1Meharry Medical College Department of Biomedical Sciences, Nashville, TN, United States of America
2Dairy Research and Technology Centre, F-30 Edmonton Research Station, South Campus, University of Alberta Edmonton, ABT, Canada
3Brandeis University, 415 South Street, Waltham, Massachusetts, United States of America
4United States Air Force, San Antonio, Texas, United States of America
5Labstream Bioinformatics Corporation, Los Angeles, CA, United States of America
6Northeastern University Department of Information Sciences, Boston, MA, United States of America
7JustUs Youth Development Automated Behavioral Analysis Corporation, Addis, LA, United States of America
8Lawrence Livermore National Laboratory, Livermore, CA, United States of America
9South End Technology Center, Boston, Massachusetts, United States of America
10University of New Haven, Department of Criminal Justice and Forensic Sciences, West Haven, CT, United States of America
11United States Department of Energy, Washington, DC, United States of America
12United States Department of Defense, Washington, DC, United States of America
13Medical Office, 524 North Donmoor Avenue, Baton Rouge, Louisiana 70807, USA
14Smith College School of Social Work, Northampton, Massachusetts, USA
15South End Technology Center Director, 359 Columbus Avenue, Boston, MA
Non-Intrusive inspection (NII) using DJI Phantom 4 drones for video surveillance of dairy manufacturing plants operational activity and the utilization of computer vision, machine learning, NoSQL databases (e.g. MongoDB, HBase, and Cassandra) and the Hadoop Ecosystem with Spark Directed Acyclic Graph Execution Engine (DAG) to analyze ATP bioluminescent sensor micrographs from biofilms on a dairy manufacturing assembly lines is a powerful threat detection technique. The detection of “bacteria in milk typically adhere and aggregate on stainless steel surfaces, resulting in biofilm formation in milk storage tanks and milk process lines. The exponential growth of biofilms in milk processing environments incorporates more opportunities for microbial contamination of the processed dairy products. These biofilms may contain spoilage and pathogenic microorganisms, such as Yersinia, enterocolitis, and strains of Escherichia coli which can survive on different surfaces for periods ranging from several hours to days. In addition, even within biofilms the most deleterious spoilage bacteria originating from raw milk is pseudomonads. The detection and predictive tracking of pseudomonads originating from raw milk and pathogenic microorganisms captured by ATP bioluminescent micrograph sensors are ingested into the Nephilim Base Unit Architecture, authentication server that can be configured on the (Access Point) AP or on an external server. We also incorporate image anomaly detection to classify micrograph biofilm images which are considered outliers (e.g. ATP biofilm sensor yielding a totally black image). Micrograph images detected as outliers are filtered, flagged, and ranked using Spark filter and window functions before encrypted data propagation.
Keywords: Non-Intrusive Inspection (NII); DJI Phantom 4 Drones; Hadoop Ecosystem; Directed Acyclic Graph Execution Engine (DAG)
Wilbert McClay., et al. "Nonintrusive Inspection Using Predictive Big Data Analytics for Biological Pathogen Threats of Biofilms from ATP Bioluminescent Sensor Micrographs for Dairy Research and Technology." EC Clinical and Medical Case Reports 7.9 (2024): 01-07.
© 2024 Wilbert McClay., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Open Access by ECronicon is
licensed under a Creative Commons Attribution
4.0 International License
Based on a work at www.ecronicon.net