DESIGN AND IMPLEMENTATION OF EXPERT SYSTEM FOR PNEUMONIA DETECTION SYSTEM

0
492

INTRODUCTION

PNEUMONIA is an illness that disturbs the lung air sacs of an infected person. It is triggered by bacteria, fungi, or a virus that infects the air sacs of lungs that fill up with discharge fluids that leads to chills, fever, coughing with mucus, and breathing trouble among persons diagnosed with this disease. Children below five years of age and elderly patients with weak immune system are vulnerable to this type of diseases. Pneumonia has killed over a million children worldwide in 2018 and remains a life-threatening disease now a days if not detected or diagnose earlier. Radiography, CT-scan, or MRI is the common method to discover pneumonia. Medical personnel check the patient’s radiograph of their chest to determine if they are infected with pneumonia or not. In addition, the usual method for finding pneumonia is through medical history and laboratory results of the patient. Radiograph of chest is penetrated through X-rays where the soft tissues produces a dark color and hard tissues like bones produces a bright color. Patients diagnosed with pneumonia shows the chest cavity signs of fluids filling the air sacs of lungs as for the radiograph picture appears brighter. Several abnormalities may be seen on lung cavities as brighter color may represent such as cancer cells, blood vessels swelling, and abnormality of heart . To validate the range and spot of an infected area of the lungs, chest x-rays is the utmost method. In these method, emergence of the disease can be imprecise and misinterpreted with another illness. Therefore, the undertaking is pleasing in the improvement of the processing in medical situations in isolated areas for pneumonia detection. The researchers were able to train and assessed CNN model’s performance and classify chest x-rays with normal and infected with disease using different classifiers. With the recent development of Computer Aided Design (CAD) tools becomes the most important field of research in artificial intelligence and machine learning. CAD systems has proven in facilitating the medical field such as breast cancer detection, classification of disease using mammograms, lung cancer detection, etc. CAD system is an applicable instrument in use today for diagnosis and classification of diseases in medical imaging. In achieving the precise diagnosis, the medical personnel integrate the CAD to assist and verify to support their decision making. Significant features of the images are valuable in employing machine learning techniques in this system compared to the traditional handcrafted features which has limitations in extracting significant features.The progress in a more intelligent future is now productive through generations. This technological improvement today reached new step closer in human intelligence. The deep learning has gained the ability in simulating the function of the human brain. It recommends the solution to solve real-life problems. The deep learning by means of the convolutional neural networks has ability in obtaining significant characteristics in image classification tasks and provides medical promising results in image analysis.CNN advantages is capable in assisting the identification of some features from an image and use this feature to generate probabilities in classifying specific input.The contribution of this study is developed an optimized deep learning models of CNN that can detect and classify pneumonia diseases efficiently. The work consists of an optimized CNN models and experimental analysis of each model towards the detection and classification of pneumonia diseases.This research article consists of the following sections: introduction, convolutional neural network, methodology, experimental results and discussion, conclusion and recommendations, acknowledgments and references.