Shibaprasad Bhattacharya

Shibaprasad Bhattacharya
Jadavpur University | JU · Department of Production Engineering

Master of Engineering


How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
Currently working as a Business Analyst at Delhivery where I build Mathematical Models to solve practical problems. Open to part-time Ph.D. positions in India or elsewhere. The domain of interest: Operations Research, Industrial Engineering. Email:
Additional affiliations
April 2021 - present
  • Analyst
September 2019 - August 2021
Jadavpur University
Field of study
  • Production Engineering
August 2014 - July 2018
Institute of Engineering & Management
Field of study
  • Mechanical Engineering


Publications (7)
Full-text available
Modeling the interrelationships between the input parameters and outputs (responses) in any machining processes is essential to understand the process behavior and material removal mechanism. The developed models can also act as effective prediction tools in envisaging the tentative values of the responses for given sets of input parameters. In thi...
In this paper, an ensemble learning method, in the form of extreme gradient boosting (XGBoost) algorithm is adopted as an effective predictive tool for envisaging values of average surface roughness and material removal rate during CNC turning operation of high strength steel grade-H material. In order to develop the related models, a grid with 246...
Full-text available
In a turning operation, involving removal of material from the outer diameter of a rotating cylindrical workpiece using a single-point cutting tool, there exist complex relationships between various cutting parameters and responses. In this paper, a turning operation under dry environment is considered with cutting speed, feed rate, and depth of cu...
In this theoretical investigation, a mathematical model is developed to study the effect of multiple stenoses on flow characteristics of streaming blood through the atherosclerotic artery. The Bingham plastic fluid model of blood has been utilized in the study to represent the non-Newtonian character of blood. The geometry of the asymmetric shape o...
Full-text available
A mathematical model is developed in the analysis for studying blood flow through an elastic artery with the consideration of slip velocity at the inner wall of the artery. Power law fluid model have been utilized in the study to account for the presence of red cells (erythrocytes) in plasma. The governing equations of Power law fluid model is solv...
Full-text available
Optimizing total energy consumption of Buildings situated in Indian urban area.


Questions (6)
I am using R here.
I am trying to predict the MRR (Material removal rate) with RF. I have 5 input parameters.
The RF model I am building in R is having a very poor accuracy. The current data has 25 points which I have divided into 18-7 for training and testing. I know the size is small so there might be the problem of over-fitting but even when I am trying it with a larger dataset (100 training, 25 testing) I am having a poor accuracy. Even linear regression is giving a better accuracy than this.
Where I am going wrong? I am attaching my R Code and the sample data below for your kind perusal. Any help would mean a lot.
I have three outputs, each with a different unit. I am searching for an error estimator with the help of which I can select the most suitable Neural Network configuration. I will have to compute the training error as well as the testing error.
With one output, any error estimator (like MAPE or RMSE) would have done the job, but I am confused what will be the best suited for this case as I have three different outputs and I need one single number as the error to compare.
Will SSE be a good fit for it?
I have a dataset with 19 training points and 6 testing points.
At first I defined the rules for 19 training sets and then tried making predictions for the rest of 6 points. But I got all constant values.
Then when I added 6 more rules, I started getting the values which were very close to the actual values.
My question is do I have to define the rest 6 rules too? Because if I do that then it undermines the intuition of "Testing".
Or do I have to reduce the levels for output Data? Because I have created 5 levels for the output data (Extremely low, Low, Medium, High, Extremely high)
Any help would mean a lot!
Hello All! I will have to use 5-6 types of Error estimators as directed by my Research guide. I have already used MAPE (Mean absolute percentage error), RMSE (Root mean square error) and R (Correlation coefficient). What other 2-3 types of estimators I can use apart from them to gauge the accuracy of my prediction?
I have successfully developed and implemented ANFIS in R with the help of FRBS package. Just one thing that is remaining is to visualize the ANFIS network.
Currently due to some constraints because of COVID, I don't have any access to Matlab while working from home. So I was wondering if there is any way to implement it in R.
While reading about Bayesian Network and it's application in different areas, I am coming across the term 'Bayesian Belief Networks' a lot. Are they the same thing or there is some fundamental difference present? Looking at different answers in Internet only increased my doubt instead of subduing it.
Any help regarding this would mean a lot. Thank you!


Cited By


Project (1)
It is a UGC sponsored Minor Research Project. The aim of the project is to study problems of Applied Mechanics having applications in Physiological Systems. The main stress was given to the problems of 'Head injury' & 'Blood flow' of the living human being.