The Luistervinq proves itself!

The Luistervinq is a solution being developed to monitor sports usage in outdoor public spaces in the most sustainable way possible. The assignment comes from Sportinnovator, by whom Datacadabra was named one of the winners of the challenge "develop a solution to make data on sporting use of public space transparent. Our solution is the Luistervinq, an AI-powered and privacy-proof activity monitor that can map four activities: walking, running, cycling and mountain biking. The Luistervinq uses two microphones and is connected to a solar panel, making it a very sustainable solution. The Luistervinq monitors outdoor usage and provides insight into the density and usage types of a particular outdoor area. This gives more notion of the various aspects regarding the health of residents, tourism and recreational use. Turning these insights into concrete actions will get even more people moving!

A successful baseline measurement in which the four classifications (walking, running, cycling and mountain biking) were well established. Since then, much has been developed in terms of software to process all the data and train the models. Currently we are developing the movement direction classification (left to right, right to left) and that the group size can be detected correctly. Regarding the hardware, a circuit board has been developed on which all the electronic components are located and connected correctly. For example, the solar panel and the battery, these two components operate on different types of voltage, so a regulation component was fitted to ensure that both operate properly.

Last week there was an exciting moment, namely the interim evaluation with the client (Sportinnovator) at the Hulsbeek in Oldenzaal. During this session, Datacadabra gave a presentation on the current status of the Luistervinq and future steps. In addition, we also gave a demonstration. For the demonstration, the Luistervinq was attached to a tree along a walking path and we live detected that when someone walks by, it is also detected and correctly classified as 'walking'. This shows that the Luistervinq can do its job well, even in the field. The client was enthusiastic and was pleased to see that real strides are being made in the project. In short, it was a successful evaluation!

In the coming weeks, we will be working on the Cloud integration and the dashboard. We will also, of course, continue to test to collect as much data as possible to continue to improve the Luistervinq. By collecting more data, the sounds can be better classified and what is detected can be determined with greater accuracy. Furthermore, there will also be another session with the user group after the vacation period, where we will discuss various aspects of the Luistervinq.