Quantum photonics based health monitoring system using music data analysis by machine learning models

Lung disease is one of the most common illnesses that should be treated in its early stages to improve the chances that patients will survive. Making the cancer diagnosis is the radiologist’s most difficult task. The advantages of a sophisticated computer-aided system for radiologists are enormous. Numerous studies use ML algorithms to detect lung cancer. To predict lung cancer, a multistage classification is most frequently used. The segmentation and data improvement classification scheme has been completed. This study suggests a unique method for detecting lung cancer combining machine learning and quantum music photonics. Here, trumpet players’ data has been gathered and examined for noise reduction, normalization, and smoothing. With the help of support kernel vector Gaussian learning and spatio convolutional perceptron learning, the characteristics of the processed data are retrieved and categorized. Different lung cancer datasets are subjected to experimental study in terms of accuracy, precision, recall, AUC, TPR, and FPR. The efficiency of the suggested strategy for the identification and categorization of lung cancer nodules is demonstrated by experimental data. The proposed technique attained accuracy of 97%, precision of 94%, recall of 85%, AUC of 72%, TPR of 55%, FPR of 45%.