(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 13, No. 6, 2022 Detection of COVID-19 from Chest X-Ray Images using CNN and ANN Approach Micheal Olaolu Arowolo 1 , Marion Olubunmi Adebiyi 2 , Eniola Precious Michael 3 Happiness Eric Aigbogun 4 , Sulaiman Olaniyi Abdulsalam 5 , Ayodele Ariyo Adebiyi 6 Department of Computer Science, Kwara State University, Malete, Nigeria 5 Department of Computer Science, Landmark University, Omu-Aran, Nigeria 1, 2, 3, 4, 6 Abstract—The occurrence of coronavirus (COVID-19), which causes respiratory illnesses, is higher than in 2003. (SARS). COVID-19 and SARS are both spreading over regions and infecting living beings, with more than 73,435 deaths and more than 2000 deaths documented as of August 12, 2020. In contrast, SARS killed 774 lives in 2003, whereas COVID-19 claimed more in the shortest amount of time. However, the fundamental difference between them is that, after 17 years of SARS, a powerful new tool has developed that could be utilized to combat the virus and keep it within reasonable boundaries. One of these tools is machine learning (ML). Recently, machine learning (ML) has caused a paradigm shift in the healthcare industry, and its use in the COVID-19 outbreak could be profitable, especially in forecasting the location of the next outbreak. The use of AI in COVID-19 diagnosis and monitoring can be accelerated, reducing the time and cost of these processes. As a result, this study uses ANN and CNN techniques to detect COVID-19 from chest x-ray pictures, with 95% and 75% accuracy, respectively. Machine learning has greatly enhanced monitoring, diagnosis, monitoring, analysis, forecasting, touch tracking, and medication/vaccine production processes for the Covid-19 disease outbreak, reducing human involvement in nursing treatment. Keywords—Machine learning; COVID-19; ANN; CNN; X-ray images I. INTRODUCTION Throughout history, there has been widespread of infectious disease among our places of residence. This has caused deterioration of every aspect of our economics and well-being as a whole. This effect has caused solutions being found through the use of machine learning as a division of artificial intelligence. Over the years there has been the existence some pandemics such as the Athenian plague [1], Ebola pandemic [2], HIV pandemic [3], Zika virus [4], black death [5], etc. Coronavirus which is a happening contactable epidemic that is all over the spheres of the world is a virus belonging to the family Coronaviridae [6]. In fighting covid-19 there has been many solutions being proffered through the use of different machine learning techniques [7]. It has also aided in various studies, including the ensemble of machine learning for the simulation of covid19 deaths [8], as well as identifying who is prone to being the next victim, diagnosing suspected individuals, developing medicine vastly, and being able to predict the next occurrence of such a remerging virus. Some computer scientists have used machine learning to test coronavirus presence such as [9] who worked on automated detection of Coronavirus disease-2019 (COVID-19) from X-ray images and used YOLO (You only look once) machine learning technique. However, his model misdiagnosed COVID-19 patients as pneumonia and predicted incorrectly in low production of X-ray images and patients with other diseases. Research uses Convolutional Neural Network (CNN) and the deep learning approach to detect multi-class brain disease using MRI images. There was no feature extraction, collection, or classification in this process because it was fully automated [10]. A system created from machine learning techniques was also created to diagnose coronavirus [11]. Artificial intelligence (AI)-based models have effectively used current noticeable data to learn the cause of current therapies on humans, provided their unique characteristics. All this will help in detecting various diseases based on each individual’s characteristics. Recent advancements in machine learning models optimized for making research through noticeable information setting can be used to learn customized treatment outcomes. However, although these models can produce correct diagnosis and predict other ailments and infectious diseases. Furthermore, regardless of how accurate most machine learning models relating to covid19 prediction appear to be, they appear to be difficult to interpret. The difficulty in detecting Covid19 infection at an early stage is also attributed to the high similarity of its symptoms to those of pneumonia. As a result, distinguishing cases of coronavirus from pneumonia is easy, which could save a patient's life. This research uses chest X-ray images to classify Coronavirus disease using machine learning classifiers (convolutional neural networks) implemented in Python, as well as rectified linear units (ReLU) to help overcome image non-linearity (in this case chest x-ray images). This research, on the other hand, suggests using a Convolutional neural network (CNN) and Artificial Neural Network (ANN) method to develop a model to detect coronavirus disease. II. REVIEWS OF RELATED WORK With the support of imaging and image-based classification methods, machine learning is now a highly important and flexible technique for detecting terminal diseases in recent years. 754 | Page www.ijacsa.thesai.org