Food Protection Trends - November/December 2020 - 464

GENERAL INTEREST PAPER

Food Safety and Quality Data Management
Using Artificial Intelligence
Mehrdad Tajkarimi, DVM MPVM PhD
EAS Independent Consultant, LLC 1700 Diagonal Road, Suite 750, Alexandria, VA 22314, USA

SUMMARY
Are you overwhelmed with operational food safety and
quality data and uncertain how to organize and analyze it
to provide justification that your food safety and quality
program is effective? Then you have a lot of company. The
food industry's access to data is not the limiting factor it
may have been 20 years ago. The limiting factor today is
having more data than there is capacity to analyze and
process into meaningful trends. Is there a solution that is
available and practical?
OVERVIEW
The food industry is in need of a holistic approach to
organize, analyze, integrate, and generate conclusions that can
help benchmark and track key performance indicators (KPIs)
related to food safety and quality (12). The application of
machine learning and artificial intelligence (AI) can provide
the conceptual tool to transform food safety and quality data
management, driving it from a parallel and repetitive control
base model toward a value-based food safety and quality
system (13). In short, AI can deliver on the need to have a
feedback loop for existing food safety and quality programs
and whether they are meeting the needs and expectations
of company quality assurance management and generate
frequent analytical information that can be summarized
in reports to company senior management teams (8).
Other outcomes of using AI in this manner are to provide a
number-based system to justify investment in a company's
food safety and quality programs, redirect resources to where
they have the most impact, and potentially lower food safety
and quality costs while enhancing delivery of superior food
safety and quality control and management (15).
Section I - What are AI and algorithms?
AI is an area of computer science that emphasizes the
creation of intelligent machines that work and react similarly
to humans. Industries that were early adopters of AI include
speech recognition, facial recognition, biometrics, planning,
and computer-based problem solving. AI algorithms learn
and improve their effectiveness similar to the learning
process for human food safety and quality professionals (7).
In the AI learning process, structured data are fed into the

computer systems and identified with a label or annotation
to be recognizable to the algorithm's data point (13). The
algorithm starts to examine the input data and compare it
with known data that the algorithm already has analyzed. The
results can then be modified by receiving more data inputs or
can solve equations for the human operator. The algorithms
can learn from data-either numerical, such as colony count
or pH, or a statement, such as auditor note (1)-creating an
output such as a simple grouping of data with means, modes,
etc., or more valuable outputs such as statistical probability
or a classification or categorization. The more data fed into
the algorithm, the more learning, data outputs, probabilities,
and classifications (Fig. 1). A real-life example is the use of
weather data placed into AI-based algorithms (models) to
provide short- and long-range weather forecasts (6, 7).
AI's reach and applicability are expanding rapidly. In the
health care industry alone, investments in this technology
are predicted to reach $6 billion by 2021 (6). What does AI
mean for the food processing industry, and how can it be
used to benefit food safety?
AI is enabling computers to think and learn in a manner
to similar humans. Google and Facebook are already using
it (e.g., search suggestions and photo recognition). The use
of AI as a tool for food safety and quality is in its infancy.
However, with effort and investment, it has the potential to
emerge as a game changer, forming a structural foundation to
incorporate facility, industry, and government data to form a
complete picture of risks, vulnerabilities, and opportunities
for improvement (Fig. 2) (6).
Application and example of AI for food safety and
quality analysis
One successful application of AI is with the Chicago
Department of Public Health (4, 5). The department
analyzes vast amounts of data on previous violations related
to food safety, including time since the last inspection,
operation period, nearby garbage and sanitation complaints,
3-day high-temperature readings, nearby burglaries, and
tobacco and alcohol licenses issued by Chicago Department
of Public Health to help identity at-risk restaurants.
Collectively, these form a picture of the potential for food
safety or quality risks.

*Author for correspondence: Phone: +1 571.447.5500; Email: MTajkarimi@easconsultinggroup.com

464

Food Protection Trends November/December

http://www.foodprotection.org/files/food-protection-trends/nov-dec-20-tajkarimi.pdf

Food Protection Trends - November/December 2020

Table of Contents for the Digital Edition of Food Protection Trends - November/December 2020