700 Journals and 15,000,000 Readers Each Journal is getting 25,000+ ReadersThis Readership is 10 times more when compared to other Subscription Journals (Source: Google Analytics)
Research Article Open Access
This paper proposes a feature selection based classification method that can be applied to better accuracy in the Digital Radiographs (DR) for the identification of Inferior Alveolar Nerve Injury (IANI). Different conventional features based on the shape and EZW (Embedded Zero tree Wavelet) based texture features are extracted using different feature extraction techniques. Then, aggregate voting of all the decision trees in the Random Forest (RF) method to get the reduced feature. Finally, Support vector machine (SVM) with RBF kernel is trained using reduced features to classify the IAN (Inferior Alveolar Nerve) injured on a healthy object. The proposed classification results are compared with PCA-DT, PCA-MLP and PSO-MLP classification algorithms. Both training and testing stages of proposed model get better classification accuracy of 96.4% and 83.58% respectively. This shows the highest classification accuracy performance among some other existing methods.
Digital radiographs, Feature selection, Inferior alveolar nerve injury, Random forest, Support vector machine, #