The computer Controlled Video Perimetry (CCVP) is a computer screening test for detecting visual function loss caused by onchocerciasis, glaucoma, etc. Installed on portable computers, the CCVP has been shown to be high acceptability in field community investigation. However, it is regarded to be difficult in obtaining reliable results from portable computer screening tests because of human behavioural variants and the lack of standard testing environment. In this paper, we propose an architecture for implementing a more reliable CCVP system. In particular, a self-organising neural network is applied to manage measurement noise caused by behavioural factors. A control unit is introduced to manage the overall behaviour of the system. The integrated test system has been used to screen optic nerve disease in onchocercal communities of rural Nigeria and the experimental results obtained from a large number of test records are very encouraging: reliable results from volatile test environments may be obtained using the proposed method.
[1]
J. Evans,et al.
Reduction in incidence of optic nerve disease with annual ivermectin to control onchocerciasis
,
1993,
The Lancet.
[2]
J. Hanley,et al.
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
,
1982,
Radiology.
[3]
Wu Jxw.
Visual screening for blinding diseases in the community using computer controlled video perimetry.
,
1993
.
[4]
Teuvo Kohonen,et al.
The self-organizing map
,
1990
.
[5]
Xiaohui Liu,et al.
Identifying the measurement noise in glaucomatous testing: an artificial neural network approach
,
1994,
Artif. Intell. Medicine.
[6]
Teuvo Kohonen,et al.
Self-Organization and Associative Memory
,
1988
.