As we know from recent events, the digital transformation of people’s lives has become a relentless force. Network connectivity is both extending its geographic reach and multiplying as 5g and FTTP networks become available in an increasing number of places. The computational power of devices continues to increase, cloud computing has become more cost effective and IoT devices themselves get smaller and more broadly implemented. Advances in sensor technology are turning everyday objects into sources of data. The combination of these trends has led us to a new place. It is now possible for a network of physical objects (vehicles, buildings, infrastructure…
As we know from recent events, the digital transformation of people’s lives has become a relentless force. Network connectivity is both extending its geographic reach and multiplying as 5g and FTTP networks become available in an increasing number of places. The computational power of devices continues to increase, cloud computing has become more cost effective and IoT devices themselves get smaller and more broadly implemented. Advances in sensor technology are turning everyday objects into sources of data. The combination of these trends has led us to a new place. It is now possible for a network of physical objects (vehicles, buildings, infrastructure, equipment of all shapes and types) to collect and exchange data and to work together. This enables devices, sensors, and systems to operate autonomously in pursuit of goals and objectives set by the human architects of the system.
How Location Intelligence transforms raw data into actionable intelligence
Knowing where something is located is a critical piece of contextual information that is integral to the successful function of the IoT. Take the example of road safety systems in a connected car. When the car senses slippery conditions its road traction systems respond within a fraction of a second to keep it on the road. It does that automatically, without needing to know where it is. However, that knowledge about a slippery road is immensely valuable to other road users if they too are likely to come across the adverse conditions.
Location data can be used in three main ways:
1) Descriptive analytics - ‘What happened?’
Data mining and analysis gives us insight into historical data. By transmitting the location of the hazard, the car can warn other cars in that area of the risk.
2) Predictive analytics - ‘What will happen?’
Use of modelling techniques to forecast the future. By collecting historical data from millions of vehicles over time and relating to weather data by location, the system can predict where and when slippery conditions will occur and warn cars before the risk is even encountered.
3) Prescriptive analytics - ‘What should be done?’
Scenario modelling and simulation to evaluate the impact of remedies. By modelling the impact of alternative solutions on the locations of interest we can rank alternative solutions based on success criteria and choose the option that minimises or eradicates the hazard.
Geo-analytics within the system
Geo-analytics enables us to answer questions which have in the past been difficult to answer, either because of lack of data or because of lack of computational power.
• What is happening in this area?
• What other things are close by?
• In what other places is a similar situation present?
• Where have we seen this before?
• Where might we see this in the future?
Traditional Geographic Information Systems (GIS) use maps to present geographic information in a way humans can understand. Geographic information is central to the IoT, but the map’s primary role is to help people when visualising the data. Within the system, sophisticated spatial queries and geo-processing algorithms built in to IoT platforms can connect data that was previously unconnected. This gives geospatial information a central role in the IoT data market described above.
ArcGIS Velocity – Big Data Spatial Analytics
Esri is taking this a step further and has this month launched ArcGIS Velocity, a new real-time and big data capability for Esri’s geospatial cloud. It enables users to ingest, visualise, analyse, store, and act upon observation data from sensors and IoT devices.
ArcGIS Velocity offers both real-time and big data analysis, with tools for geofencing, incident detection, and trend assessment. Real-time event data can be filtered, processed, and sent to multiple destinations, allowing you to connect virtually any type of streaming data and automatically alert personnel when specified conditions occur.
Users can also design analytic models to process high-volume historical data and gain insights into patterns, trends and anomalies.
Key capabilities include:
Connect to real-time, streaming IoT data from multiple feeds and visualise directly in maps.
Speed up your analysis and gain answers faster when you set up analytical models in the cloud.
• Alert and actuate
Act on this geo-spatial analysis by sharing the results and alert stakeholders when it matters.
ArcGIS Velocity will transform organisations by allowing them to truly understand, in real time, events as they unfold and offer descriptive, predictive & prescriptive analytics to inform operations, as well as enhanced business intelligence.
For more information please visit esriuk.com/velocity or contact email@example.com
Want to know more? Esri are exhibiting at this year's Total Telecom Congress 2020 virtual event, 27th & 29th October 2020. Register your place now for more information.