For several decades, people have captured and analyzed data to obtain valuable information. One of the lessons learned is that the more integrated the data we use to act, the more depth information has. This led to a second discovery, as crucial as the first: results and business value also increase when analytics, and not just data, are integrated, shares Rob Armstrong, data evangelist, and Teradata analytics.
Here comes into play the power of solutions that have driven and enabled integrated data models and complex analytics. In recent years, advanced analytics have been added, incorporated into the database, such as 3D geospatial (latitude, longitude, and elevation). Today, a further step has been taken and functions and time series have been added. In addition to the already existing temporary functions, to go further, to the next dimension: the fourth dimension of time.
When companies can combine, or overlay, analytics, they get information faster, and new results generate more value. Let’s quickly see some of the cases in which the dimensions of time and space in business analytics are integrated.
Transport and logistics
One of the most obvious use cases is transportation and logistics. Over the past few years, companies have been adopting predictive maintenance plans for their vehicles. By bringing together the functions of time series and geospatial, not only can they know when something is wrong, but also have a better understanding of why.
For example, two similar trucks show very different wear patterns, and it is necessary to find out the cause. From this first perception, you can find where the trucks traveled, the conditions (such as slope, weather or traffic), as well as the information provided by the sensors. A user can ask to be shown the wear and tear of the vehicle components when driving at high altitude and with a steep slope or that the engine is diagnosed on a winding road, compared to the journey on a straight highway.
When looking at both spatial and temporal perspective, there is a greater predictive capacity. As a result, distribution routes or vehicle type can be planned to minimize damage and increase productivity.
Mobility as a service
Let’s take this example a little further: to mobility as a service. Again, we can apply the dimensions of time and space to the management of a fleet of vehicles, but with the addition of temporary data to understand the availability of drivers or special events that happen within a specific area of the city.
By adding temporary periods, you can ask questions such as: “What is the expected passenger volume in Boston during the NBA playoffs, and what kind of vehicle do I need to have available quickly?” Another question could be: “What is the usual route for seniors in Phoenix between 10:00 and 16:00 on weekdays?” Thus, you can better plan the routes and offer discounts to maximize the number of passengers with lower expenses of the fleet.
We are already talking about using analytics and optimizing transport, so let’s look at smart cities and urban planning. Here, the ability to understand not only time but also the place of use is fundamental.
Trying to make the most of public services in urban areas is a complicated problem. The center of a city receives a great flow of people who come and go, with the sequential use of public services and a pattern of extreme fluctuations when the day ends and the night begins.
Urban planners should answer the following questions: “What is the difference in transportation patterns after having widened the road?” “Did we solve the problem or simply move the bottlenecks to other areas?” “Are transport centers aligned with peak and non-peak hours to minimize congestion and maximize the flow of people and products?”
To find the answers to these questions, the temporary data provided by the sensors located on the roads, those that capture the movement of pedestrians and the coordination of the traffic lights, all must be collected and integrated with temporary data, which identify the periods of activity, special events and road closures.
It is said that it is not enough to have the data: you have to analyze them. And this translates into the following requirement: we must act on analytics to obtain value and the action is developed in the peripheral devices when we are in the fourth dimension. At this point, timely and specific information is needed to achieve the best results.
An example that could be analyzed is between vehicles: peripheral devices receive and send information and sensors of cars collect data, but it is necessary to obtain them from all cars to understand the wide range of facts and potential results. The data is collected, analyzed, and then new rules and alerts are sent to all vehicles. This is a kind of “swarm intelligence” since we do not want every motorist to suffer an accident for learning to avoid it.
Another example of this nexus of time and space are taken to the periphery occurs in medical devices and wearables. Collecting data from all of them about the level of physical activity of the patients, as well as the variables of their location (weather, pollution, altitude, etc.) helps doctors to analyze the events better to treat new patients with a focus preventive.