Integrating our Traffic Systems – how crowdsourced big data is going to save us
One ‘quick win’ we can make off the back of emerging and developing technologies is in the area of local transport. Crowdsourced Big Data is going to save us. We’ve probably all heard about developments in the field of the physical vehicle, i.e. self-driving cars and self-convoying road haulage trucks etc, yet there is something really quite simple that we can do right now and the benefits would huge.
Our cities suffer from problems that we’ve become resigned to, such as air pollution and congestion both of which are exacerbated by under capacity. We’re already familiar with the pain of the commute, the long drawn out journey from the suburbs into town and back again. We could potentially solve this issue quite quickly. By combining our transport systems, buses, trains and other modes with the data we all hold and we have an effective solution.
Technology has already penetrated bus timetabling systems such as live data feeds from GPS monitoring of bus locations which feeds live arrival/departure boards at bus stops. Nowadays it would also be hard to find a company that actually has a printed version of their timetable. However, this ‘penetration’ is just the beginning. There’s another source of data, one that most of us carry, which could offer a live overview of a city’s entire transport network without a single penny of investment.
Anonymous Tracking of Smartphones
The ubiquitous Smartphone contains an array of sensors, including GPS, accelerometer, gyroscope, digital compass and more, which are capable of producing a constant stream of data. Individual units of movement, tracked by a phone’s GPS and processed en masse, can give detailed information on journey times, speed and destinations.
Is the time right for a fully integrated transport system?
Modern Smartphone traffic mapping is Big Data at work. Google Traffic, for example, works by analysing the GPS determined location transmitted by a large number of mobile phone users. By calculating the speed of a number of users along a length of road Google is able to deliver a live view of traffic conditions. Basically, when a threshold of users is noted in a particular area moving at a particular speed the overlay along roads on the map changes colour and it’s amazingly accurate. Apple has a similar system.
Crowdsourced big data
Essentially this is crowdsourced traffic data. Now imagine if we could combine this data with efficient ticketing across a range of transport modes, buses, trams, trains, taxis, city bikes and others, it would then be possible to create a flexible and responsive system, which can tailor transport solutions to every person’s needs.
Individuals would be able to drop a pin in their destination as they leave home and then be guided by their choice of the fastest, cheapest, healthiest or most environmentally friendly route to their destination on a given day, by whatever means. That would be in incremental improvement on current navigation systems. If you combined this data with other apps, you could actually choose to take the route that keeps you at your healthiest or lets your next appointment know you’ll be slightly late. Your routes would be responsive to changing weather and road closures, with flexible timetables and services, to cater for a wet Tuesday when everyone wants to take the bus rather than walk or cycle. This system would be constantly ‘learning’ and improving.
It is relatively straightforward to automatically schedule extra services in real time if, say, there’s an unusually large number of people waiting at a particular stop. With sophisticated machine learning, which processes large amounts of historical data to detect patterns, slumps and hikes in demand could be preempted.
All of this is achievable but there are two key issues. Firstly the small matter of privacy and secondly the sharing of data amongst competitors.
Using location services data without compromising users’ privacy is a challenge. When dealing with location information, anonymisation can only take you so far. Google actually deletes its location data as soon as it’s been used for the specific purpose. In terms of encouraging private companies, such as Google and Apple, to share their data they might well see that there are gains to be made by collaborating. One solution would be the introduction of a ‘data broker’ service.
There are various models for implementation here, from both the public and private sectors. For example the public sector, in its role of ‘facilitator of choice’, could provide the data as a service, having first purchased it from the carrier. Once subscribed other providers could offer services which benefit the consumer. The model would see providers putting their anonymized data into ‘the pot’(publish), and then being able to subscribe to certain data to draw from the brokerage system.
We may even get to the point where the more data you are willing to share about yourself the more choice/ advice/ level of service could be offered.