IoT and AI are two of the most popular topics in technology, and that’s a good reason why business technologists need to understand them. The two technologies are highly symbiotic, so planning how they can support each other for the benefit of business users is critical.
What is IoT?
IoT is a network of devices rather than people. IoT applications are normally built from devices that detect real-world conditions and then trigger actions to respond in some way. Often the reaction involves steps that affect the real world. A simple example is a sensor that, when activated, turns on some lights, but many IoT applications require more complicated rules to link triggers and actions.
The messages representing triggers and actions/commands in IoT flow through what is usually a . is called control loop† The part of an IoT application that receives the triggers and initiates the actions is the center of that loop and where the IoT rules reside.
The control loop is only part of the overall information flow in an IoT application — the part that actually receives information about real-world process conditions and generates real-world responses. Most IoT applications also generate some business transactions. For example, reading a shipping manifest at the entrance to a warehouse can open the gate for the driver – a control loop decision – as well as generate a transaction to receive the goods on the manifest into inventory – a business transaction. Decisions made in the control loop must meet application latency requirements, which are often referred to as the length of the control loop.
Control loops often require just simple processing to close the loop and create a real response to an event. An example of this is entering a code to open a gate. In other cases, the processing necessary to make a decision is more complicated. When processing needs to apply more decision factors, the time it takes to make these decisions can affect the length of the control loop and the ability of IoT to provide the expected functions. For example, a half-minute delay by having an employee scan a manifest before allowing a truck into a freight yard can reduce the capacity of the yard. IoT could read a QR code on the manifest and make necessary decisions much faster, speeding up goods traffic.
What is AI?
AI is a class of applications that interpret circumstances and make decisions similar to the way humans respond to their senses, but without the need for direct human intervention.
There are three broad forms of AI in use today, namely:
- Simple or rules-based AI is software with rules or policies that relate trigger events to actions. These rules are programmed, so some people may not recognize this as a form of AI. However, many AI platforms rely on this strategy.
- Machine Learning (ML) is a form of AI where the application learns behavior instead of having it programmed. Learning can take the form of monitoring a live system and relating human reactions to events, then repeating them when the same circumstances arise, either by analyzing past behavior or having the data provided by an expert.
- Inference or neural networks use AI to build an “engine” designed to mimic a simple biological brain and draw inferences that generate responses to triggers based on what the engine “infers” from the conditions. Today, this technology is most commonly used in image analysis and complex analyses.
All three of these forms of AI are designed to replace human intelligence, but their ability to represent something even approaching actual human intelligence increases as you progress through the three in the above order.
How can IoT and AI support each other?
In IoT, real world events are signaled and processed to create an appropriate response. Simply put, any IoT application that uses software to generate a response to a trigger event is at least a basic form of AI, and AI is then essential to IoT. The question for IoT users and developers is not whether AI should be used, but how far AI can go. That depends on the complexity and variability of the real-world system supporting IoT.
Simple rules-based AI would say “When the trigger switch is pressed, light A turns on”, and a more advanced evolution might say “When the trigger switch is pressed, and it’s dark† turn on light A.” This represents not only event recognition (trigger switch), but also state recognition (it is dark). Programmers use state/event tables to describe how a sequence of events is interpreted in multiple states, but this only works if there is a limited number of states that can be easily recognized.
Referring to the example of a truck arriving at a warehouse with goods to store, simple AI could provide the driver with a means to enter a code to go through a security gate. This would eliminate the cost of hiring an employee at the gate. It is also possible to read a barcode or RFID tag on the vehicle itself and grant access without entering a code. This would allow the truck to continue driving while validating its right to enter, further speeding up the process.
If more conditions need to be analyzed to determine a response to an IoT event, the process is beyond the capabilities of the simple AI application. As the it is dark state was replaced by one called, I need more lightand the IoT system would not respond to a specific trigger switch, but to the task a person was trying to perform, simple AI would not be enough.
In that situation, the ML form of AI can track the arrival of a truckload of goods in the warehouse. Over time, it could learn when the drivers and workers needed more light and activate the switch without the person having to do anything. Alternatively, an expert can perform expected tasks and “learn” the software when more light would be appropriate. AI/ML software would then eliminate the need for a programmer to build each IoT application.
In the inference form of AI, the IoT application tries to collect as much information as possible, mimicking what a person feels. It then applies inference rules, such as: people cannot work where the light level is lower than xand from the perceived circumstances and the application of those rules, decides to turn on a light.
Inference-based AI requires more complicated software to collect conditions and define inference rules, but it can respond to a wider range of conditions without being programmed. The same level of inference processing could determine whether additional workers should be assigned to unloading because the goods are urgently needed, work is behind schedule, or simply because workers are available. All of this could improve freight traffic and the overall efficiency of truck drivers and warehouse workers.
IoT is about using computer tools to automate processes in the real world, and like all automation tasks it is expected to reduce the need for direct human participation. While IoT aims to reduce human work, it does not eliminate the need for human judgments and decisions. That’s where AI can step in and significantly improve the IoT system.