Forecasting demand using Big Data

By: Patrick McSharry, University of Oxford

Cornmarket (street in Oxford)

As we walk, cycle or drive around Oxford, make telephone calls, send texts or emails and do our shopping, many of us are unaware of exactly how much data is being generated by our activities. “Big data” is a catch-phrase for describing the overwhelming volume, velocity and variety of this stream of information. Big data has the potential to provide many opportunities for the public and private sectors, offering a means of fusing different sources of information and supporting decision-making in real-time.

Perhaps the most interesting aspect of big data is how it deepens our understanding of human behaviour seen through the collective actions of many individuals. We tend to consume services following the temporal cycles in our everyday lives. There are three evident cyclical patterns based around the hour of day, the day of the week and the season of the year. All of these patterns can be seen in electricity consumption, call centre activity, internet usage, financial transactions, traffic flow and the use of healthcare services.

Fortunately the repetition of these patterns offers potential for accurate demand forecasting. Services can be delivered with greater efficiency if staff and limited resources are scheduled in order to meet forecasted demand. The National Grid has been balancing supply and demand for years and knows the value of accurate forecasts. If they get it wrong, the lights go out and everybody notices. While power outages still happen in many countries, we take it for granted in the UK that we have reliable access to electricity at all times. Amazingly, we are relatively tolerant of imbalances in supply and demand in other sectors and this may explain why sophisticated demand forecasting is not widely utilised.

Take healthcare, for example. The NHS has a target of seeing 95% of patients arriving in A&E within four hours. Until recently there was little information about the performance of our local hospitals or indeed how they compare with the rest of the country. Now weekly A&E data about the percentage of patients seen in four hours is available. This week the John Radcliffe Hospital A&E scored 87.1%, slightly less than the national average of 91.5%. Here is a chance for Oxford City to become smarter.

There are many opportunities to use big data and quantitative models to forecast demand, develop early warning systems and improve staff scheduling. The graph below shows the average hourly A&E arrivals at the John Radcliffe for different days of the week. We immediately see the hour of the day effect with low demand during the night and two peaks at 12:00 and 18:00. Most striking is the near doubling of arrivals in the early hours of Saturday and Sunday, which can be attributed to the effect of weekend partying and pubs closing at 11:00 on Friday and Saturday night. While A&E staff are well aware of the additional burden caused by weekend festivities, the data analysis paints a clear picture of its impact on arrivals.

graph of A and E demand in Oxford

Big data can facilitate a better understanding of social behaviour and the effect of the environment. Arrivals increase on bank holidays. Temperature is another important factor with arrivals increasing in warm weather. But this is just the start. Forecasts of extreme weather events and information about social events could be used to construct an accurate model.

Patrick McSharry @patrickmcsharry is a Senior Research Fellow at the Smith School of Enterprise and the Environment, Faculty Member at the Oxford-Man Institute of Quantitative Finance, and co-author of Big Data Revolution.

Being There: exploring issues of privacy and digital personhood in public spaces

Research teams at the University of Oxford and other centres will explore issues of privacy and the challenges of being able to appear in public in proxy form, in particular the challenge of having robot proxies in public places.

This will involve the capacity to track micro-contacts between multiple individuals in real time, and at the same time to capture and process information about the emotional and nonverbal communicative qualities of behaviours across time.

Preserving and Measuring Privacy

The Oxford Internet Institute will focus on techniques that allow humans to interact with robots and each other whilst balancing the desire for privacy against the need to share information in modern connected environments. In particular they will seek to embed privacy in the design of robots. While robots can record and transmit what they see and hear, the research is trying to find ways to prevent robots from unnecessarily revealing the identities of those they have recorded.

Localization System

The Sensor Network Group in the University of Oxford’s Department of Computer Science will investigate the feasibility and accuracy of a positioning system. This system will enable the tracking of humans and robots in any space, indoor or outdoor.
In order to address this challenge, the team will investigate the use of a novel indoor localization technology based on low-frequency magnetic fields.

You can read more about the project here

EmerGent : Mining social media in large-scale emergencies

By: John Boyle, Oxford Computer Consultants

One of the biggest sources of Big Data is social media. This represents a continuous feed of unstructured, unvalidated near real-time information about citizens’ experience.

picture of flooding

When a big city undergoes a crisis, such as a flood, earthquake or riots, masses of valuable information pours into social media sites such as Twitter and Facebook. Currently the emergency services have no established methods of monitoring this data, filtering it and integrating the results into crisis management.

As part of the European EmerGent project, Oxford Computer Consultants are developing cloud-based emergency management services to gather and mine social media for large-scale crises. A service is being developed that can take the stream of social media surrounding a large scale event and transform it into a data source which is relevant, self-consistent and actionable. Social media is already the fourth greatest source of information in a crisis (according to a US Red Cross survey) and is readily available for computing systems to capture and analyse. But how do we quickly process terabytes of data?

picture of police in riot gear

How can we parse text with misspellings and in different languages? Can we find false information (as happened in the London riots)? How do we present this so that it is readily understood? How do we maintain citizen confidentiality within privacy legislation?

We are building on our data mining tools and techniques for text-based analysis, and mapping from the REACT project. We are the EmerGent partner responsible for ensuring that all data is used within European Data Protection Laws.

And beyond the project, OCC will be assisting the emergency services in their integration of social media within their incident management and be seeking other opportunities where the technology can benefit Governments and Industry.

The EmerGent project has received funding from the European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement no 608352.

Oxford plans innovative Wireless Electric Bus project

By: Oxfordshire County Council

Oxfordshire County Council and Oxford City Council are excited to announce a commitment to work on a joint study for an innovative Wireless Electric Bus project.

Working in partnership with Oxford Bus Company, MBK Arup Sustainable Projects (MASP), and sister company eFleet Integrated Service (eFIS), the plan is to trial the use of double decker buses that can be wirelessly charged.

 Wireless Electric Bus

MASP, a joint venture company between Mitsui & Co., Ltd, and Ove Arup & Partners Ltd., and enabling company eFIS have successfully implemented an electric single deck bus trial in Milton Keynes. There is now a vision for all parties to study the technical and commercial feasibility of replacing the existing busy Park and Ride buses in Oxford with a fleet of around 20 new electric vehicles. The buses will have zero tail pipe emissions and will be the first double decker vehicles of their kind to operate in the UK.

The new electric buses will recharge their batteries wirelessly during their working day. Power transmitted from a coil buried in the road at the Park and Ride stops will be picked up by a similar coil on the underside of each bus. Ten minutes parked over a coil will replenish the energy needed to run each bus for the day.

It is hoped to have the trial running by the end of 2016. The project will contribute to improving the air quality in Oxford, demonstrate the commercial viability of low carbon transport and develop an economic model for the more widespread use of electric vehicles for mass transit systems. Hopefully, this will lead to greater confidence and investment in green transport across the world.

Councillor Ian Hudspeth, Leader of Oxfordshire County Council said: “Having a full electric Park and Ride fleet would be a great asset for Oxford, giving businesses the confidence that Oxfordshire County Council and the bus operators are open and ready for innovative transport solutions to enable the County to solve the challenges that the transport network faces.”

Luke Marion Finance & Commercial Director at Oxford Bus said: “Oxford Bus Company has been at the heart of the community for 135 years. We’ve always been at the leading edge of green, environmentally-friendly innovation. We are delighted to be working with our partners to test the viability of this innovative concept.”

Councillor John Tanner, Oxford City Council’s Board Member for a Cleaner Greener Oxford says: “This is a very exciting study for Oxford and we are extremely pleased to be playing our part.

“Projects like this will help us achieve our ambition of improving the city’s air quality and creating a low carbon Oxford for everyone.”

This article orginally published on the website of Oxfordshire County Council.

8 things you might not know about Oxford’s driverless tech

By: Pete Wilton, University of Oxford

Lutz driversless pod

Today, at an event in London, the government has revealed the outcome of a review of UK regulations for driverless cars as well as the launch of trial projects in three locations.

Today is also the first chance to see prototype driverless LUTZ Pathfinder pods built for one of the trials being driven around pedestrianized areas in Milton Keynes.

The Mobile Robotics Group (MRG) at Oxford University’s Department of Engineering Science is involved in both announcements and has been at the forefront of autonomous vehicle research in the UK for over a decade, here’s a brief run-down of what you need to know:

1. Oxford tech is in the LUTZ driverless pods
Technology developed at Oxford University’s Mobile Robotics Group (MRG) is at the heart of the LUTZ Pathfinder pods. It enables the pods to navigate and understand their environment, so knowing exactly where they are on a pavement or pathway and being able to recognise and avoid pedestrians and obstacles. The Oxford team will be working with the Transport Systems Catapult (TSC) and project partners over the coming months to build autonomous systems into the pods, eventually doing away with the need for a steering wheel or human driver.

2. Wildcat shows off early tech back in 2011
The Oxford researchers first showed off their autonomous technology in March 2011 installed in a Bowler Wildcat 4X4 built by BAE Systems. Data gathered from cameras and lasers mounted on the Wildcat could be processed on board fast enough to be used in navigation and it was demonstrated driving around Begbroke Science Park, near Oxford. Coming only a year after Google announced it was testing driverless vehicles on California roads the Wildcat was a trail-blazer for autonomous vehicle research in the UK.

3. Does not rely on GPS to navigate
Oxford’s autonomous vehicle tech does not rely on GPS to navigate because GPS doesn’t work well in built-up environments and is in any case not precise or reliable enough to give an exact location. Neither does the Oxford approach use embedded infrastructure such as beacons and guide wires, which often guides robots in factories, as this would be impractical and far too expensive for use in most environments.

Instead the Oxford approach to navigation uses algorithms that combine machine learning and probabilistic inference to build up maps of the world around it using data from on-board sensors and ‘learn as it drives’. The maps it builds (and updates) are like memories of a route which can be accessed to allow the vehicle to guide itself through places it has been before.

4. Robot Car demonstrated in 2014
February 2014 saw the first public demonstration of the Oxford Robot Car: Oxford University technology installed in a modified Nissan Leaf electric car that enables the vehicle to drive itself for stretches of a route. Robot Car was shown driving autonomously around private roads at Begbroke Science Park with the driver able to take his/her hands off the wheel as the car steered itself and stopped when confronted with an obstacle, such as a pedestrian walking out into the road.

The technology is controlled from an iPad on the dashboard which flashes up a prompt offering the driver the option of the car taking over for a portion of a familiar route – touching the screen then switches to ‘auto drive’ where the robotic system takes over. At any time a tap on the brake pedal returns control to the human driver.

For a long time Robot Car was the only autonomous vehicle in the UK with permission to go on public roads and the team’s work in collaboration with the Department for Transport fed into the government’s legislative review. Development of the Oxford Robot Car continues alongside the technology for the LUTZ pods and the team’s other robotics research .

5. Blueprint for a low-cost system
One key aim of the Oxford research is to produce autonomous systems that are affordable and would be relatively simple to build into ordinary vehicles. The approach is made possible by advances in 3D laser-mapping that enable a system to rapidly build up a detailed picture of its surroundings. The 2014 Robot Car demonstration showed that the combination of this laser-mapping, cameras, and the team’s clever software, can enable a vehicle to learn to navigate a route and know exactly where it is on the road. The system used for the demonstration was estimated to cost around £5000 but the team believe that systems that deliver limited autonomy – driving you ‘some of the time in some of the places’ – could eventually cost around £100.

6. Robot Car is being tested around Oxford
What does the world look like to a driverless car? As Oxford researchers continue to develop all the components needed for a complete system to drive itself on the public road the team has released new videos from tests around Oxford. The videos show how some of Oxford’s most iconic locations – including the Sheldonian Theatre on Broad Street – are mapped and interpreted by the technology. The footage also shows how the system detects people and other traffic.


7. Self-driving or driverless?
Whilst the ultimate vision is for a car to drive itself without the need for any intervention from a human driver there are likely to be many stages on the road to fully autonomous vehicles. During the 2014 tests of Robot Car a trained human driver was behind the wheel at all times to take over control whenever necessary and this is also true of all current testing – in this sense they are not yet ‘driverless’. Initial autonomous systems for cars are likely to be able to drive ‘some of the places some of the time’ offering to take over familiar routes such as the school run or daily commute. However, systems for vehicles such as the LUTZ pods that are designed to drive at lower speeds in less hazardous pedestrianized environments, may be able to achieve full ‘end to end’ autonomy sooner, doing away with the need for a driver altogether.

8. It’s not just about driverless cars …
Driverless cars may hog the headlines but the same Oxford University technology in both the LUTZ pods and Oxford Robot Car has many other applications. Current MRG projects include robotic survey systems for roads and railways and robotic rovers for use on other planets. In November 2014 Professor Ingmar Posner and Professor Paul Newman, leaders of the Oxford Mobile Robotics Group (MRG) founded a new spin-out firm, Oxbotica, to commercialise MRG’s robotics and autonomous systems technologies.

This posting originally appeared in the Oxford Science Blog

Digital Oxford

Digital Oxford is an independent organisation that sets out to make Oxford and Oxfordshire a global destination for digital business.

The digital industry in Oxfordshire is already worth an estimated £500m or more, which comes from the 40% of the 3,000+ businesses in the county who are are digital. (Source: Oxford Inspires).

Oxford and Oxfordshire have the start-ups, the success stories, the skills base, the world-class universities and research institutions, and the passion to make it one of the best places to grow a digital business in the UK.

This is already happening, with local companies that at the top of their game nationally and internationally, such as:

  • Vicon, based in Botley, who have been at the cutting edge of motion capture technology – both hardware and software – since the 1980s.
  • The award winning Oxford Space Systems based on the Harwell Science & Innovation Campus
  • Nominet who manage the .uk and .wales domains from the Oxford Science Park
  • Sophos, web security company, whose global HQ is in Abingdon.
  • Leading games and technology company NaturalMotion founded in Oxford and with offices in the city centre.
  • The UK’s largest independent vacation rental website Holiday Lettings who are also based on the Oxford Science Park and were brought by Trip Advisor last year.
  • Williams F1, who are based near Wantage.

You can read more about Digital Oxford here.

At the forefront of autonomous vehicle research in the UK

The Oxford Mobile Robotics Group (MRG) at Oxford University’s Department of Engineering Science has been at the forefront of autonomous vehicle research in the UK for over a decade.

The group’s technology is at the heart of the driverless LUTZ pods, currently on trial in Milton Keynes. It enables the pods to navigate and understand their environment, so knowing exactly where they are and being able to recognise and avoid pedestrians and obstacles. The team is working with the Transport Systems Catapult (TSC) and project partners to build autonomous systems into the pods.

The Oxford researchers first demonstrated their autonomous technology in March 2011, only a year after Google announced it was testing driverless vehicles on California. Its technology does not rely on GPS because that doesn’t work well in built-up environments and is not precise enough. Nor does it use embedded infrastructure such as beacons and guide wires, as this would be impractical and far too expensive.

Instead, the approach to navigation uses algorithms that combine machine learning and probabilistic inference to build up maps of the world around it using data form on-board sensors and ‘learn as it drives’. The maps it builds (and updates) are like memories of a route which can be accessed to allow the vehicle to guide itself through places it has been before.