IoT and AI are two of the hottest topics in tech, which is a good reason business technologists need to understand them. The two technologies are very symbiotic, so planning how they can support each other to benefit business users is critical.
What is IoT?
IoT is a network of devices rather than people. IoT applications are typically built from devices that sense real-world conditions and then trigger actions to respond in some way. Often the answer includes steps that influence the real world. A simple example is a sensor that, when triggered, turns on some lights, but many IoT applications require more complicated rules to link triggers and actions.
Messages representing triggers and actions/commands in IoT flow through what is commonly called a control loop. The part of an IoT application that receives the triggers and initiates the actions is the central point of that cycle and the place where the IoT rules reside.
The control loop is only one part of the total 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 could open the door for the driver (a control loop decision) and also trigger a transaction to receive the goods represented in the manifest into inventory (a transaction). commercial). . Decisions made in the control loop must meet the latency requirements of the application, which are often referred to as length of the control loop.
Control loops often only require simple processing to close the loop and create an actual response to an event. Entering a code to open a door is an example of this. In other cases, the necessary processing to decide is more complicated. When processing must apply more decision factors, the time required to make these decisions can affect the length of the control cycle and the ability of the IoT to provide the expected features. A half-minute delay in a worker scanning a manifest before admitting a truck to a loading yard, for example, could reduce the yard’s capacity. IoT could read a QR code on the manifest and make the necessary decisions much faster, speeding up the movement of goods.
What is AI?
AI is a class of applications that interpret conditions and make decisions, similar to the way people respond to their senses, but without requiring direct human intervention.
There are three broad forms of AI in use today, which are as follows:
- Simple or rule-based AI it is software that has 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 are based on this strategy.
- Machine learning (ML) it is a form of AI in which the application learns the behavior instead of having it programmed. Learning can take the form of monitoring a live system and relating human responses to events, and then repeating them when the same conditions occur, either by analyzing past behaviors or having an expert provide the data.
- Inference or neural networks use AI to build an “engine” that is designed to mimic a simple biological brain and make inferences that generate responses to triggers based on what the engine “infers” the conditions to be. Today, this technology is most often applied to image analysis and complex analysis.
All three forms of AI are designed to represent human intelligence, but your ability to represent something even close to real human intelligence is greater the further you go through all three in the order above.
How can IoT and AI support each other?
In IoT, real-world events are signaled and processed to create an appropriate response. So, in a simple sense, any IoT application that uses software to generate a response to a triggering 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 to use AI, but how far AI can be taken. That depends on the complexity and variability of real-world system IoT supports.
Simple rule-based AI would say “If the trigger is pressed, turn on light A”, and a more sophisticated evolution might say “If the trigger is pressed, and it’s dark, turn on light A”. This represents not only event acknowledgment (trigger-switch), but also state acknowledgment (it’s dark). Programmers use event/state tables to describe how a series of events is interpreted in multiple states, but this only works if there are 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 a means for the driver to enter a code to pass through a security gate. This would eliminate the cost of hiring a worker to answer the door. It is also possible to read a barcode or RFID tag on the vehicle itself and allow entry without entering a code. This would allow the truck to keep moving while its right of entry was being validated, further speeding up the process.
If more conditions must be analyzed to determine a response to an IoT event, the process falls outside the capabilities of the simple AI application. If he it is dark state was replaced by one called, I need more lightand the IoT system was to respond not to a specific activation switch but to the task a person was trying to accomplish, simple AI would not suffice.
In that situation, the ML form of AI could monitor the arrival of a truck full of goods at the warehouse. Over time, it could learn when drivers and workers need more light and flip the switch without the person having to act. Alternatively, an expert could perform the expected tasks and “teach” the software when more light would be appropriate. AI/ML software would eliminate the need for a programmer to build each IoT application.
In the form of AI inference, the IoT application tries to collect as much information as possible, mimicking what a person feels. Then apply rules of inference, such as people cannot work where light levels are below xand based on the intuited conditions and the application of said rules, he decides to turn on a light.
Inference-based AI requires more complicated software to collect conditions and define inference rules, but can respond to a broader range of conditions without being programmed. The same level of inference processing could determine whether additional workers should be assigned to offload, because goods are urgently needed, work is running late, or simply because workers are available. All of this could improve the movement of goods and the overall efficiency of truck drivers and warehouse staff.
IoT is about using computing tools to automate real-world processes, and like all automation tasks, it is expected to reduce the need for direct human involvement. Although IoT is aimed at reducing human labor, it does not eliminate the need for human judgments and decisions. That is where AI can step in and significantly improve the IoT system.