Peter Burge
Royal Holloway, University of London
20 Papers
355 Citations
Peter Burge is an academic researcher from Royal Holloway, University of London. The author has contributed to research in topics: Mobile telephony & Artificial neural network. The author has an hindex of 9, co-authored 20 publications. Previous affiliations of Peter Burge include University of London.
Chat about Author
Papers
An Unsupervised Neural Network Approach to Profiling the Behavior of Mobile Phone Users for Use in Fraud Detection
Peter Burge,John Shawe-Taylor +1 more
TL;DR: The current status of research on fraud detection undertaken as part of the European Commission-funded ACTS ASPeCT (Advanced Security for Personal Communications Technologies) project is discussed, with a new decaying technique, which maintains these profiles such that short-term information is updated on a per toll ticket basis whilst the update of the long-term behavior can be delayed and controlled by the user.
79
•Proceedings Article
Detecting Cellular Fraud Using Adaptive Prototypes.
Peter Burge,John Shawe-Taylor +1 more
- 01 Jan 1997
TL;DR: Using a recurrent neural network technique, prototypes are uniformly distributed over Toll Tickets to form statistical behaviour proFdes covering both the short and long-term past to be prepared for the would-be fraudster for both GSM and UMTS.
Fraud detection and management in mobile telecommunications networks
Peter Burge,John Shawe-Taylor,C Cooke,Yves Moreau,B. Preneel,C Stoermann +5 more
- 28 Apr 1997
TL;DR: The paper discusses the status of research on detection of fraud undertaken as part of the European Commission-funded ACTS ASPeCT (Advanced security for personal communications technologies) project, and explores the detection of fraudulent behaviour based on a combination of absolute and differential usage.
61
Novel Techniques for Fraud Detection in Mobile Telecommunication Networks
Yves Moreau,Bart Preneel,Peter Burge,John Shawe-Taylor +3 more
- 01 Jan 2007
TL;DR: The status of research on detection of fraud undertaken as part of the European Commission-funded ACTS ASPeCT (Advanced Security for Personal Communications Technologies) project is discussed, which is exploring the detection of fraudulent behaviour based on a combination of absolute and differential usage.
32
•Proceedings Article
A hybrid system for fraud detection in mobile communications.
Yves Moreau,Ellen Lerouge,Herman Verrelst,Joos Vandewalle,Christof Störmann,Peter Burge +5 more
- 01 Jan 1999
TL;DR: The integrated rule-based and neural network architectures developed as a number of di erent fraud detection tools for GSM networks are integrated into a hybrid detection tool and the performance of the hybrid system is optimized in terms of the number of subscribers raising alarms.
25