According to the researchers, the application of explainable artificial intelligence to Behavioral Internet techniques could help provide a more reliable and understandable framework for modifying human behaviors. According to a study, this combination of Internet of Things devices, artificial intelligence, data analytics and behavioral sciences can also bring benefits to users and businesses.
UK-based researcher Haya Elayan deepened the concept of Internet of Behaviors (IoB) and its integration with Explainable Artificial Intelligence (XAI) algorithms to observe the impact of changing behaviors related to the Internet of Things. IoB is the confluence of Internet of Things (IoT) devices combined with advanced sensors, computer vision, facial recognition, other biometric indicators or location tracking, which when they are added to the knowledge of human psychology and data analysis, can influence, incite or change humans. behavior – a powerful method.
“Nowadays, the use of IoT, cloud computing, and artificial intelligence (AI) has made it easier to track and modify user behavior by changing IoT behavior,” he says. she. Elayan presented his findings in September 2021 in the IEEE study, Internet of Behavior (IoB) and explainable AI systems to influence IoT behavioras well as Moayad Aloqaily and Mohsen Guizani, professors from Qatar University.
Elayan, who is currently pursuing a Masters in Data Science at University of Leeds in the UK and is also a research scientist for xAnalytics Inc., headquartered in Ottawa, Canada, created an XAI platform and leveraged the use of IoB to apply it to a home electricity consumption end-use case. The research aimed to change consumer behavior towards more environmentally friendly consumption patterns, thereby reducing energy consumption, energy waste and costs. Applying such a platform provided users with initial cost and energy savings, she reports.
“A system based on IoB and XAI has been proposed in an electric energy consumption usage scenario that aims to influence the user’s consumption behavior to reduce energy consumption and costs,” says- does she in the study. “The scenario results showed a decrease of 522.2 kilowatts of active power from baseline consumption over a 200-hour period. It also showed a total saving on energy costs of 95.04 euros for the same period.
Elayan asserts that during natural disasters or crises, in particular, such as a global pandemic, IoB and XAI can be used in meaningful ways to help improve or save lives. “Many behavioral aspects have been changed by the COVID-19 pandemic, such as customer interaction with brands, employee work procedures, and business engagement with consumers,” explains the researcher. “All of these and other examples have an economic, technological and physiological effect. Therefore, monitoring people’s behavior becomes crucial to influence it in adverse situations. For example, using machine learning for mask recognition tasks is a way to get people to follow regulations and watch for negligence.
The data scientist experienced an IoB-related environment first-hand when she was at home in Jordan during the pandemic; the experience led to the genesis of his research. “I was using apps to track my health and quarantining based on app data,” says Elayan. “If someone in our office was infected, we would receive a quarantine notification because we were in the same place with someone who was infected. This experience made me want to understand what monitoring was [aspect] was and how it influenced me. This is how the process started for me, generating my interest.
It’s the addition of XAI that makes the difference, she says, because it provides a layer of understanding for users, building their confidence during the behavior change process. “If we’re using AI to analyze user behavior, you can easily use XAI to let people understand what that AI model is doing and why, and just give a better insight into the system,” he explains. she. “Therefore, the process of tracking, analyzing and influencing behavior will become much easier as you develop a reliable platform with the user understanding what is going on, how it is happening and what is going on. “
The explainable approach also helps overcome a common challenge in using IoB called the ostrich effect. “There’s a challenge to the internet of behaviors called the ostrich effect, people basically being scared,” she says. “And you may encounter resistance when trying to influence and change people’s behavior because it’s a sensitive area. You are dealing with sensitive data and you are dealing with their behaviors. In order not to encounter this, or to manage this resistance and other psychological factors related to comfort and stress, XAI helps us to provide the user with the understanding and confidence required for the system that uses an AI model .
Elayan and the research team relied on IBM’s AI Explainability 360 to help explain the AI model. The study also had to ensure that cybersecurity elements protected data elements in motion, including anything that was returned to users, which is a key element of IoB’s ability to influence their behavior. “Because we transmit user data, we analyze it, we save it, we send the results back to the user. It was difficult to determine which security system to use,” admits Elayan.
However, selecting the appropriate artificial intelligence algorithm was not straightforward, the researcher points out. “[Another challenge] was using or choosing the right AI technique to implement in this system, because the structure of the data is quite different, the system and how it connected to our architecture [was unique]suggests Elayan. “And you’re using different technologies, you’re using the Internet of Things, you’re using smart meters, and you’ve got end users. So what’s the right AI technique to use to speed up the process, protect data, and enforce security systems and technologies at different levels and processes throughout the system?
Another complication was the lack of hardening of IoT devices and cybersecurity. “From an IoT perspective, security schemes are limited,” she notes. “Sometimes you need to develop your own security schemes to preserve data on IoT devices.”
Another problem was the lack of regulations and standards related to the ethical use of data, Elayan continues. “One of the major challenges of the Internet of Behavior is how companies apply user data and how they analyze it. Users should be aware of this because companies mostly try to gain their own benefits and make more money, and maybe they misuse or misuse user data. [when] behaviour change. To take advantage of it, they can harm the end customer just to make more money.
IoB can be a powerful tool, given that it focuses on human nature. The behavioral aspect of humans, and not necessarily other characteristics – such as cognition, emotion, personality and communication – is responsible for the tendency to act, and when combined with digital networks and devices , it is a powerful factor. First discussing the IoB in 2012, Professor Göte Nyman from the Department of Psychology at the University of Helsinki reportedly explained that if human behavior was attributed to devices with specific addresses, it would be possible to benefit from the knowledge acquired by analyzing the history of models in many companies, societal, health, political and many other fields. More than 10 years later, the commercial market for IoT sensors is expected to reach $22.48 billion by 2023, with 29.3 billion connected devices available, according to research produced by CISCO and cited by the researcher.
Elayan wants to apply the IoB to the medical industry, which would require additional standards and cybermeasures, she points out. The IoB, like any digital effort, when paired with patient data, could be subject to attack.
“Behavioral data is a type of sensitive and personal data, and its collection, storage or analysis must be accompanied by transparency and ethical use,” she notes. “The user has the right to be informed about this process as well as to know that their privacy is preserved and protected from abuse. But focusing on the behavior will let us know how to influence and treat the person,” says Elayan .
“I look forward to applying this technology to healthcare as I know we have promising results in saving electricity and I am sure that its application to healthcare will bring great added value.”