Virus Prediction Using Machine Learning Techniques

• Published in: 2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS) Vol. 1; pp. 1174 - 1178
• Main Authors: Reji, Jerin, Kumar, R Satheesh
• Format: Conference Proceeding
• Language: English
• Published: IEEE 25-03-2022
• Subjects: Animals; ANN; Artificial neural networks; Computational modeling; Feature extraction; KNN; Machine learning; Machine learning algorithms; Prediction; Support vector machines; SVM; Virus
• DOI: 10.1109/ICACCS54159.2022.9785020
• EISSN: 2575-7288

In biological aspects, a virus is a microorganism that is smaller in size and can replicate within a host organism. A virus can affect a variety of living organisms like animals and plants. The genetic codes can be DNA or RNA. A virus cannot replicate itself. It needs a host organism for replication. A human being, an animal, or a plant can be this host organism. This replication can cause various effects in living organisms. These effects can lead to various diseases. Viruses are different in their biological structure and can affect some regions in the animal body. So the task of detecting all types of viruses, in the same way, is not possible. Thus, there is a need for different detection techniques for different viruses. Various viruses, diseases, and machine learning algorithms for detecting these diseases are covered in this study. For the review process in this study, ten different articles were chosen. In creating machine learning models for disease diagnosis, each of these publications uses a variety of machine learning algorithms and feature selection methods. Support vector machine (SVM), Linear model (LM), Linear regression (LR), K-Nearest Neighbors (KNN), Artificial neural network (ANN), K-means, and other machine learning approaches are utilized in these publications. Various feature selection approaches and machine learning methods are used in these articles. Because of that, the suggested model's accuracy varies. This research can be used to blend different machine learning algorithms into one or to gain a better understanding of viruses and diseases.