Covid-19 Data Preprocessing Approach in Machine Learning for Prediction
摘要
Artificial Intelligence (AI) is a vast field that allows the development of programs capable of simulating human intelligence. One of the most used AI techniques that is very important the preparation of raw data which is called data preprocessing in Machine Learning. Data preprocessing is a technique that makes the data clean for machine learning and improves the performance of the model. With the different steps that we found already defined we set up a simpler architecture for data preprocessing. For that purpose, we worked with 5644 data simple of Covid-19. After analyzing the contours of our data; we have as steps of this architecture first the collection of data, the cleaning of these data, the encoding, the normalization of the data, the imputation to manage the missing values, then the selection of variables and finally the selection of features. We obtain an accuracy of 78% as a result of our experimentation with a very small error rate. This Covid-19 detection prediction result shows that data preprocessing plays an important role in Machine Learning.