ABSTRACT
It has been determined that lung cancer is the key factor responsible for the increased cancer mortality rate seen by this generation. In order to successfully treat lung cancer, early diagnosis of symptoms is an imperative necessity. In order to establish a sustainable prototype model for the treatment of lung cancer that does not have a negative impact on the natural environment, the most recent technology breakthroughs, such as the Internet of Things and computational intelligence, may be applied. As a result, there will a less time and effort throughout the operation, and you will have access to a more expedient method of diagnosing lung cancer that will require the assistance of a lesser number of people. In this paper, we present a transfer learning-based algorithm to classify the lung cancer from the input real time data based on the training of the classifier by UCI datasets. The method involves pre-processing, feature extraction and classification using transfer learning. The simulation is conducted in python to test the efficacy of the model against UCI repository datasets. The results of simulation shows that the proposed method achieves higher classification accuracy, precision, recall and f-measure than the existing methods.
