As explained in my interim report, my circumstances have changed since I applied for the Fellowship. The two main points are:
Overall these changes have been positive, and have given a wider base and a wider set of intellectual inputs to my research.
The research has, as planned, centred on computer applications that are context-aware. An example of such an application is one to aid a tourist: the tourist carries a mobile computer with attached sensors to record the user's context (for example their location may be determined by a GPS sensor), and information about nearby tourist sites is automatically presented on the computer screen as they move from one place to another.
As sensors become cheaper and more ubiquitous, they can detect an ever richer context, e.g. location, temperature, orientation, objects nearby, computer state, etc. Moreover the sensor-detected context can be augmented or overridden by a virtual context set by the user; for example they might set some preferences, or override their true location by a location they want to pretend to be at.
Context-aware applications already exist in a limited form, for example some mobile phone companies provide an application that tells you the nearest hotels to your current location. However, in order to realise their potential, these applications need to cater for richer contexts and wider sources of information.
A key conclusion, early in my research programme, was that the methods that current context-aware applications use for retrieval of information do not scale up beyond small contexts and limited information sources. New approaches are needed to meet the needs of context-aware retrieval (CAR), and I decided to focus the research programme on this need; this focus was more than envisaged in the original proposal.
The first step, done in close collaboration with Dr. Jones, was to look at two established fields:
Both these fields have made immense strides over the last thirty years -- it is still a wonder to me that a web search engine will search a billion pages in a negligible time -- and CAR can potentially gain from this. We studied the relationship of CAR to traditional IR and IF, and published two papers [3, 4] on this. In simple terms our conclusions were: (1) CAR is a mixture of IR and IF plus a bit extra; (2) giving good performance in CAR, in terms of speed and relevance of the information found, is harder than in IR or IF; (3) to compensate for (2), we need to find some particular advantages of CAR that can be exploited.
A more specific conclusion was the the IR concept of `best match' retrieval needed to be adopted in CAR. This concept is that, instead of a `yes or no' Boolean retrieval, each potential document for retrieval should be given a score giving how well it matches the user's needs; this score is derived from weighting various contributory factors -- for example in CAR one factor may be the location, and the weight of this might be changed according to the user's circumstances.
In order to investigate new approaches to CAR, I decided to construct a new retrieval engine, based on the previous `stick-e note' work described in my Leverhulme application, but:
The new engine has been successfully implemented by Lindsey Ford, who was employed on the project. It was working by July 2001, and has been improved since in the light of usage. We have used it as a testbed to evaluate our new ideas (see below). It is now a stable base which both we and other researchers can use to plug in algorithms representing our ideas and test them out. It now runs to over 5000 lines of Java.
I did not personally work on this implementation, though I specified it. Instead I spent the bulk of the programme exploring new ideas to improve the performance of CAR. I believe that one advantage of CAR that we can exploit is that the user's context normally changes slowly and semi-predictably. For example the location of a tourist will normally change slowly, and future locations can be predicted -- though sometimes the prediction will be upset by a change in direction. I have designed new matching and weighting algorithms to exploit this (for example a location just ahead has more weight than a location behind). I have also designed caching techniques that try to build a cache of all the documents the user may need during the next 10 (say) minutes. A cache is much smaller and faster to search than a full document collection, and has further advantages on mobile devices that are only periodically connected. We have built embryo applications, mostly in tourism, to test our ideas. Together with Dr. Jones, I have produced a paper [1] on this work, and this has been accepted for an ACM conference in March 2002. Another paper is in preparation.
The CAR work has represented about three-quarters of my time (a higher proportion than envisaged), but there has also been subsidiary work. Firstly, I have done some work, involving Exeter students, on user interfaces for context-aware work. So far this work has not replicated the success of the CAR work.
A second, more successful, activity has been working with staff at Southampton University (where I have become a Visiting Professor) on fundamental studies of hypertext, and, more recently, how hypertext retrieval relates to CAR. We have published one paper [2] and have two in preparation.
Obstacles to the work have not been major. As ever, I have sometimes gone down a blind alley and run into a wall (one such blind alley, foreshadowed in my original proposal was an emphasis on triggering information to the exclusion of other ways of delivering information). On the practical side, the first person I employed was barely up to the job. However, the second, Lindsey Ford, was outstanding, and since his employment represented the bulk of the budget, I was satisfied overall.
I paid the bulk of the award to the University of Exeter after I moved here. Sadly this resulted in a lot of problems. The most serious was that they miscalculated how long we could employ Lindsey Ford, with the result that we overspent that part of the budget, and had to ask Leverhulme's permission to vire. (I must share the blame for this, as I should have checked the calculations.)
Articles in learned journals and books:
There is a web site for my research programme: http://www.dcs.ex.ac.uk/~pjbrown/car_project/
The retrieval engine constructed under the programme is available in demonstration form. In a real application the context is set automatically (e.g. location by GPS), but in the demonstration the user enters this manually. The demonstration uses a large collection of data kindly supplied to us by South West tourism. We undertook not to make this available publicly; however, Leverhulme could run the demonstration via: http://www.dcs.ex.ac.uk/~pjbrown/cgi_bin/form. I have also tried to promote an awareness of the research by lectures, and demonstrations to companies. As a result, two companies have agreed to be collaborators on a new research project at Exeter University.
I attended two international conferences: CHI 2000 (Amsterdam), where I participated in a workshop on context-awareness, and HUC-2K (Bristol). I also made several visits to UK research centres, and outside collaborators, especially Xerox, have provided many useful inputs to my work. I have had a paper [1] accepted for an international conference, the ACM Symposium in Applied Computing, to be held in Madrid in March 2002, and plan to attend.
| Activity | Cost in pounds |
|---|---|
| Employment of research assistants | 11,297.57 |
| Consumables | 410.00 |
| Travel in the UK | 549.06 |
| Attendance at international conferences | 1174.56 |
| Attendance at future international conference | 500.00 |
| Other | 150.00 |
| TOTAL SPENT | 14081.19 |
| Activity | Income in pounds |
|---|---|
| Award from Leverhulme | 15820.00 |
| Interest obtained from money prior to spending | 84.36 |
| TOTAL INCOME | 15904.36 |
I am therefore pleased to return the underspend of £1823.17. This was mainly caused by my having access to facilities freely provided by Exeter University, together with less travel than anticipated to the University of Kent.
The above figures include two expenditures that Leverhulme has given special permission for: (1) the overspend on employment and (2) the contribution towards presenting a paper at a conference to be held after the end of the grant.
Finally, I expect you often hear this, but I will say it: my research has blossomed since I `retired'. This is largely because research is my sole focus. I am grateful to the Leverhulme Trust for helping make this happen.
Peter Brown, December 2001