Analytics as a concept is not new and has been there since the evolution of human being. However, in the past 20 plus years, there has been a systematic approach to Analytics based on data stored in a structured format, in computers. This is the concept of data-driven analytics. Initially, it was in the form of simple reports on operational data. Later with the advent of Storage technologies, there arose the concepts of historical storage called Data Warehouses and Data Marts. This gave rise to more advanced forms of Analytics like OLAP or Multi-Dimensional Analytics, Predictive Analytics and Prescriptive Analytics. Even the reporting has evolved based on these Historical Data, to show more complex Representations in the form of Dashboards, Graphs, Visual representation of data, leading to sophisticated Analytics tools called Visualization tools.
While this progress has been happening in the world of Analytics, there is a parallel, related and interesting development happening in the world of Image Processing. This is the usage of Cameras to build AR (Augmented Reality) applications. Better Telecom Bandwidths, Powerful Mobile cameras, AR techniques have made it possible now to View, Point, Detect and Transmit an Identified object's coordinates and other information to the Backend Systems for further processing.
There is also another technology called the Image Analytics, which can leverage the image captured by the AR application to do the relevant Image Analytics and pass it back to the AR application.
This article attempts to bring a Convergence of the above three Technologies Viz.: Visualization Technologies (backed by Huge Historical Databases or Big Data), Image Analytics and AR Technologies, to bring out the Next Generation Class of Analytics called as "Ground-Zero" Analytics.
Ground-Zero Analytics is basically trying to see the Descriptive, Predictive and Prescriptive Analytics, in Real-time at the Location where it is Happening, using Mobile Cameras, AR Technologies and Visualization Technologies.
Data has been around in computer systems for more than a few decades in the form of Files, Databases – either in Structured or Un-Structured forms. However, it is only recently that the data management has encompassed Huge Volumes, Variety and Velocity of data, to deliver faster processing to the downstream Reporting and Visualization applications.
The data is stored in files, Databases, Data Lakes, Data Warehouses, Subject oriented Data Marts, Analytical Databases – all with the single goal of providing valuable information to the downstream Reporting and Visualization applications – through which Business can view their data in multiple dimensions across time, place, products, people.
Data Visualization is the most Intuitive approach to depicting the Processed data to the Business Users. This uses various visualization techniques like Graphs, Plots, Tables and many more to show various sets of related data, in a single view to the Business User, so he or she can make an informed decision about their business scenarios. The current Data Visualizations tools and technologies talk about a Business Unit or Business area in the form of Data or Visuals and it is up to the Business User to have the domain knowledge of their Business or a photographic memory of their Business area, or branch or office or Warehouse or Stores.
Augmented Reality is the concept of the user seeing the reality upon which embedded information is also shown. This is not difficult to imagine. While watching a News Channel, we see the actual video footage (say of the Cricket Field) and on top of it we see Data being shown (maybe of the flight path of the ball). This is the simplest form of Augmented reality.
However, the AR (Augmented reality) in the context of Data Visualizations can get a bit more complex and much more Dynamic in nature. While the camera shows the Image of a particular domain, the domain itself is marked with specific points (either in a Marker or Markerless mode), such that when a particular Point in the Domain is in View of the Camera, the AR system can detect the Specific Point and then become aware of what that Specific Point is.
Example: When the camera is pointed toward a Refinery pipeline, the specific point on the pipeline can tell the AR system that this is a "Crude Oil" carrying pipeline toward the Main Refinery. It will also know based on the GPS coordinates of the "Crude Oil" carrying pipeline.
With this basic information about the "Crude Oil" carrying pipeline, like the Actual Image from the Camera, its GPS coordinates, and the Marker Inputs, being passed onto the AR system, there is now scope for Mashing this AR information with its related Analytics information, to derive newer forms of Analytics. This is the core concept of this article and is called "Ground-Zero-Analytics"
AR-based "Ground-Zero" analytics is the concept of using the AR-based information like Image, GPS coordinates, Marker information as inputs to a Backend Data Visualization Engine in realtime. The Backend Visualization Engine would then pull the relevant information about the "Marker" in context, build the necessary Charts, Graphs, Historical Summaries and then show in real-time these, Analytical Insights on the "Image" being looked at by the camera, with Zero Latency.
So, in our example, while the Camera is looking at the "Crude Oil" pipeline, at the same time the AR system would pass on information like the Image, GPS coordinates, Marker Inputs to the Data Visualization systems and Image processing systems.
The Data Visualization systems would pull out the "Crude Oil" pipeline-related information, from the databases, like Date of Installation, last Service or Inspection Date, Expected Lifetime of the Pipeline, Any History of Leakages, Breakages, Fire, etc for this "Crude Oil" pipeline. The Data Visualization system would then do the specified analysis and then build the necessary Dashboard, Graphs, Charts, or Additional Textual information – and then show it on the Screen as an Overlay on the Image being shown in the Camera – all in realtime.
In addition to the Data Visualizations, the AR systems will also pass the image of the "Crude Oil" pipeline to an Image Processing engine, to detecting any Faults, Cracks, etc. This would then be passed to the Analytical Systems and finally recommend "Preventive Maintenance" instructions on the Screen, again all in realtime.
Hence by converging AR technologies with Image Processing/Recognition and Data Visualizations, we can take the Analytics from a Backroom activity to "Ground-Zero" where the Report or Dashboard is being spoken or analyzed about, in realtime. This is the concept of the "AR-based Ground-Zero" analytics.
Shown below is a high-level Technical Approach to implementing an AR-based "Ground-Zero" analytics:
The AR system would expose their AR data to an AR Receiver which would then curate this data and then pass it to the Consuming Systems like Data Management, Visualization and Image Processing Applications.
These Consuming applications would then pass on their relevant Analytical insights to the Visualization Outputs, Text Outputs, Image Processing Outputs and Analytics Output Modules (as shown in the above diagram).
These Analytical Outputs would then be passed onto the AR Transmitter Custom Software Module, which would then pass on their relevant information back to the AR Scenes, which can then display the same as additional Data or Insights or Intelligence on top of the current Scene in view of the Display Screen.
AR-based Ground-Zero Analytics is the real-Time Avatar of the Offline Analytics that we are used to seeing on our Laptops and Mobiles in the form of reports, Dashboards and Visualizations, for the past few decades. While these serve our purpose fairly well, we still have to map (in our mind), the Real-World Scene/Domain about which this particular reports or dashboard or Visualization is talking about.
However, with an AR-based "Ground-Zero" analytics, we can implement the concept of "Get your Insights when you See it and Where you see it", in realtime.
This can be very useful in situations where latency is crucial and we cannot wait for the offline BI and Analytics systems to do their analysis and then enable us to do after-the-fact analysis. An opportunity for Sales or Preventive Care could be lost.
AR-based "Ground-Zero" Analytics can be the future of all reporting and Visualizations and if merged with the Digital-Viewing-Glasses, then we can be a walking-Encyclopaedia in the True-Sense.
There are hundreds of similar Use Cases as it is applicable to any Business Domain and any Industry like Newspaper, Advertising, Flyers, Books, Reference Books and Journals, Libraries, Detective Agencies, RTO offices, Traffic Violations, Legal Opinions, Medical Inference, Archaeology, Mining Industry, Port Management, Shipping Container Analytics and hundreds of other applications in all Domains of our lives and hence this concept of Ground-Zero Analytics is Ubiquitous in nature and only limited by our imagination, innovation and inquisitiveness.
In this article, an attempt has been made to using three existing technologies like Augmented Reality (AR), Data Visualizations (backed by Data warehouses and Predictive/Prescriptive Analytics) and Image Processing, to come out with a Next-Generation Reporting Concept of Realtime "Ground-Zero" Analytics. Ground-Zero Analytics is not a complicated concept, it just involves the integration of Outputs/Inputs from AR, Data Visualization and Image Processing engines, to generate Augmented Analytics on top of the Realtime Scene being Viewed. This would enable the users to have Realtime relevant and additional data about their object in view, and thus make intelligent and Data-Driven decisions in real-time.
Ground-Zero Analytics could soon be the new normal for all Operational Analytics, which can co-exist with the traditional Reports, Dashboards and Visualizations which would be used for Offline after-the-fact analysis on a detailed level over a historical period of time.
Ground-Zero Analytics is basically trying to see the Descriptive, Predictive and Prescriptive Analytics of an Object-in-View in Real-time at the Location where it is Happening, using Mobile Cameras, AR Technologies, Visualization Technologies and Image Analytics – thus making it a solid platform for the Intelligent Viewing Glass Assistant of the Near-Future.
The author, Harikrishna S Aravapalli, is a Software professional with around 20+ years of IT experience in the areas of Data, Data warehousing, Business Intelligence, Predictive Analytics, Social Medial Analytics, Visualization in various roles like Developer, Technical Lead, BI Architect, Manager and a Solution Architect. He is currently working as a Senior Solution Architect in the areas of Data, Analytics and Advanced Analytics in a major IT company in their Data & Analytics practice. His email id is krishpalli123@gmail.com
Join our WhatsApp Channel to get the latest news, exclusives and videos on WhatsApp
_____________
Disclaimer: Analytics Insight does not provide financial advice or guidance. Also note that the cryptocurrencies mentioned/listed on the website could potentially be scams, i.e. designed to induce you to invest financial resources that may be lost forever and not be recoverable once investments are made. You are responsible for conducting your own research (DYOR) before making any investments. Read more here.