Analytics for the Internet of Things (IoT)

Bring in geography

Geography is a very powerful aid in understanding IoT data when devices are located in a variety of places. A thousand devices centered in Denver, Colorado are likely to provide different data values than a thousand devices spread evenly across the state. Patterns that are not obvious from statistical analysis of the data can become very obvious when shown on a map.

Look at the geographic location of the weather station precipitation data on a map. Are there clusters of stations in certain areas? If the locations are not evenly distributed, would an average rainfall calculation for the state based on device readings represent the actual average rainfall for the state? Probably not.

Geographic distribution of sample data ...