Extraction And Analysis Of Covid-19 Data Using Techniqus K-Means Clustering By Data Mining Techniques

The goal from this study Data mining techniques like K-Means Clustering are used to investigate the Covid-19 Coronavirus Diseases. Researcher's prediction will not only allow detection and pipeline to predict how much money their detection method for COVID-19 will make, but it will also allow them to justify their characteristics, such as type of infection and choice of vaccine in order to reach a certain detection using data mining-based model. In this way, the lack of cultural data was no longer an issue with new COVID-19 predictions. With the data mining algorithm, researchers provide prediction at 15 to 20 different methods with an accuracy above 80% after training. The training is performed on 80% of data while the testing is done on remaining 20% of data. Such prediction will also allow other interested third parties to predict the success of a COVID-19 detection before it is released on open-source community. In the process of prediction, some researchers found the variables most associated with COVID-19 detection, and to see how the various prediction models are affected by them. Nevertheless, those data mining-based methods can greatly benefit from modern artificial intelligence techniques for this purpose that can handle complex features and give out great prediction results. Therefore, employing historical COVID-19 data and using them in data mining algorithms to predict disease could save companies millions of dollars on rather unsuccessful detection. The results were adopted by quantitative prediction identical to the classification of COVID-19 using artificial intelligence. The results achieved by the SMV model with ML sentiment analysis have a very high accuracy in predicting behavior (87.71 %). Correcting many types of behavior for different people and its ability to perform is much better than predicting all COVID-19 with a decrease in loss.