Asset Details
Do you wish to reserve the book?
FFT based ensembled model to predict ranks of higher educational institutions
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
FFT based ensembled model to predict ranks of higher educational institutions
Do you wish to request the book?
FFT based ensembled model to predict ranks of higher educational institutions
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
FFT based ensembled model to predict ranks of higher educational institutions
2022
Overview
Predicting international rankings has always been a demanding area for Universities and Higher Educational Institutions (HEIs) all over the world in the recent decade. In this research work, a novel tool EnFftRP (Ensembled Fast Fourier Transformed Ranking Prediction) is developed for predicting international ranks of various universities and HEIs. It uses a hybrid ensembled model in duology with the Fast Fourier Transformation (FFT). Ensemble model improves the prediction accuracies which are elevated further using FFT. The fourier processing algorithm, being an influential computational concept for data anatomy is a novel approach applied to the ensembled model. A combination of six base models Decision Tree, Support Vector Machine, Multilayer Perceptron, K-Nearest Neighbour, Random Forest and Logistic Regression are deployed for the construction of ensembled model. The data set being used is Shanghai World Ranking University Dataset for 14 years ranging from 2005 to 2018. It is split into training and test data set. The training data set is considered from year 2005–2014 and the test dataset from 2015 to 2018. It is empirically established that proposed tool produces highly promising prediction parameters as accuracies (95%), specificities (94.41%), sensitivities (95.54%), Productively Predicted Values (94.94%), Non-Productively Predicted Values (95.07%), F1-score (97.40%) and Kappa score (0.90) as compared to obtained by similar models like RSFT and others. To the best of our knowledge, till now no tool exists which can predict the ranks of HEIs with this much high predictive power.
Publisher
Springer US,Springer Nature B.V
