Feature Selection Optimisation in an Automated Diagnostic Cancellation Task

Chindaro, Samuel and Guest, Richard and Fairhurst, Michael and Razian, Mohammad A. and Potter, Jonathan (2004) Feature Selection Optimisation in an Automated Diagnostic Cancellation Task. In: Meisenberger, Klaus, ed. Computers Helping People with Special Needs: 9th International Conference, ICCHP 2004, Paris, France, July 7-9, 2004. Proceedings. Lecture Notes in Computer Science, 3118 . Springer Verlag, pp. 1047-1053. ISBN 9783540223344. (The full text of this publication is not available from this repository)

The full text of this publication is not available from this repository. (Contact us about this Publication)
Official URL
http://dx.doi.org/10.1007/978-3-540-27817-7_154

Abstract

This paper describes an investigation into feature selection and classification in the automation of a standard target cancellation task for the diagnosis of visuo-spatial neglect. Alongside a conventional assessment based on the number of targets cancelled, a series of time-based dynamic features have been algorithmically defined which can be extracted by capturing the test subject's response on a graphics tablet connected to a computer. We identify the diagnostic capabilities of the individual features and show that dynamic data contains important indicators for neglect detection. Furthermore, employing standard pattern recognition techniques, we establish the optimum feature vector size and classifier for a multi-feature analysis of a test attempt and show that an improvement in diagnostic error rate is achievable over any single individual feature.

Item Type: Book section
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image Analysis, Image Processing
Divisions: Faculties > Science Technology and Medical Studies > School of Engineering and Digital Arts > Image and Information Engineering
Depositing User: Yiqing Liang
Date Deposited: 25 Sep 2008 20:31
Last Modified: 17 Jul 2014 08:49
Resource URI: http://kar.kent.ac.uk/id/eprint/8656 (The current URI for this page, for reference purposes)
  • Depositors only (login required):