Analytics and the Internet of Things

The original conception of the Internet of Things (IoT) was of a network of physical objects or “things” embedded with electronics, software, sensors, and connectivity to enable objects to exchange data with a centralized operator and/or other connected devices.

Smart grids, smart homes and smart cities were all representations of what an IoT could be/do.

The IoT equivalent of the human brain is the cloud-based analysis of the data rising up from sensors to generate insights and decide on actions. Much of the benefit of the Internet of Things lies in our ability to leverage the (useful) data we collect with it. This is the “analytics of things,” and this area has, in many ways, received the least attention of all. This is unfortunate, because it is analytics that can add the most business, lifestyle, and health value to the IoT. It has been said that “data without meaning, without soul, will not move people to change their behaviors over the long term.”1 Value-added analytics are what many early adopters of activity trackers believe has been most missing and disappointing.

Sensor data have some unique attributes, so related analytics are unique as well. The data are typically continuous and fast-flowing, so there must be processes for continuous analysis of the data. Technologies such as “complex event processing” and “event stream processing” bring the data to the analysis capability, where they are processed in real time, and then results are sent back where they are needed. Because there is so much data, a major focus of the analytics of things is anomaly detection. Is something broken in our operational network? Does a bike ride appear to be in the middle of a corn field? Are you about to end the day without reaching 10,000 steps? Analytics can identify situations that require some form of human intervention.

Some other typical analytical applications for the IoT include the following:

  • Comparative usage—how your consumption of a resource (for example, calories) compares with others in similar situations
  • Understanding patterns and reasons for variation—developing statistical models that explain variation
  • Predictive asset maintenance—using sensor data to detect potential problems in machinery (or your body) before they actually occur
  • Optimization—using sensor data and analysis to optimize a process, as when a lumber mill optimizes the automated cutting of a log, or a poultry processor automates the preparation of a chicken, or when is the healthiest time to go to sleep or when in your sleep cycle to wake up
  • Prescription—employing sensor and other types of data to tell the user what to do, as when an activity tracker nudges you to get off the couch or sit up straight
  • Situational awareness—piecing together seemingly disconnected events and relating them to a larger repository of data to put together an explanation, as when a series of readings from activity trackers, glucose monitors, connected scales, and other devices tells you that you are in danger of contracting diabetes

The analytics of things is often a precursor to cognitive action—taking action based on the results of analyzed sensor data. Comparative usage statistics, for example, might motivate an energy consumer to cut back on usage, while smart thermostats can monitor and optimize the household environment. Predictive asset maintenance suggests the best time to service machinery, which is usually much more efficient than servicing at predetermined intervals. A municipal government could analyze traffic data sensors in roads and other sources to determine where to add lanes and how to optimize stoplight timing and other drivers of traffic flow.

Data Mining vs. Machine Learning vs. Deep Learning

Data Mining

Data mining can be considered a superset of many different methods to extract insights from data. It might involve traditional statistical methods and machine learning. Data mining applies methods from many different areas to identify previously unknown patterns from data. This can include statistical algorithms, machine learning, text analytics, time series analysis and other areas of analytics. Data mining also includes the study and practice of data storage and data manipulation.

Machine Learning

The main difference with machine learning is that just like statistical models, the goal is to understand the structure of the data – fit theoretical distributions to the data that are well understood. So, with statistical models there is a theory behind the model that is mathematically proven, but this requires that data meets certain strong assumptions too. Machine learning has developed based on the ability to use computers to probe the data for structure, even if we do not have a theory of what that structure looks like. The test for a machine learning model is a validation error on new data, not a theoretical test that proves a null hypothesis. Because machine learning often uses an iterative approach to learn from data, the learning can be easily automated. Passes are run through the data until a robust pattern is found.

Deep learning

Deep Learning combines advances in computing power and special types of neural networks to learn complicated patterns in large amounts of data. Deep learning techniques are currently state of the art for identifying objects in images and words in sounds. Researchers are now looking to apply these successes in pattern recognition to more complex tasks such as automatic language translation, medical diagnoses and numerous other important social and business problems.

Machine Learning and IoT

Machine learning has experienced a boost in popularity among industrial companies thanks to the hype surrounding the Internet of Things (IoT). Many companies are already designating IoT as a strategically significant area, while others have kicked off pilot projects to map the potential of IoT in business operations.

As a result, nearly every IT vendor is suddenly announcing IoT platforms and consulting services.

But achieving financial benefits through IoT is not easy. The lack of concrete objectives is disconcerting. The advancement of digitization and IoT places new prerequisites on both buyers and sellers. Many businesses have failed to clearly determine what areas will change with the implementation of an IoT strategy.

In other words, clearly defined, concrete intermediary objectives are missing. For example, industrial companies produce a massive amount of data on a daily basis. However, by and large, companies fail to systematically collect, store, analyze and use such data to improve process efficiency or meet other goals.

Furthermore, not many vendors are able to establish, in concrete terms, to the client how to prudently create positive impact on business operations with IoT solutions. Simply the promise of a cloud-based IoT platform is not enough.

2017 IIoT Security Survey

2017 IIoT Security Survey

“Industry professionals know that the Industrial Internet of Things security is a problem today. More than half of the respondents said they don’t feel prepared to detect and stop cyber attacks against IIoT,” said David Meltzer, chief technology officer at Tripwire. “There are only two ways this scenario plays out: Either we change our level of preparation or we experience the realization of these risks. The reality is that cyber attacks in the industrial space can have significant consequences in terms of safety and the availability of critical operations.”

Technavio – Global IIoT Sensors Market in Oil and Gas Industry 2018-2022

Market analyst firm Technavio has a new report that provides a comprehensive analysis of the global IIoT sensors market in oil and gas industry by product such as temperature sensors, flow sensors, flow sensors, pressure sensors, and other sensors. The report also provides a comprehensive analysis of the growth opportunities for companies in this market in regions such as the Americas, APAC, and EMEA.

The growing focus of the oil and gas industry on reducing the cost is encouraging them to adopt IIoT sensors as the installation of these sensors takes less time. In addition, the sensor manufacturers are increasingly offering sensors with easy assembling options and technical advancements. Moreover, the rising competition among major manufacturers of sensors and service providers of IoT products is increasing, which in turn, will boost the adoption of these sensors in the oil and gas industry. Research analysis on the global IIoT sensors market in oil and gas industry identifies that the growing commercial acceptance of IIoT sensors will be one of the major factors that will have a positive impact on the growth of the market. Technavio’s market research analysts predict that the market will grow at a CAGR of more than 5% by 2022.

The preference for industrial internet of things enabled smart asset monitoring solutions add intelligence to automated workflows, real-time alerts, dynamic edge control of assets, cross-domain analytics, insights from data, real-time visibility, and predictive maintenance. This is driving the adoption of smart asset monitoring, which in turn, is identified as one of the key trends that will stimulate growth in the IIoT sensors market in oil and gas industry throughout the projected period.

GE – The Industrial Internet of Things for Developers

GE recently launched a new book, Industrial Internet of Things for Developers, that explains much of what needs to be understood by those interested in and tasked with developing applications for the Industrial Internet of Things (IIoT). Foremost among these is that if you are going to create applications for the IIoT, the development process must change.

Forbes technology contributor Dan Woods provided a review of the book, highlighting how it helps orient developers to the unique elements of IIoT by focusing on four areas:

  • Systems at the edge. Developers must understand the different characteristics of edge systems, which may be anywhere: on high-speed rail, under the ocean, in a factory, down a mine shaft, and more. The book shows the differences between OT and IT applications, highlighting how much more static the OT world is. With OT, the top priority is always to keep operations going, rather than embracing rapid change. Developers will have to understand fully how these edge systems function before being able to build effective apps.
  • Changes to platform development. The book also suggests that platform development must change. In the traditional world of development, full stack developers build applications from the ground up. But there is a new stack on the edge and if you’re going to build applications on the edge that connect centrally, you need a platform that can communicate from the edge to the cloud. That platform must have a distributed architecture, with end-to-end security and be able to handle the unique types of data edge devices generate. Data must be able to flow from the edge to the platform, where it can be transformed and analyzed. But control of the entire process must be able to flow down from the enterprise level, through the platform, to the edge. Security is important, because edge devices are especially vulnerable.
  • Digital twins. To create applications that provide an ability to understand what’s happening with advanced equipment, companies will need to create digital twins. These are electronic doppelgangers of physical equipment that use sensor-generated data from that equipment to create digital replicas. With digital twins, you can monitor the physical world digitally. And you can do so on whole fleets of equipment. In the past, an operator would put his hand on pump and see if its vibrations indicated it was working improperly. With digital twins, you can put a digital hand on every pump at all times to see how everything is operating, and see the relationships between all your equipment and devices. The result is a much improved ability to assess the functioning of your equipment, as well as the ability to optimize your systems, and detect problems proactively, rather than reactively. IIoT applications must be able to incorporate digital twin data.
  • New IIoT development teams. The book also highlights the need for companies to create different teams to build IIoT applications than they have had for applications in the past. Instead of creating applications with just an app developer and a business analyst, you need people who are the experts in the edge environment and the many standards and protocols there, full stack developers, domain experts who understand the physics of the equipment and can help create digital twins, and data scientists who can analyze the data generated by it. This brings in a wider range of skill sets. Assembling such a team is only the first step—you have to package their accumulated knowledge into components that can be used over and over again across the business. In addition to using traditional development techniques, these teams will have to be able to knit together applications with low code environments, as not every person involved in application development will have extensive coding skills. Finally, the development process—particularly as it relates to voluminous edge data—will also become more automated and assisted by machine learning.

Cisco – Patent Application for Blockchain, IoT Integration

Cisco has recently filed a U.S. patent application for an invention that it describes as a, “Block Chain Based IoT [Internet of Things] Device Identity Verification and Anomaly Detection.”

The concept has to do with enabling a blockchain-based system that could record changes to the conditions affecting and captured by sensors (i.e., smart objects) in a network and instrumentalize network relationships and the data that the network generates in order to exercise control over those nodes.

The application lists “the smart grid, smart cities, and building and industrial automation” among the types of Low-Power and Lossy Networks (LLNs) that might operate more efficiently with the integration of the invention. The smart objects/sensors that could, at least partially, comprise these networks include “lights, appliances, vehicles, HVAC (heating, ventilating, and air-conditioning), windows and window shades and blinds, doors, [and] locks,” as well as actuators – automated devices that can, for instance, start an engine.