Role of Classification Model with Fuzzy Model to Predict Covid-19: A Comparative Study

The ongoing Coronavirus pandemic is the infectious disease brought about by the latest discovered coronavirus, and is affecting many countries globally. At the present time it is difficult to test everybody globally so a model is developed in this paper that can help in predicting the risk of coronavirus. A decision tree is constructed for this purpose based on certain attributes like fever, dry cough, tiredness, difficulty to breath, and chest pain;and is compared using various other methods. Classification Functions are used for the prediction and the results are compared based on accuracy. It was observed that Multilayer Perceptron classifier achieved the highest accuracy of 95.31%, however the generated tree using J48 achieved same accuracy (90.63%) as that of LMT & Logistic classifiers. Rules generated by Decision tree are then used in the Fuzzy Inference System using MATLAB to give predictions related to the disease risk. © 2021, Springer Nature Switzerland AG.

[1]  Wim Naudé,et al.  Artificial Intelligence Against Covid-19: An Early Review , 2020, SSRN Electronic Journal.

[2]  Allan Tucker,et al.  Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection , 2020, ArXiv.

[3]  Umut Ozkaya,et al.  Coronavirus (Covid-19) Classification Using CT Images by Machine Learning Methods , 2020, RTA-CSIT.

[4]  Mayank Aggarwal,et al.  Fuzzy Rule Based System to predict COVID19 - A Deadly Virus , 2020, International Journal of Management and Humanities.

[5]  Ali Narin,et al.  Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks , 2020, Pattern Analysis and Applications.

[6]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .

[7]  Yaozong Gao,et al.  Large-scale screening to distinguish between COVID-19 and community-acquired pneumonia using infection size-aware classification , 2021, Physics in medicine and biology.

[8]  Alexander Wong,et al.  COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images , 2020, Scientific reports.

[9]  Umut Ozkaya,et al.  Coronavirus (COVID-19) Classification Using Deep Features Fusion and Ranking Technique , 2020, Big Data Analytics and Artificial Intelligence Against COVID-19: Innovation Vision and Approach.

[10]  Y. Hu,et al.  Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China , 2020, The Lancet.

[11]  Alexandra Luccioni,et al.  Mapping the Landscape of Artificial Intelligence Applications against COVID-19 , 2020, J. Artif. Intell. Res..

[12]  COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification , 2020, Inf..

[13]  G. Pandey,et al.  SEIR and Regression Model based COVID-19 outbreak predictions in India , 2020, medRxiv.

[14]  Joseph Paul Cohen,et al.  COVID-19 Image Data Collection: Prospective Predictions Are the Future , 2020, ArXiv.

[15]  Yan Bai,et al.  Presumed Asymptomatic Carrier Transmission of COVID-19. , 2020, JAMA.

[16]  Ting Yu,et al.  Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study , 2020, The Lancet.

[17]  Gurjit S. Randhawa,et al.  Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study , 2020, PloS one.

[18]  X. Wang,et al.  Clinical characteristics of COVID-19 and the model for predicting the occurrence of critically ill patients: a retrospective cohort study. , 2020, medRxiv.