A Novel All Possible Periodic Sets Ensemble Linear Regression Scheme – a Case Study of Construction Accidents (Fatal Falls) Prediction
Rahul Konda *
Department of Civil Engineering, Osmania University, Hyderabad, Telangana, India.
Ramesh Chandra Bagadi
Department of Civil Engineering, Osmania University, Hyderabad, Telangana, India and Ramesh Bagadi Consulting LLC (R042752), Madison, 53715, Wisconsin, USA.
V. S. S. Kumar
Department of Civil Engineering, Osmania University, Hyderabad, Telangana, India and NITTR Chennai, Ministry of HRD, Government of India, India.
Suresh Kumar. N
Department of Civil Engineering, Osmania University, Hyderabad, Telangana, India.
*Author to whom correspondence should be addressed.
Abstract
In this research investigation, the authors have proposed an All Possible Periodic Sets Ensemble Linear Regression Scheme. In this case, all possible periodic sets are considered (evaluated with all holistic variable integral periodicities of Time Instants computed backwards with respect to one step future forecast position of the given series) and their predictors for a particular considered future co-ordinate is evaluated. We again pro-rate these thusly found future values using an Inner Product value obtained by the normalized vector consisting of all the points of the given dataset under linear regression analysis (arranged in a chronological order) along with its future prediction value of the afore-considered future time co-ordinate of concern and any set normalized vector among the all possible sets of the data co-ordinates (also arranged in chronological order only that the missing points shall be denoted by zero) along with its future prediction value of the afore-considered future time co-ordinate of concern, in the computation of the Ensemble Weighted Average. The entire computational analysis is performed in R Programming Software environment.
Keywords: Linear regression, R programming software