The value of AI in IoT analytics
In many parts of Asia, seasonal torrential rains lead to flooding that damages property and the livelihoods of citizens. While in the past city governments, citizens and businesses could do next to nothing but ride out unwelcoming flood waves and the potential illnesses they carry, technologies such as the Internet of Things (IoT), machine learning (ML), and artificial intelligence (AI) can provide respite for more forward-looking leaders.
This is the case of the DKI Jakarta Provincial Government‘s Flood Control System in the Jakarta Smart City App. Developped by Jakarta Smart City in collaboration with the Jakarta Water Resource Service (DSDA) to optimize flood risk management in Jakarta, the project involved the use of IoT, AI and ML as part of an early warning system against the risk of flooding in the city.
As more organizations deploy the IoT in commercial and industrial environments, the amount of data derived from these devices and sensors can prove significant in improving quality, operational efficiency and, in the case of Jakarta, saving lives and property from natural disasters.
Kenneth KohHead of Industrial Consulting at SAS Institute, asserts that the speed and accuracy with which an IoT system reacts to its environment is critical. However, with devices and other sensors in a typical system generating overwhelming amounts of data, traditional tools and methods can slow down the process of understanding that data.
Can you explain what AI-integrated IoT is?
Kenneth Koh: Processing data at the edge or near it enables IoT systems to be more agile and impactful. But the quality of a data-driven action is only as significant as the quality of the data-driven insights it acts upon.
The IoT itself is nothing new for manufacturers. Manufacturers have been collecting and storing machine sensor data for decades. The value proposition for them lies in AIoT – analyzing that data, at the edge in real time, using AI and ML to drive efficiency and value.
By equipping IoT systems with AI capabilities, a wide variety of data, structured and unstructured, can be processed at the edge. High-quality information is made available at increased speeds for systems to act on.
The AI-integrated IoT and how it unlocks business value
Kenneth Koh: AI-integrated IoT improves operational efficiency and productivity while reducing costs. It also drives innovation towards better customer service, better products, and faster product deployment to market.
Embedding AI in IoT devices enables edge computing, enabling the deployment of IoT systems in situations where consistent 5G networks are not available. For example, logistics providers can use IoT sensors in their transportation fleet to monitor the internal and external conditions of their vehicles, even in remote parts of vehicle routes.
In addition to edge computing, AI-embedded IoT uses machine learning to develop actionable insights from the terabytes of data an IoT system generates daily. In the example above, the data collected from these sensors is sent to the cloud in real time, allowing technicians to deal with vehicle breakdowns more accurately and much faster.
Manufacturers can also use this information to predict when a particular plant system or equipment would fail, allowing technicians to implement preventative maintenance. Proactive detection of faulty equipment saves valuable man hours while reducing costly unplanned downtime.
On the retail side, information from IoT systems can be used to identify optimal product prices and minimize disruptions to their supply chains.
ML and its role in IoT analytics
Kenneth Koh: Machine learning is the advantage of AI-embedded IoT over other IoT deployments. Systems can learn by processing data generated by sensors using various advanced analytical methods such as decision trees, random forests, gradient boosting, neural networks, support vector machines and factorization machines.
This creates savings for companies in terms of working hours and specialists in the organization. Without the need for extensive training in AI systems, specialists can focus on other critical tasks as non-data scientists can access, visualize and process the data.
Machine learning capabilities are also increasing the range of data that AI systems can access and process: online and offline visual images, text, and even verbal speech. The increase in the volume and quality of available data increases the value and impact of the resulting information.
Combined, these machine learning capabilities increase both the speed and volume of data processing, enabling real-time actionable insights that are crucial in many IoT systems.
How AIoT Supported Jakarta Smart City: Using SAS’s AI-powered platforms, Jakarta Smart City was able to integrate real-time multi-source data and provides advanced analytics with IoT, machine learning and AI technology to provide emergency/disaster forecasting capability and optimization to serve the public. The result is an emergency flood response to mitigate the risk of floods in Jakarta.
Since the IoT has historically been an operational technology, whose job is it to secure the IoT?
Kenneth Koh: The introduction of IoT is blurring the lines between IT and OT in enterprises. Sensors and devices are connected to the network to create new systems and improve processes. At the same time, this convergence exposes traditional OT equipment and systems to threats against which they were previously isolated.
The fact is, true device security is a combination of technologies, processes, and best practices. Thus, securing IoT systems should not be the exclusive domain of OT or IT teams, but lead to closer and more effective collaboration between the two.
However, this is easier said than done, as IT security teams and OT security teams often don’t speak the same language and struggle to understand each other’s point of view.
Responsibilities are distributed quite differently; priorities often diverge and regulations governing OT security and IT security can sometimes contradict each other. Obtaining an overview of all assets within a given environment makes it clear which assets and processes should never go down.
By doing so, organizations can establish and practice unified cybersecurity that ensures confidentiality, integrity, and availability of data.
Name a best practice for IT and operational technology staff working together.
Kenneth Koh: In the manufacturing sector, data is very time-sensitive. For example, if the chemical concentration of a process deviates from the optimum, the engineer may only have a few minutes to react and save several tons of product.
In many semiconductor processes, engineers have only seconds to react. In such situations, Analytics must move to the “edge”, which means that the data must be analyzed and decided at the machine or shop floor level, and not in the back office or engineering.
This requires the ability to perform analyzes where they are needed – on the machine, on the production floor, in the cloud or in the back office.
One of the biggest challenges is around data silos. For organizations that are not implementing IT/OT convergence, due to a patchwork of unintegrated or partially integrated business applications and systems. Without careful planning, the introduction of new data sources (eg IoT sensors) will compound the problem.
Implementing a data integration platform to connect IoT systems to organizations’ existing technology stack breaks down silos between historical and future data while providing all teams with the same access through a single point of contact. single control. This ensures that IT and OT teams are on the same page, establishing a foundation for better IT/OT convergence.