Last week we ran our Data in Motion Hack Week with AWS and Geovation, as we aimed to find solutions to some of London’s key transport challenges through the innovation and creativity of developers working with our open data. Those taking part in the Hack Week were asked to come up with solutions to help tackle some specific challenges that we face in the capital today, and we were delighted to see the incredible standard of entries at the end of the week.
Maximising capacity on the transport network, maximising capacity on the roads & improving air quality.
API, Scoot, passenger flow, air quality (from KCL).
Innovation, commercial viability, and relevance to the key challenges.
The Winning Solution
The winning team was WSO2, who came up with a fantastic ‘Live Journey Planner’ prototype.
This was a particularly impressive solution, taking the data from many modes of transport and overlaying passenger flow/train loading and pollution data. This would allow users to plan a route based on how busy their stations/routes are, whilst also taking air quality into account. This was a brilliantly innovative solution, being crowned the worthy winner of our first prize ahead of a range of fantastic ideas from the other teams.
Summary of the Solutions
The Hack Week gave our panel of judges a fantastic opportunity to see how TfL’s open data can continue to be used to power ever more creative, innovative and useful solutions to a range of challenges facing the capital.
As well as our winning solution, there were a range of truly excellent ideas on show and we’d like to thank each and every one of our teams for their efforts, and congratulate them on a really impressive range of solutions that were developed over the week. With more than 8,500 developers currently working with our data to power over 500 apps, it was a pleasure to see the latest brilliant ideas for transport apps that are powered by TfL’s open data.
Here’s a brief summary of each of the solutions:
Team 1: Hemil, Sunil and Anil – Crowdsourced Clean Air (idea)
The idea focussed around building an IoT service that collects data from cheap and disposable sensors around the city.
Team 2: Kostya – Deep Learning (idea)
This was a theoretical take on how TfL can address three key questions; travelling safely, travelling quickly and arriving on time.
Team 3: Gene Wyld – Managing Capacity (prototype)
This solution monitors the crowding on trains and in stations, helping passengers pick a route based on how busy the stations are.
Team 4: Gene Wyld (2nd solution) – Road Capacity (prototype)
This was presented as a heatmap of the congestion across the road network in London.
Team 5: Pickup Infinity – Managing Capacity on the Roads (prototype)
This was a visualisation of the hot spots on the roads, and was based on average levels of traffic on the road in a given area.
Team 6: WSO2 – Live Journey Planner (prototype)
Our winning solution, as described above.
Team 7: Mohammad Shah – Bus Imbalance (idea)
Looking into how to spread load across buses, including a reader on the side of the bus to inform passengers of bus crowding.
Team 8: Opearlo – Voice controlled travel updates (prototype)
A solution using voice commands to find transport updates and pick routes based on speed or congestion.
Team 9: Moray, Riekon Analytics – Bike Distribution (idea)
A cycle hire solution to help improve the distribution of bikes, using a demand-driven market to encourage particular journeys.
Team 10: UrbanThings – Commuchi (prototype)
An idea around the gamification of journeys, with the aim of getting people to travel / walk on less congested or polluted routes.
Team 11: DataTonic – Anomaly Detection on the Roads (protype)
A solution aiming to map anomalies on the road network, and ultimately help people to avoid disruption as much as possible.
If you were a part of the Data in Motion Hack Week, we’d love to hear what you thought of the week, so please do leave us a comment below. Similarly, if you were unable to attend the event and have any questions or comments on the Hack Week or anything related to TfL’s open data, please leave your thoughts in the comments section below.