記事

Taking Analytics to the 4th Dimension

4D analytics combines geospatial, temporal and time series data to do advanced analysis of time and space. Learn how to uncover new insights today.

Rob Armstrong
Rob Armstrong
2019年9月5日 4 分で読める
4D analytics and smart cities
For many years, people have captured and analyzed data to gain insights. One of the lessons learned over time is that the more the data being acted on is integrated, the more insight is deepened. This has led to a second, equally important realization: Business value and outcomes are also increased when the analytics themselves, not just the data, are integrated.

This is where the power of the Teradata comes into play. Over the years Teradata has driven and enabled integrated data models and complex analytics. In recent years we added advanced in-database analytics such as 3D geospatial (latitude, longitude, and elevation). Now we take the next step by adding time series data and functions, in addition to already existing temporal capability, to take you further: To take you to the next dimension – 4th dimension of time.

What is 4D Analytics

4D analytics is advanced analytics that combines geospatial, temporal and time series data to make it quicker and easier for businesses to analyze time and space, especially for IoT and other edge computing applications that process variable time and location data.
4D-analytics-blog_600x400a.jpg
When businesses can combine – or layer – analytics, business insight happens faster and new outcomes provide higher value. Teradata accelerates your ability to adapt to change, and when time is money, this gives your business a huge competitive advantage. Let’s take a quick look at some use cases of integrating time and space dimensions into your business analytics.
When businesses can combine – or layer – analytics, business insight happens faster and new outcomes provide higher value. Teradata accelerates your ability to adapt to change, and when time is money, this gives your business a huge competitive advantage.

Transportation and Logistics

One of the most obvious use cases is in the transportation and logistics arena. For the past few years, companies have been moving to predictive maintenance plans for their vehicles. By adding geospatial and time series capabilities together they can not only know when things are going wrong but also have a better understanding as to why.

For example, two similar trucks are showing significantly different wear patterns, but the question is why. Based on your initial insight, you can now look to see where the trucks have been driving, the conditions such as road slope, weather, traffic, as well as the sensor information. A user can now ask “Show me the wear and tear on vehicle parts when driving at high altitude and steep slope” or “Give me engine diagnostics where the road contains ess-curves versus a straight highway.”

By looking at both the space and time perspective, there is greater predictive capability. As a result, you then have the opportunity of planning delivery routes or type of vehicles to minimize breakage or increase productivity.

Bottom line benefit: Optimize fleet effectiveness, reduce costs, improve customer satisfaction.

Mobility as-a-service

Let’s take this example a little further into the arena of mobility as-a-service. Again, we can apply the time and space dimensions for fleet management but with the addition of temporal data to understand driver availability or special events within a defined city area.

By adding the temporal periods, you can now ask questions such as “What is the expected rider volume in Boston during the NBA playoffs, and what type of cars do I need to have readily available?” Another possible question can be “What is the typical trip for senior citizens in Phoenix during the hours of 10:00 and 4:00 on weekdays?” As a result, you can plan for better ride-pooling and offer discounts to maximize ridership with reduced fleet expenses.

Bottom line benefit: Optimize for best customer experience, max efficiency, max profitability.

Smart Cities

Since we touched on using analytics and optimizing transportation, let’s go another step further into the arena of smart cities and urban planning. Here the ability to understand not only the time of usage but also the location of usage is of paramount importance.

Trying to maximize public services in the urban area is a tricky problem. A city center is a constant ebb and flow of humanity, of utility usage, with extreme pattern shifts as day turns to night.

City planners need to answer questions such as “What are the difference in traffic patterns after widening the road in 2017?” “Did we resolve a problem or simply move the bottlenecks to other areas of the city?” “Are the transportation centers aligned to the peaks and events to minimize congestion while maximizing the flow of people and products?”

To find answers to these questions the time series data from road sensors, sensors capturing pedestrian movement, and the coordination of traffic lights all need to be ingested and integrated with temporal data, which identifies the periods of activity, special events, or road closures.

Bottom line benefit: Improve traffic throughput, improve resident satisfaction, reduce energy consumption and carbon emissions.

Edge Computing

People say that just having data is not enough – You need to analyze it. I will take this to the next imperative: You need to act on analytics to get value, and the action takes place at the edge devices when you are in the 4th dimension. This is where you need targeted and timely information to get the best outcomes.

The edge devices are both senders and receivers of information. Car sensors are capturing data, but you need data from all the cars to understand the wide array of potential events and outcomes. The data is ingested, analyzed and then new rules and alerts are sent back to all the cars. This is a type of “swarm intelligence” as you don’t want each individual car to experience an accident to know how to avoid it.

Another example of this nexus of time and space being pushed to the edge is in medical devices and wearables. Gathering data from all patients about their level of exercise as well as any location variables (weather, pollution, altitude, etc.) helps doctors better analyze events to treat new patients more proactively.

Start Getting More Value Out of Your Data

4D Analytics is available to Teradata customers on Vantage. If you’re on a previous version and curious to learn how 4D Analytics makes it quicker and easier to do advanced analysis of time and space contact us today.

Never miss a beat. Get the latest news, updates, and tips in your inbox once a month when you subscribe to Teradata Vantage Updates.
 
Tags

Rob Armstrong について

Since 1987, Rob has contributed to virtually every aspect of the data warehouse and analytical arenas. Rob’s work has been dedicated to helping companies become data-driven and turn business insights into action. Currently, Rob works to help companies not only create the foundation but also incorporate the principles of a modern data architecture into their overall analytical processes.

Rob Armstrongの投稿一覧はこちら

知っている人に滞在

Teradataのブログを購読して、毎週あなたに配信されるインサイトを入手する



テラデータはソリューションやセミナーに関する最新情報をメールにてご案内する場合があります。 なお、お送りするメールにあるリンクからいつでも配信停止できます。 以上をご理解・ご同意いただける場合には「はい」を選択ください。

テラデータはお客様の個人情報を、Teradata Global Privacy Statementに従って適切に管理します。