PNEUMONIA DETECTION SYSTEM USING DEEP LEARNING
Abstract
Pneumonia, a severe respiratory infection, remains a major global health concern, especially in low-resource settings. Early detection is crucial for effective treatment, but traditional diagnostic methods, such as physical examinations, X-ray interpretations, and blood tests, are time- consuming and prone to human error. This project proposes an automated pneumonia detection system using deep learning techniques, particularly Convolutional Neural Networks (CNNs), to enhance diagnostic accuracy and efficiency. The system utilizes a large dataset of chest X-ray images to train the model, with techniques like transfer learning and data augmentation employed to improve performance. Evaluations show that the model achieves over 95% accuracy, demonstrating its ability to reliably classify pneumonia cases. The research also addresses challenges such as dataset limitations, over fitting, and the practical integration of the system in clinical environments. This project highlights the potential of deep learning to revolutionize pneumonia diagnosis by providing faster, more accurate results, ultimately improving patient outcomes and supporting healthcare professionals.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.