Research Article

A Novel Ensemble Earthquake Prediction Method (EEPM) by Combining Parameters and Precursors

Table 8

List of significant attributes.

AttributesSignificant attribute descriptionType

CountryThe data of three countries India, Nepal, and Kenya are combined derived from precursor dataIndependent
YearWe have considered the data for the span of 5 years (2015-2019), and it has been derived from the period at which the earthquake occurred above mentioned countriesIndependent
New_time_ist_ hourThe time at which earthquake occurred is obtained by converting the local time of Nepal and Kenya to Indian standard time and included data which already have Indian timeIndependent
Day_periodThe day was bucketed into 6 slices like the readings of the day are grouped into six categories, early morning (2 am to 5 am), morning (6 am to 9 am), afternoon (10 am to 12 pm) late afternoon (1 pm to 4 pm) evening (5 pm to 9 pm), and late evening (10 pm to 1 am)Independent
WeekdaysThe name of the specified week of the day is represented by the name like 1st, 2nd, 3rd, and 4th weekIndependent
TimestampsIt is considered the date and time of country I; here, it is Indian standard time and dateIndependent
Local_timeNepal is 15 minutes ahead, thus the conversion of local time of Nepal to India; Kenya local time is 2.5 hours behind India, thus conversion of Kenya time to IndiaIndependent
DayWhether the time of occurrences is during day or night timeIndependent
WeekendWhether the day of occurrence is weekend or notIndependent
Country_IndiaOut of three countries which country India’s time is considered by conversion of other countriesIndependent
Year_2015Out of five different years, individual year 2015 based on the mean data of that specified yearIndependent
Year_2016Out of five different years, individual year 2016 based on the mean data of that specified yearIndependent
Year_2017Out of five different years, individual year 2017 based on the mean data of that specified yearIndependent
Year_2018Out of five different years, individual year 2018 based on the mean data of that specified yearIndependent
Q1Quarter is divided into four categories like summer, winter, autumn, or spring; it is Q1 of the year summer having high tempIndependent
Q2Quarter is divided into four categories like summer, winter, autumn, or spring; it is Q2 of the year winter having low tempIndependent
Q3Quarter is divided into four categories like summer, winter, autumn, or spring; it is Q3 of the year autumn having moderate tempIndependent