Radio Network Analytics Using Crowdsource Data
BI Nordic presents a new way of thinking and working within the data analytics and artificial intelligence area. The amount of collected crowdsourced data is continuously growing. Companies are collecting this type of data as a part of their IoT solution. To be able to give as accurate and statistically confident results as possible, high volume of data is of key importance.
Using crowdsourced data, the operators can cut down on the cost for their currently expensive data collection investments compared to traditional methods.
An interactive 3-D web-based map solution visualizes network traffic. These state-of-the-art web components optimize the end-user experience. Extra layers showing site details and demographic data are added to the solution to help the end-user make correction decisions.
The crowdsourced data is pre-processed and fed into an AI engine with both geographical clustering and supervised learning capabilities. It is used to identify hotspots, trace traffic patterns, and facilitate fault detection in operations.
Crowdsourced data is collected when/where/how the user is using the network. This means that the collected data can reveal rush hours, high intense areas, as well as technologies used in the network.