How AI can improve the security of facility entrances

by brittney_cutler | March 30, 2022 2:30 pm

[1]

By Kurt Measom

While artificial intelligence (AI) has made an impact in a myriad of technology sectors, it is still in its infancy in the physical security industry. AI’s ability to simulate the human intelligence process by acquiring and learning certain tasks and behaviors is well suited for some of physical security’s redundant tasks. The artificial neural network (ANN) is at the heart of this learning process, as thousands of sensors mimic the human brain by absorbing data and information from its environment, assessing its meaning or threat level through its sensory devices, such as video cameras, access control and secure entrance systems, Internet of Things (IoT)-powered devices, and social media and other big data resources to then coordinate the appropriate response.

John Carter, co-founder of a smart security solutions provider, wrote in a SIA Technology Insights[2] newsletter, “No physical security devices have benefited more from AI than physical access control systems. When integrated with an AI-based solution, an access control system can now quickly react to threats and adjust permissions accordingly. Having the ability to identify anomalous events, insider threats, and hazardous situations and dynamically change permissions is a major breakthrough for the physical security world.”

The use cases for AI in access control and secured entrances are many, ranging from its ability to identify unusual activity like off-hour and abnormal access to the creation of a risk-adaptive entry process that would prevent ingress and egress to areas posing a potential danger to staff or employees. While turnstiles may not have changed dramatically in form, their use within a layered security solution can provide invaluable data to an AI-based system. Anomalous traffic patterns or unusual access can be identified before individuals reach higher security areas. Randomized spot checks, controlled throughput, and directed traffic flows can be initiated and managed via intelligent, risk-based solutions as threats are detected.

Thanks to the rapid growth of AI it translates into a safer environment

According to research and analysis firm ABI Research[3], the total installed base of devices with artificial intelligence capabilities will grow from $2.7 billion in 2019 to $4.5 billion in 2024. Global spending on AI systems will hit $97.9 billion in 2023, which is two-and-a-half times the 2019 spend, according to market intelligence firm IDC’s Worldwide Artificial Intelligence Systems Spending Guide[4].

There is good reason for this rapid growth. The use of artificial intelligence improves operational efficiencies and system effectiveness with a number of additional benefits. Organizations can save costs, improve security, provide better customer service, reduce negative environmental impact, and possibly even save lives using AI.

[5]

That is not just hyperbole. For example, without a doubt, the most pressing problem facing governments, families, and every organization around the world right now is the COVID-19 pandemic. In the recent past, biopharma companies have adopted artificial intelligence to help solve health problems by locating meaningful patterns within extremely large data sets. Medical publication Fierce Biotech notes, according to Arvind Ramanathan, a technology leader at the U.S. Department of Energy’s Argonne National Laboratory[6], the lab is providing supercomputing resources to a public-private consortium of COVID-19 researchers right now.

When translated to a security environment, the reason artificial intelligence is so effective is because it ‘learns’ in very much the same way as humans do. However, AI does so at a vastly more rapid rate. It has the capability of ingesting massive quantities of data, analyzing it, and using it to make extremely accurate predictions about what will happen in the future given a variety of differing models. Depending on the desired outcome, AI can evaluate the conditions and inputs enabling it to deliver a new model to optimize the occurrence of that specific result. As more data becomes available through use of the system or device, AI can continue to optimize and grow in efficiency.

With the evolving dynamics of cloud storage and the fast-growing volume of security data, AI has become a disruptive technological force across all segments of the physical security industry. Among the biggest beneficiaries has been video surveillance, which can leverage faster processing to deliver more and better analytics. Beyond surveillance, building automation, fire systems, intrusion detection, and physical and network access control are now benefitting from AI built into many core competencies.

Secure entrances embrace AI

[7]

It seems clear AI has the potential to play an important role in making exterior and interior entrances more secure. While AI will be able to help in many security-related tasks, such as discerning people from objects at a facility’s perimeter and interior entrances, detecting attempted piggybacking, and spotting and analyzing potentially lethal objects and dangerous people, AI alone cannot take action to prevent unauthorized human intrusions or deny the entry of dangerous objects.

As we move to greater converged technology at the edge, the quandary is how AI may practically interplay with entry solutions, such as revolving doors, turnstiles, and swing doors, to accomplish risk-reduction goals. Disconnect between the objectives of the facility’s owner and building code regulations can further complicate the security blueprint.

The process of improving operational effectiveness using AI can equally be applied to security entrances. Due to the range of specific project needs, as well as the variety of other security systems that may need to be integrated, adding AI functionality to security entrance systems is typically done via a collaborative effort with a selected third-party solutions provider. This way, the particular functions and strengths of the selected AI software can match the specific project conditions and constraints.

For example, video analytics with AI capabilities are being deployed to address use cases, such as people and dangerous object detection, piggybacking, and facial recognition at secured entrances. The increased integration of AI providers with traditional security entrance partners has resulted in improvements in many of the factors considered to be fundamental to operations. These include:

∞ price;

∞ speed;

∞ ease of use; and

∞ integration with other systems and sensors.

It is crucial manufacturers’ goals align with their end users’ needs when it comes to driving the development of embedded solutions with advanced sensors (e.g. cameras, microwaves, and LIDAR), operational analytics (facial and pattern recognition, tracking, and object discrimination), and active response (entry lockout, alert notification) which now prevent or deter risks detected at the entry.

“To this point, the security entrance must be part of the general building operations design, clearly separated from an architect’s complete authority. Most secured entries are specified in Division 28 [Electronic Safety and Security], outside of building design since it is structural and falls under code compliance surrounding emergency egress as well as building capacity and throughput. Therefore, if this is to work, the rules for design and the merging of Division 28 and Divisions 8 (Openings) and 11 (Equipment) must become refined, practical, and widely accepted,” says consultant Ben Butchko, CEO at a security solutions provider, and a former security engineer with ExxonMobil.

Security entrances often combine a number of systems, sensors, and requirements to achieve the goal of tailgating mitigation. When deployed, these entrances are inherently an integrated solution combining access control, mechanical hardware, sensors, algorithms, and, most importantly, design.

[8]

The addition of surveillance cameras around doors or security entrances can be an example of adding video deployment primarily for the sake of forensics: the ability to tie what took place at the entrance to an alarm condition (e.g. a forced or jammed/propped entrance/exit or a tailgating incident). This functionality can be enhanced by analytics. For example, facial recognition could be used to determine the individuals that set off the alarm condition. Analytics can also be proactive, determining a crowd has gathered, and then automatically activating additional security entrances, bringing them online and ready for credentials until the crowd has passed through.

Additionally, at this time there is an increasing demand for touchless access to support health and safety initiatives due to COVID-19.

“In this case, the integration of technologies and the use of machine learning can be leveraged to provide efficient, safe, and secure access. Machine learning and AI are well adapted to leveraging data sets and, over time, gaining an understanding of conditions and matching them to access control and individual requirements,” said Salvatore D’Agostino, CEO of a security systems provider.

Calculating the AI benefits

So, what functions can AI potentially add at a secured entrance? Currently, some of the best applications of AI are those that replace human effort at tasks that would be tough for people to do reliably and consistently, such as learn behaviors of staff, employees, and contractors and identify people and monitor them 24/7.

If a camera with AI is paired with a security entrance solution, such as a turnstile, security revolving door, or mantrap portal, and monitoring that entrance continuously, it could improve the detection capabilities currently built into these entrances in terms of identity verification and anti-tailgating/anti-piggybacking. Currently, security entrances detect tailgaters by using near-infrared sensors—an alarm is generated if two separate objects appear to break through the sensor beams. In security revolving doors and mantrap portals, near-infrared, ‘time of flight’ technology is paired with optics to create a 3D image of the objects inside the door, and algorithms and sampling data are used to determine whether there is one or more people.

False rejection happens when these technologies incorrectly reject a user (e.g. a person enters a door with a box of pizza and wears a backpack). Advanced AI can fill the gap by improving its models for recognizing people (through learned movement patterns and spacing of features) and objects, which can, in turn, decrease the false rejection rate. For example, it could ‘learn’ to know the difference between inanimate objects being worn or carried through the entrance versus living users.

Butchko says machine learning as well as deep learning has been used for many years in the big data world to identify trends and produce metrics regarding human intent. The use of “synthetic cognition” or AI is part of the drive for establishing ways to create the correlation to human patterns and the completion of tasks in the hopes of creating greater efficiencies in business practice.

“Within the security industry we see a trend by companies to leverage these specific engines to gain greater benefits from access control, VMS (video management system), intrusion detection, and tracking systems. It can be seen as a double-edged sword, because tracking learned behavior can help define potential vulnerabilities and unmask possible threats. It can also lead to privacy and discrimination concerns, especially when intent and analytic detail are not clear,” Butchko says.

Proactive and predictive possibilities

D’Agostino sees the convergence of AI into security spaces not known for their reliance on analytic data reshaping the landscape. AI can be used as a proactive step against intrusion at a security entrance like a swing door or turnstile and integrated into the access control and video security systems to provide rich analytics and situational awareness.

“It has long been known that there are often patterns to humans, and to the same extent, enterprise behavior. Access control, surveillance, and intrusion detection systems collect large amounts of data that is often stored and then deleted without much analysis. Enterprises are now more attuned to the ability to leverage this data. These are evolving now to common data formats, real-time analytics, and predictive tools. It seems like there would be a similar evolution in the capabilities of physical security systems where it is not so much as what is happening at a turnstile, swing door, or entryway, but what is going to happen,” contends D’Agostino. “This would leverage the existing systems, sensors, and data collection capabilities and use big data and analytics to drive management and monitoring. The more physical security systems adopt standard data types, sets, and structures (using syslog for logging is a simple example) and the more intelligent these systems become, the more intelligence can be put into the predictive analytics.”

The future of AI and security entrances

Artificial intelligence has been a part of the global technology lexicon since Arthur C. Clarke’s 1968 science-fiction film, 2001: A Space Odyssey. In that film, HAL (the heuristically programmed algorithmic computer) was introduced as the sentient AI that controlled the systems of the Discovery One spacecraft. HAL was capable of speech, facial and speech recognition, natural language processing, lip reading, interpreting emotional behaviors, automated reasoning, spacecraft piloting; and was a great chess player.

Clarke’s genius, and his vision of what artificial intelligence and machine learning might look like more than five decades into the future, has manifested itself in everything from automated factories and automobiles to our constant companions, Siri and Alexa. With the evolving dynamics of cloud storage and the ability to harness and proactively employ an ever-increasing pool of big data, AI in the form of machine learning and deep learning has become a disruptive technological force in the physical security industry.

The current stresses to security technology and policy to meet new COVID-19 safety mandates will expedite how AI is integrated into future security entrance solutions. The push for touchless and frictionless access options and the increase in contact tracing protocols at many organizations will expand the integration of secure entrances with building control systems to help provide additional insight into potential threats and mitigate them.

Kurt Measom serves as vice-president of technology and product support, and is part of Boon Edam’s Enterprise Account Security Team. A 25-year Boon Edam veteran, Measom, over the past four years, has worked as a security solutions advisor to many Fortune 1000 companies and is currently a Lenel-certified associate. Measom graduated from the University of Utah with BS and MBA degrees and currently lives with his wife and children in the Salt Lake City area, Utah.

Source URL: https://www.constructionspecifier.com/how-ai-can-improve-the-security-of-facility-entrances/

---