Riders using our products can join the See.Sense community via our app. This allows them to unlock a range of compelling features in the app, and enable sharing of aggregated and depersonalised See.Sense ride insights.
See.Sense products contain patented sensor technology, capable of monitoring the rider's environment up to 800 times per second. We use edge processing and AI on the devices to process the data in real-time before we send the data to the cloud. This means data insights are very granular, enabling unique insights not possible by using an app alone.
Watch this video to understand more about what we do, and how our technology works:
See.Sense data insights are highly differentiated from other methods of data collection:
Better representation - our projects have shown that we can attract a wide range of users to our projects, for example our last project in Dublin involved 45% women. Given that a light is a safety product it has a broad appeal, compared to an app which tends to have a narrower appeal, skewing the data to particular segments.
Granularity of the data - our patented sensor technology makes use of edge-processing and AI on the device itself before data is sent. This means we collect data at much more granularity than an app can, allowing analysis of road surface, braking and swerving, collisions etc, that are not possible to collect using an app.
Unique Road Surface data - up to data data on road surface conditions from the perspective of a cyclist is difficult and expensive to obtain. Our data has been shown to have a high correlation with an visual inspection assessment, thereby saving time and cost.
Near-Real-Time - Census data on commuter journeys can be up to ten years old and tends to under-represent those who undertake journeys for school runs or shopping, which is more likely to be women. By contrast, See.Sense data is near real time, enabling more accurate and up to date insights to be generated.
Persistent- Sensor data allows persistent data feed, allowing insights to be reported automatically over time. Compare this to existing data sources such as police and hospital reports which have long lag times and suffer from under-reporting.
Cost Efficient yet complimentary - Static bike counters such as totem poles, and loops and video cameras mounted on street lights are expensive to install and maintain. See.Sense data can compliment these data sets, adding extra insights such as origin-destination to the analysis.