7.
Conclusion
\label{conclusion}
The motive of this work is to develop a diagnostic model for earlier
detection and accurate prediction of dengue disease. Dengue is a human
life threatening disease due to serve depletion of platelets. In this
work, PSO-ANN based diagnostic model is proposed for earlier detection
and accurate prediction of dengue disease. In the proposed model,
initially PSO method is adopted to optimize the parameters of ANN
approach and after parameters optimization, ANN approach is applied to
dengue disease dataset for finding dengue affected patients. Further,
10-crossfold method is employed to validate the results of the proposed
diagnostic model. From results, it is seen that the proposed model
provides better results in comparison to other approaches like ANN, DT
NB, and PSO. It is also observed that parameter optimization of ANN has
significant impact on its performance and resulted in improved
performance than simple ANN approach. But, it is also observed that
PSO-ANN model having large computational time than other approaches. It
is concluded that PSO-ANN based diagnostic model is capable to detect
the dengue disease earlier and diagnosis it more accurately.