Authors :
Aleena Anto; Shelja Jose M
Volume/Issue :
Volume 8 - 2023, Issue 1 - January
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3K5tWIT
DOI :
https://doi.org/10.5281/zenodo.7638759
Abstract :
The intensity of Seismic damage prediction
is an important task that aims to predict seismic
events in real time from historical data or seismic time
series. Due to the increase in seismic data available
over the past few decades, research in the field of
seismic event detection has achieved considerable
success using neural networks and other machine
learning techniques. An earthquake is the negative
impact. That it significantly harms a community. An
earthquake causes loss of life. The system predicts the
intensity of damage to be occurring in an earth quake
with the help of previous text data. The system
predicts magnitude and depth value. Using this value
(Magnitude and depth) predict the intensity of
damage. This work, proposes a random forest, KNearest Neighbor (KNN), and support vector machine
(SVM) for earthquake damage prediction. Finding
out the best model from various Machine Learning
algorithms to build prediction models, evaluate the
accuracy and performance of these models. Among
these three methods Random forest regressor
algorithm shows the most accurate result with 98%
accuracy.
Keywords :
KNN, SVM, Random Forest Regressor, Magnitude, and Depth.
The intensity of Seismic damage prediction
is an important task that aims to predict seismic
events in real time from historical data or seismic time
series. Due to the increase in seismic data available
over the past few decades, research in the field of
seismic event detection has achieved considerable
success using neural networks and other machine
learning techniques. An earthquake is the negative
impact. That it significantly harms a community. An
earthquake causes loss of life. The system predicts the
intensity of damage to be occurring in an earth quake
with the help of previous text data. The system
predicts magnitude and depth value. Using this value
(Magnitude and depth) predict the intensity of
damage. This work, proposes a random forest, KNearest Neighbor (KNN), and support vector machine
(SVM) for earthquake damage prediction. Finding
out the best model from various Machine Learning
algorithms to build prediction models, evaluate the
accuracy and performance of these models. Among
these three methods Random forest regressor
algorithm shows the most accurate result with 98%
accuracy.
Keywords :
KNN, SVM, Random Forest Regressor, Magnitude, and Depth.