applied to effectively diagnosis and
prediction of dengue disease. The parameters setting of all approaches
is illustrated in Table 3. The k-cross fold validation method is also
used to validate the results of the proposed approach. Further, a
confusion matrix is designed to evaluate the performance of PSO-ANN
approach.Confusion matrix defines the relationship between value
predicted by the model & actual value. The upper left cell of confusion
matrix denotes the number of data classified as true while they are true
(i.e. True positives) and the upper right cell denotes the number of
data classified as true while they actually were false (i.e., false
positive). The lower left cell denotes the number of data classified as
false while they actually were true (i.e., false negatives) and lower
right cell denotes the number of data classified as false while they
were actually false (i.e. True, False). The performance of the PSO-ANN
diagnostic model is measured using accuracy, sensitivity, specificity,
error rate and area under curve (AUC) parameters. The results of the
proposed model are also compared with other approaches like Naïve Bayes,
Decision Tree, ANN and
PSO.
\label{this-section-summarizes-the-results-of-our-study.-in-this-work-a-pso-ann-based-approach-is-applied-to-effectively-diagnosis-and-prediction-of-dengue-disease.-the-parameters-setting-of-all-approaches-is-illustrated-in-table-3.-the-k-cross-fold-validation-method-is-also-used-to-validate-the-results-of-the-proposed-approach.-further-a-confusion-matrix-is-designed-to-evaluate-the-performance-of-pso-ann-approach.confusion-matrix-defines-the-relationship-between-value-predicted-by-the-model-actual-value.-the-upper-left-cell-of-confusion-matrix-denotes-the-number-of-data-classified-as-true-while-they-are-true-i.e.-true-positives-and-the-upper-right-cell-denotes-the-number-of-data-classified-as-true-while-they-actually-were-false-i.e.-false-positive.-the-lower-left-cell-denotes-the-number-of-data-classified-as-false-while-they-actually-were-true-i.e.-false-negatives-and-lower-right-cell-denotes-the-number-of-data-classified-as-false-while-they-were-actually-false-i.e.-true-false.-the-performance-of-the-pso-ann-diagnostic-model-is-measured-using-accuracy-sensitivity-specificity-error-rate-and-area-under-curve-auc-parameters.-the-results-of-the-proposed-model-are-also-compared-with-other-approaches-like-nauxefve-bayes-decision-tree-ann-and-pso.}