Niall Adams

I am Reader in Statistics in the statistics section of the Mathematics department at Imperial College. This page includes information about:

Contact details

Phone: +44 (020) 7594 8574

Fax: +44 (020) 7594 8517

e-mail: n.adams@imperial.ac.uk

Postal address:
Department of Mathematics
South Kensington Campus
Imperial College London
LONDON
SW7 2AZ
United Kingdom


Teaching

No courses this term


Research

I am involved in research in bioinformatics, classification and data mining. I am the leader of the classification and data mining research group in the Statistics section. My full publication info is here

Presently, I am particularly interested in a number of things:

Statistical analysis for cell biology

Modern microscopy enables cell biologist to obtain high resolution 3D images of the cell nucleus. We are especially interested in the spatial configuration of sub-nuclear bodies, and the relationship of configuration to function. This raises new challenges for imaging and analysis. Some recent work

McManus, K.J., Stephens, D.A., Adams, N.M., Islam, S. A., Freemont, P.S. and Hendzel, M. J., 'The transcriptional regulator CBP has defined spatial associations within interphase nuclei' PLOS Comput. Biol., 2(10), (2006), 1271-1283.

Shiels, C., Adams, N.M., Stephens, D.A., Islam, S., and Freemont, P.S., 'Quantitative analysis of cell nuclear organisation' PLOS Comput. Biol., 3(7), (2007), 1161-1168.

Russell, R.A., Adams, N.M., Stephens, D.A., Batty, E., Jensen, K. and Freemont, P.S., 'The stable count thresholding (SCT) algorithm for segmentation of fluorescence microscopy images', Biophys. J, (2009), Volume 96, Issue 8, Pages 3379-3389 in press

This is on-going collaboration with Paul Freemont and Dave Stephens.

Streaming data methodology

Advances in data acquisition technology have enabled the continuous collection of data in a variety of contexts, notably sensor networks. Such contexts require data analysis algorithms that operate with a single view of each data item, and the have the capacity to adapt to changes in the underlying stochastic mechanism. Some recent work

Tasoulis, D.K., Ross, G. and Adams, N.M., 'Visualising the clustering structure of data streams' in 'Advances in Intelligent Data Analysis VII' Lecture Notes in Computer Science, 4723, Berthold, M.J., Shaw-Taylor, J. and Lavrac, N. eds(Springer) 2007, 81-92.

Anagnostopoulos, C., Adams, N.M. and Hand, D.J. 'Deciding what to observe next: adaptive variable selection for regression in multivariate data streams' in 'Proceedings of the ACM Symposium on Applied Computing (SAC)', 2008, 961-965.

Tasoulis, D.K., Adams, N.M., and Hand, D.J., 'Selective fusion of out-of-sequence measurements', Data Fusion, (2009), accepted.

This work is partially supported by the ALADDIN project.

Classification and data mining

Classification problems are ubiquitous, and are a good example of the effectiveness of Statistics in the real world. I am especially interested in complicated contexts, like credit card fraud detection. Outputs from the EPSRC ThinkCrime project include

Hand, D.J., Whitrow, C, Adams, N.M., Juszczak, P. and Weston, D.J., 'Performance criteria for plastic card fraud detection tools' J. Oper. Res. Soc., 58, (2008), 956-962.

Juszczak, P., Adams, N.M., Hand, D.J., Whitrow, C. and Weston, D.J., 'Off-the-peg and bespoke classifiers for fraud detection' Comput. Stat. Data An., 52, (2008), 4521-4532.

Weston, D.J., Hand, D.J., Adams, N.M., Whitrow, C., and Juszczak, P., 'Plastic card fraud detection using peer group analysis' Adv. Data An. Classif., 2(1), (2008), 45-62.

Whitrow, C., Hand, D.J., Juszczak, P., Weston, D.J., and Adams, N.M., 'Transaction aggregation as a strategy for credit card fraud detection', Data Min. Knowl. Disc., in press, (2008).

Data mining involves various types of analysis on large data sets. We have been involved in defining the sub-area of "pattern detection and discovery", concerned with finding small local structures in large data sets. Some work in this area includes

Hand, D.J., Adams, N.M., and Bolton, R.J. (eds.), 'Pattern Detection and Discovery' Proceedings of the ESF Exploratory Workshop, Lecture Notes in Artificial Intelligence, 2477, (Springer: Berlin) 2002.

Hand, D.J., Adams, N.M., and Heard, N.A. (invited) 'Pattern discovery tools for detecting cheating in student coursework' in 'Local Pattern Detection' Lecture notes in Computer Science 3539, Morik, K. Boulicault, J.-F. and Siebes, A. ed(Springer) 2005, 39-50.

Cohen, P.R., Adams, N.M., and Heeringa, B. 'Voting Experts: an algorithm for segmenting sequences' Intelligent Data Analysis, 11(6), (2007), 607-625.


Organisation

Royal Statistical Society

I am a member of the committee of the Statistical Computing section of the Royal Statistical Society, having been chair 2005-2008. In addition, I am a member of the "recordings" and "data and society" working groups.

Intelligent Data Analysis

I have been a member of the program committee for the last 4 conferences, and was involved in the organisation of the 2001 conference:

Hoffman, F., Hand, D.J., Adams, N.M., Fisher, D. and Guimaraes, G. (eds.), 'Advances in Intelligent Data Analysis' Proceedings of the 4th International Conference, IDA 2001, Lecture Notes in Computer Science, 2189, (Springer: Berlin) 2001.

I was co-chair of the program committee for IDA 2009, held in Lyon, August 2009. Proceedings here .

Breaking news!In an exciting development, an extra IDA conference is being planned for May 2010, in Arizona, USA. The website is now available space.

Editorial

I am an associate editor of

Applied Statistics, Journal of the Royal Statistical Society, Series C

Statistical Analysis and Data Mining

I am a regular member of the program committee of the:

International Symposium on Intelligent Data Analysis

ACM Symposium on Applied Computing, data mining track

Workshops

Dimitris Tasoulis, Alex Rogers, and I organized a workshop on Streaming data mining for sensor networks at IFCS '09. Also, giving an invited talk on streaming data and credit scoring

I was one of the organisers for the joint RSS/ASC meeting on data mining , 21 April 2009, at Imperial College. Giving an opening talk on data mining

I organised a workshop about sequential decision making, at Imperial College, 30 March 2009.