P
Pijush Samui
Researcher at National Institute of Technology, Patna
Publications - 297
Citations - 5906
Pijush Samui is an academic researcher from National Institute of Technology, Patna. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 31, co-authored 236 publications receiving 3230 citations. Previous affiliations of Pijush Samui include Kunsan National University & University of Massachusetts Lowell.
Papers
More filters
Journal ArticleDOI
Determination of contaminatated wells to no3-n: a novel vulnerability assessment tool
Pijush Samui,Barnali M. Dixon +1 more
TL;DR: In this article, a regional scale integrated GIS-based modeling approach was used to predict NO3-N contamination of ground water in a cost effective way. And the developed RVM has been compared with the Artificial Neural Network (ANN) and SVM models.
Journal ArticleDOI
Application of deep learning approaches to predict monthly stream flows
Huseyin Yildirim Dalkilic,Deepak Kumar,Pijush Samui,Barnali M. Dixon,S. Yeşilyurt,Okan Mert Katipoğlu +5 more
Journal ArticleDOI
Performance of traditional and machine learning-based transformation models for undrained shear strength
TL;DR: In this article , the performance of traditional transformation models is compared to that of machine learning (ML)-based models, and the influence of data coherence is studied by using two datasets of different quality.
Book ChapterDOI
Multivariate Adaptive Regression Spline Based Reliability Analysis of Stability of Durgawati Earthen Dam
TL;DR: In this paper, multivariate adaptive regression splines (MARS) method is used to carry out reliability analysis of Durgawati earthen dam and the steady and transient state seepage is considered while calculating reliability index.
Journal ArticleDOI
A Hybrid DNN Model for Travel Time Estimation from Spatio-Temporal Features
TL;DR: In this article , a hybrid deep learning model that extracts the optimal feature points from the existing dataset using a stacked autoencoder is presented to predict the travel path and travel time between two geographic points.