Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Filters

2014 - 20205

Settings

Has files: NoSubject: search.filters.subject.Bayesian

Search Results

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Parameter estimation using heat transfer models with experimental data using a combined ann-Bayesian approach
    (Begell House Inc., 2014) Gnanasekaran, N.; Shankar, N.T.; Balaji, C.
    A hybrid approach, wherein Markov Chain Monte Carlo simulations are used in a Bayesian framework, in conjunction with artificial neural networks (ANN) is developed for solving an inverse heat conduction problem. Steady state three-dimensional heat conduction from a Teflon cylinder with uniform volumetric internal heat generation is considered. The goal is to estimate qv, given the heat transfer coefficient h, the thermal conductivity k and temperature data at certain fixed locations on the surface of the cylinder. For the purposes of establishing the soundness and efficacy of the approach, temperatures obtained by a numerical solution to the governing equation for known values of the parameter qv are first used to retrieve the quantities of interest, followed by retrievals with actual measurements. In order to significantly reduce the computational time associated with the MCMC simulations, first, a neural network is trained with limited number of solutions to the forward model. This serves as a surrogate to replace the forward model (conduction equation) during the process of retrievals with Markov Chain Monte Carlo simulations in a Bayesian framework. The performance of the proposed hybrid technique is evaluated for different cases.
  • No Thumbnail Available
    Item
    Hybrid intelligent bayesian model for analyzing spatial data
    (Springer Verlag service@springer.de, 2018) Velmurugan, J.; Venkatesan, M.
    Spatial data mining refers to the extraction of Geo Spatial Knowledge, maintaining their spatial relationships, along with other interesting patterns not explicitly stored in spatial datasets. The overall objective of this research work is to apply GIS based data mining classification modeling techniques to assess the spatial landslide risk analysis in Nilgris district, Tamilnadu, India. Landslide is one of the most important hazards that affect different parts of India in the every year. Landslides cover broad range impact on the people of the affected area in terms of the devastation caused to material and human resources. Landslide is generated by various factors such as rainfall, soil, slope, land use and land covers, geology, etc. Each landslide factor has a different level of values. The ranking of values and assignment of weight to the landslide factor gives good classification of landslide risk level. Data science and soft computing play major role in landslide risk analysis. The rank and weight are assigned to the landslide factor and its different levels using classification data science techniques. In this paper, we proposed a new model with integration of rough set and Bayesian classification called Hybrid Intelligent Bayesian Model (HIBM) to analyze the possibilities of various landslide risk level. The proposed model is compared with real-time data, and performance is validated with other data science models. © 2018, Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Computation of error model for the inverse bioheat transfer problem
    (Dalian University of Technology, 2018) Gnanasekaran, N.; Vishweshwara, P.S.
    An inverse estimation of size and location of tumor is proposed in this paper using Bayesian framework. The forward model comprises of the Pennes equation and solved using commercial software. The forward solution of the problem is validated against the available literature and the results are found to be promising. Estimation of the size and location of the tumor is attempted based on Bayesian framework along with the Markov chain Monte Carlo method. This paper also demonstrates 2D and 3D modelling of the cancerous tissue and exploits the advantage of 2D model in the computation of MCMC method. An Approximation Error Model (AEM) is proposed in order to statistically account the model error during the estimation of the unknown parameters. The results of the AEM provide a new trend in the parametric study of cancerous tissue. © 2018 by the authors of the abstracts.
  • No Thumbnail Available
    Item
    A novel framework for the estimation of interfacial heat transfer coefficient using Bat algorithm during solidification of metal casting
    (Toronto Metropolitan University, 2019) Vishweshwara, P.S.; Gnanasekaran, N.; Arun, M.
    In the present work, the interfacial heat transfer coefficient (IHTC) at the mold metal interface is estimated during solidification of Al-4.5wt%Cu alloy using ANN-Bat-Bayesian framework. The forward model comprises of a one dimensional transient governing equation for the solidification of metal casting and is solved using explicit finite difference scheme with the available IHTC correlation from the literature. Within the range of values of constants of IHTC correlation, a set of numerical simulation is performed and corresponding temperature output is trained using Artificial Neural Network (ANN). The network created acts a fast forward model replacing the FDM scheme during IHTC estimation thus reducing computational time. Bat algorithm is used as inverse method along with the Bayesian framework, that drives towards the accurate retrieval of unknown parameters. © 2019, Toronto Metropolitan University. All rights reserved.
  • No Thumbnail Available
    Item
    A Surrogate Forward Model Using Artificial Neural Networks in Conjunction with Bayesian Computations for 3D Conduction-Convection Heat Transfer Problem
    (Springer, 2020) Kumar, M.K.; Vishweshwara, P.S.; Gnanasekaran, N.
    The present work describes the determination of heat flux at the boundary for a conjugate heat transfer problem based on a coupled three-dimensional conduction-convection fin numerical model, also referred to as complete model. The model is developed using commercially available software and solved along with Navier–Stokes equation in order to acquire the required temperature distribution. An inverse analysis is proposed by treating the boundary heat flux as unknown while the temperatures of the fin are known. The inverse analysis is greatly accomplished with the help of Bayesian framework that combines the solution of the forward model and the simulated measurements. Markov chain Monte Carlo (MCMC) is applied to explore the sample space that drives samples to proper convergence and the selection or acceptance of the new samples is performed using Metropolis–Hastings algorithm. Thus, the novelty of the present work is the use of artificial neural network (ANN) as surrogate model, that not only retains the full nature of the complete model but also acts as a fast forward model in the inverse analysis, within the Bayesian framework that quantifies the uncertainty of heat flux. The results of the present work emphasize that even for noise-added temperature data the final estimates are very close to the actual values and the uncertainty of the unknown heat flux is reported in terms of standard deviation accompanied by mean and maximum a posteriori (MAP). © 2020, Springer Nature Singapore Pte Ltd.