Mitigation steps to control Covid-19 outbreak in Indonesia need to take. One of those step is forecasting the spread of the disease. This study compare two artificial neural network models in catching the pattern of Covid-19 positive total cases in Indonesia. Data Training used in this study is Indonesian total positive cases of Covid-19 from March 2 until May 26. The next 10 days data become data testing to show the model accuracy in predicting Covid-19 total cases. MLP shows a better prediction comparing to ELM.Three different prediction accuracy measurement is used – MAE, MAPE, and RMSE. All of them shows less value in MLP than in ELM.

This study use Classroom Action Research (PTK) or Classroom Action Research with research subjects, namely class X TKJ 1 SMKN 10 Makassar, totaling 36 people. This research was conducted with the aim to determine the level of certainty or confidence in each answer given by students so that it can be classified between students who experience a concept error in understanding a concept with students who understand the concept. The study was conducted in two cycles, each cycle there were 3 meetings using action procedures namely planning, implementing, observing and reflecting using cooperative learning models. Data collection is done by pretest at the beginning of the cycle, posttest at the end of the cycle, observation of student activities and CRI assessment of the answers given by students in a question. The results of this study indicate that using the Certainly Of Response Index (CRI) assessment index can help to distinguish between students who understand the material, students who experience misconceptions and students who do not understand the material.