Purpose: Pneumonia is a common and possibly fatal illness among children hence prompt and precise diagnosis is essential for the proper course of therapy. X-Ray pneumonia diagnosis is impacted by cross-diagnosis, perplexing benign abnormalities, hazy images, exploding deeper network parameters, time complexity and higher accuracy. Diagnosing pneumonia in children might be difficult because of the weak clinical signs and low sensitivity of microbiological investigations. Hence, the objective of this research is to build a meta-learning model in Machine Learning that can precisely analyze the image features and build generalized model to identify the presence and diagnose the type of pneumonia in child chest radiographs. Methods: The suggested meta-model makes use of three supervised classifiers, including decision tree, nearest neighbor’s classifier and support vector classification as well as three ensemble classifier such as adaptive boosting, random forest and gradient boosting classifier. These classifiers are trained on pixel intensity features extracted from a sizable Karmany dataset of radiology images and make preliminary predictions. Results:A robust hard voting meta-model classifier is built to diagnose pneumonia variant with bacterial or viral infection with an accuracy score of 94.54% and F1-Score of 94.34%. Conclusion:The suggested research shows a resilient machine learning meta-model that overcomes the overfitting issue that is typically seen in traditional machine learning models like SMO, MP, LDA, Xgboost and ERBM for pneumonia diagnosis. Proposed classifier has greater generalized prediction performance over 64*64 trainable size input. The findings demonstrate that prediction accuracy, resource usage, and temporal complexity all rise together with the size of the preprocessed radiograph, potentially resulting in resource depletion. Additionally, with the increase in size of the radiograph, less preprocessing wall time and CPU time are needed. This research endeavor is being assisted by Radiologist, Sun Lab Diagnostic, Virar, and Cardinal Gracious Memorial Hospital, Vasai, for clinical conduct and validation of outcomes.