• e - ISSN No : 2832-4277
IJRTTE Logo

INTERNATIONAL JOURNAL OF RECENT TRENDS IN TECHNOLOGY AND ENGINEERING (IJRTTE)

Classification of Covid-19 Dataset using Machine Learning

Krishnaveni
Student, Hindusthan College of Engineering and Technology, India.
Privietha P
Assistant Professor, Department of Computer Applications, Hindusthan College of Engineering and Technology, India.

Keywords: classification, COVID, Logistic Regression, XGBoost, Random Forest

Abstract

The project entitled as “Classification of covid-19 analysis using Machine language” is a dataset analysis. The term data analytics refers to the process of examining datasets to draw conclusions. Data analytic techniques enables raw data and uncover patterns to extract valuable insights. Readily available datasets from Kaggle website is used for classification process. Classification is a supervised learning task and pandas is a python library. In order to construct a classification model machine algorithm is predefined. The training model is used or predict a class for new coming document. Seaborn is a library that users Matplot underneath to plot graphs. It will be used to visualize random distribution Dataset. Training is the process that makes the system ‘learn’ the pattern typical classification. We use the default scikit-learn implementation of logistic regression and linear support vector machine for multi-label classification, which trains one classifier per class using a one-vs-rest scheme.
Download Certificate
Details

References

  1. Ashutosh Adhikari, Achyudh Ram, Raphael Tang, and Jimmy Lin. 2019a. Docbert: Bert for document classification. ArXiv, abs/1904.08398.
  2. Simon Baker, Ilona Silins, Yufan Guo, Imran Ali, Johan Hogberg, Ulla Stenius, and Anna Korhonen. ¨ 2016. Automatic semantic classification of scientific literature according to the hallmarks of cancer. Bioinformatics, 32 3:432–40.
  3. Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. Long former: The long-document transformer. arXiv:2004.0515.
  4. Ali S, Patterson M. Spike2vec: An efficient and scalable embedding approach for covid-19 spike sequences. In 2021 IEEE Conference on Big Data (Big Data) 2021 Dec 15 (pp. 1533-1540).
  5. Ali S, Bello B, Patterson M (2021a) Classifying covid-19 spike sequences from geographic location using deep learning. arXiv preprint arXiv:211000809 GISAID Website (Accessed: 10-12-2021) . https://www.gisai dorg/
  6. Leung CK, Chen Y, Hoi CS, Shang S, Cuzzocrea A (2020a) Machine learning and olap on big covid-19 data. In: 2020 IEEE International Conference on Big Data (Big Data), pp 5118–5127
  7. Leung CK, Chen Y, Shang S, Deng D (2020b) Big data science on covid-19 data. In: 2020 IEEE 14th International Conference on Data Science and Engineering (BigDataSE), pp 14–21
  8. Ali S, Mansoor H, Arshad N, Khan I (2019a) Short term load forecasting using smart meter data. In: International Conference on Future Energy Systems, pp 419–421
  9. Lundberg SM, Erion G, Chen H, Himmelfarb J, Bansal N, Lee SI (2020) From local explanations to global understanding with explainable ai for trees. Nat Mach Intell 2(1):2522–5839
  10. Ali S, Shakeel MH, Khan I, Faizullah S, Khan MA (2021) Predicting attributes of nodes using network structure.