The Internet of Things and Artificial Intelligence are two of the hottest topics in technology, which is a good reason why enterprise technologists should understand them. The two technologies are very complementary, so it is important to plan how to support each other to benefit enterprise users.
What is the Internet of Things?
The Internet of Things is a network of devices, not people. IoT applications are typically built from devices that sense real-world conditions and then trigger actions to respond in some way. Response often includes 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 complex rules to associate triggers and actions.
Messages that are triggers and actions/commands in IoT flow through what is usually called control loop. The part of the IoT application that receives the triggers and initiates the actions is the central point of that loop and the place where the IoT rules are.
The control loop is only a 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 the manifest when entering the warehouse may open the gate to the driver – the decision of the control loop – and also creating a transaction for the receipt of goods represented in the manifest in stock – a business transaction. Decisions made in the control loop must meet application latency requirements, often referred to as Length from the control loop.
Control loops often only require simple manipulation to close the loop and generate a true response to an event. Entering a code to open a gate is an example. In other cases, the processing needed to make a decision is more complex. When processing must apply more decision factors, the time required to make these decisions can affect the length of the control loop and the ability of the IoT to provide the expected features. A half-minute delay in a worker scanning a manifest before a truck is brought into the freight yard, for example, can reduce yard capacity. The Internet of Things can read the QR code in the manifest and make the necessary decisions faster, which will speed up the movement of goods.
What is artificial intelligence?
Artificial intelligence is a class of applications that interpret conditions and make decisions, similar to how people respond to their senses, but without the need for direct human intervention.
There are three broad forms of artificial intelligence in use today, which are as follows:
- Simple or rule-based AI A program that contains rules or policies that link triggered events to actions. These rules are programmed, so some people may not recognize this as a form of artificial intelligence. However, many AI platforms rely on this strategy.
- machine learning (ML) It is a form of artificial intelligence where an app learns behavior rather than programming it. Learning can take the form of observing a living system and relating human responses to events, then repeating it when the same conditions occur, either by analyzing past behaviors or having an expert provide the data.
- Heuristics or neural networks Use artificial intelligence to build a “engine” designed to mimic a simple biological brain and make inferences that generate responses to stimuli based on what the motor “infers” conditions. Today, this technique is most often applied to image analysis and complex analytics.
All three of these forms of AI are designed to represent human intelligence, but their ability to represent something so close to actual human intelligence is greater as you advance through the three in the order above.
How can the Internet of things and artificial intelligence support each other?
In the Internet of Things, real-world events are referenced and manipulated to create an appropriate response. In a simple sense, then, any IoT application that uses software to generate a response to a trigger event is at least a basic form of AI, and hence AI is essential to the IoT. The question for IoT users and developers is not whether they will use AI, but to what extent AI can be used. It depends on the complexity and diversity of the real-world IoT support system.
An AI based on simple rules might say “if the power button is pressed, turn on light A,” and a more complex development might say “if the power button is pressed, And it’s darkAnd the Turn on the light a. “This is not just event recognition (the power switch), but also event recognition (it’s dark). Programmers use state/event tables to describe how to interpret a series of events in multiple states, but this only works if there are a finite number of states which are easily identifiable.
Referring to the example of a truck arriving at a warehouse and goods for storage, simple AI could provide a way for a driver to enter a code to pass through a security gate. This would eliminate the cost of hiring a worker attending the gate. It is also possible to read the barcode or RFID tag on the vehicle itself and allow entry without entering a code. This will allow the truck to continue moving as its right of entry has been validated, speeding up the process.
If more conditions are to be analyzed to determine the response to an IoT event, the process falls outside the capabilities of a simple AI application. if it was it’s dark One case called, I need more lightand the IoT system was responding not to a specific switch but to the task the person was trying to do, a simple AI would not suffice.
In this case, an ML AI model might monitor the arrival of a truckload of goods at the warehouse. Over time, it can learn when drivers and workers need more light and activate the switch without having to act. Alternatively, the expert may perform the expected tasks and “teach” the program when more light is appropriate. The AI/ML software then eliminates the need for a programmer to build each IoT application.
In the inference form of artificial intelligence, an IoT application attempts to gather as much information as possible, simulating what a person is feeling. Then rules of inference are applied, such as People cannot work where the light levels are less than xand from the concrete conditions and application of those rules, decides to turn on the light.
Inference-based AI requires more complex software to collect conditions and define inference rules, but it can respond to a wide range of conditions without being programmed. The same level of inference processing can determine whether additional workers should be assigned to offload, because goods are urgently needed, work is behind schedule or simply because workers are available. All this can improve the movement of goods and the general efficiency of truck drivers and warehouse personnel.
The Internet of Things is about using computer tools to automate real-world processes, and like all automation tasks, it is expected to reduce the need for direct human participation. Although the Internet of Things aims to limit human action, it does not eliminate the need for human judgments and decisions. This is where AI can step in and significantly improve the IoT system.