Selected article for: "mean root and square error mean root"
Author: Narinder Singh Punn; Sanjay Kumar Sonbhadra; Sonali Agarwal
Title: COVID-19 Epidemic Analysis using Machine Learning and Deep Learning Algorithms
  • Document date: 2020_4_11
    • ID: 0him5hd2_24
    Snippet: The regression approaches for epidemic analysis are trained and tested on realtime data [2] using the number of confirmed, recovered, and death cases as the label for the corresponding day. With extensive experiments, machine learning approaches are implemented with the polynomial kernel of degree 6 and other coefficient values as gamma=0.01, epsilon=1, and C=0.1. The standard DNN consists of a dense input layer with 128 neurons, three hidden den.....
    Document: The regression approaches for epidemic analysis are trained and tested on realtime data [2] using the number of confirmed, recovered, and death cases as the label for the corresponding day. With extensive experiments, machine learning approaches are implemented with the polynomial kernel of degree 6 and other coefficient values as gamma=0.01, epsilon=1, and C=0.1. The standard DNN consists of a dense input layer with 128 neurons, three hidden dense layers with 256 neurons and output layer is consists of a single neuron whereas the RNN, consists of three stacks of LSTM layers having 64 neurons combined with 10% dropout to avoid the overfitting problem and final output layer with a single neuron. The mean squared error (MSE) is the most widely used objective function and root mean square error (RMSE) as a metric function for evaluating the regression models. The MSE loss can be computed by using equation 1.

    Search related documents:
    Co phrase search for related documents
    • coefficient value and machine learning: 1, 2, 3, 4
    • coefficient value and machine learning approach: 1
    • corresponding day and machine learning: 1, 2
    • death case and epidemic analysis: 1, 2, 3
    • death case and machine learning: 1, 2, 3, 4, 5, 6, 7
    • death case and mean squared error: 1, 2, 3, 4
    • death case and metric function: 1
    • death case and MSE mean squared error: 1
    • dense layer and LSTM layer: 1
    • dense layer and machine learning: 1
    • epidemic analysis and LSTM layer: 1
    • epidemic analysis and machine learning: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10
    • epidemic analysis and mean squared error: 1
    • epidemic analysis and MSE mean squared error: 1
    • extensive experiment and machine learning: 1
    • final output layer and machine learning: 1, 2
    • input layer and LSTM layer: 1, 2, 3
    • input layer and machine learning: 1, 2, 3
    • input layer and mean squared error: 1