Apurba Narayan Das

Apurba Narayan Das

Auto-generated profile, based on publicly available information

Apurba Narayan Das

Department of Industrial Engineering and Management

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022 in Complexity
Verified
Journal Article
Open access
PDF file
SRS. M. Taslim Uddin Raju
S. M. Taslim Uddin Raju
ASAmlan Sarker
Amlan Sarker
ADApurba Das
Apurba Das
MIMd. Milon Islam
Md. Milon Islam
Mabrook Al-RakhamiMabrook Al-Rakhami
Mabrook Al-Rakhami
FAFahad Albogamy
Fahad Albogamy
This paper aims to introduce a robust framework for forecasting demand, including data preprocessing, data transformation and standardization, feature selection, cross‐validation, and regression ensemble framework. Bagging (random forest regression (RFR)), boosting (gradient boosting regression (GBR) and extreme gradient boosting regression (XGBR)), and stacking (STACK) are employed as ensemble models. Different machine learning (ML) approaches, including support vector regression (SVR), extreme learning machine (ELM), and multilayer perceptron neural network (MLP), are adopted as reference models. In order to maximize the determination coefficient (R2) value and reduce the root mean square error (RMSE), hyperparameters are set using the grid search method. Using a steel industry dataset, all tests are carried out under identical experimental conditions. In this context, STACK1 (ELM + GBR + XGBR‐SVR) and STACK2 (ELM + GBR + XGBR‐LASSO) models provided better performance than other models. The highest accuracies of R2 of 0.97 and 0.97 are obtained using STACK1 and STACK2, respectively. Moreover, the rank according to performances is STACK1, STACK2, XGBR, GBR, RFR, MLP, ELM, and SVR. As it improves the performance of models and reduces the risk of decision‐making, the ensemble method can be used to forecast the demand in a steel industry one month ahead.

1 September 2015 in Ain Shams Engineering Journal
Verified
Journal Article
Open access
PRPranab Kanti Roy
Pranab Kanti Roy
ADApurba Das
Apurba Das
HMHiranmoy Mondal
Hiranmoy Mondal
AMAshis Mallick
Ashis Mallick
This work aimed at studying the effects of environmental temperature and surface emissivity parameter on the temperature distribution, efficiency and heat transfer rate of a conductive–radiative fin. The Homotopy Perturbation Method (HPM) being one of the semi-numerical methods for highly nonlinear and inhomogeneous equations, the local temperature distribution efficiencies and heat transfer rates are obtained using HPM in which Newton–Raphson method is used for the insulated boundary condition. It is found that the results of the present works are in good agreement with results available in the literature

1 January 2021 in International Journal of Fluid Mechanics Research
Verified
Journal Article
Closed access
PDF file
SSSandip Saha
Sandip Saha
PBPankaj Biswas
Pankaj Biswas
SRSantanu Raut
Santanu Raut
ADApurba Narayan Das
Apurba Narayan Das
Considering four various forms of baffle (plane, trapezoidal, triangular and isosceles) with sixteen baffle configurations, numerical simulations of steady, incompressible turbulent air hydro-thermal phenomena have been studied in a rectangular micro-channel which have key role in modeling heat exchangers. The governing equations have been solved using finite volume method and employing SIMPLE algorithm. To study the turbulence phenomenon, SST k – ω turbulence model has been used. For all the forms of channel, flow structure, normalized velocity profile, normalized skin friction coefficient, normalized friction factor, local, average Nusselt number and thermal enhancement factor have also been studied at different Reynolds number (Re). Among all the baffles, it has been found that trapezoidal-triangular baffles provide the highest Nusselt number and triangular-isosceles baffles provide the lowest thermal enhancement factor.

1 January 2022 in International Journal of Fluid Mechanics Research
Verified
Journal Article
Closed access
PDF file
SSSandip Saha
Sandip Saha
SRSantanu Raut
Santanu Raut
ADApurba Narayan Das
Apurba Narayan Das
In this work, we have investigated the turbulent hydrothermal airflow characteristics over a rectangular channel embedded with rectangular, triangular, and trapezoidal baffles in the outer walls of it. The finite-volume method with the second-order upwind scheme has been used to discretize the governing equations and, employing the SST k-ω turbulence model, the turbulent airflow structure has been described. For nine different cases, several phenomena of thermal behaviors have been studied at the values of Reynolds number in [5000-20,000]. It is found that existence of trapezoidal baffles in the channel [case-3(c)] gives the maximum value of Nusselt number and the increase in Reynolds number induces rise in the values of Nusselt number, friction factor. The outcomes of this work provide the basis for more optimization in various heat-exchanger shell and tube models.