Paper Title
Lung Cancer Detection by Integration of GAN and AE Techniques With Iot and Cloud Computing

Abstract
The Internet of Things (IoT) and cloud computing have grown exponentially in the previous ten years, elevating the quality of healthcare services. Simultaneously, lung cancer is recognized as a hazardous illness that raises the yearly worldwide death rate. Generative Adversarial Network (GAN) and Auto Encoder (AE) are now the most efficient image categorization technique, particularly for medical imaging. The two most efficient techniques to enhance the results are feature selection and parameter optimization, which are often handled separately. In this work, an optimum techniques used for classifying lung images is presented. The parameters are improved, feature selection and classification is accomplished by integration of GAN and AE techniques.Three dimensions are used for experimentation: feature extraction, feature selection, parameter optimization and testing is done. 2000 low-dosage, archived lung PET pictures are used as part of a benchmark image database to evaluate the performance of the proposed method. The approach that is being given demonstrates its higher performance on every test image that is applied in several ways. Furthermore, it attains an average accuracy of 94.62 for classification, a considerable improvement over the approaches that were examined. The data set created is stored in cloud. The tested results are transmitted to any place using IoT, where any patients or doctors can visualize. Keywords - GAN, AE, DNN, Machine Learning Algorithms, IoT, Cloud Computing