National Institute of Technology Rourkela

राष्ट्रीय प्रौद्योगिकी संस्थान, राउरकेला

ଜାତୀୟ ପ୍ରଯୁକ୍ତି ପ୍ରତିଷ୍ଠାନ ରାଉରକେଲା

An Institute of National Importance

Course Details

Subject {L-T-P / C} : CH3311 : Chemical Engineering Mathematics { 3-0-0 / 3}

Subject Nature : Theory

Coordinator :

Syllabus

Module 1 :

Fundamentals of Data [5 lectures]
Data and its attributes, Types of Data, Data visualization, Data quality, Data Preprocessing - Dimensionality Reduction and Principal Component Analysis, Statistical Interpretation of Data.
Assignments using Excel and MATLAB

Module 2 :

Essential Mathematica Methods for Machine Learning [5 lectures]
Introduction to Classification and Clustering, Binomial Classification, K-means and Hierarchical Clustering, Linear and Polynomial Regression.
Mini projects using MATLAB

Module 3 :

Function Approximation and Interpolation Techniques [10 lectures]
Function approximation - weighted least squares and orthogonal polynomials; Interpolation - Newton's, Stirling's and Lagrange's formulas; Cubic splines and its application in numerical differentiation and integration; Finite difference methods for solution of ODE and PDE.
Assignments using python/MATLAB

Module 4 :

Time Series Analysis [8 lectures]
Stochastic Process, Stationarity and Heteroscedasticity, Autocorrelation, Cross-correlation and Multicollinearity, Time Series Models (AR, MA, ARMA and ARIMA) and their applications.
Mini Projects using python/MATLAB

Module 5 :

Neural Networks [8 lectures]
Logistic regression and activation functions, Structure of neural networks, Types of neural networks, Feed forward neural networks (FNN), Recurrent neural networks (RNN), Application of FNN and RNN.
Mini projects using Python/MATLAB

Course Objective

1 .

To provide an understanding of data fundamentals

2 .

To introduce essential mathematical methods for machine learning

3 .

To develop skills in function approximation and interpolation techniques for solving engineering problems

4 .

To familiarize students with time series analysis

5 .

Enable students with knowledge of neural networks with practical applications

Course Outcome

1 .

Students will be able to explain different types of data, preprocessing techniques and statistical interpretation methods and apply data visualization and dimensionality reduction techniques

2 .

Students will be able to implement classification, clustering and regression techniques for solving real-world problems

3 .

Students will be able to apply function approximation, interpolation methods, and finite difference techniques for obtaining numerical solutions to problems in engineering applications

4 .

Students will be able to analyze time series data and develop time series models (AR, MA, ARMA, and ARIMA) for forecasting applications

5 .

Understand the structure and types of neural networks such as FNN and RNN and apply them to practical problems involving machine learning and deep learning

Essential Reading

1 .

Moreira, J., Carvalho, A., & Horvath, T., A General Introduction to Data Analytics, John Wiley & Sons , 2019

2 .

Sastry, S, S., Introductory Methods of Numerical Analysis, Prentice Hall India Learning Private Limited , 5th Edition, 2012

3 .

Mills, T. C., Applied Time Series Analysis: A Practical Guide to Modeling and Forecasting, Academic Press Elsevier Inc , 2019

4 .

McClarren, R. G., Machine Learning for Engineers: Using Data to Solve Problems for Physical Systems, Springer , 2021

Supplementary Reading

1 .

Roffel, B., Betlem, B., Process Dynamics & Control: Modeling for Control and Prediction, John Wiley & Sons Ltd , 2006

2 .

Kundu, M., Kundu, P. K., & Damarla, S. K., Chemometric Monitoring: Product Quality Assessment, Process Fault Detection and Applications, CRC Press, Taylor & Francis Group , 2018

Journal and Conferences

1 .

AIChE Annual meeting