomedicine
Calibration
Computation by Abstract Devices
Computational Biology/Bioinformatics
Experimental methods
Honey
Mites
Mitochondrial DNA
Modelling
Neurosciences
Parasites
Qualitative analysis
Research facilities
Tracking
Video
Viruses
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The present work offers an innovative and automatic approach for detecting, tracking, analyzing, and reporting the natural behavior of the Varroa destructor mite and its activity from videos provided by the Tropical Apicultural Research Center (CINAT) in Costa Rica. These videos correspond to the presence of V. destructor in capped Africanized worker honeybee cells in a controlled environment. The main objective of this paper is to present an automatic report of the identification of the mite behavior based on mite information (bioinspired information). First, a calibration system was implemented to enhance the frame. This calibration was achieved by searching the movement-active area (MAA) and the geometrical definition of the V. destructor mite. Then, an automatic detection and tracking was applied. Finally, an automatic classification was used to establish the mite activity. This approach reached up to 92.83% for all processes: detection, tracking, behavior analysis, and activity reporting, in real time and showing a cognitive model of the mite. The proposed approach provides an automatic tool and objective measurement against manual and qualitative methods traditionally applied in this kind of analysis, with a significant potential to be used as a reference in the modeling of the behavior of the V. destructor mite.
ISSN:1866-9956
1866-9964
DOI:10.1007/s12559-017-9471-7